changeset 0:8cac332dbc77 draft default tip

Uploaded
author cpt
date Fri, 17 Jun 2022 13:13:47 +0000
parents
children
files cpt_renumber_gbk/BIO_FIX_TOPO.py cpt_renumber_gbk/cpt-macros.xml cpt_renumber_gbk/macros.xml cpt_renumber_gbk/renumber.py cpt_renumber_gbk/renumber.xml cpt_renumber_gbk/test-data/MS105.genbank cpt_renumber_gbk/test-data/renumbered.gbk cpt_renumber_gbk/test-data/renumbered.tsv
diffstat 8 files changed, 3058 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_renumber_gbk/BIO_FIX_TOPO.py	Fri Jun 17 13:13:47 2022 +0000
@@ -0,0 +1,85 @@
+import Bio.GenBank
+
+
+def record_end(self, content):
+    """Clean up when we've finished the record.
+    """
+    #from Bio import Alphabet
+    #from Bio.Alphabet import IUPAC
+    from Bio.Seq import Seq, UnknownSeq
+
+    # Try and append the version number to the accession for the full id
+    if not self.data.id:
+        assert "accessions" not in self.data.annotations, self.data.annotations[
+            "accessions"
+        ]
+        self.data.id = self.data.name  # Good fall back?
+    elif self.data.id.count(".") == 0:
+        try:
+            self.data.id += ".%i" % self.data.annotations["sequence_version"]
+        except KeyError:
+            pass
+
+    # add the sequence information
+    # first, determine the alphabet
+    # we default to an generic alphabet if we don't have a
+    # seq type or have strange sequence information.
+    
+    #seq_alphabet = Alphabet.generic_alphabet
+
+    # now set the sequence
+    sequence = "".join(self._seq_data)
+
+    if (
+        self._expected_size is not None
+        and len(sequence) != 0
+        and self._expected_size != len(sequence)
+    ):
+        import warnings
+        from Bio import BiopythonParserWarning
+
+        warnings.warn(
+            "Expected sequence length %i, found %i (%s)."
+            % (self._expected_size, len(sequence), self.data.id),
+            BiopythonParserWarning,
+        )
+    """
+    if self._seq_type:
+        # mRNA is really also DNA, since it is actually cDNA
+        if "DNA" in self._seq_type.upper() or "MRNA" in self._seq_type.upper():
+            seq_alphabet = IUPAC.ambiguous_dna
+        # are there ever really RNA sequences in GenBank?
+        elif "RNA" in self._seq_type.upper():
+            # Even for data which was from RNA, the sequence string
+            # is usually given as DNA (T not U).  Bug 2408
+            if "T" in sequence and "U" not in sequence:
+                seq_alphabet = IUPAC.ambiguous_dna
+            else:
+                seq_alphabet = IUPAC.ambiguous_rna
+        elif (
+            "PROTEIN" in self._seq_type.upper() or self._seq_type == "PRT"
+        ):  # PRT is used in EMBL-bank for patents
+            seq_alphabet = IUPAC.protein  # or extended protein?
+        # work around ugly GenBank records which have circular or
+        # linear but no indication of sequence type
+        elif self._seq_type in ["circular", "linear", "unspecified"]:
+            pass
+        # we have a bug if we get here
+        else:
+            raise ValueError(
+                "Could not determine alphabet for seq_type %s" % self._seq_type
+            )
+
+        # Also save the chomosome layout
+        if "circular" in self._seq_type.lower():
+            self.data.annotations["topology"] = "circular"
+        elif "linear" in self._seq_type.lower():
+            self.data.annotations["topology"] = "linear"
+    """
+    if not sequence and self.__expected_size:
+        self.data.seq = UnknownSeq(self._expected_size)#, seq_alphabet)
+    else:
+        self.data.seq = Seq(sequence)#, seq_alphabet)
+
+
+Bio.GenBank._FeatureConsumer.record_end = record_end
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_renumber_gbk/cpt-macros.xml	Fri Jun 17 13:13:47 2022 +0000
@@ -0,0 +1,115 @@
+<?xml version="1.0"?>
+<macros>
+	<xml name="gff_requirements">
+		<requirements>
+			<requirement type="package" version="2.7">python</requirement>
+			<requirement type="package" version="1.65">biopython</requirement>
+			<requirement type="package" version="2.12.1">requests</requirement>
+			<yield/>
+		</requirements>
+		<version_command>
+		<![CDATA[
+			cd $__tool_directory__ && git rev-parse HEAD
+		]]>
+		</version_command>
+	</xml>
+	<xml name="citation/mijalisrasche">
+		<citation type="doi">10.1371/journal.pcbi.1008214</citation>
+		<citation type="bibtex">@unpublished{galaxyTools,
+		author = {E. Mijalis, H. Rasche},
+		title = {CPT Galaxy Tools},
+		year = {2013-2017},
+		note = {https://github.com/tamu-cpt/galaxy-tools/}
+		}
+		</citation>
+	</xml>
+	<xml name="citations">
+		<citations>
+			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
+			<citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {E. Mijalis, H. Rasche},
+				title = {CPT Galaxy Tools},
+				year = {2013-2017},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation> 
+		<yield/>
+		</citations>
+	</xml>
+    	<xml name="citations-crr">
+		<citations>
+			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
+			<citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {C. Ross},
+				title = {CPT Galaxy Tools},
+				year = {2020-},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation>
+		<yield/>
+		</citations>
+	</xml>
+        <xml name="citations-2020">
+		<citations>
+			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
+			<citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {E. Mijalis, H. Rasche},
+				title = {CPT Galaxy Tools},
+				year = {2013-2017},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation>
+                        <citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {A. Criscione},
+				title = {CPT Galaxy Tools},
+				year = {2019-2021},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+                        </citation>
+                        <yield/>
+		</citations>
+	</xml>
+        <xml name="citations-2020-AJC-solo">
+		<citations>
+			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
+                        <citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {A. Criscione},
+				title = {CPT Galaxy Tools},
+				year = {2019-2021},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+                        </citation>
+                        <yield/>
+		</citations>
+	</xml>
+        <xml name="citations-clm">
+		<citations>
+			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
+			<citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {C. Maughmer},
+				title = {CPT Galaxy Tools},
+				year = {2017-2020},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation>
+                        <yield/>
+		</citations>
+	</xml>
+        <xml name="sl-citations-clm">
+			<citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {C. Maughmer},
+				title = {CPT Galaxy Tools},
+				year = {2017-2020},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation>
+                        <yield/>
+	</xml>
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_renumber_gbk/macros.xml	Fri Jun 17 13:13:47 2022 +0000
@@ -0,0 +1,105 @@
+<?xml version="1.0"?>
+<macros>
+  <xml name="requirements">
+    <requirements>
+	<requirement type="package" version="3.8.13">python</requirement>
+	<requirement type="package" version="1.79">biopython</requirement>
+	<requirement type="package" version="1.2.2">cpt_gffparser</requirement>  
+	<yield/>
+    </requirements>
+  </xml>
+  <xml name="ldap_ref"
+    token_name="dn_ref"
+    token_label="Pick a DN"
+    token_fromfile="ldap_people.loc">
+        <repeat name="repeat_@NAME@" title="@LABEL@">
+          <param name="@NAME@" label="Select a @LABEL@" type="select">
+            <options from_file="@FROMFILE@">
+                <column name="name" index="0"/>
+                <column name="value" index="1"/>
+            </options>
+          </param>
+        </repeat>
+    </xml>
+  <xml name="ldap_ref_single"
+    token_name="dn_ref"
+    token_label="Pick a DN"
+    token_fromfile="ldap_people.loc">
+          <param name="@NAME@" label="Select a @LABEL@" type="select">
+            <options from_file="@FROMFILE@">
+                <column name="name" index="0"/>
+                <column name="value" index="1"/>
+            </options>
+          </param>
+    </xml>
+	<xml name="gbk_feature_type"
+		token_label="Feature type to remove"
+		token_multiple="True"
+		token_optional="False"
+		token_name="positional_2">
+    <param label="@LABEL@" optional="@TOKEN_OPTIONAL" multiple="@MULTIPLE@" name="feature_type" type="select">
+      <option value="-10_signal">-10_signal</option>
+      <option value="-35_signal">-35_signal</option>
+      <option value="3'UTR">3'UTR</option>
+      <option value="5'UTR">5'UTR</option>
+      <option value="CAAT_signal">CAAT_signal</option>
+      <option selected="true" value="CDS">CDS</option>
+      <option value="C_region">C_region</option>
+      <option value="D-loop">D-loop</option>
+      <option value="D_segment">D_segment</option>
+      <option value="GC_signal">GC_signal</option>
+      <option value="J_segment">J_segment</option>
+      <option value="LTR">LTR</option>
+      <option value="N_region">N_region</option>
+      <option value="RBS">RBS</option>
+      <option value="STS">STS</option>
+      <option value="S_region">S_region</option>
+      <option value="TATA_signal">TATA_signal</option>
+      <option value="V_region">V_region</option>
+      <option value="V_segment">V_segment</option>
+      <option value="all">all</option>
+      <option value="assembly_gap">assembly_gap</option>
+      <option value="attenuator">attenuator</option>
+      <option value="enhancer">enhancer</option>
+      <option value="exon">exon</option>
+      <option value="gap">gap</option>
+      <option value="gene">gene</option>
+      <option value="iDNA">iDNA</option>
+      <option value="intron">intron</option>
+      <option value="mRNA">mRNA</option>
+      <option value="mat_peptide">mat_peptide</option>
+      <option value="misc_RNA">misc_RNA</option>
+      <option value="misc_binding">misc_binding</option>
+      <option value="misc_difference">misc_difference</option>
+      <option value="misc_feature">misc_feature</option>
+      <option value="misc_recomb">misc_recomb</option>
+      <option value="misc_signal">misc_signal</option>
+      <option value="misc_structure">misc_structure</option>
+      <option value="mobile_element">mobile_element</option>
+      <option value="modified_base">modified_base</option>
+      <option value="ncRNA">ncRNA</option>
+      <option value="old_sequence">old_sequence</option>
+      <option value="operon">operon</option>
+      <option value="oriT">oriT</option>
+      <option value="polyA_signal">polyA_signal</option>
+      <option value="polyA_site">polyA_site</option>
+      <option value="precursor_RNA">precursor_RNA</option>
+      <option value="prim_transcript">prim_transcript</option>
+      <option value="primer_bind">primer_bind</option>
+      <option value="promoter">promoter</option>
+      <option value="protein_bind">protein_bind</option>
+      <option value="rRNA">rRNA</option>
+      <option value="rep_origin">rep_origin</option>
+      <option value="repeat_region">repeat_region</option>
+      <option value="sig_peptide">sig_peptide</option>
+      <option value="source">source</option>
+      <option value="stem_loop">stem_loop</option>
+      <option value="tRNA">tRNA</option>
+      <option value="terminator">terminator</option>
+      <option value="tmRNA">tmRNA</option>
+      <option value="transit_peptide">transit_peptide</option>
+      <option value="unsure">unsure</option>
+      <option value="variation">variation</option>
+    </param>
+	</xml>
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_renumber_gbk/renumber.py	Fri Jun 17 13:13:47 2022 +0000
@@ -0,0 +1,397 @@
+#!/usr/bin/env python
+import BIO_FIX_TOPO  # NOQA
+import argparse
+import sys  # noqa
+from Bio import SeqIO
+
+import logging
+
+logging.basicConfig(level=logging.INFO)
+log = logging.getLogger()
+
+# gene and RBS features are also included in the tagged features list, but are dealt with specifically elsewhere.
+# This is used to filter out just valid "in gene" features
+TAGGED_FEATURES = ["CDS", "tRNA", "intron", "mat_peptide"]
+
+
+def renumber_genes(
+    gbk_files,
+    tag_to_update="locus_tag",
+    string_prefix="display_id",
+    leading_zeros=3,
+    forceTagMatch=False,
+    change_table=None,
+):
+
+    for gbk_file in gbk_files:
+        for record in SeqIO.parse(gbk_file, "genbank"):
+            if string_prefix == "display_id":
+                format_string = record.id + "_%0" + str(leading_zeros) + "d"
+            else:
+                format_string = string_prefix + "%0" + str(leading_zeros) + "d"
+
+            # f_cds = [f for f in record.features if f.type == 'CDS']
+            # f_rbs = [f for f in record.features if f.type == 'RBS']
+            # f_gene = [f for f in record.features if f.type == 'gene']
+            # f_intron = [f for f in record.features if f.type == 'intron']
+            # f_trna = [f for f in record.features if f.type == 'tRNA']
+            # f_pep = [f for f in record.features if f.type == 'mat_peptide']
+            # f_oth = [f for f in record.features if f.type not in ['CDS', 'RBS',
+            #                                                      'gene', 'intron',
+            #                                                      'tRNA', 'mat_peptide']]
+            # Apparently we're numbering tRNAs now, thanks for telling me.
+            # f_oth2 = []
+            # for q in sorted(f_oth, key=lambda x: x.location.start):
+            #    if q.type == 'tRNA':
+            #        q.qualifiers['locus_tag'] = format_string_t % tRNA_count
+            #        tRNA_count += 1
+            #        f_oth2.append(q)
+            #    else:
+            #        f_oth2.append(q)
+            # f_oth = f_oth2
+
+            # f_care_about = []
+
+            # Make sure we've hit every RBS and gene
+            # for cds in f_cds:
+            # If there's an associated gene feature, it will share a stop codon
+            #    if cds.location.strand > 0:
+            #        associated_genes = [f for f in f_gene if f.location.end ==
+            #                            cds.location.end]
+            #    else:
+            #        associated_genes = [f for f in f_gene if f.location.start ==
+            #                            cds.location.start]
+
+            #    # If there's an RBS it'll be upstream a bit.
+            #    if cds.location.strand > 0:
+            #        associated_rbss = [f for f in f_rbs if f.location.end <
+            #                           cds.location.start and f.location.end >
+            #                           cds.location.start - 24]
+            #    else:
+            #        associated_rbss = [f for f in f_rbs if f.location.start >
+            #                           cds.location.end and f.location.start <
+            #                           cds.location.end + 24]
+            #    tmp_result = [cds]
+            #    if len(associated_genes) > 0:
+            #        tmp_result.append(associated_genes[0])
+
+            #   if len(associated_rbss) == 1:
+            #       tmp_result.append(associated_rbss[0])
+            #   else:
+            #       log.warning("%s RBSs found for %s", len(associated_rbss), cds.location)
+            # We choose to append to f_other as that has all features not
+            # already accessed. It may mean that some gene/RBS features are
+            # missed if they aren't detected here, which we'll need to handle.
+            #    f_care_about.append(tmp_result)
+
+            #####-----------------------------------------------------------------------------------------------------------#####
+            # Build list of genes, then iterate over non-gene features and sort into containing genes.
+            # tags are assigned based on genes, so start the lists with the gene features
+            f_gene = sorted(
+                [f for f in record.features if f.type == "gene"],
+                key=lambda x: x.location.start,
+            )
+            oldNames = []
+            for x in f_gene:
+              if tag_to_update in x.qualifiers.keys():
+                oldNames.append(x.qualifiers[tag_to_update])
+            
+            f_rbs = sorted(
+                [f for f in record.features if f.type == "RBS"],
+                key=lambda x: x.location.start,
+            )
+            f_tag = list()
+            f_sorted = sorted(
+                [f for f in record.features if f.type in TAGGED_FEATURES],
+                key=lambda x: x.location.start,
+            )
+            # genes not in the TAGGED_FEATURES list are exluded from the processing and assumed to already be clean
+            clean_features = sorted(
+                [
+                    f
+                    for f in record.features
+                    if f.type not in TAGGED_FEATURES and f.type not in ["gene", "RBS"]
+                ],
+                key=lambda x: x.location.start,
+            )
+
+            f_processed = []
+            for gene in f_gene:
+                tag = [gene]
+                if gene.location.strand >= 0:  # Be strict on where to find starting RBS
+                    geneComp = gene.location.start
+                else:
+                    geneComp = gene.location.end
+                # find the gene's RBS feature
+                for rbs in [f for f in f_rbs if f not in f_processed]:
+                    if is_within(rbs, gene) and (
+                        rbs.location.start == geneComp or rbs.location.end == geneComp
+                    ):
+                        if (tag_to_update not in rbs.qualifiers.keys()): 
+                          tag.append(rbs)
+                          f_processed.append(rbs)
+                          break
+                        elif (tag_to_update not in gene.qualifiers.keys()): # This will gurantee qual is in gene and RBS for next check
+                          tag.append(rbs)
+                          f_processed.append(rbs)
+                          break
+                        elif (not forceTagMatch) or (rbs.qualifiers[tag_to_update] == gene.qualifiers[tag_to_update]):
+                          tag.append(rbs)
+                          f_processed.append(rbs)
+                          break 
+                        
+                # find all other non-RBS features
+                for feature in [f for f in f_sorted if f not in f_processed]:
+                    # If the feature is within the gene boundaries (genes are the first entry in tag list),
+                    # add it to the same locus tag group, does not process RBS
+                    if is_within(feature, gene):
+                        if tag_to_update not in feature.qualifiers.keys():
+                        # catches genes and CDS feature that are intron-contained.
+                          if feature.type == "CDS":
+                            if (
+                                feature.location.start == gene.location.start
+                                or feature.location.end == gene.location.end
+                            ):
+                                
+                                tag.append(feature)
+                                f_processed.append(feature)
+                          else:
+                            tag.append(feature)
+                            f_processed.append(feature)
+                        elif (not forceTagMatch) or (tag_to_update in gene.qualifiers.keys() and feature.qualifiers[tag_to_update] == gene.qualifiers[tag_to_update]):
+                          tag.append(feature)
+                          f_processed.append(feature)
+                    elif feature.location.start > gene.location.end:
+                        # because the features are sorted by coordinates,
+                        # no features further down  on the list will be in this gene
+                        break
+                f_tag.append(tag)
+
+            # Process for frameshifts and mat_peptides (inteins)
+
+            # check for overlapped genes
+            # at this point, relevant features are put into tag buckets along with the containing gene
+            # matin the form of [gene, feature1, feature2, ...]
+            for rbs in [f for f in f_rbs if f not in f_processed]:
+                dupeRBS = False
+                for x in f_processed:
+                  if x.type == "RBS" and (tag_to_update in rbs.qualifiers.keys() and tag_to_update in x.qualifiers.keys() and rbs.qualifiers[tag_to_update] == x.qualifiers[tag_to_update]):
+                    dupeRBS = True
+                if dupeRBS:
+                  change_table.write(
+                    record.id
+                    + "\t"
+                    + rbs.type
+                    + ":"
+                    + (rbs.qualifiers[tag_to_update][0])
+                    + "\t[Removed: Parent gene already had an RBS]\n"
+                  )
+                else:
+                  change_table.write(
+                    record.id
+                    + "\t"
+                    + rbs.type
+                    + ":"
+                    + (rbs.qualifiers[tag_to_update][0])
+                    + "\t[Removed: RBS did not both fall within boundary of gene and share a boundary with a gene]\n"
+                  )
+
+
+            tag_index = 1
+            delta = []
+            for tag in f_tag:  # each tag list is one 'bucket'
+                new_tag_value = format_string % tag_index
+                for feature in tag:
+                    original_tag_value = delta_old(feature, tag_to_update)
+                    feature.qualifiers[tag_to_update] = [new_tag_value]
+                    # Once the tag is renumbered, it's added to the clean list for later output
+                    clean_features.append(feature)
+                    delta.append(
+                        "\t".join((record.id, original_tag_value, new_tag_value))
+                    )
+                tag_index += 1
+
+            # Why must these people start at 1
+            # Because we have to modify the array we work on a separate one
+            # clean_features = f_oth
+            # delta = []
+            # for index, feature_list in enumerate(sorted(f_care_about, key=lambda x: x[0].location.start)):
+            #    for f in feature_list:
+            #        original_tag_value = delta_old(f, tag_to_update)
+            #        # Add 1 to index for 1-indexed counting for happy scientists
+            #        new_tag_value = format_string % (index+1)
+            #        f.qualifiers[tag_to_update] = [new_tag_value]
+            #        clean_features.append(f)
+            #        delta.append('\t'.join((record.id, original_tag_value, new_tag_value)))
+
+            # Update all features
+            record.features = sorted(clean_features, key=lambda x: x.location.start)
+            
+            for feature in [f for f in f_sorted if f not in f_processed]:
+                if feature.type == "CDS":
+                  if tag_to_update in feature.qualifiers.keys() and forceTagMatch:
+                    failNameCheck = True
+                    for x in oldNames:
+                      for tag in feature.qualifiers[tag_to_update]:
+                          if tag in x:
+                            failNameCheck = False
+                      if not failNameCheck:
+                        break
+                    if failNameCheck:
+                      change_table.write(
+                        record.id
+                        + "\t"
+                        + feature.type
+                        + ":"
+                        + (feature.qualifiers[tag_to_update][0])
+                        + "\t[Removed: (Tag check enabled) CDS did not both share a start/end with and fall within a gene with the same " + tag_to_update + " value]\n"
+                      )
+                    else:
+                      change_table.write(
+                        record.id
+                        + "\t"
+                        + feature.type
+                        + ":"
+                        + (feature.qualifiers[tag_to_update][0])
+                        + "\t[Removed: CDS did not both fall within boundary of gene and share a boundary with a gene]\n"
+                      )  
+                  elif tag_to_update in feature.qualifiers.keys():
+                    change_table.write(
+                        record.id
+                        + "\t"
+                        + feature.type
+                        + ":"
+                        + (feature.qualifiers[tag_to_update][0])
+                        + "\t[Removed: CDS did not both fall within boundary of gene and share a boundary with a gene]\n"
+                    )
+                  else:
+                    change_table.write(
+                        record.id
+                        + "\t"
+                        + feature.type
+                        + ": No "
+                        + tag_to_update
+                        + "\t[Removed: CDS at (" + str(feature.location.start) + "," + str(feature.location.end) + ") did not both fall within boundary of gene and share a boundary with a gene]\n"
+                    )
+                else:
+                  if tag_to_update in feature.qualifiers.keys() and forceTagMatch:
+                    failNameCheck = True
+                    for x in oldNames:
+                      for tag in feature.qualifiers[tag_to_update]:
+                          if tag in x:
+                            failNameCheck = False
+                      if not failNameCheck:
+                        break
+                    if failNameCheck:
+                      change_table.write(
+                        record.id
+                        + "\t"
+                        + feature.type
+                        + ":"
+                        + (feature.qualifiers[tag_to_update][0])
+                        + "\t[Removed: (Tag check enabled) Feature did not fall within a gene it shared a " + tag_to_update + " value with]\n"
+                      )
+                    else:
+                      change_table.write(
+                        record.id
+                        + "\t"
+                        + feature.type
+                        + ":"
+                        + (feature.qualifiers[tag_to_update][0])
+                        + "\t[Removed: Feature not within boundary of a gene]\n"
+                      )
+                  elif tag_to_update in feature.qualifiers.keys():
+                    change_table.write(
+                        record.id
+                        + "\t"
+                        + feature.type
+                        + ":"
+                        + (feature.qualifiers[tag_to_update][0])
+                        + "\t[Removed: Feature not within boundary of a gene]\n"
+                    )
+                  else:
+                    change_table.write(
+                        record.id
+                        + "\t"
+                        + feature.type
+                        + ": (has no "
+                        + tag_to_update
+                        + ")\t[Removed: Feature not within boundary of a gene]\n"
+                    )
+            change_table.write("\n".join(delta) + "\n")
+
+            # Output
+            yield record
+
+
+def delta_old(feature, tag_to_update):
+    # First part of delta entry, old name
+    if tag_to_update in feature.qualifiers:
+        return feature.qualifiers[tag_to_update][0]
+    else:
+        return "%s %s %s" % (
+            feature.location.start,
+            feature.location.end,
+            feature.location.strand,
+        )
+
+
+def is_within(query, feature):
+    # checks if the query item is within the bounds of the given feature
+    sortedList = sorted(query.location.parts, key=lambda x: x.start)
+    for x in sortedList:
+      if (
+          feature.location.start <= x.start
+          and feature.location.end >= x.end
+      ):
+        if x.strand < 0 and x == sortedList[-1]:
+          return True
+        elif x.strand >= 0 and x == sortedList[0]:
+          return True
+    #else:
+    return False
+
+
+# def fix_frameshift(a, b):
+#    #checks if gene a and gene b are a frameshifted gene (either shares a start or an end and an RBS)
+#    if a[0].location.start == b[0].location.start or a[0].location.end == b[0].location.end:
+#        # It is likely a frameshift. Treat is as such. Find shared RBS, determine which CDS is which
+#        big_gene = a if (a[0].location.end - a[0].location.start) > (b[0].location.end - b[0].location.start) else b
+#        small_gene = a if big_gene==b else b
+#        rbs = [f for f in a if f.type == 'RBS']
+#        # In the way that the tag lists are generated, the larger gene should contain both CDS features.
+#        # Retrieve and dermine big/small CDS
+#        cdss = [f for f in big_gene if f.type == 'CDS']
+#        big_cds = cdss[0] if (cdss[0].location.end - cdss[0].location.start) > (cdss[1].location.end - cdss[1].location.start) else cdss[1]
+#        small_cds = cdss[0] if big_cds==cdss[1] else cdss[1]
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Renumber genbank files")
+    parser.add_argument(
+        "gbk_files", type=argparse.FileType("r"), nargs="+", help="Genbank files"
+    )
+    parser.add_argument(
+        "--tag_to_update", type=str, help="Tag to update", default="locus_tag"
+    )
+    parser.add_argument(
+        "--string_prefix", type=str, help="Prefix string", default="display_id"
+    )
+    parser.add_argument(
+        "--leading_zeros", type=int, help="# of leading zeroes", default=3
+    )
+
+    parser.add_argument(
+        "--forceTagMatch", action="store_true", help="Make non-CDS features match tag initially"
+    )
+
+    parser.add_argument(
+        "--change_table",
+        type=argparse.FileType("w"),
+        help="Location to store change table in",
+        default="renumber.tsv",
+    )
+
+    args = parser.parse_args()
+    for record in renumber_genes(**vars(args)):
+        SeqIO.write(record, sys.stdout, "genbank")
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_renumber_gbk/renumber.xml	Fri Jun 17 13:13:47 2022 +0000
@@ -0,0 +1,58 @@
+<?xml version="1.0"?>
+<tool id="edu.tamu.cpt.genbank.RelabelTags" name="Renumber GenBank Genes" version="0.4" profile="16.04">
+    <description>relabels/renumbers GenBank tags according to rules</description>
+  <macros>
+    <import>macros.xml</import>
+		<import>cpt-macros.xml</import>
+  </macros>
+  <expand macro="requirements"/>
+  <command detect_errors="aggressive"><![CDATA[
+python $__tool_directory__/renumber.py
+  $file
+--tag_to_update "${tag_to_update}"
+--string_prefix "${string_prefix}"
+--leading_zeros "${leading_zeros}"
+$forceMatch
+--change_table $change_table
+
+> $output
+
+]]></command>
+  <inputs>
+    <param label="GenBank file" name="file" type="data" format="genbank" />
+    <param help="Which tag is used to store gene numbers" label="Tag to update"
+        name="tag_to_update" type="text" value="locus_tag"/>
+    <param help="A string to use as a prefix for the numbering. Will be used as XXXXXXNNN where XXXXXX is the string and NNN is a numerical identifier. Using &quot;display_id&quot; has special meaning, it will use the genome's name/accession number"
+        label="String prefix" name="string_prefix" type="text" value="display_id"/>
+    <param label="Number of leading zeros/padding" name="leading_zeros"
+        type="integer" value="3"/>
+    <param name="forceMatch" label="Force Updated Tags to initially match in addition to location checks. " help="If tag is not present, only location and type checks will be used to infer renumber" type="boolean" truevalue="--forceTagMatch" falsevalue="" checked="True" />
+  </inputs>
+  <outputs>
+    <data format="genbank" name="output">
+    </data>
+    <data format="tabular" name="change_table">
+    </data>
+  </outputs>
+  <tests>
+      <test>
+          <param name="file" value="MS105.genbank" />
+          <param name="leading_zeros" value="10" />
+          <param name="forceMatch" value="" />
+          <param name="string_prefix" value="MS105_" />
+          <output name="genbank" value="renumbered.gbk" />
+          <output name="change_table" value="renumbered.tsv" />
+      </test>
+  </tests>
+  <help>
+Gene Renumbering Tool
+=====================
+
+Renumber genes in a genome.
+
+Subfeatures, such as CDS or intron, will attempt to be grouped with their associated gene, based on location. CDSs and RBSs must share either a start or an end boundary with their parent gene, and also fall entirely within the boundary of said gene. All other features only need to fall within the boundary of a gene. 
+
+If the tag check is enabled, then whatever qualifier is selected for updating (such as locus_tag), the subfeatures must also have the same value as any canidate parent gene had for that qualifier. This is useful for subfeatures such as introns, which may be inside more than one gene and could potentially get renumbered to the wrong parent in a location-only check. However, if your dataset does not already have a consistent naming convention, other valid heirarchies could get dropped. The log file will list what features got dropped based on tag checks, so be sure to use that to verify all data made it through.
+</help>
+		<expand macro="citations-2020" />
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_renumber_gbk/test-data/MS105.genbank	Fri Jun 17 13:13:47 2022 +0000
@@ -0,0 +1,1069 @@
+LOCUS       NODE_2_length_39       39186 bp    DNA              UNK 01-JAN-1980
+DEFINITION  NODE_2_length_39186_cov_113.152335
+ACCESSION   NODE_2_length_39186_cov_113
+VERSION     NODE_2_length_39186_cov_113.152335
+KEYWORDS    .
+SOURCE      .
+  ORGANISM  .
+            .
+FEATURES             Location/Qualifiers
+     gene            57..345
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_001"
+     RBS             57..60
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_001"
+     CDS             70..345
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_001"
+                     /product="hypothetical protein"
+     gene            complement(408..723)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_002"
+     CDS             complement(408..713)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_002"
+                     /product="hypothetical protein"
+     RBS             complement(719..723)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_002"
+     gene            complement(888..1173)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_003"
+     CDS             complement(888..1160)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_003"
+                     /product="hypothetical protein"
+     RBS             complement(1170..1173)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_003"
+     gene            complement(1180..2369)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_004"
+     CDS             complement(1180..2358)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_004"
+                     /product="hypothetical protein"
+     RBS             complement(2367..2369)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_004"
+     gene            complement(2399..2975)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_005"
+     CDS             complement(2399..2965)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_005"
+                     /product="hypothetical protein"
+     RBS             complement(2973..2975)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_005"
+     gene            complement(2984..3146)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_006"
+     CDS             complement(2984..3136)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_006"
+                     /product="hypothetical protein"
+     gene            complement(3137..3265)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_007"
+     CDS             complement(3137..3250)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_007"
+                     /product="hypothetical protein"
+     RBS             complement(3144..3146)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_006"
+     RBS             complement(3263..3265)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_007"
+     gene            complement(3269..3507)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_008"
+     CDS             complement(3269..3490)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_008"
+                     /product="hypothetical protein"
+     RBS             complement(3505..3507)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_008"
+     gene            complement(3638..4310)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_009"
+     CDS             complement(3638..4300)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_009"
+                     /product="endonuclease"
+     gene            complement(4297..5531)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_010"
+     CDS             complement(4297..5520)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_010"
+                     /product="methylase"
+     RBS             complement(4307..4310)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_009"
+     gene            complement(5507..5956)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_011"
+     CDS             complement(5507..5938)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_011"
+                     /product="Vsr endonuclease"
+     RBS             complement(5528..5531)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_010"
+     RBS             complement(5944..5948)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_011"
+     gene            complement(6206..6823)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_012"
+     CDS             complement(6206..6811)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_012"
+                     /product="hypothetical protein"
+     RBS             complement(6820..6823)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_012"
+     gene            complement(6824..7338)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_013"
+     CDS             complement(6824..7327)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_013"
+                     /product="hypothetical protein"
+     RBS             complement(7335..7338)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_013"
+     gene            7428..7644
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_014"
+     RBS             7428..7430
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_014"
+     CDS             7441..7644
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_014"
+                     /product="hypothetical protein"
+     gene            7623..7847
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_015"
+     RBS             7623..7626
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_015"
+     CDS             7635..7847
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_015"
+                     /product="hypothetical protein"
+     gene            complement(7827..8964)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_016"
+     CDS             complement(7827..8948)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_016"
+                     /product="integrase"
+     RBS             complement(8960..8964)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_016"
+     gene            complement(9156..9851)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_017"
+     CDS             complement(9156..9842)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_017"
+                     /product="hypothetical protein"
+     gene            complement(9839..12634)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_018"
+     CDS             complement(9839..12634)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_018"
+                     /product="zinc finger CHC2-family protein"
+     RBS             complement(9848..9851)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_017"
+     gene            complement(12637..12899)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_019"
+     CDS             complement(12637..12885)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_019"
+                     /product="hypothetical protein"
+     gene            complement(12882..13256)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_020"
+     CDS             complement(12882..13244)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_020"
+                     /product="hypothetical protein"
+     RBS             complement(12895..12899)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_019"
+     gene            complement(13249..13454)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_021"
+     CDS             complement(13249..13443)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_021"
+                     /product="hypothetical protein"
+     RBS             complement(13253..13256)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_020"
+     gene            complement(13440..13620)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_022"
+     CDS             complement(13440..13604)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_022"
+                     /product="hypothetical protein"
+     RBS             complement(13452..13454)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_021"
+     RBS             complement(13618..13620)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_022"
+     gene            complement(13686..13908)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_023"
+     CDS             complement(13686..13898)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_023"
+                     /product="hypothetical protein"
+     RBS             complement(13904..13908)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_023"
+     gene            complement(13985..14246)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_024"
+     CDS             complement(13985..14233)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_024"
+                     /product="ogr-like transcriptional regulator"
+     gene            complement(14221..14438)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_025"
+     CDS             complement(14221..14424)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_025"
+                     /product="hypothetical protein"
+     RBS             complement(14243..14246)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_024"
+     RBS             complement(14436..14438)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_025"
+     gene            complement(14464..14672)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_026"
+     CDS             complement(14464..14661)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_026"
+                     /note="KL3 gp11"
+                     /note="HHpred to MobC, Arc, RelB, > 98%"
+                     /product="ribbon-helix-helix DNA binding protein"
+     gene            14623..15462
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_027"
+     CDS             14623..15462
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_027"
+                     /note="This start is more in line with where BLASTp
+                     alignments begin and leaves space for a divergent
+                     regulatory DNA sequence between genes"
+                     /product="repressor protein correct start?"
+     RBS             complement(14670..14672)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_026"
+     RBS             14688..14690
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_027"
+     CDS             14704..15462
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_027"
+                     /note="This start is more in line with where BLASTp
+                     alignments begin and leaves space for a divergent
+                     regulatory DNA sequence between genes"
+                     /product="repressor protein correct start?"
+     RBS             14985..14988
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_027"
+     CDS             14995..15462
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_027"
+                     /note="This start is more in line with where BLASTp
+                     alignments begin and leaves space for a divergent
+                     regulatory DNA sequence between genes"
+                     /product="repressor protein correct start?"
+     gene            15621..15928
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_028"
+     RBS             15621..15624
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_028"
+     CDS             15635..15928
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_028"
+                     /product="hypothetical protein"
+     gene            complement(15979..17082)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_029"
+     CDS             complement(15979..17070)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_029"
+                     /product="P2 D homolog; tail protein"
+     gene            complement(17067..17539)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_030"
+     CDS             complement(17067..17525)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_030"
+                     /product="P2 U homolog; tail protein"
+     RBS             complement(17079..17082)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_029"
+     RBS             complement(17535..17539)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_030"
+     gene            complement(17547..20788)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_031"
+     CDS             complement(17547..20774)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_031"
+                     /product="P2 T protein; tape measure protein"
+     RBS             complement(20786..20788)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_031"
+     gene            complement(20899..21261)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_032"
+     CDS             complement(20899..21249)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_032"
+                     /note="nearly identical to gp18 of KL3"
+                     /product="P2 E protein; tail protein"
+     RBS             complement(21258..21261)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_032"
+     gene            complement(21307..21829)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_033"
+     CDS             complement(21307..21816)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_033"
+                     /product="tail tube protein"
+     RBS             complement(21825..21829)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_033"
+     gene            complement(21832..23018)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_034"
+     CDS             complement(21832..23004)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_034"
+                     /product="P2 tail sheath"
+     RBS             complement(23014..23018)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_034"
+     gene            complement(23057..23692)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_035"
+     CDS             complement(23057..23680)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_035"
+                     /product="tail fiber protein"
+     RBS             complement(23690..23692)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_035"
+     gene            complement(23698..26346)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_036"
+     CDS             complement(23698..26334)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_036"
+                     /note="hit Milo tailocin (69% identity) over 100% coverage
+                     (780aa) starting from position 105 to 878"
+                     /product="tail fiber protein (BceTMilo like)"
+     gene            complement(26337..26893)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_037"
+     CDS             complement(26337..26879)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_037"
+                     /product="tail protein"
+     RBS             complement(26344..26346)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_036"
+     gene            complement(26884..27801)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_038"
+     CDS             complement(26884..27789)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_038"
+                     /product="baseplate protein"
+     RBS             complement(26891..26893)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_037"
+     gene            complement(27786..28157)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_039"
+     CDS             complement(27786..28148)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_039"
+                     /product="baseplate wedge"
+     RBS             complement(27797..27801)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_038"
+     gene            complement(28145..28952)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_040"
+     CDS             complement(28145..28936)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_040"
+                     /product="baseplate protein"
+     RBS             complement(28154..28157)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_039"
+     gene            28891..29247
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_041"
+     RBS             28891..28894
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_041"
+     CDS             28900..29247
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_041"
+                     /product="hypothetical protein"
+     RBS             complement(28950..28952)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_040"
+     gene            29239..29782
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_042"
+     RBS             29239..29241
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_042"
+     CDS             29249..29782
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_042"
+                     /product="hypothetical protein"
+     gene            complement(29762..30239)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_043"
+     CDS             complement(29762..30229)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_043"
+                     /product="tail protein"
+     gene            complement(30229..30657)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_044"
+     CDS             complement(30229..30645)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_044"
+                     /product="tail protein"
+     RBS             complement(30236..30239)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_043"
+     RBS             complement(30655..30657)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_044"
+     gene            complement(30759..31209)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_045"
+     CDS             complement(30759..31199)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_045"
+                     /product="spanin (s)"
+     gene            complement(31196..32018)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_046"
+     CDS             complement(31196..32005)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_046"
+                     /product="endolysin"
+     RBS             complement(31207..31209)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_045"
+     gene            complement(32002..32286)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_047"
+     CDS             complement(32002..32274)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_047"
+                     /product="holin"
+     RBS             complement(32015..32018)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_046"
+     gene            complement(32276..32632)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_048"
+     CDS             complement(32276..32620)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_048"
+                     /product="hypothetical protein"
+     RBS             complement(32282..32286)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_047"
+     RBS             complement(32630..32632)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_048"
+     gene            complement(32636..32853)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_049"
+     CDS             complement(32636..32842)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_049"
+                     /product="P2 X protein; tail protein"
+     gene            complement(32842..33321)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_050"
+     CDS             complement(32842..33321)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_050"
+                     /note="100% identical to KL3 gp37"
+                     /product="capsid completion protein (L)"
+     RBS             complement(32851..32853)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_049"
+     gene            complement(33421..34124)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_051"
+     CDS             complement(33421..34110)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_051"
+                     /product="terminase endonuclease subunit (M)"
+     gene            complement(34107..35134)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_052"
+     CDS             complement(34107..35120)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_052"
+                     /product="capsid protein (N)"
+     RBS             complement(34122..34124)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_051"
+     RBS             complement(35131..35134)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_052"
+     gene            complement(35156..35984)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_053"
+     CDS             complement(35156..35968)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_053"
+                     /product="capsid protein (O)"
+     gene            35976..37882
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_054"
+     RBS             35976..35978
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_054"
+     RBS             complement(35982..35984)
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_053"
+     CDS             35993..37882
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_054"
+                     /product="terminase ATPase subunit (P)"
+     gene            37867..38934
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_055"
+     RBS             37867..37870
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_055"
+     CDS             37879..38934
+                     /locus_tag="CPT_NODE_2_length_39186_cov_113.152335_055"
+                     /product="portal protein"
+ORIGIN
+        1 tttgtttttt ttttttttca agcagaagac ggcatacgag ataatgagcg gtgactggag
+       61 ttcagacgtg tgctcttccg atctgtcccc tccccgcctg cgggcttcgc ttggcagggc
+      121 ggttttagtg cactgggtcg accagctcgg cggcccttgt ggcgcgggat ttcgcgtgat
+      181 tcgcgggggc cggaaatcgt gcgttttgat gctcgacgat gcgcaatcgt gcaaccgcac
+      241 gaccgtcgaa ggccgttcgc tgcgatcgcc ggttcacgcg gggcgccgtc gccgacagtg
+      301 ccggcgacgg cgccggccgg tcaggctcgg ctgtcgtttc gttgacgggg tagagctgca
+      361 gtgcgctacc aatggtcggc gcgtgtcgcg ctcatcctcg gccgaagtca ctttctcttg
+      421 cgacgggcgg atcctcgcga ggtaggaagc gagccaacat caatgtcgtg acgttgagcg
+      481 gtccaatact gcagcttcga aatctcgatg agcagatcat cagagcgatc ccggagatcc
+      541 cgatagttgt agcgatcggc cgcaatacga atcgactcaa gtcgcgcccg ccaatatgcg
+      601 ggatcgcgga tcgacgcccc aagcggaaac tcgtcgcggt ttttcgaaag ggtttgtagg
+      661 gcatttttta catgcaccag atctcgttca atcccatcgt aacgatcaca catacttacc
+      721 cccgtaagcg tattgcccac aatacagcgg ccacggctgc tctggctcat aagattcagt
+      781 tagaggtaga aagagagccg tgcctcgtac cccctacggg acacggcccc aacacgggaa
+      841 tcaattgctc ccgcgagcca actacacaac cttacggcac gctcacttca caattccgcg
+      901 cgcgtcaaat gtcgggttcc ggatgatgtg tcgagtgttc gccatgtcgg cacactatgc
+      961 gcggcattgg agcggactcc acttctgttc gcgttttcga cgctcgtttt atgtgatgcc
+     1021 agatctaccg ccaacagtcc gaaatcgata atcgccacgg cgaccaatgc aatcacccat
+     1081 cggatatttc tcgatcttcg caccttcttt gaagggacgc cgtaaagcag acgctcatag
+     1141 tcttccggat cgatcggcat atcctaggtc tccgtcgcgt cattcgacca atcgcgcagg
+     1201 cgtgagcgcg ccatagtacg gcccgacacc acctgccccc gatgcttggc atttgtccgg
+     1261 attgttgctc atctccattt ggatgtattt cccgcttccg ccaactgctt gatcaatgtg
+     1321 tacacacgca aatgcaagga tccgctcgta ggacgttgtc gtgagatcct gaacaatcgg
+     1381 gaccaggaca tactcgcaag ctttgttgcc ggcggcgcta cagtcgttga cggatgtgta
+     1441 cagcgttgtc ttcgtgccag gttggatata ggtgcacgtt gcgtctggtg tggagcaaac
+     1501 accacttggc gatccaattg atgacgggtc tggattaccg ttggatatca agttgcgcac
+     1561 ggtcggcaca tcgttggcgg ttgtatcgaa agtcgtccat tgacctgctt cgcaaggacc
+     1621 agcgtggtat gacgaggtca cataaaaggt gtacggttgt ccgaccgttt ggttgggctg
+     1681 gcctgagcca ggcggtgtcg tggacgttgc gactttgggc tttccgttcg tcgaatccca
+     1741 gtactggtca tacatgcact tcgtcagcgc aaccgggaat agcgcacccg aaccaacgtt
+     1801 tccggggtcc gaaatgaccg cgacagccac ggcgttctcg ggtacagact ggaaccccca
+     1861 aagcctcgcc agaaatgaag gaacgccgcc gccattcttc gttccagagc ggctgacaac
+     1921 cacctgcact gcaggcttgc cgacggccgg cgatgacggc atcgaggttt gaaggccctt
+     1981 gacgctaccg gtgacgtccc agtaaccgta cgacacatcg gacgtatatc ctgtcagcgt
+     2041 tttattcgac gacttgttta acgagacacc cagcacagcc tgggcttggg ccgtcgccca
+     2101 atctggaact gcggcctttg tattgctgca ttgcgctcgc gggtagatgc atggcgctcc
+     2161 ggccagggcg gcagcatcgg ctgcgttctg cagttcattc cggacaacaa aaagatagcc
+     2221 gacgtcgatt gcgagggcgg caaagccgag cagaatcgac atcaagaaag cgacggttat
+     2281 cgctaccgca cctctctgat tctgacgagt cttcaaaccg cagcgcatgt gcattgactt
+     2341 tctgggcgcg caaggcacac ctacagaccg tgaacgagtg cgatccatga ccggctcctc
+     2401 attcattgtt catgacagtg gtagccgtca acgtcagcag cttgcttaac ggaccaatcc
+     2461 acgaacccaa agccagtcca gtgaatttgt acgtgacggt aacagtaagg ggtgtgccaa
+     2521 agcttccacc ttgaccagac ggtacggaga cggttggtgt tgacgtgctg cccaagctga
+     2581 tgagatggct ttggcagtag ttgagagcga cggtctgtat gtcggttgtt gtcgctttcg
+     2641 gcgttttgag aacaatcccc gcgcgcgcac cttcccggct tgcgtttgtg atgacggctt
+     2701 ggtcgaacat cacaagtccg aactcgataa tgccgaacag aatcagtagc agcacgggaa
+     2761 gtaccagtgc aaattccaca acagcaacgc ctcgttgctt ctgccagttt ttccgattcg
+     2821 tcattttttt tccccgttga gccaagcctt tgtggcttgc agcgtccgct gaccaggtcg
+     2881 ccatcagtgc gtcgattcgt cgcatttgaa tgcgcagatg gaggcgcgcc atccggttgc
+     2941 gcgaaccgaa cgagccgggt cccaaataca cgcccacact tggtcagtga cttagcaaaa
+     3001 cgcgcgccat acgcagtccg cgcttgtggc atgaggcgct tgattgagct atgggcggac
+     3061 aaaaaatggg gtggcatcgg aaatgtttca ggcttgtacc gtgaaacaca aattcggcgt
+     3121 cgaccgcgcc tcccacctac aagctcatgc acgttagaag gggagagatt ggcccggaag
+     3181 attcaaatct gaaacgccga agagtccgaa gggtgaccgt cgacatccct ctccgttgtt
+     3241 cgcggggcaa atccaggacg ggctctttct atctccctgc gcatgccggc cggctcagcc
+     3301 gcccggctaa ggcgacagcc gcaagcgggt gaggtctcgt ctgcccgcga cagaccggtg
+     3361 gcgagccgga ggccttgtgc cacgcagcgg cacggggccg ggtcagagtc ggaagatgcc
+     3421 gactctgacc cggcgcgcgc agttgtgacc ccgccccacc tgcccgtaaa aatgagcggt
+     3481 ttttatgcac tcatgcaccg ggtgctccgg gccgcccggc gtgggccgcg cggcgatcgg
+     3541 tggggcgatt tcgttatgca gttttatgcg ccttggttat gcattctcgt catccagcga
+     3601 gttatggcgc aactccggcc gcagggcgat ctcataccta gggctgttgg tcgggcccca
+     3661 agacgtgatg cgatgccggg aatgagatgg tggcgaagta attctgtaca tcccgaatga
+     3721 tgtgctcttg cgtctcttcc cgaaccttgc acttttctgc ccatgcacgt cccggatgca
+     3781 agacgtccca tcgcggacgc aacccgttgt atcgaccgct gcctggatcg tgattcccaa
+     3841 agccatcaat caaagcgttc caaagcggtg caaacttcga gatcagcagc gactcgccca
+     3901 gcgggatcca aatgtcgtcg accaccaaga agcggcagac gaaatccttg atgtctaagt
+     3961 tggcggcaag ctgaacgctt tctgcgtgct ctcgtaggcg gtcgtaaagg gctttgctgc
+     4021 gaacctcacc tacgccgccg cctttgcgag cacccttcgg cactgctttc ccaacataaa
+     4081 tgggagcctg aagcacaccg tttcgattcc gttcggccaa gggcgcgtaa gcttcgaagt
+     4141 cgccaacgta atagatggca tagatgccga caccaaagaa ttgcttcaac tcgccaagag
+     4201 gctgcggttt ctgttcgagc atcgcctcag cgacacttgc gccgaggttc ttcttgtcga
+     4261 gcggattaaa ggggatgatg tttccaatcg aatccgtcat gccgcccctc gcgctgttac
+     4321 gcgccggcgc gccagttgct caagttgaac gatcgccaac cgctccgcga cgcttcgtgc
+     4381 cacgacgtgg ccaagtgcga cagggacggc gttaccgagc tggcgcatgg tttctgtcca
+     4441 tgaaccgtgg aacttgaagc cgtcggggaa ggtttgcaca cgcgccgact cgcgaatcga
+     4501 gaaatagcgg accgagccgt ccgtgttgac aagcatgttc tcgccgcccg gcacgccatg
+     4561 atcgccagct ttcagagttt tagctggcaa atcgagcggg ctgccggtgt ggccgggata
+     4621 gacgcgggca cccggctgga agcgatgatc ctggtattga ctcgccgtcc gcgcaagtgg
+     4681 gctcggtagg cctgcaatcg cgtcacggac ggttcgccaa ggcaactcgg tcgcgaacgg
+     4741 gagcgagcca gcgaggcgcc gcacgcggct tgccaccgat tctggcatcg tcggccgcgc
+     4801 acggcgcggc acttggtggc gttcccaata ttcgccagtg atccattggt cgcgtagcag
+     4861 gctgtcgtag ctgtgcgtcg ggcgtggaaa gctccaatcc acgtcaaggt cggaacggaa
+     4921 gcccacgatg aatacgcgct cacgcttttg cggaacgcca tagtcggcag cattcaccaa
+     4981 cgtgggaacc acgttgtaag tcagcttttt gcccttctgg cggccgctcg tgcgttcggc
+     5041 ttgcaagcgc aggagatggt cgaaccattc ctcgttgcgg cgtgccggca cctctggaaa
+     5101 ctcgagctgc agcaggatgt attggtagta gttggcaaac gtggagcgcg tcaggccctt
+     5161 gacgttttcc acgatgaagg ctttcgggcg cagtttgcgc acgatatcca ccgttgcagg
+     5221 gaacatgtcg cggctgtcgt cgtgtgcctg atgcttgccg cccatcgaga acggttggca
+     5281 cggcggaccg cccgctaaca ggtcgatttc ctctccttct aggctcgacc agtcaaattt
+     5341 gcgaacgtca ccctcgtaaa gtggccaatc cgccaccaag ggaaagcctc gccgctggtt
+     5401 ctcacgaatc gtgtcgcatg cccatcgatc ccattcgacc accgccagag gcttgaagcc
+     5461 ggcaaggccg acccccatcg cgaggccgcc cgcgcctgcg tatagctcaa ctgccttcat
+     5521 tgttgttctc cgtgtcgtct aagaaggccc tgacacggag ggtcaggacc acctcatcct
+     5581 tcacttcaca ttcccatatt gtcaaaactt tccagccgag cgcgctgagt tgtcgctcga
+     5641 cttccttatc tcgttcggca ttcgcctcaa gcttgggccg ccaaaaatcc agtcgcgatt
+     5701 tcggcaggcg cgctagacgg caaccttcgt gccggtgcca gaagcatccg tggacgaata
+     5761 tcaccttgcg tctcttcgag aacaccaagt cgggacgtcc aggcagccct tttccgtgaa
+     5821 gccggtaacg gtagcccaag cgatggatca ggctccgaac gatcagttcc ggcttggtgt
+     5881 tcctgccttt gatgcgcgac atgcgctcgc tgcgctccgc aggggtaaga ctatccaaga
+     5941 cggcctccgc gctcatgccg gggcgattgt aacgccttga agggtagacc gggcgtgttg
+     6001 agcgattggt gcggcgagca actcgggatg tttggcaact gcgagattct cgcggcagcc
+     6061 agttgcggcg tggccctttg tttgcgcccg ggcaggcgtc gatagagggt cgacagaagg
+     6121 tgcttcaatg cggcttggtc ataactggcc ggacgtggct tgggcaaaaa aaagctcgcc
+     6181 gtagcgagct ttagttgatt ctaggttagc gcctagcgag catatttttt actcggtatt
+     6241 ccatcgcagg attcgatacg cggaaacgag gcgccatttg agcagtgaat cgatccagtg
+     6301 gcatcttttc cgtgccgttt tcacgcttgt aagcgtcgat gatcggcttg ccgacggacc
+     6361 ggatcaactc cgcgggcatg aggagttccg ccgcgaagtt gtttgcttcc gactcgtgtc
+     6421 tcgtccaata agattcgctg cgactcatcg tgctcttgtc atcaacgaac tcaagccgcc
+     6481 cctcgacgcg gtgcatgcaa aagtggccaa tttcgtgcgc aagcgtaaac ctacgccgcg
+     6541 gttcatacgc gttctggttg gtgtttatcc agaccttggc tctaccttcg ggctcgagcg
+     6601 agatcaggcc cacggtatcg ctatcgaccg gcgctgacgt tgagccgtgg taagtgggcg
+     6661 actcgataac atcgatacct aagagttttg cgacagcgtc gacgtcgacc ggcggtgcac
+     6721 ccgcaaagat ctcgtagtcg aattcgtcct tcaggtattt ccccaaatcc gacacggtca
+     6781 acatttgggg ggcagcagtt tgagtaacca tgtgacctcc ctcttacgaa gattgcaaat
+     6841 cgtccaaggc atccttctcg ttgcgagcat cattcgcccg ctggccagca tcggcctttc
+     6901 gtcttgcgac aatttcgctc agtttttcct caacgctgtc gctcacactc tggacgacac
+     6961 cggggttctt catcagctct ttgacgaact tcactgcttt ctcttcgtct gtcgcaagct
+     7021 gtgagagcag ggccttgaac gcattctcta tgtgagagtc cttctccatc gcgaagtgct
+     7081 cgctgaagat catgcccgca atcgccaaga ctgcggcaac tgctgcaata acgaaggttg
+     7141 tgtagacgat gtaagtattg gcaatcgaga ctgcatccga cgatgcgaca gtgagcggcg
+     7201 tgctccagcg attgatcgca gtaaacgcaa caatcgatcc tgcgatccct ccgcagaacc
+     7261 cgccgagtaa gccgcgagtc tcgcgagcaa accaacgcgt aacaagccct ttttccccgg
+     7321 tcgccatcgt tcttaccttg taattttatc agagtactgg atgtatacac agtattgcat
+     7381 gcagcttcag gccgaagcat atcaccttag cgagatggtg caagtttagg cattcgtcaa
+     7441 gtggcttgca tgttcgaacg gttttttttc actgggggac agagtgccgg aagctcggga
+     7501 cacacaagcg aggaccggcc cgtggcgatg tcgatgtgta gatacgcggg agaggcggaa
+     7561 gagggcaact gtttaaccga gctcagtgca agctacagtg aaattacagt ttggatgagc
+     7621 ttgggtagcc ctgattggcc ttgatctgcc ttggttttgc agattgcgag ttgcgcaagg
+     7681 cattgattta taaaggactg tggtgcgctg ataaaactcc gaaggcaggg gttgctggtt
+     7741 cgatcccagc cgggcgcgcc aagcctagta aggcttccag ccgtttcgtt acttcatcgt
+     7801 attcccccgt tacagtgaaa ttacagttag ccggctgcgg tctgtagtgt ttccggcggc
+     7861 gctgacgctg tttcgcgcgg taactcgatc acctgcgcaa ccggcaagtg cgactgcacc
+     7921 cactgcgcca aatgtgccgc cgacaggtgt gcgtagcgct gcaccatctc cagcgtttcc
+     7981 cacccgccca actccttcaa tacctgtaac ggcgtgccgc gctgcacgtg ccagctcgcc
+     8041 caggtgtgac gcaggtcgtg ccagcggaag tcgctgatgc cggcgcgctt caacgccttg
+     8101 cgccaggctt cggtcacggt ctgatagacc ggccggccgt ggtagacgaa cacactgtcg
+     8161 acgtactcgg gtgcgcgctt cttcccgcgc tggcgcagca gcacggcgat cgccgtttcg
+     8221 gacagcggca ccgtgatcgc cttcttcgcc ttcgcctggt ccggatgaat ccaggcgacg
+     8281 cgccgcacga tgtcgacctg cgaccactgc aacccggtca cgttcgagcg gcgcagccct
+     8341 gtctccagcg cgaagcgcgc catgtcggcc aggtgctcag gcaactcggc cagcaaccgt
+     8401 tcggcctggg gcggcgtgag ccagcggata cgcttctgcg cgaccttcgt gcgcttcgtg
+     8461 accggcacgc ggtccagcca ttcccactcg acagccgcgt tcagcacggc cttcagcacg
+     8521 ccgattactc gcgtcacggt gccggcgctg acgcactcat cggtggtcac gatcccgtgc
+     8581 ttcgtgcgga tcaccttcgg ttccctccgt ttggcgaggg cgatagcgtc gatgcggttg
+     8641 cggtcgatgt cggtcaacgc gacgccggac aggtgttggt caagccagcg aaggtgcgtt
+     8701 ttcgacgttt ccaggctcgg cagcccttcg cgatcgccga cataacggac aaccgcatcg
+     8761 ttccaggtat agcggggctt gtggccgagc ttcacctggt tccacagctc gaccttcagg
+     8821 cggtcgtaga actcctgggc ttgtgctttg ttgctggtgc cagtgctgcc ttgtatgacc
+     8881 ggaccgccgc caggcggggt gagacggtaa taccagttgg gactgttact gcgtttatag
+     8941 agcgacatga ttcgagtttc tcctgcgggt cgccctgcac aactcgcgga atccattctc
+     9001 cggcgaggta acgctgcagg gcaactgtcg aaaacatcca gcgcttgccg accttccgac
+     9061 caggcagcgc gccagccttc gctttcaggc gcaccgtttc agggtgcgcg ccgagcagcg
+     9121 cggcggcttg ttcgaggttc acggtgttca tcgggctatc tcccgagtgc gacgcggcgg
+     9181 ggggaggggc aaaacaactc gtggattcgt ggcatgccct gtttttcgtg cgtaaccaac
+     9241 tgattcttaa ggtttttgat tgccatcatt tgccatgaaa aacccgtggc actcccttcc
+     9301 gactcgtggc ctaaaaaata ggcagcgccc gcgactcgtg gcaaaacgcg cccgactcgt
+     9361 ggcatggcgt atcggtcaat tttcgcccct tccacgtatt ctttcttctt ctttttcaat
+     9421 gaattagaga gagaagagaa agggacggcg gcggccggcg caaaaaccgg actagtggca
+     9481 aaaacgcatc gactggtggc aattcgaatg cgattcatgg cggctctcgc ttcaagaatc
+     9541 aaagacttac gagcggacag ccccgaaaac cacgattcgc gtgcgctgcc tgcccgttcc
+     9601 ctgtggaaaa accggcccgc gcgccccctc tccctcaagg cccgcgtagt tgcccggccg
+     9661 tttcgactcg cgggggggac ggggggaagc gggcagcacg gcggccgcgt gacgacgtgc
+     9721 gccgattgct gcgcgcatcg acgcacgcac cggaaacccg aatacagggc cgctacgcgg
+     9781 ccggaatgaa tgagggaaga ggaacggccg cacggcggcc gtatcggctg agagcgggtc
+     9841 atgcgcgacc ccgctgctcg gtcgcgtcgg tggccaagtc ttcgcgaatg gacacgtgca
+     9901 gcccgaaggc ggccaggcgg tccagcgaaa tcggcgtgag gtacggcacg cggcgcgtgt
+     9961 agatgcgccg ctcgacttcc ttctcgccga ccacgacgcc ggcgtgcttg agttgcgcct
+    10021 tgaacacgcg atccgatttc accggcaggc cgttccattt gtcgcgcagt gcgctcgtgt
+    10081 gggcgatgtg gtccatcacg tggcccgtgc gcagcagcag gcagaactcg ccgtcgacca
+    10141 tgtcgaacgt gtacgggtgc ttgtagttgc cgccgtcgat ctccgacagc acggtttcca
+    10201 tgatccacac ccacggctcg cgatcggcgc tcgtctcggc gatgtggccg ttcatttcgg
+    10261 cgagcaggtc gcgcgggaag tccccttcgc tcgggtccat gccggcgaac tcgcacaggt
+    10321 agcgccaggc gagcgcgacg gccgcatagt tgccggccat ccgcttcgcg ccgtcgtcct
+    10381 cgccgctcgc gcggcagttg gccagcgcct tgtcgcgcag tgtcgcgtac tggtcggaca
+    10441 cggcgcgctt gtccaagccg gcgaggaatt cgagccactg gcgaaccggg aagcgcggca
+    10501 ggtcgtcggg catcagcggg ccgcgcttgc cggtcagcgt cgtccgcaca agcttgccga
+    10561 gcaggctgcg caccggaacg tcctcgccgg ccagcatcac gggcgcgcac aacaggtatt
+    10621 cggtcatgtc ggtcccgcgt cgtgttacgg tgtactggta gttctcctgc agcaggccga
+    10681 ccgccttgtc gatcacgtcc tgccggcgcg cggacagctc ttcccatccg accgggtggc
+    10741 tcgtgtggct gatgctggtc agcaggcgga actcggtctg cagcgactgc cccgagaaca
+    10801 tcgtgaacgc gagcgagcgt tcaagccgct tgatgagcgt cgacttaccg gcgcccttgt
+    10861 tcgcctggat cgtgatgtgc ggccagaagc cgagcaacgc cttcaggtgg ccgccgagcg
+    10921 cccacacgag cgggatcgtc gccgcgttct gcttgaacgt cgcctggtac gcggtaatga
+    10981 cgcggcgcgc gtcgctggcc gggccggtcg ggaaggtcag gttgtgatac gggcactgct
+    11041 tgtcggcttc ggtgaagtag cagtccggtc cctcgttgac gatcagacgg ccatcgcgcc
+    11101 aggcgagccc gacgaagttc gccgcctggc gtgcgccgag gtcggcgccg cgctccagga
+    11161 tgttgaccat gcgcttgaac ggcgccggcg cccagatcgg gccgaacttg ccccactggt
+    11221 cgacgttgtg gagctggtcg tcgagcatca cgcggcgcac gagctgcgcg ccgtggcgcg
+    11281 gcgcttggac cgatacggcg aaatagacgg tgggtgcctg gtcagcgtcg cccgtcatcg
+    11341 tcgacgtcgc gctcgccacg gacacgcggc taatgccggc gatgcggaag ccgcacaggt
+    11401 ccgtcatgac gggcgtttcg acgccgcttt cctcgttctt gtccatcttc gtgatgtagc
+    11461 tggtgaagtc cggccgcacg cggaaacgcc agtactgcgc gaagtcgtgc gacggcagga
+    11521 agatgcgcgg ccggccgcga cgcgtggcgt cgccggcgag gccggcgatg agccacggct
+    11581 cgagctggtc gagtgcgcgc tgcagatcgg ccgggccgcg cagttgcagg tagtcgttca
+    11641 cgtcgttgat cggcttgacg gctttctcgc cgtccgcgag gtcggcgaac caattcgcct
+    11701 ggtcgacgag cacggcgctg atgttcagtg ccgtcaaccg ttcgtagagc gcccaggcag
+    11761 cttccggccc gggccggcgg ccggcgcgcg ggtggccgtc cgcgaacggc tcgtcattgt
+    11821 ccaggcagat cacgacctgt ttgccgcgca ggaacgcgaa gtcgatgccg tcgacgttcg
+    11881 ccaggccgcg cagcgcgagc gcggccgcgc catggatcgc gcaggtgtcg atcgacagcg
+    11941 cattgatcgc gctttcgacg atgaacacgc gcttcgcctt gtcgagccgg cgaggatcgg
+    12001 cggtccagcc gtagcccgct ttgtcgccct gggtctgcgt cttgacgccg ccgttgagcg
+    12061 cgggatcgac gtagcgcatg tcgacggcga cgacgcgcgc gtcgcccggt gcgcgcacga
+    12121 tgaacgccgc ggccgggccg gcgtggccga cttcgccggc ggcgaccttc gagctggtcc
+    12181 aggtgttgaa gccgagcgag cgcgctgcga tcgccgcgtc gatcgcagcg gcggaaatgc
+    12241 cgcggccgcc gaggtattcg cgcacctggt cacgctcggc gaagcaccga tcggcgatgt
+    12301 attcgaccgt cgttttctcg cggcgctctg cgggcgcctg gcgatcgagc gggatgccgt
+    12361 atgcatcgtg caggtagcgc accgcgtcgg cgaccgtgcc gccgcgcgcg tgaatgacca
+    12421 ggtcgatgca cgagccgccg acgtcggcgc tatggtcgcg ccagccggtg ccgtgcttcg
+    12481 ggtgattcac gtagatcgac agtgacgggc ttttgtcgtc gtgctgcggc gagtggtata
+    12541 gcgcgcggtc gccgccgcgg ccgcgcttca agccgaggcg atcggcgagg tcgtgcaggt
+    12601 cgatgcgttg tttcagttcg tcgatcgagg ccatcgttat tgctgttggt gcagggaaag
+    12661 ggcggcaggg ttgccgggtg tcgcggggct gtcgacgagc gcgcggagcg cgccggccga
+    12721 cgcggggaag gcaagcgcaa ggcgatcgcc gaggacgctg acgaacaggg cgagcgcggc
+    12781 gatgcgttgc atgccgccgg gttcatggtc gaagcgaagc acgtcggcgg ctgccgcgat
+    12841 ggaagccgcg agcgcggcat cgtgaggggt agtcgtgtgc ttcatgcggc ggcgcctccg
+    12901 aggatgtcgt gatggttctg ttgcaggcgc tgaacggcgt gctgcagctc gtagcgcgag
+    12961 gtgatcgcct ggtcgagcat ggtgcgcagg cgcttgcggt tgcgttcgag attcgacgtc
+    13021 gcgttcgcga gggctgcggt acgcgtcgcg ccgtggccga tgcgcatgcc cgatatcagg
+    13081 tgcgtgacga cgcacttttc ggggtggccg tcgtgcaggt gcgactcggt gtgaataccg
+    13141 aatgcggcgc cggcatcgtt cgggatgaca acatgatcgc cggcgacggt gcgcaggccg
+    13201 gccgaagtca gcagttcgta gcggatggtg ggctcgttcg tcatcgtgtc agctccgcgg
+    13261 cggcacagac caggccagcg ctgcgaccag gacgaccatt gcgatgacgc cgatcacgaa
+    13321 agcgatcggc cgggcgagcc gaacgtcgaa caggcgcagc acgtcggcgg ctaggtagta
+    13381 gacgccggtg agagaaaggg aaagcatcag cagcacgccg atgctgaaaa cgtagggctt
+    13441 catgatgtgg ttccaggtga gtacgccggc ggccggcgcg ggcggatcag tcgaagtcgt
+    13501 tcgcggcgcg gcgcttcccg tcgatggcag gcaactcgga cgcgggttct cgatcgcgcc
+    13561 acacgttcgc cgtgcattcg aaggcgtggc gggcagccgg gcacagggcg tcgaaattcc
+    13621 cgaccatgcg caggcggcgc cacatcgcgc gcaggtctag gtcggtgagg ggcgcgcgca
+    13681 tcggatcagt gcagaacgat gggcgtcagg acaggcatgc cggcgtcggc gtcccaatga
+    13741 cagcccaaca cgtagccgag ccggcgggcg gtgccgacga acacgagcgg atcgatgtcg
+    13801 gcgcgccaca gtgcgcgcag gtattcgcgg cgcttgtcga gcgacaggca agtcggatcg
+    13861 aactgcatca cgacggcggt agaggcgagg gtggccatgc gatctccttt ttttgggcaa
+    13921 aaaaagcccc tcgcgccggt taggcacgat gcgaggggaa aacaggggaa aggggtttag
+    13981 gtcgctagac gggcagttcg agctgctcga cgagacgctc gcgcacgttt ggtgagagcg
+    14041 gcaggtgtag cgacagattc ggggtcgcgg acggcgacaa ggtgcgcgcg aactccatgt
+    14101 tcacgatgta ggtgtggccg cactcgacgt tgttgcactg gaaggtgact tcccggaagg
+    14161 tctgggacat ttcgcggctg ctgcgcgcgg tcgcgcgcgt gcggcagtgc gggcagcggt
+    14221 tcaggattcg catgtcggct tactccggac gaggtacaag gcgcggccgc ggccgttcat
+    14281 ctgcttggca gtgcggcgaa ggcggcgctt ggcgagccac tcgactgtcg cttctaggga
+    14341 gggcaggtcg tgcaaggtgc gcacgcgttc cagcacgtcg cggtcggcgt ccgagagggc
+    14401 aatttccgtg ctggtttcgg gcatcggtgg agctactcat tgttggcggt tcggtgcctt
+    14461 cgctcaggcg ccggcgcggt ccagaatcga ggtgttgcgt tcggcgagta cagcggtcgc
+    14521 ttcgcgcatc acgatgtcgc ggattagcac ggcgagttgc tcgccctggt agttcgcgag
+    14581 cgccgtgaga acggcctgct cgtagtcgtc gaagcggacg gtgtgcttgt tgttgcggat
+    14641 gcgcttggga tcgggataca tgcaggcttc tcaattcacg agcgggcgga acgggaacgt
+    14701 gggatggcgc gcagctcgct cgcgccgatg cggatcagct cgcgcgccat gctcgaaatc
+    14761 gagcgattgc gctgctcagc gagctgttcg agctcgtcgc gttccgtgga agtgagccgg
+    14821 acgtacacgg gcttgtccga cagggtgccg cgtggcgatc ggcgcgggcc tttggcggta
+    14881 gtcatggtcg gtatactttg ttggttagcc ttgcgttacg gtaaggctag tgtaatgagc
+    14941 aaaaaacgtc tcgtcaacga tattaggaaa attatgtctc aagtggggag tcgcttgcgg
+    15001 gaagagcgct tgcggatcgg actgagccag gacgaatttg ccgccgtggg cggtatcact
+    15061 cggcgttcac agtcggcgta tgaatcggac gagcggtcgc ccgatgcaag ctatctgtta
+    15121 ggcgtccgcg caatcggcgt cgatatttac tacgtgctga ccggcgagcg aatttccgcc
+    15181 gagcatggag caggcgaggt gaaagcagac agtgaggagg cagagttcct ggaggtatat
+    15241 cggcaactca acgagactgg caaagcgacc ttgcaatcgt tcattggtag cgttctaaat
+    15301 caggccatca tgctcaagac gggcacgcca cggcgcgcga agcgcctgcc ggagaaccgc
+    15361 cgcgcagcgc tcgacgagcg catggcggaa aacgtcgatc gtgcgatggc ggaaatcgag
+    15421 cgtttgcgcg ccgagcgggc tgcgaaggac ggaaagaagt agtccgggcg cgtcgtcgcg
+    15481 cgcgggccat tcttcacaca aacactgtat atccatccag tattgggtta gcatcttgaa
+    15541 agccggcgat gctggcgacg tggacggatt ccgaggcaac cacgtcgtgt tgagtgccgc
+    15601 cggtccgtga acgtgtttgt gagggaccag aagaatgagc atcgacatga agcacaacaa
+    15661 cggcgcggtc ggcgtgttga cggctgccga tcgtcacgcg gacgcacgcg ccggagcaac
+    15721 gggccggata cgattccgtt cggacctgac tggaagcgag cgcgatgttg cgcgcgctgc
+    15781 gatcgacgat gccatgcagt ctgtcggcca ggtgctcgaa gttgcgcttc aggcgatggg
+    15841 aaatcttcgt gttgcacgcg cggcgcttgg gcggtgcgac gacgggccgc caatccgtgc
+    15901 gaatatgaat gatcgctaca attcgtagtt gaccgtctcc catagcaagc aacctgaagc
+    15961 ccgccgtgtg cgggcttttt actttccgcc tttcttgaaa tgcgaccggt gccgctcggt
+    16021 cgtcggatcg tcgcgcattt cgaggtcgag cccggtcgtg aatccgccgt cactgtcgat
+    16081 ggtgtgcgtt gccttcttca cgagccacgc ggtttcgtcg atttcgggct tgaagcccga
+    16141 cagcgtgacc ggcatttcgg ggaacagatc ggcgcggccg cgcgcgagcg aatagcgcat
+    16201 cgtcgcctgg ctgcgctgca tgcgcttgaa ctcggcctgc gccgcggctc gcgcttcggc
+    16261 ctccgtcgcg tagtcctccg gcagcacctt cacattcttg ttgttctccc cgccaacgat
+    16321 gaccgacttc cgcttcgcct tgccgttcga atggtagtgc gcgcgcacgg ccgagtaatt
+    16381 ttcccgttcg gacacgtggt acgcatgctg gtcgccgctc gcgcgcgtca gattcaacac
+    16441 ctcgaacgat ttcccgctga cggtcttgcc ggtgccgatc ggcgtgaaga gcagccgcaa
+    16501 atccttgacg ttcatcactg cgtcgtagcg cttcgccagc cgcgtcagaa acgacatatc
+    16561 gctttcgtgg gtctggtcga tgtgcgcgat cacgatcttc gccagcgtgt ccgcgacggc
+    16621 gggcgtcagc ttgtagcggc cggcgatcgc gcgcacgatc gagccgatcg tctgcttgtg
+    16681 ccagctcttc tcacgacgct cctgcatgcc gttcgacatc gaggccgagc gtgcgcgcac
+    16741 ggtcagcgtg tcgggcgcgc cgctatgttc gaactcggtc acgacgaacg tgcccttgtc
+    16801 gacgagctgc tcgccggccc agccgatcga caccttgatt tcatcgccgc gcttgggcag
+    16861 cgccagatcg ccgcgcgagt cgtcgagcac caggtcgatc gtatccgcgt cgtcagagcg
+    16921 cgattccgtg agggtcagcg attcgagccg cggcaggaac cgccgcgaga tgtcccggcc
+    16981 gccgagcgtg atgcggtagt cggccatcgg ctcgacacgt tcgagccgat acacagcagc
+    17041 gttcgagtgt tcggtcgcgc gcgtcgtcat gccttcggct ccgcgttcgc tgcatcatcg
+    17101 gcttccgctt catcgataag cgccgcatcc tggtcgatgc gcagcgcgtc gtcgtcgacg
+    17161 cattcgagcg tcaacgtgaa ttcgatcctg cgcgcggtgc cttcgcgggt gaagtaacgt
+    17221 cgcgtttcgt cgagccctac gatgaggtac gcgccgtaga cggtcccgag accgtcgacc
+    17281 aacacgtacg cttcgccgac gtttgccatc tggacgagct ggtcgagcga cgcgctggtg
+    17341 ccgatttgat ccggcgcgat gaggccgtcg agcgtgatga catcgtcgcc ctggccggtg
+    17401 tactggcgag catcgcgcgc gccgatacgc gacttcttcg gatgcttcca gttccggcgg
+    17461 cgcttcagct cgtggaaggg ggcggtagtc aggctgaaca cgaattgatc cagcgacagc
+    17521 aacatgggac agatcctccg tgaatgtcag tcggacaggc gcgagccggc gcgcccacgc
+    17581 tgcgcgcgtt cgcgacgatc cagctcggcg gccacggcgc gggcgatcgc gcgcggatcg
+    17641 tcgccggcct gcgggtaaat gttgatgacg atcgacgcag gcgcggcggc cgatgcagac
+    17701 gatgttgcag ccggacccga tgccgcgatc ggcggccgcc gatcgattgg cacgagtggc
+    17761 gcggccgtcg acagcgcggg tgtgccgaac ccggttacgg cggccgtcgc aagcccgagc
+    17821 gccgcgcgcg cgacgccgcg ctgctctccc gccataccga gcgcggcccc ctcgccgacg
+    17881 aatccgccca gctcggcgaa cacgcggctc gggctgtgaa tgccgagctt ttccttgaac
+    17941 cacgtcacgg ttgagttcgc gacgttcgtg atggcctcct tcacggcgcc caggccgttc
+    18001 gtgatgccgt tgaccaggcc cgatatcagg ttggccccga attccgccat cttctcggcg
+    18061 accttggcgg ccacgacgat gatgttcgcg agccattcac caaagccccg gcccgcgttg
+    18121 ctggccttgt ccagactttc cttgctcgcg tcgaccggcc ccaacaggcg ggaaatccag
+    18181 tcccacacgc ccttgacggc atccatcagc caattgaagg cgggcttgag cggctcgaac
+    18241 atcgcgccga gcacaccgaa tacgcggctg aaaatcggcg cgagcggttg cagaccttcg
+    18301 gtcaagccct gccagaagcc ggagaagaac gccttgatcg gttcccaata tcggacgatg
+    18361 agcagcgcgg ccagcgcgat cccggtgatg acgaggccga ccgggttcat gagcgccaca
+    18421 cggccgacga acatcagcat ttgagcgagc ccgccgagcg cggcgccgac gcctttgatt
+    18481 gcgccgactg caccgccctt gatgagaccg cccgcaccct tgagcgcatc gaccgacatc
+    18541 ccggcgacgc cgcggttgcc cgcgtactgc cgtgcggcgg tccagcgcga gacgacggcc
+    18601 gcgcgcgacg cggccgcctg agcggcgacc gcgcgccaca cctgggcggt gtattgccga
+    18661 gcggcgacca gaccgtcttt catcgacgtg gctgccgtgc ggctccactg cgcgacggtc
+    18721 gacacggccg cgcggccggc ggctgggatg ccttcgcgca gcgttcgtgc ataaccgcgc
+    18781 aacgtcgcca aagccgtgcg tggcgatgat gccgaccagg cggcggccag ggcggtgcgc
+    18841 atgcgcgcgg cggtcgtgcg cacagcattg ccgacaacag agaaccggga agccgcaccc
+    18901 gacaaccgcc cgaagccgcc cgcgctcgca ccgagcgtgc gcgcgagaaa gccgccctga
+    18961 atgccgagcg tcgccatgct gaatcgcacg atcgcgagcg gcccgagaat gcccgcgagc
+    19021 acaatcgtga acgtccccat gacgacgagc agcgcggcga acgcggcgag cacggacaga
+    19081 atgaccttca ccgcggcgcc gtggcgctga atcaggccga tgaggccgac gagaatctcg
+    19141 cgggtcttgt cgagcgccgc gttgtacagc ggtgcgatgc gctcgccgat ctcgcggcgc
+    19201 aagtcgcggc ccttcgcgag caggtcgttt tccttgccct gcgtttgcag cgcagcgagc
+    19261 ttcgccgcgt cgtcgatgcc gtatgcgccg cggttgagct tttcgttctt gtgaatctgg
+    19321 tcgcgctgca tgtacatagt cgtgaacaga ttcgacgcag tccggttggt gaagatcgtc
+    19381 gaaatcatgt ctttcacctt gtccggatca gtgatcccct tcgcggccag cttcggcaga
+    19441 aacacctttt ccagccattc gagcggcgac gccttgaaca gatcgccgcc agtgagcgca
+    19501 ccgggcttga tttccttgat cgtgccgatt ttcgtatcga tgaccttttt tcggtcgagc
+    19561 agcccgagcg cgatcatctg gttcgctgca cgcttcgttg tcttgccctg gtacgcgttg
+    19621 ctgtacgcgg acatgaggcc ggtgccgacg ccgtggccgc ccatttcctg gatcagcggt
+    19681 tccatctggt aatagaacgc gtcctggcgc atctgtttcg ccgcgacgcc gcccgtctgg
+    19741 atgaagttgc gccattcgtc gccgccgacg cgcccgccgg tcgccgacag caccttctgc
+    19801 accatgttcg cttcgttctt gaacgtcgct tcgtctttcg tgccgccgcg cagctcgatc
+    19861 accttcagca tgttcatgaa tttctcttcg ttcgcgtgcg cgtcttccgc gccgaacagt
+    19921 gcttcgttgg cgaacttcat tttcgcgagc gttggcatga ccatctgcgc gtgatgctcg
+    19981 tccgcgaaga tcgacaacgc gtcgcgcatc agcgtcatgt tgtcggacgt gctgacgccc
+    20041 atcatgttca tcgcgcgtac gtacttctcg gcgtcctgcg ttgcttggtc gccgaggccg
+    20101 agcgccgtga tgcgcgctcg ttcgttcgtc attttcttgg cttcgtcaag cgtgccgccg
+    20161 aggccgccga gcatgcgcat gccagtagac cgggcggcgt agccgccgat tgccatcccg
+    20221 ccggctacgc cctgcatcgc ctgcatcttg ccgcgcgctg cggcgagctt tcgatcgcgt
+    20281 tccgtcagcg cttcgagctg gcgcgtctgc gcctgcatcg tggccgtcgt cgacgcgatg
+    20341 tttgagcgca gcgtgcgctc gtgctgtgcg aggttgcgcg tctcgatgcc ggcctgcgcg
+    20401 agccggccgc gcatctcgtc gacggcggcc gcctgctttt tctgctcggc gcgtaagcgt
+    20461 gacgctgcct ggcgtgcgcg cgccatgtcg gcgaccatct gcttcgtggg cgggccgaat
+    20521 gcgtgcagtg agccggcgag cgccttcacg ttggattgcg ccgcgccgag cttcttcgtg
+    20581 gtgtcggcga gcccggcgcg catttcgcgg aacgaggcga cagctttctg ttgcttgccc
+    20641 agttcggcaa gctcgccacg cgtcgccttc aacgactgcg cgagcccctt gttgctgttc
+    20701 agcatgttcc gtaagggctt cgtccagttg tcgaccatgt cgaacatgac gcgcagtttc
+    20761 agggcgttgt ccatcgttac tcgtgtccgc ttcgtatccg ggcgcgctcg cgccaatcca
+    20821 tcagctcaga aagggaaagg tcgtccatgt cacggggtgt ccagccgaac accgtcgcga
+    20881 catcggccat cgcgtcttct acgcgttcag ggattccatg ctcgctttca gcgccttcgg
+    20941 catcaaaaaa ccggcgaaga taccccccaa tgccacgagg tcggccgggt ccatcaacgt
+    21001 gacatccatc tcggtcagcg tcggcgtgct gatgcgaggc agcaccttgc gcagcgcgtc
+    21061 cacgtcgagg ttcacgagtg ccgcgagcga cgtgccgcgc aaggcgcctg cggacggctt
+    21121 cgcaagggtc acatgcgtga tggtctgctc gccgcgcacg atcggcgtgt cgaaggtgtg
+    21181 cgtgttggcc gcgatcgcgt cgagcacggc gccgccggtg gtggtgttgt tggtgtcgag
+    21241 ggtcgtcatg ttgcgtatcc tgatgatgat ctaaagggat gcccgcggcg tgcgcggggc
+    21301 gaagcgttac aggccgattg cctggcgcag accggcgagc aggtcgttac cgttgatctt
+    21361 ctcgatcatg ttgatgaaat ccatctcgat cagatcctgg ccgttgatgg acagcttgta
+    21421 gtagctggct gccgtcgtga ccttgaaatc ggtgtcttcc ttcggcttgg ccgtacccat
+    21481 gtcgatttcc ttgtggcgac cgcgcacgac gatttcgacg gaatcgtagg tcttcgaatc
+    21541 ctcgcgctgg tagccgccgg agaaacggag ctgcacgccg tcgtgcgtgg tgatgccgta
+    21601 catccgaatg acatcctcca tgaagccgcc gcaggtccat tcgagctgga tagcctcctg
+    21661 gccgaagtcg atcggaatcg ggccgctcat gccgccgccc tggtaatcct ccatctttcg
+    21721 tgacagcttc gggagctgga tttccttcgt ctcgccgacg aagttggtgc cgttgtgaaa
+    21781 caggttgaag cctttcagct tgcggggcat acccatgtgt ttgactcctg gttaggccga
+    21841 cacgcgcgag gcgaaatcgg cgagatagcg atcggtgatg cgctggcgca gcttcaggtt
+    21901 ttcgagcggc gggaccggcg tgtagtcgta gtcgatccac gtgccgcccg acgtcagctc
+    21961 gtcggtcgtg ttcggctccg ggtcgtacca ggcgccgccg ccgatcagct cgccgaccga
+    22021 gacttcgcgg cggaaccacg cgttgatgtt ctcgatgatg tcccgcgcgc gcgacgggtt
+    22081 gagcgggccg tcgacgacgc ccatttgttc ttcggcgatc gtgtcggcga tcacctgcgc
+    22141 cgaacgcgtg tagttctcga agaagaactt gccgtccgcg tcacacgtgc gcgagcccca
+    22201 gaagcggaag ccgttccggt tgacgagcgt ggtgacctgg ttctcgttca gataacccgc
+    22261 gtccgtcgcc gggtcttgca aatcccacga cacgtccgcg ctgatgccag tcacgccgtt
+    22321 gacgacgacg ttcgacagcg tcttgtgcca gccgatgtcg ttgtcgatct tcgcgcgcag
+    22381 gccggcggcg atcgccggtg ccgggatggt gacggtcgag ttcgtcacgt cgtcccagcc
+    22441 gagccagtcc ggccagatca ccatgatttc gcgttgaccg aactgcttgc ggtacgcgac
+    22501 cgcctcttcc ttcgtcttgc agccgtgcgc cgccacgtaa acgaacgcgc gcagcgactg
+    22561 cgcgatcgtc gcgaatgccg cggcgacggg ctgcgtgtcg aggccgggtg cgaccaggat
+    22621 gcgcggcttc acggcgagct tcccctgcgc cgccagcagc gccttcatgc cggtgtactt
+    22681 gccgtccggc gtgacggtgc cgatgacgtt cgtcgtcgtc tcggcttcgt cctttccgtc
+    22741 cgcgacgcgc acgacgacgg tgacgggctt cgtctgcttg ccgatcgcgt cgagcgtgcg
+    22801 gcgcagcgtg cccttcgtgc cggccttgcc gagcgcggcg atgacgttcg tcagcagcac
+    22861 cggcgtgtcg agcgggaacg tcgccgggtc ggcgtcggcg ccggtgcaga caatgccgag
+    22921 cacggccgtg gagaccgtgc gaatcggccg gccgccttcg ttaatttcga tgacgcgtac
+    22981 gccgtggtgg taatcctgcg gcatggtatg caactcctat atgtatacag gtgagaggaa
+    23041 acgggagagc ccgttgtcag gtcgatgcga tgggggccgg ttgttgcggt tcgatcggct
+    23101 cggtgggcgc cacgtatggc gcgggcgttg cgggccacgc cacggcatcc ggaaacgtgt
+    23161 cggtgttgat cgtggacacg agcgccatct ggtacgcgga ccaggctttg aagtagtagg
+    23221 tgccttcgtc atcgagcagg ccggcggcat acgcatcggc cttccctgcg ttcgcgcgcc
+    23281 gtgcgatttc catcagtcgt tcgaactcgg ccatcgcggc gtcgcgtttt tcgcgtgcga
+    23341 tcagctcggg cggcaccgtc catgcaccgt cgatccacgc atgacgcggc gacggtcgcg
+    23401 gctcggtggt cagttccaga tcgtcgggcg tcttgccagc gatcgcgatt tcgacgggct
+    23461 cgccggtgtc ggtgcggtag cagacgcgtc cgcggaagtc cggcagcagg aaccaagcgc
+    23521 cgtcacgata gaacggccag gtggtcggcg tgcgcggcgg cggcgcatcg atcgtcgcgg
+    23581 acgatggaat gagccagcgg ccgtcattgc gcggatcggc gtcgggctgg ctgctggtca
+    23641 ggtattcgcc ggtcgacggg ctgtagtggt gaatcagcat gtttcgaggt ccgtaagtta
+    23701 gtaggcgcgg atcatggcga gcagcgtgat gttgcgtggc cgtgcttcgt tgccgccgtc
+    23761 tgcgccgatc gtgattgcat gcgagtgggc gccggcccca ccgatgccga cgttgtggcc
+    23821 gtgattcccg gcatcgttca gccaaatgcc ggtgccgcgc cggtcggtcg tgccgttgta
+    23881 ctggccgtcg ttctccgtgt tgtatccgcc accggtcagt tgactcgatc cgccgctatc
+    23941 ggtgttgcgt gcgatcacga caaacgggtg atcgtgtcca ggatcgttca catagtgatt
+    24001 gtggttgccc tgcccgtctg tccaggccga gtgcgcgtga tcgccgacag cagcggcgga
+    24061 tgcgccgtgc gcgtgcgaac ggttctggtc gccctggtac gagccgatgg cgcgctgcgg
+    24121 atcgatgtcg ttacggccgt ctgcccaaca gcggatgaac tcgccgcgca tctcgggcag
+    24181 gcggaacgtc gtcgcgccgt caccggtcga gaagcaaccc cagcgaccgt tcagccattc
+    24241 ggcctcggac acgagcgcgc cgcttgcctg agcgtaggcc cacagcgccg gatagtcggc
+    24301 gcgattcacg aggacaccgt tggctttgag gaaaccggcg cgcgccaatg tgcggggttc
+    24361 gaagacaatc tggccgacag tcacggtcga aatcgcagac agcacccatt ccgtcgtcgc
+    24421 caggcgcgtc gagcgatcgc cctgcggtgg cgtcggacct tggacgggtc gttcgaagtt
+    24481 cgttccactc ggcgtgaatg tcacctgggg gagcgagttg cacgtgatcc cgaacgaacc
+    24541 atctgcgatg tgataaaggc ccgtgtccgg cgctccgtcg ttttggaacg tgagcgaagg
+    24601 agaaccggca ctaccttccg acaggaaaat acgcttgccc ggatcgaacc acacgtccgc
+    24661 ggacatcgtt ccgcctttca ggcgatcgag tggcgtcacg ttgcccgagt gccacacggg
+    24721 ctttccgtcg acacggagcg aatggtcgga cgtgaagtat tggaacgagc ccgcgttgcc
+    24781 gccccaccag ccgacagaat tggggttgcc gtagaagtag ccgtcgatgg gacccagacg
+    24841 catacgtccc tcggatacgg cattgccaat cgtcagttcg ccgcgaatgt tgacgttgcc
+    24901 gccgagcgtc gcacccgacc ccagatcgtc gattctgacg aagccggatt cgagattcca
+    24961 tgcaaacgga cggaagtcgt tgaacgtgcc atccgggtca cccttcttcg tcgacagcag
+    25021 atagacgttc gtcccgtcat ttcgaaaaaa tgcaccgtag ccgccacacg ttgctcgaaa
+    25081 atgcgcaccg cctgcgtcca tttctcgcga ggttaagccc cccttgaacg tggcgcttcc
+    25141 cccggcttgg atcgcgttgc ggccatcgtc gccgacatcg ccgacgagca ggcgcttcgg
+    25201 aagtgaaaag acctgcgtgc ttcggtcgac gcgaaacgct gggaactgcg tgacgccatc
+    25261 gtcgtcgaac gcgttcaatc cgaagttgtt gccggcattt ccgccggtgg tagcgccatc
+    25321 tcgcttgaac agagaccacc gcaccttccc gccatcggca aagaacagtg tcgagaaact
+    25381 gccggcgccg ccgtcgattg aaacggcctt cgaatagctg gtgccttcgg tgacggtatt
+    25441 gccaccgacc agaagccgtg agccgccgtc gtcgttcttc acgtcgccga tgagaacgcg
+    25501 gccgccgtag gtgatgcgta cggcgcgcgc ctggtacccg tctgtctggg tgtcgttggc
+    25561 cgttttgttg agccagatat cgaggtactc gcgcccccac gcaccgccgt cgaaccccga
+    25621 ccggaccgtc gcgattagac gggtgccagt gtcgacgttg ttaccgccga acgtgccata
+    25681 caggcgaacc cgaccctcgc ggccggtctt accggacggt gggcgaatcg tgacgtgcgc
+    25741 ggcgtccggg cccgcgtcga actccgcgac gacggggccg gtaaatttcg cgccagtcag
+    25801 cgcggcgtac cgggctgcgg cagtcttcgg cgtgatggcg cgcgagtcgt ccgcgcccgc
+    25861 gtcgacttcg gcctgcgtgg cgagttctac gacgcccttg cgttcggtcg tcgccggcgg
+    25921 attcagaaac gtggccgggc caaactgaag ctgcgccgcg tcgatcgacg cgaacacgat
+    25981 gtcgctcgcg agcagcagca tggcggccgg cgacttttca agaatgggcg tgctctgcac
+    26041 gtagacaccg aacaacacgc cgttgtccag gtacaggccg tacgcgtaca acgtgtactg
+    26101 gtcgttcgtg tcgtcctgga tgacgacgtg cacggtgtcc ggcgcgacgt tttcgccgcc
+    26161 gaacgtcgtc acacgcttgc gctcgttcgg cagggtcttc atgcccttgt cgaacgcgaa
+    26221 cgcggcggtg ccgagaccga tttcggcgac gcggcgcgac gtgatgccgg tgttacccgc
+    26281 ggcgacgagc gctgcgcggc cggcgtcggt gatttgaatc aggtttccag ccatattcag
+    26341 gtatccgaga gggacaggcg gcaatagacc gcggcgcgcg cgccggcgcc gacgcgctgc
+    26401 gtgccggtct cgccaaagcc ctgcttgaag atgtagtgcg cggtaccgcg cttcgcgcga
+    26461 tcgacttccg cgcggatgtc ggcgacgtac tcggcggtcg cgggcacgcc gtcgcggctg
+    26521 ccgaccgtca gcacgatctc gaacgtgccg ggcttgccgc gtggcgtcat ctcgaaccac
+    26581 tcgcgcatcg ccacgttcgc gccgaacgac gcgcagacct ggcgcacggc ctcggccgtg
+    26641 cccttgatcc gggcaatgcg gatagcggtc ttcacgcgcg cgcgcttgac ctgctcgggc
+    26701 cagtagtctt tccaggtctc gacgccgacg tgccaggcga gccagggcag gaaggccagc
+    26761 gggattgcgt ccgggtccat cagcgtgccg atgtcgaccg ggatgccgct gattcgcgcg
+    26821 ttggtctcgg ccaagcgccg ctcgagcgcg gtcgcgttcg ggggcagcaa cgagggcatc
+    26881 ggcctattca tccgcgaccc cgccgtcgat cagctcgatt cctgtgcagt agggcgcctg
+    26941 ctcgcccgtc acggcgacgc cgccggccgg cgagtcgagc aataccttct gcacgcccgc
+    27001 cacgcgcatt gccgcgtgca ggccgtcgac cgtcacttcc atgccgatgc ggtgcatgtc
+    27061 ggcggcaaac ttcgccgtgc gcttgttcgc ttccgcgagc gcgaccgcgc gatccgggcc
+    27121 ggagaagaat cgcagcgtcg agcggatcgc gtagcgcacg atttttgcgc tttgcacgat
+    27181 cacttcatcg gtctgcggcc gcttgccttc cagattcttc ttcacgatct cgatcagctc
+    27241 ggcgctcgcg gtgccgtcac cttcgcgcga caggatcgtg acgaccatca cgcacggttc
+    27301 cgggctgaac gcggcggcgg acagcacgcg gccatcggcc gaacgcgcat ggaacacgta
+    27361 cgcttcttca ggaccggcga cggagaagcc gcgcggcgcg agctgcacgc gctcgcgcag
+    27421 gctgtcgtcg tcttcgtaga ccggatctac gccgttttca ggatcgccgg ccgagatgac
+    27481 caggcgttcc acgtcgaaga gggcggcgat gtgttcgagc gtcgtgccgc gtgcatatgc
+    27541 gagcaggatg ccgcgggcct tgtcgttgat gagctggcgc agcagcactt cgcgataggc
+    27601 gttttcttgc aacgatcgcg tcaacggttc ggattcgagc gcgagcgtcg cggcgatctc
+    27661 ggcgcgttgg tcggccgggt atagggaaat gagccgcgcc ttgcgttcag caaagaccgt
+    27721 ttcgaagtcg agcgggtcga cgatatcggg cgccggcagt tgcgacaggt cgatcggcgt
+    27781 cgttctcatg cgctgactcc tttcgacacg ggcacgcgca gcgatacggg ctcgtcgcgc
+    27841 tcgtcggtcc atccttcgat gtcgacgagc tgctgaccgg cgaacgcctc atcggtatcc
+    27901 gccacgagtt gcacgcgggt gatggtcaga cgcggctccc agcgcatcag cgcggcagcg
+    27961 gcggccgcat acaggcgaat gcgcgtcgcg ccattggtcg gtgcgtcgat caggtccggc
+    28021 agttccgagc cgaacgaacg gcgctggatg cacgagccga gcggggtcgt cagaatccgg
+    28081 ccgatcgact gcgacaggtg ttcgatgccc gaaatcgcgc gaccggtaac ggcgttcatg
+    28141 cccttcatgc gccaccccgg atcggcttcg acgtaacggc gaattcgccc tgcgcctggt
+    28201 gcgggtgatt gatgaggctg acgccgcctg cgcgcacgtc gccggtgagg tctgcactgc
+    28261 cgtcgatctt catcacggcg ccgccgtcgc cgcccttgcc ggtcataccg gattcgaacg
+    28321 tgagcgggcc tttcacggtc agcgatttcg tcacggtcgc gtcaccgtcg agcaggatgt
+    28381 gctcggcctg cacggtcgcg tccttcgtct gcacgacgac ggcgcccggt gcgacaacgc
+    28441 gtacggtcgc gccggccggc agcgcggccg tcagcgcgtg cgccgcgtgg tcgtagctga
+    28501 cgcgcgcgcc gtccgcgtag atgcgggtgt gggtgttcgg ggagttgtct ggtgccggcg
+    28561 cggcgtccga gtagaggccg cgcagggcga ctgcctgcgc gaagtcgccc atcgggccga
+    28621 gcagcacaac ctgctcgccc tttgtcggcg gaagccattc gcgcgtgctg ccagccgccg
+    28681 gcgtgagcca gggaatccag ttggtttgca ggccgtcgtc ggcggattcg ccgaccgcga
+    28741 cgcgacagag gcccgtgccg tagtcgacat cgagaatcga gcccttgcgc acggcgttgc
+    28801 gtgcctgccg ttgaatttcg ttcgcatcca tgccgaccat gttgccggcc gtcctcgcgt
+    28861 gacgcgagcg aatgcaaatg tcgtgctcgc gggtacagca tgctcgtcgc gcgcgcgagc
+    28921 aaacgtgagt cgacaatcgg cattacgcgc tcaacgacgt ggtttgcaca cgtcgcgagt
+    28981 gtccctttca cgctgcctct gaaccatgac gattcacatt tccgacgccg cgcccgcggc
+    29041 cgacattgcc ccaatgctca accagcttca tcgtgtcgat gcactcgcat tggcgcgcac
+    29101 actgccggat cagtccgtcg acctggtgtt caccgatccc ccgtacgcat cgggcggctt
+    29161 gcacctgtcc gcacgaacgc gcgcaccgag ccagaagtac atcaacagcg acacgaaggc
+    29221 ggtctatacc gacttcgaag gcgataacat ggatcaacgc gcctgggcgt tctggtgcca
+    29281 tgcctggctg accgagtgtc gccgtgcgat gaagcccggc gcgctactcg tttgcttcat
+    29341 cgactggcgc cagctcgcga cgttgacgga cgtggtgcag gcggccggcc tgacgctgcg
+    29401 cggcatcgcc gtatgggaca aaacgccagg tcgtacccgg ccgcgtcgag gcgggttcgc
+    29461 gcaacaggcc gaattcatcg tatgggcgag ccgcgggccg atgaacgata gcgacgtgta
+    29521 cctgccgggc gtgtttccga cgcggctggc gctgccgaag caacacgtca cggaaaagcc
+    29581 gatcgagctg gcacgcgacg tggtgcgcct ggtgcccgat ggcggcgtcg tgtgcgacct
+    29641 gttcgccggt tccgggacgt tcctggtcgc cgcccgcgaa gccggcctgc agtgggtcgg
+    29701 atgtgagacg agccaggcgt atcacgcgat cgcgtcgacg cgcctggctg ccgtgaatga
+    29761 ttcagcggtt gaggtagcgt agcagccggt cgcgcacgag ttcgcgatcg actgagctga
+    29821 agccgagcac gacgcgaacc ggatactgcg cgagcgggcc gcccggttcg acgggggcct
+    29881 tctggccttc ctggtgaacg cgcacgatgc gcgacaggcg gtcgtcgaag ccgatcgcaa
+    29941 gccccgtgtc gtcgacatcg atccgcagat agcgggcggt gcgcagcttg cgaaacatcg
+    30001 cctgccgctt gatgcggccg accttggcgc gcaagccctt gccgcccttc ttgatcttgc
+    30061 gcggcacgta cgcgctgccg tccgggtttt gctgcgcggc gacgcgcgac tgctgcgcgc
+    30121 ggcgcatatc gcgccccagc tcgcggaata gtcgccgacg agctgccggc gccagcttcg
+    30181 cgagcagccc gccggcccac ttctcaagtg cacgcagttc gtcgtccatc acaccaccca
+    30241 atgttcgtcc gcgtcgtcga cgtgttcgac cgtgcggcgg ccgtcgtcgt ccgtaccgac
+    30301 tacaacgctt tctgtaagtt tcagcttgat cgcgaggtcg acggcatcgt tggcgaggat
+    30361 gtcggcgatg aacgtcatcc catcgcggcg ctggtcggcg ttggtcacga ggtcgggctg
+    30421 gtttgcgcgc gcccattcga cgacggcgat catcacgtcg tcggcgctgc cgatgaagtc
+    30481 gcggatgaga atctcgcact cgtaccggta ttcgaacgac ggcgtgcgtg tgccggtcgc
+    30541 gacgatgtgg ccgtcgttga tgaagacgac gagcaggtcg ggcgcagcgg cgagctgcgg
+    30601 aagcgcagcg acgagcgcgg cgcgcaggct gttcggttta atcatgggcg ggggcctgcc
+    30661 ggttcggctg actgcgcgcc tggcactcgg ccaccatgtc gacttcggcc gcacagcgcg
+    30721 cccatgccgc ccgcgcgatg gtcagcgcgt cgctcagatc accgttcgtc tgcgggtgag
+    30781 ctgccggcag cgcgcaccgg gtcaccgtcg cgcacgcgtt gagcgtaatc gtcggcgccg
+    30841 gtgagggcgg ggctgctgtg caggcgcaca acgtcgtcag gcaggcgagc agtagcccac
+    30901 gcgcgaacgg cttcgttctc atcgacgagt ctccggagtt gcgattgata cgcggcgagc
+    30961 gtcgcgtcga ccgcgccgcg tgtgcggtcg agctgcgcgc gctgcaggtc tttctcgcgg
+    31021 gcgtccgtga gcagccggcc gatgattgcg tcgcgcgcac ccacgtcctg tttcgcctgg
+    31081 cgggcggcat cctgtgccgt ggcgaggcgt ccctgcagcg cgcgcacata ttgcgcgccg
+    31141 gcgaccgccg cgacgagcac cgcgagcgcc agccagaagc gaacgcccgg catgttcacg
+    31201 cggccgcctt cgcgccggcg tagcgttcgt acgcctgggc gagcttcgcg tcgtacaggt
+    31261 tgcgggcata gtccgggccg ttgtaaccct tcgcgaacgc cgcccacttc cggttcttca
+    31321 gcgcggacag cagcgacgag tcagccgcga cgaagcgcac gaacccgtcg agctggtcgc
+    31381 cctcgctcgt ctccatccgc gcgacgaact cgtcgatgct cgcgtagccg aggcgcttcc
+    31441 agtggtagcc catcacctgg aacgcgcccc agctcgccga ttcgtaggcc gatgccgcgt
+    31501 ggacgcgcgc ggcggtgtcg agccgcacgt attcggcggc gccgccctgg tagccgcccg
+    31561 gcttctggtt gacgacgttc gggaacagca gcgagtagtg gacggcgtca ttcgcgccga
+    31621 tgctgtcgac gagctgccga tacatgacat gccgctcgaa caggatcacg ggccgtccgt
+    31681 ccgccagaaa ccccgagccg cgtgattcca cttcgttgac ggcgcgcacg catgcgggcg
+    31741 acacgccgag cttgtccgcg gcgcgcgcga tgtccgcttc cgtcaggtgt ttgcggtcgc
+    31801 gctggccggc cgacagcacg gcgtacgtgt tcgggccggc gatcccatcg acgacgatcc
+    31861 cggccgcggc ctggagcgcc ttcaccgctt gctcggtcgc ttcgtcgtac aggtgggaca
+    31921 cgtcgagcgc gtagccggcg cgggcgagac gttgctgcag cagaccgact tccgcgccgc
+    31981 ggtcgttgaa acggaggata ttcatgattc gttgctccgg agaaggcgcg cgacgttccc
+    32041 gcgcgcgagg tacacaaaca gggccagcaa tacggcctgt acggcctgga agaagccgac
+    32101 cggtttcggg tggatgagca gctcgattgc cgagccgccg gaaatcgcga cgatcagcca
+    32161 ggccgtccag gcgacgtgcg aacggtgccg cgcgccgttc ttccggtagg tcagcacgcg
+    32221 caggatgacg gcgaggtgcg cggcgagtgc gaccagggca aacgacaggt gcatgtcatt
+    32281 tccccctgcg gatcagcgcg ccgaagtcga tatccttcac gcgctccatc agcgtcagcg
+    32341 tgaccgtgat gacgagcgcg gcggcgaaga acgcggcgac gcccgacgag cggaccggca
+    32401 cgatgtgggt gatttccggc gcggcgagat aacccatcac gagcgagatg agcatgtacg
+    32461 cggcgcgccg gccgatgccg aggtctttcg aggtgacgac gacaagcgcc gcgccggcga
+    32521 acgcgccaat cagcgcgtcg ccgtcgatgc ccggcgcgat gccggccagg ccgatcgcgg
+    32581 cggccagcgc tgcggcggta gtggtgttcg gttcagccat tcggacaatt ccaggtcagt
+    32641 caaacagttg caggaggggc ttcgtctgct cgatcgtgtt cagctcgggc atgtcgacga
+    32701 cggttcccat cggcagcacg acgcccagct cggcgaggcc gggattggct tccaggaccg
+    32761 cttcgacggt gccggccgtg ctggcgtagt ggcgccagca aacggcgtcg agcgtttcac
+    32821 cctgaagcgt ggagactttc atcagatcag ctcaaccgtc gagcgcgcga cgcccagaat
+    32881 gtcgctgatg gcccaccgcg cgttgcggcg cgactcgtcg acggttacgg ccagctcggc
+    32941 cgctacctgt ccgccgctct tcgtcgaatc gaagccgcgg tatttctccg tcacatccgc
+    33001 atgcgccagg tggtagaccg cgcgccggta acggaacaca tgcacggatt cgccgtcgac
+    33061 acgctcggcc ggcacgtcgg caagcgaacc cgcgcccgct gtccgctgcc gcgcgcgcca
+    33121 cgcggccagc tcgtcgttga cggtcagcat ggcgtcgcgc gcggcgtggc gcaggcgttc
+    33181 gcgcgtcacg gtgccgtcca ggcgcatcgc gtcgcgcagc gccgacaggt cgatgtccgg
+    33241 gaagaagccg tcgttcgtca gcgtgccgtc gatcggcgac gccgcgacgg caggcgcagc
+    33301 agtggcaacg aaactgttca tggtcgattc ggggagtgat ggcggtggac cgaaggtcag
+    33361 ggcctgtgtc cgtcaggcgt tgggccgtgc cttcggtgtc gccatgccgg ggtgggctct
+    33421 ttacgtgcct tcggcgccgt cgccctgacg gcccgtggct tcgatcagct tcgagagccg
+    33481 atcgatgtcc tttttcacgc cgacgcgatc gttcaacgat agcgcgcggc gcagatagtc
+    33541 gagggcgcgc ggcgggtcgg cttcctgtac ggcgtagccg agcgccttgc agagcttcgc
+    33601 gcgcacctgg tcgtgcatgt ccgcttcggc cgtcagctcg tcgaccagct ccaggctggc
+    33661 ggcttcgaac gtgctgcgct ccaggaacgc ggccagcgcg gcatcggcga actgttcggc
+    33721 gacgacggag gcgagcgacc gttcgaactg gtcgggcagc gcgagaccgt gcgtgagcgc
+    33781 gtaggcggcg atcgcgagcg caccgtcgta gtcgccggcg tcgatgcgcc agaccatgac
+    33841 cgtcacgagt acgtcgtcct gggcgccgcg gccgccgttc aacacgcccg ccacgtagtc
+    33901 ggcgtactcc ggcagcaact tccgcttcag ttcgaccttg cgggcgaccg actgcacgcc
+    33961 cttcagggcg cggcggtcgg ccgcgagctt cgcgagcatc agctcgtacg gcgtcgcacc
+    34021 ggccatcgtc tgaccaggcg cagtcgcggc cgccgcgcgg gcggccgaca cacgcgcgaa
+    34081 gtgcgcgcga gcgggcgtgt tgatcgtcat gccgccacca gctcgatgtt ttccgcgacg
+    34141 cagccgcaac cgaagtcttc gacgacatac gcgtcgttcg acgattcgta gttctcgatt
+    34201 tggtcgcgct tcgggttgtc gatcagcgag cgacggcgtg caccttcctg gaagtagatc
+    34261 gacaggtttt ccagcttcgt caccatcatc gcgcgcttcg ggaagaacgg cacacgcacg
+    34321 gccggcaggt tgccgatgcg cttctggctg acgatcaggt cggccgcgag ctgctcggtc
+    34381 ggtgcctgcg ccgtgttgac gatcgggaaa tacttgtcgt gcagcagctc gcggccgcag
+    34441 atcacgacga ggcccgtatc ttcctggaac cacgggtcga tcatcgacga cacgatgtcc
+    34501 atcacgagcg cgtcgaggtt cacatagtcg ccgcccttac cgacgagcac cttgccggct
+    34561 tccttcgcac cttcgtgcag cacgcggtgc cctgcgcggt cgcgatactg ttgcagccag
+    34621 ccgatattca cgtcctgcaa cagcgggttc gccgctttgt ccgtcgacag cgccgcctta
+    34681 acgccattcc agccgatcat gatccggtcg agcgcggact ggttgaggat cacgttgcgg
+    34741 atgcgctgct ggaagtcggg gaatttcgcc caggcgtcga gcttgcggta cgtaatggcc
+    34801 gtgtcgtagt cggttttttc gcagcggtag cggttgctat cgagcgcggt cgggtcgatc
+    34861 ggctgacgtt cagccttcgt cgtgtcggtg cggctcgcga tcggaccgga taccgacagg
+    34921 ccgagctttt cgccttccag ttcggtcacg ggcaggatgt tgatgctctt caggaatgcg
+    34981 ctcgattcct gcatcttggt ttcgagtgtt tgctggacgg acggctcgac ggcgaatttc
+    35041 tgcgacacgt cgtcggtgtc gttgagcttg gcaatttgcg cggcgtactt acggtacgcc
+    35101 tggcgcgttt ccttcttcat gagttgggtt ctccggggtg tgagcgtgga agggatcagc
+    35161 agtcggtcac gagctcgccg gtcgagccgg tcgacggctg gcgccgcggt gcgccgttat
+    35221 cggttgccga cagcttcgcg gtcagtgctt cgacggcggc gaccgcttcg tcggcacgct
+    35281 tcttcgcggc ggccgcgtct tgctgcgcgg cggtcaggtc gacgcgcagc gcggcgacat
+    35341 cgcggccctg ctgactcgcg aacccggcga tctcttcgac tgcgtggcgc acgtcagcat
+    35401 cacgttggtc gtccgtcgag cgattgcgcg cgaacatgcc tttgacgatg gagagcaggc
+    35461 tcgtcgattc gggttcgcct tcgaactcga tcgacgtttc gcacgcggcc gagaacaggt
+    35521 tgttcgaacg gcgcgccgcg aattgcagtg cttcggtgcc gaggctcgcc gggtcgtcgg
+    35581 tcgcggccag gccgaccaga tacgcttcgc cgatgtcggc gaagtcgggg ttgacttcga
+    35641 tcgatgtgaa aaccttctgg cgcttcttcg acagcgcgac cagctcgtcg gtcggatcga
+    35701 gctgcgcgta cagccccatc ttgcctttca gcgggccgtc ttcgatctcg gatgccttca
+    35761 gcgcgatcac atcgccatac gcgccgaacg ggttggttgc cgagagcggc gcccatccct
+    35821 tcaggtgctc gatattgaga cgcgcgccgt acagttcgcg gttgtagttc ttcgccatct
+    35881 gcgtgagcca ttcgcgcttg atctcgcgac cgtcgacagt cgcaccttcg accgcgacgc
+    35941 ggaaaaactt cgttttgttg gttgccatag agagaggtcg aaccgtgggt cagtgaatgt
+    36001 ggttctcatg ttcgaccttc acgcgctacg gctcaacgag cggcgtgtgt tgctcgcacg
+    36061 ggtacgtagt gcttcgcgtg atcgcgcgcg cgcgtcgccc tacgcttgcc gcatgctcga
+    36121 aacgacaaat ccaattcaac gcgaagcgaa cgtgcgacag atcgcgcgct cgctctactg
+    36181 gcaaggctgg cgcatctcgt cgatcgcacg gcatctcgaa ctgaagcccg cgaccgtggc
+    36241 gtcgtggtgc cgtcgcgaca agtggaaaga cgcaacgccg atcgagcgca tcgaggcggc
+    36301 ggccgaaacg cgcctgatgg tcctgattgc gaaggacaag aaggacggcg cggactacaa
+    36361 ggaaatcgac ctgctcggcc ggcagattga gcggctcgcg cgcgtgcaga aatacgggga
+    36421 gacggggaag gaaggcgacc tgaaccccaa catcgccgcg cgcaatgccg ggccgaagcg
+    36481 caagccgccg cgcaacgaaa tcagcgagga acagcacgag cggatcgtgg cggcgttccg
+    36541 cgaatcgctg ttcgactacc agaaggtctg gtatcgcaat ggcgatcaac gcacgcgcaa
+    36601 catcctgaag tcacggcaga tcggcgcgac ttggtatttc tcgcgcgaag cgttcgtcga
+    36661 cgcgctcgaa accggccgca atcagatttt tctgtcggcc agcaaggcgc aggcgcacgt
+    36721 cttcaaacag tacatcgcgc agttcgcgcg tgacgcggcc gacgtggaac tgaccggcga
+    36781 tccgatcatc ctgccgaacg gcgcgattct gtatttcctg gggacgaacg cgcgcacggc
+    36841 gcagtcgtat cacggcaatt tctatttcga cgaatacttc tgggttccga agtttcgcga
+    36901 gctgaacaag gtcgcgtcgg gcatggcgat gcacaagcgc tggcgcaaga cctacttcag
+    36961 cacgccgtcg agcatcacgc atgaggcgta tgcgttctgg agcggcgcgc acgcgaaccg
+    37021 cggccgcgca gccgccgatc gtatccagat cgacacgagc cacgaagcgc tcgtgcgcgg
+    37081 catgctgggc gaggacgcac agtggcgcca gatcgtgacg attctggatg cgatggcggg
+    37141 cggctgcgac ctgttcgaca tcgacgagct gcgccgcgaa tacagcgccg aggaattcgc
+    37201 caatctgctg atgtgcgcgt tcatcgatga ttcgctgtcg gtgttcaagc tggccgagct
+    37261 gcagcgctgc atggtcgact cgtgggagga atgggccgac gacttctcgc cgctgctgct
+    37321 gcgcccgttc ggctatcgcg aggtatgggt tggctacgat ccggcgctga ctggcgactc
+    37381 ggccggcctg gtcgtcgtgg cgccgccgcg ggtcgagggt ggggcgtttc gcgtgctcga
+    37441 acgtcatcag ttccgcggta acgacttcga ggaacaggcc gcggcgatcg agcagatcac
+    37501 gcagcgctac aacgtcggct acatcgcgat cgacacgaca ggcatggggc agggggtcta
+    37561 tcagctcgtg cgcaagttct acccggccgt cgtcgcgttg aactactcgc ccgaggtgaa
+    37621 aactcgcctc gtgctgaaag ggcaatccgt tatccgcaat ggccgcctgc aattcgacgc
+    37681 gggctggacc gacctggccg ctgccttcat ggcgatcaaa cagaccatga cgccgagcgg
+    37741 tcgacagacg acgttcacgg ctgaccggaa cgacgagacc ggtcacgcgg atctagcgtg
+    37801 ggcctgcctg cacgcgatcg accgcgaacc gctcgccggc ggcgacatca attcttcatc
+    37861 tttcacggag ttctattcat gagcaagcgc cgatcgcgcg cgccgcgcac gttcgcggcc
+    37921 gcgccggatt cgggcgccgc cggcgccgcg ccggcgcgcg ccgaggtctt caccttcgac
+    37981 gatcccacgc cggtcatgaa ccgggcggag attctcgatt acgtcgaatg ctggtcgaac
+    38041 ggcgattggt tcgagccgcc tgtcagcttc gccggcctgg cgaaatcgtt tcgcgcgagc
+    38101 acgcaccaca gctcggcgct gtacttcaag gcgaacgtgc tggcgtcgac attccggccg
+    38161 cacaagtggc tgtcgcggca cgcgttcgaa cggtgggcgc tcgattttct gacgttcggc
+    38221 aacggctacc tggaacgccg ccgcaatcag ctcggcgaca cgctgcgact cgaaccagcc
+    38281 ctggcgaaat acacgcggcg caaggcagat ttcagcggct tcgtgtacgt gaacggctgg
+    38341 caggacaagc acgagttcga gccgggcagc gtgttccagc tcatgcgacc ggacatcaac
+    38401 caggaggtgt acggcctgcc cgaatatctc agctcgcttc actcggcgtg gctgaacgaa
+    38461 tcgtcgacgt tgttccggcg gaagtactac gaaaacggga gccacgccgg cttcatcctc
+    38521 tacatgaccg acgcggcgca gaaacaggag gatgtcgaca acatgcgcac ggcgttgaag
+    38581 aacgcaaagg ggccgggcaa tttccgcaac gtgttcatgt acgcgccggg cgggaagaag
+    38641 gacggcatcc agctcattcc cgtgtcggag gtcgcggcga aggacgagtt cttcaacatc
+    38701 aagaacgtga cgcgcgacga cctgctcgcc gcgcatcgcg tgccgccgca actgctcggc
+    38761 atcgtgccga gcaactcggg gggcttcggc acgccggaca ccgcggcgcg cgtgttcggc
+    38821 cggaacgaaa tcaagccact gcaggcgcgc ttcgccgagc tgaatgactg gctcggcgaa
+    38881 gaggtcgtgt cgttcgacga ttacgagatt ccgccggttc cggcggccga gtagcgcacg
+    38941 cggcgattcg aagtcatgcg gcagggccgc gcaccgggca accgggcgcg gccctttttg
+    39001 cgtttggggc cggcgcgatt agaggggcta cagcggcttg gccgtccgca gggtgcgcaa
+    39061 gggtcggacg ccgcaaggcg ggagccgcag cgagcctgtc gtccggccgt gcagggtgtc
+    39121 ccgcggggtg gggagggggc agggaggccc gcgccgcgcc cgccgctgcg cggtcccctc
+    39181 cccgcc
+//
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_renumber_gbk/test-data/renumbered.gbk	Fri Jun 17 13:13:47 2022 +0000
@@ -0,0 +1,1063 @@
+LOCUS       NODE_2_length_39       39186 bp    DNA              UNK 01-JAN-1980
+DEFINITION  NODE_2_length_39186_cov_113.152335.
+ACCESSION   NODE_2_length_39186_cov_113
+VERSION     NODE_2_length_39186_cov_113.152335
+KEYWORDS    .
+SOURCE      
+  ORGANISM  .
+            .
+FEATURES             Location/Qualifiers
+     gene            57..345
+                     /locus_tag="MS105_0000000001"
+     RBS             57..60
+                     /locus_tag="MS105_0000000001"
+     CDS             70..345
+                     /locus_tag="MS105_0000000001"
+                     /product="hypothetical protein"
+     gene            complement(408..723)
+                     /locus_tag="MS105_0000000002"
+     CDS             complement(408..713)
+                     /locus_tag="MS105_0000000002"
+                     /product="hypothetical protein"
+     RBS             complement(719..723)
+                     /locus_tag="MS105_0000000002"
+     gene            complement(888..1173)
+                     /locus_tag="MS105_0000000003"
+     CDS             complement(888..1160)
+                     /locus_tag="MS105_0000000003"
+                     /product="hypothetical protein"
+     RBS             complement(1170..1173)
+                     /locus_tag="MS105_0000000003"
+     gene            complement(1180..2369)
+                     /locus_tag="MS105_0000000004"
+     CDS             complement(1180..2358)
+                     /locus_tag="MS105_0000000004"
+                     /product="hypothetical protein"
+     RBS             complement(2367..2369)
+                     /locus_tag="MS105_0000000004"
+     gene            complement(2399..2975)
+                     /locus_tag="MS105_0000000005"
+     CDS             complement(2399..2965)
+                     /locus_tag="MS105_0000000005"
+                     /product="hypothetical protein"
+     RBS             complement(2973..2975)
+                     /locus_tag="MS105_0000000005"
+     gene            complement(2984..3146)
+                     /locus_tag="MS105_0000000006"
+     CDS             complement(2984..3136)
+                     /locus_tag="MS105_0000000006"
+                     /product="hypothetical protein"
+     gene            complement(3137..3265)
+                     /locus_tag="MS105_0000000007"
+     CDS             complement(3137..3250)
+                     /locus_tag="MS105_0000000007"
+                     /product="hypothetical protein"
+     RBS             complement(3144..3146)
+                     /locus_tag="MS105_0000000006"
+     RBS             complement(3263..3265)
+                     /locus_tag="MS105_0000000007"
+     gene            complement(3269..3507)
+                     /locus_tag="MS105_0000000008"
+     CDS             complement(3269..3490)
+                     /locus_tag="MS105_0000000008"
+                     /product="hypothetical protein"
+     RBS             complement(3505..3507)
+                     /locus_tag="MS105_0000000008"
+     gene            complement(3638..4310)
+                     /locus_tag="MS105_0000000009"
+     CDS             complement(3638..4300)
+                     /locus_tag="MS105_0000000009"
+                     /product="endonuclease"
+     gene            complement(4297..5531)
+                     /locus_tag="MS105_0000000010"
+     CDS             complement(4297..5520)
+                     /locus_tag="MS105_0000000010"
+                     /product="methylase"
+     RBS             complement(4307..4310)
+                     /locus_tag="MS105_0000000009"
+     gene            complement(5507..5956)
+                     /locus_tag="MS105_0000000011"
+     CDS             complement(5507..5938)
+                     /locus_tag="MS105_0000000011"
+                     /product="Vsr endonuclease"
+     RBS             complement(5528..5531)
+                     /locus_tag="MS105_0000000010"
+     gene            complement(6206..6823)
+                     /locus_tag="MS105_0000000012"
+     CDS             complement(6206..6811)
+                     /locus_tag="MS105_0000000012"
+                     /product="hypothetical protein"
+     RBS             complement(6820..6823)
+                     /locus_tag="MS105_0000000012"
+     gene            complement(6824..7338)
+                     /locus_tag="MS105_0000000013"
+     CDS             complement(6824..7327)
+                     /locus_tag="MS105_0000000013"
+                     /product="hypothetical protein"
+     RBS             complement(7335..7338)
+                     /locus_tag="MS105_0000000013"
+     gene            7428..7644
+                     /locus_tag="MS105_0000000014"
+     RBS             7428..7430
+                     /locus_tag="MS105_0000000014"
+     CDS             7441..7644
+                     /locus_tag="MS105_0000000014"
+                     /product="hypothetical protein"
+     gene            7623..7847
+                     /locus_tag="MS105_0000000015"
+     RBS             7623..7626
+                     /locus_tag="MS105_0000000015"
+     CDS             7635..7847
+                     /locus_tag="MS105_0000000015"
+                     /product="hypothetical protein"
+     gene            complement(7827..8964)
+                     /locus_tag="MS105_0000000016"
+     CDS             complement(7827..8948)
+                     /locus_tag="MS105_0000000016"
+                     /product="integrase"
+     RBS             complement(8960..8964)
+                     /locus_tag="MS105_0000000016"
+     gene            complement(9156..9851)
+                     /locus_tag="MS105_0000000017"
+     CDS             complement(9156..9842)
+                     /locus_tag="MS105_0000000017"
+                     /product="hypothetical protein"
+     gene            complement(9839..12634)
+                     /locus_tag="MS105_0000000018"
+     CDS             complement(9839..12634)
+                     /locus_tag="MS105_0000000018"
+                     /product="zinc finger CHC2-family protein"
+     RBS             complement(9848..9851)
+                     /locus_tag="MS105_0000000017"
+     gene            complement(12637..12899)
+                     /locus_tag="MS105_0000000019"
+     CDS             complement(12637..12885)
+                     /locus_tag="MS105_0000000019"
+                     /product="hypothetical protein"
+     gene            complement(12882..13256)
+                     /locus_tag="MS105_0000000020"
+     CDS             complement(12882..13244)
+                     /locus_tag="MS105_0000000020"
+                     /product="hypothetical protein"
+     RBS             complement(12895..12899)
+                     /locus_tag="MS105_0000000019"
+     gene            complement(13249..13454)
+                     /locus_tag="MS105_0000000021"
+     CDS             complement(13249..13443)
+                     /locus_tag="MS105_0000000021"
+                     /product="hypothetical protein"
+     RBS             complement(13253..13256)
+                     /locus_tag="MS105_0000000020"
+     gene            complement(13440..13620)
+                     /locus_tag="MS105_0000000022"
+     CDS             complement(13440..13604)
+                     /locus_tag="MS105_0000000022"
+                     /product="hypothetical protein"
+     RBS             complement(13452..13454)
+                     /locus_tag="MS105_0000000021"
+     RBS             complement(13618..13620)
+                     /locus_tag="MS105_0000000022"
+     gene            complement(13686..13908)
+                     /locus_tag="MS105_0000000023"
+     CDS             complement(13686..13898)
+                     /locus_tag="MS105_0000000023"
+                     /product="hypothetical protein"
+     RBS             complement(13904..13908)
+                     /locus_tag="MS105_0000000023"
+     gene            complement(13985..14246)
+                     /locus_tag="MS105_0000000024"
+     CDS             complement(13985..14233)
+                     /locus_tag="MS105_0000000024"
+                     /product="ogr-like transcriptional regulator"
+     gene            complement(14221..14438)
+                     /locus_tag="MS105_0000000025"
+     CDS             complement(14221..14424)
+                     /locus_tag="MS105_0000000025"
+                     /product="hypothetical protein"
+     RBS             complement(14243..14246)
+                     /locus_tag="MS105_0000000024"
+     RBS             complement(14436..14438)
+                     /locus_tag="MS105_0000000025"
+     gene            complement(14464..14672)
+                     /locus_tag="MS105_0000000026"
+     CDS             complement(14464..14661)
+                     /locus_tag="MS105_0000000026"
+                     /note="KL3 gp11"
+                     /note="HHpred to MobC, Arc, RelB, > 98%"
+                     /product="ribbon-helix-helix DNA binding protein"
+     gene            14623..15462
+                     /locus_tag="MS105_0000000027"
+     CDS             14623..15462
+                     /locus_tag="MS105_0000000027"
+                     /note="This start is more in line with where BLASTp
+                     alignments begin and leaves space for a divergent
+                     regulatory DNA sequence between genes"
+                     /product="repressor protein correct start?"
+     RBS             complement(14670..14672)
+                     /locus_tag="MS105_0000000026"
+     CDS             14704..15462
+                     /locus_tag="MS105_0000000027"
+                     /note="This start is more in line with where BLASTp
+                     alignments begin and leaves space for a divergent
+                     regulatory DNA sequence between genes"
+                     /product="repressor protein correct start?"
+     CDS             14995..15462
+                     /locus_tag="MS105_0000000027"
+                     /note="This start is more in line with where BLASTp
+                     alignments begin and leaves space for a divergent
+                     regulatory DNA sequence between genes"
+                     /product="repressor protein correct start?"
+     gene            15621..15928
+                     /locus_tag="MS105_0000000028"
+     RBS             15621..15624
+                     /locus_tag="MS105_0000000028"
+     CDS             15635..15928
+                     /locus_tag="MS105_0000000028"
+                     /product="hypothetical protein"
+     gene            complement(15979..17082)
+                     /locus_tag="MS105_0000000029"
+     CDS             complement(15979..17070)
+                     /locus_tag="MS105_0000000029"
+                     /product="P2 D homolog; tail protein"
+     gene            complement(17067..17539)
+                     /locus_tag="MS105_0000000030"
+     CDS             complement(17067..17525)
+                     /locus_tag="MS105_0000000030"
+                     /product="P2 U homolog; tail protein"
+     RBS             complement(17079..17082)
+                     /locus_tag="MS105_0000000029"
+     RBS             complement(17535..17539)
+                     /locus_tag="MS105_0000000030"
+     gene            complement(17547..20788)
+                     /locus_tag="MS105_0000000031"
+     CDS             complement(17547..20774)
+                     /locus_tag="MS105_0000000031"
+                     /product="P2 T protein; tape measure protein"
+     RBS             complement(20786..20788)
+                     /locus_tag="MS105_0000000031"
+     gene            complement(20899..21261)
+                     /locus_tag="MS105_0000000032"
+     CDS             complement(20899..21249)
+                     /locus_tag="MS105_0000000032"
+                     /note="nearly identical to gp18 of KL3"
+                     /product="P2 E protein; tail protein"
+     RBS             complement(21258..21261)
+                     /locus_tag="MS105_0000000032"
+     gene            complement(21307..21829)
+                     /locus_tag="MS105_0000000033"
+     CDS             complement(21307..21816)
+                     /locus_tag="MS105_0000000033"
+                     /product="tail tube protein"
+     RBS             complement(21825..21829)
+                     /locus_tag="MS105_0000000033"
+     gene            complement(21832..23018)
+                     /locus_tag="MS105_0000000034"
+     CDS             complement(21832..23004)
+                     /locus_tag="MS105_0000000034"
+                     /product="P2 tail sheath"
+     RBS             complement(23014..23018)
+                     /locus_tag="MS105_0000000034"
+     gene            complement(23057..23692)
+                     /locus_tag="MS105_0000000035"
+     CDS             complement(23057..23680)
+                     /locus_tag="MS105_0000000035"
+                     /product="tail fiber protein"
+     RBS             complement(23690..23692)
+                     /locus_tag="MS105_0000000035"
+     gene            complement(23698..26346)
+                     /locus_tag="MS105_0000000036"
+     CDS             complement(23698..26334)
+                     /locus_tag="MS105_0000000036"
+                     /note="hit Milo tailocin (69% identity) over 100% coverage
+                     (780aa) starting from position 105 to 878"
+                     /product="tail fiber protein (BceTMilo like)"
+     gene            complement(26337..26893)
+                     /locus_tag="MS105_0000000037"
+     CDS             complement(26337..26879)
+                     /locus_tag="MS105_0000000037"
+                     /product="tail protein"
+     RBS             complement(26344..26346)
+                     /locus_tag="MS105_0000000036"
+     gene            complement(26884..27801)
+                     /locus_tag="MS105_0000000038"
+     CDS             complement(26884..27789)
+                     /locus_tag="MS105_0000000038"
+                     /product="baseplate protein"
+     RBS             complement(26891..26893)
+                     /locus_tag="MS105_0000000037"
+     gene            complement(27786..28157)
+                     /locus_tag="MS105_0000000039"
+     CDS             complement(27786..28148)
+                     /locus_tag="MS105_0000000039"
+                     /product="baseplate wedge"
+     RBS             complement(27797..27801)
+                     /locus_tag="MS105_0000000038"
+     gene            complement(28145..28952)
+                     /locus_tag="MS105_0000000040"
+     CDS             complement(28145..28936)
+                     /locus_tag="MS105_0000000040"
+                     /product="baseplate protein"
+     RBS             complement(28154..28157)
+                     /locus_tag="MS105_0000000039"
+     gene            28891..29247
+                     /locus_tag="MS105_0000000041"
+     RBS             28891..28894
+                     /locus_tag="MS105_0000000041"
+     CDS             28900..29247
+                     /locus_tag="MS105_0000000041"
+                     /product="hypothetical protein"
+     RBS             complement(28950..28952)
+                     /locus_tag="MS105_0000000040"
+     gene            29239..29782
+                     /locus_tag="MS105_0000000042"
+     RBS             29239..29241
+                     /locus_tag="MS105_0000000042"
+     CDS             29249..29782
+                     /locus_tag="MS105_0000000042"
+                     /product="hypothetical protein"
+     gene            complement(29762..30239)
+                     /locus_tag="MS105_0000000043"
+     CDS             complement(29762..30229)
+                     /locus_tag="MS105_0000000043"
+                     /product="tail protein"
+     gene            complement(30229..30657)
+                     /locus_tag="MS105_0000000044"
+     CDS             complement(30229..30645)
+                     /locus_tag="MS105_0000000044"
+                     /product="tail protein"
+     RBS             complement(30236..30239)
+                     /locus_tag="MS105_0000000043"
+     RBS             complement(30655..30657)
+                     /locus_tag="MS105_0000000044"
+     gene            complement(30759..31209)
+                     /locus_tag="MS105_0000000045"
+     CDS             complement(30759..31199)
+                     /locus_tag="MS105_0000000045"
+                     /product="spanin (s)"
+     gene            complement(31196..32018)
+                     /locus_tag="MS105_0000000046"
+     CDS             complement(31196..32005)
+                     /locus_tag="MS105_0000000046"
+                     /product="endolysin"
+     RBS             complement(31207..31209)
+                     /locus_tag="MS105_0000000045"
+     gene            complement(32002..32286)
+                     /locus_tag="MS105_0000000047"
+     CDS             complement(32002..32274)
+                     /locus_tag="MS105_0000000047"
+                     /product="holin"
+     RBS             complement(32015..32018)
+                     /locus_tag="MS105_0000000046"
+     gene            complement(32276..32632)
+                     /locus_tag="MS105_0000000048"
+     CDS             complement(32276..32620)
+                     /locus_tag="MS105_0000000048"
+                     /product="hypothetical protein"
+     RBS             complement(32282..32286)
+                     /locus_tag="MS105_0000000047"
+     RBS             complement(32630..32632)
+                     /locus_tag="MS105_0000000048"
+     gene            complement(32636..32853)
+                     /locus_tag="MS105_0000000049"
+     CDS             complement(32636..32842)
+                     /locus_tag="MS105_0000000049"
+                     /product="P2 X protein; tail protein"
+     gene            complement(32842..33321)
+                     /locus_tag="MS105_0000000050"
+     CDS             complement(32842..33321)
+                     /locus_tag="MS105_0000000050"
+                     /note="100% identical to KL3 gp37"
+                     /product="capsid completion protein (L)"
+     RBS             complement(32851..32853)
+                     /locus_tag="MS105_0000000049"
+     gene            complement(33421..34124)
+                     /locus_tag="MS105_0000000051"
+     CDS             complement(33421..34110)
+                     /locus_tag="MS105_0000000051"
+                     /product="terminase endonuclease subunit (M)"
+     gene            complement(34107..35134)
+                     /locus_tag="MS105_0000000052"
+     CDS             complement(34107..35120)
+                     /locus_tag="MS105_0000000052"
+                     /product="capsid protein (N)"
+     RBS             complement(34122..34124)
+                     /locus_tag="MS105_0000000051"
+     RBS             complement(35131..35134)
+                     /locus_tag="MS105_0000000052"
+     gene            complement(35156..35984)
+                     /locus_tag="MS105_0000000053"
+     CDS             complement(35156..35968)
+                     /locus_tag="MS105_0000000053"
+                     /product="capsid protein (O)"
+     gene            35976..37882
+                     /locus_tag="MS105_0000000054"
+     RBS             35976..35978
+                     /locus_tag="MS105_0000000054"
+     RBS             complement(35982..35984)
+                     /locus_tag="MS105_0000000053"
+     CDS             35993..37882
+                     /locus_tag="MS105_0000000054"
+                     /product="terminase ATPase subunit (P)"
+     gene            37867..38934
+                     /locus_tag="MS105_0000000055"
+     RBS             37867..37870
+                     /locus_tag="MS105_0000000055"
+     CDS             37879..38934
+                     /locus_tag="MS105_0000000055"
+                     /product="portal protein"
+ORIGIN
+        1 tttgtttttt ttttttttca agcagaagac ggcatacgag ataatgagcg gtgactggag
+       61 ttcagacgtg tgctcttccg atctgtcccc tccccgcctg cgggcttcgc ttggcagggc
+      121 ggttttagtg cactgggtcg accagctcgg cggcccttgt ggcgcgggat ttcgcgtgat
+      181 tcgcgggggc cggaaatcgt gcgttttgat gctcgacgat gcgcaatcgt gcaaccgcac
+      241 gaccgtcgaa ggccgttcgc tgcgatcgcc ggttcacgcg gggcgccgtc gccgacagtg
+      301 ccggcgacgg cgccggccgg tcaggctcgg ctgtcgtttc gttgacgggg tagagctgca
+      361 gtgcgctacc aatggtcggc gcgtgtcgcg ctcatcctcg gccgaagtca ctttctcttg
+      421 cgacgggcgg atcctcgcga ggtaggaagc gagccaacat caatgtcgtg acgttgagcg
+      481 gtccaatact gcagcttcga aatctcgatg agcagatcat cagagcgatc ccggagatcc
+      541 cgatagttgt agcgatcggc cgcaatacga atcgactcaa gtcgcgcccg ccaatatgcg
+      601 ggatcgcgga tcgacgcccc aagcggaaac tcgtcgcggt ttttcgaaag ggtttgtagg
+      661 gcatttttta catgcaccag atctcgttca atcccatcgt aacgatcaca catacttacc
+      721 cccgtaagcg tattgcccac aatacagcgg ccacggctgc tctggctcat aagattcagt
+      781 tagaggtaga aagagagccg tgcctcgtac cccctacggg acacggcccc aacacgggaa
+      841 tcaattgctc ccgcgagcca actacacaac cttacggcac gctcacttca caattccgcg
+      901 cgcgtcaaat gtcgggttcc ggatgatgtg tcgagtgttc gccatgtcgg cacactatgc
+      961 gcggcattgg agcggactcc acttctgttc gcgttttcga cgctcgtttt atgtgatgcc
+     1021 agatctaccg ccaacagtcc gaaatcgata atcgccacgg cgaccaatgc aatcacccat
+     1081 cggatatttc tcgatcttcg caccttcttt gaagggacgc cgtaaagcag acgctcatag
+     1141 tcttccggat cgatcggcat atcctaggtc tccgtcgcgt cattcgacca atcgcgcagg
+     1201 cgtgagcgcg ccatagtacg gcccgacacc acctgccccc gatgcttggc atttgtccgg
+     1261 attgttgctc atctccattt ggatgtattt cccgcttccg ccaactgctt gatcaatgtg
+     1321 tacacacgca aatgcaagga tccgctcgta ggacgttgtc gtgagatcct gaacaatcgg
+     1381 gaccaggaca tactcgcaag ctttgttgcc ggcggcgcta cagtcgttga cggatgtgta
+     1441 cagcgttgtc ttcgtgccag gttggatata ggtgcacgtt gcgtctggtg tggagcaaac
+     1501 accacttggc gatccaattg atgacgggtc tggattaccg ttggatatca agttgcgcac
+     1561 ggtcggcaca tcgttggcgg ttgtatcgaa agtcgtccat tgacctgctt cgcaaggacc
+     1621 agcgtggtat gacgaggtca cataaaaggt gtacggttgt ccgaccgttt ggttgggctg
+     1681 gcctgagcca ggcggtgtcg tggacgttgc gactttgggc tttccgttcg tcgaatccca
+     1741 gtactggtca tacatgcact tcgtcagcgc aaccgggaat agcgcacccg aaccaacgtt
+     1801 tccggggtcc gaaatgaccg cgacagccac ggcgttctcg ggtacagact ggaaccccca
+     1861 aagcctcgcc agaaatgaag gaacgccgcc gccattcttc gttccagagc ggctgacaac
+     1921 cacctgcact gcaggcttgc cgacggccgg cgatgacggc atcgaggttt gaaggccctt
+     1981 gacgctaccg gtgacgtccc agtaaccgta cgacacatcg gacgtatatc ctgtcagcgt
+     2041 tttattcgac gacttgttta acgagacacc cagcacagcc tgggcttggg ccgtcgccca
+     2101 atctggaact gcggcctttg tattgctgca ttgcgctcgc gggtagatgc atggcgctcc
+     2161 ggccagggcg gcagcatcgg ctgcgttctg cagttcattc cggacaacaa aaagatagcc
+     2221 gacgtcgatt gcgagggcgg caaagccgag cagaatcgac atcaagaaag cgacggttat
+     2281 cgctaccgca cctctctgat tctgacgagt cttcaaaccg cagcgcatgt gcattgactt
+     2341 tctgggcgcg caaggcacac ctacagaccg tgaacgagtg cgatccatga ccggctcctc
+     2401 attcattgtt catgacagtg gtagccgtca acgtcagcag cttgcttaac ggaccaatcc
+     2461 acgaacccaa agccagtcca gtgaatttgt acgtgacggt aacagtaagg ggtgtgccaa
+     2521 agcttccacc ttgaccagac ggtacggaga cggttggtgt tgacgtgctg cccaagctga
+     2581 tgagatggct ttggcagtag ttgagagcga cggtctgtat gtcggttgtt gtcgctttcg
+     2641 gcgttttgag aacaatcccc gcgcgcgcac cttcccggct tgcgtttgtg atgacggctt
+     2701 ggtcgaacat cacaagtccg aactcgataa tgccgaacag aatcagtagc agcacgggaa
+     2761 gtaccagtgc aaattccaca acagcaacgc ctcgttgctt ctgccagttt ttccgattcg
+     2821 tcattttttt tccccgttga gccaagcctt tgtggcttgc agcgtccgct gaccaggtcg
+     2881 ccatcagtgc gtcgattcgt cgcatttgaa tgcgcagatg gaggcgcgcc atccggttgc
+     2941 gcgaaccgaa cgagccgggt cccaaataca cgcccacact tggtcagtga cttagcaaaa
+     3001 cgcgcgccat acgcagtccg cgcttgtggc atgaggcgct tgattgagct atgggcggac
+     3061 aaaaaatggg gtggcatcgg aaatgtttca ggcttgtacc gtgaaacaca aattcggcgt
+     3121 cgaccgcgcc tcccacctac aagctcatgc acgttagaag gggagagatt ggcccggaag
+     3181 attcaaatct gaaacgccga agagtccgaa gggtgaccgt cgacatccct ctccgttgtt
+     3241 cgcggggcaa atccaggacg ggctctttct atctccctgc gcatgccggc cggctcagcc
+     3301 gcccggctaa ggcgacagcc gcaagcgggt gaggtctcgt ctgcccgcga cagaccggtg
+     3361 gcgagccgga ggccttgtgc cacgcagcgg cacggggccg ggtcagagtc ggaagatgcc
+     3421 gactctgacc cggcgcgcgc agttgtgacc ccgccccacc tgcccgtaaa aatgagcggt
+     3481 ttttatgcac tcatgcaccg ggtgctccgg gccgcccggc gtgggccgcg cggcgatcgg
+     3541 tggggcgatt tcgttatgca gttttatgcg ccttggttat gcattctcgt catccagcga
+     3601 gttatggcgc aactccggcc gcagggcgat ctcataccta gggctgttgg tcgggcccca
+     3661 agacgtgatg cgatgccggg aatgagatgg tggcgaagta attctgtaca tcccgaatga
+     3721 tgtgctcttg cgtctcttcc cgaaccttgc acttttctgc ccatgcacgt cccggatgca
+     3781 agacgtccca tcgcggacgc aacccgttgt atcgaccgct gcctggatcg tgattcccaa
+     3841 agccatcaat caaagcgttc caaagcggtg caaacttcga gatcagcagc gactcgccca
+     3901 gcgggatcca aatgtcgtcg accaccaaga agcggcagac gaaatccttg atgtctaagt
+     3961 tggcggcaag ctgaacgctt tctgcgtgct ctcgtaggcg gtcgtaaagg gctttgctgc
+     4021 gaacctcacc tacgccgccg cctttgcgag cacccttcgg cactgctttc ccaacataaa
+     4081 tgggagcctg aagcacaccg tttcgattcc gttcggccaa gggcgcgtaa gcttcgaagt
+     4141 cgccaacgta atagatggca tagatgccga caccaaagaa ttgcttcaac tcgccaagag
+     4201 gctgcggttt ctgttcgagc atcgcctcag cgacacttgc gccgaggttc ttcttgtcga
+     4261 gcggattaaa ggggatgatg tttccaatcg aatccgtcat gccgcccctc gcgctgttac
+     4321 gcgccggcgc gccagttgct caagttgaac gatcgccaac cgctccgcga cgcttcgtgc
+     4381 cacgacgtgg ccaagtgcga cagggacggc gttaccgagc tggcgcatgg tttctgtcca
+     4441 tgaaccgtgg aacttgaagc cgtcggggaa ggtttgcaca cgcgccgact cgcgaatcga
+     4501 gaaatagcgg accgagccgt ccgtgttgac aagcatgttc tcgccgcccg gcacgccatg
+     4561 atcgccagct ttcagagttt tagctggcaa atcgagcggg ctgccggtgt ggccgggata
+     4621 gacgcgggca cccggctgga agcgatgatc ctggtattga ctcgccgtcc gcgcaagtgg
+     4681 gctcggtagg cctgcaatcg cgtcacggac ggttcgccaa ggcaactcgg tcgcgaacgg
+     4741 gagcgagcca gcgaggcgcc gcacgcggct tgccaccgat tctggcatcg tcggccgcgc
+     4801 acggcgcggc acttggtggc gttcccaata ttcgccagtg atccattggt cgcgtagcag
+     4861 gctgtcgtag ctgtgcgtcg ggcgtggaaa gctccaatcc acgtcaaggt cggaacggaa
+     4921 gcccacgatg aatacgcgct cacgcttttg cggaacgcca tagtcggcag cattcaccaa
+     4981 cgtgggaacc acgttgtaag tcagcttttt gcccttctgg cggccgctcg tgcgttcggc
+     5041 ttgcaagcgc aggagatggt cgaaccattc ctcgttgcgg cgtgccggca cctctggaaa
+     5101 ctcgagctgc agcaggatgt attggtagta gttggcaaac gtggagcgcg tcaggccctt
+     5161 gacgttttcc acgatgaagg ctttcgggcg cagtttgcgc acgatatcca ccgttgcagg
+     5221 gaacatgtcg cggctgtcgt cgtgtgcctg atgcttgccg cccatcgaga acggttggca
+     5281 cggcggaccg cccgctaaca ggtcgatttc ctctccttct aggctcgacc agtcaaattt
+     5341 gcgaacgtca ccctcgtaaa gtggccaatc cgccaccaag ggaaagcctc gccgctggtt
+     5401 ctcacgaatc gtgtcgcatg cccatcgatc ccattcgacc accgccagag gcttgaagcc
+     5461 ggcaaggccg acccccatcg cgaggccgcc cgcgcctgcg tatagctcaa ctgccttcat
+     5521 tgttgttctc cgtgtcgtct aagaaggccc tgacacggag ggtcaggacc acctcatcct
+     5581 tcacttcaca ttcccatatt gtcaaaactt tccagccgag cgcgctgagt tgtcgctcga
+     5641 cttccttatc tcgttcggca ttcgcctcaa gcttgggccg ccaaaaatcc agtcgcgatt
+     5701 tcggcaggcg cgctagacgg caaccttcgt gccggtgcca gaagcatccg tggacgaata
+     5761 tcaccttgcg tctcttcgag aacaccaagt cgggacgtcc aggcagccct tttccgtgaa
+     5821 gccggtaacg gtagcccaag cgatggatca ggctccgaac gatcagttcc ggcttggtgt
+     5881 tcctgccttt gatgcgcgac atgcgctcgc tgcgctccgc aggggtaaga ctatccaaga
+     5941 cggcctccgc gctcatgccg gggcgattgt aacgccttga agggtagacc gggcgtgttg
+     6001 agcgattggt gcggcgagca actcgggatg tttggcaact gcgagattct cgcggcagcc
+     6061 agttgcggcg tggccctttg tttgcgcccg ggcaggcgtc gatagagggt cgacagaagg
+     6121 tgcttcaatg cggcttggtc ataactggcc ggacgtggct tgggcaaaaa aaagctcgcc
+     6181 gtagcgagct ttagttgatt ctaggttagc gcctagcgag catatttttt actcggtatt
+     6241 ccatcgcagg attcgatacg cggaaacgag gcgccatttg agcagtgaat cgatccagtg
+     6301 gcatcttttc cgtgccgttt tcacgcttgt aagcgtcgat gatcggcttg ccgacggacc
+     6361 ggatcaactc cgcgggcatg aggagttccg ccgcgaagtt gtttgcttcc gactcgtgtc
+     6421 tcgtccaata agattcgctg cgactcatcg tgctcttgtc atcaacgaac tcaagccgcc
+     6481 cctcgacgcg gtgcatgcaa aagtggccaa tttcgtgcgc aagcgtaaac ctacgccgcg
+     6541 gttcatacgc gttctggttg gtgtttatcc agaccttggc tctaccttcg ggctcgagcg
+     6601 agatcaggcc cacggtatcg ctatcgaccg gcgctgacgt tgagccgtgg taagtgggcg
+     6661 actcgataac atcgatacct aagagttttg cgacagcgtc gacgtcgacc ggcggtgcac
+     6721 ccgcaaagat ctcgtagtcg aattcgtcct tcaggtattt ccccaaatcc gacacggtca
+     6781 acatttgggg ggcagcagtt tgagtaacca tgtgacctcc ctcttacgaa gattgcaaat
+     6841 cgtccaaggc atccttctcg ttgcgagcat cattcgcccg ctggccagca tcggcctttc
+     6901 gtcttgcgac aatttcgctc agtttttcct caacgctgtc gctcacactc tggacgacac
+     6961 cggggttctt catcagctct ttgacgaact tcactgcttt ctcttcgtct gtcgcaagct
+     7021 gtgagagcag ggccttgaac gcattctcta tgtgagagtc cttctccatc gcgaagtgct
+     7081 cgctgaagat catgcccgca atcgccaaga ctgcggcaac tgctgcaata acgaaggttg
+     7141 tgtagacgat gtaagtattg gcaatcgaga ctgcatccga cgatgcgaca gtgagcggcg
+     7201 tgctccagcg attgatcgca gtaaacgcaa caatcgatcc tgcgatccct ccgcagaacc
+     7261 cgccgagtaa gccgcgagtc tcgcgagcaa accaacgcgt aacaagccct ttttccccgg
+     7321 tcgccatcgt tcttaccttg taattttatc agagtactgg atgtatacac agtattgcat
+     7381 gcagcttcag gccgaagcat atcaccttag cgagatggtg caagtttagg cattcgtcaa
+     7441 gtggcttgca tgttcgaacg gttttttttc actgggggac agagtgccgg aagctcggga
+     7501 cacacaagcg aggaccggcc cgtggcgatg tcgatgtgta gatacgcggg agaggcggaa
+     7561 gagggcaact gtttaaccga gctcagtgca agctacagtg aaattacagt ttggatgagc
+     7621 ttgggtagcc ctgattggcc ttgatctgcc ttggttttgc agattgcgag ttgcgcaagg
+     7681 cattgattta taaaggactg tggtgcgctg ataaaactcc gaaggcaggg gttgctggtt
+     7741 cgatcccagc cgggcgcgcc aagcctagta aggcttccag ccgtttcgtt acttcatcgt
+     7801 attcccccgt tacagtgaaa ttacagttag ccggctgcgg tctgtagtgt ttccggcggc
+     7861 gctgacgctg tttcgcgcgg taactcgatc acctgcgcaa ccggcaagtg cgactgcacc
+     7921 cactgcgcca aatgtgccgc cgacaggtgt gcgtagcgct gcaccatctc cagcgtttcc
+     7981 cacccgccca actccttcaa tacctgtaac ggcgtgccgc gctgcacgtg ccagctcgcc
+     8041 caggtgtgac gcaggtcgtg ccagcggaag tcgctgatgc cggcgcgctt caacgccttg
+     8101 cgccaggctt cggtcacggt ctgatagacc ggccggccgt ggtagacgaa cacactgtcg
+     8161 acgtactcgg gtgcgcgctt cttcccgcgc tggcgcagca gcacggcgat cgccgtttcg
+     8221 gacagcggca ccgtgatcgc cttcttcgcc ttcgcctggt ccggatgaat ccaggcgacg
+     8281 cgccgcacga tgtcgacctg cgaccactgc aacccggtca cgttcgagcg gcgcagccct
+     8341 gtctccagcg cgaagcgcgc catgtcggcc aggtgctcag gcaactcggc cagcaaccgt
+     8401 tcggcctggg gcggcgtgag ccagcggata cgcttctgcg cgaccttcgt gcgcttcgtg
+     8461 accggcacgc ggtccagcca ttcccactcg acagccgcgt tcagcacggc cttcagcacg
+     8521 ccgattactc gcgtcacggt gccggcgctg acgcactcat cggtggtcac gatcccgtgc
+     8581 ttcgtgcgga tcaccttcgg ttccctccgt ttggcgaggg cgatagcgtc gatgcggttg
+     8641 cggtcgatgt cggtcaacgc gacgccggac aggtgttggt caagccagcg aaggtgcgtt
+     8701 ttcgacgttt ccaggctcgg cagcccttcg cgatcgccga cataacggac aaccgcatcg
+     8761 ttccaggtat agcggggctt gtggccgagc ttcacctggt tccacagctc gaccttcagg
+     8821 cggtcgtaga actcctgggc ttgtgctttg ttgctggtgc cagtgctgcc ttgtatgacc
+     8881 ggaccgccgc caggcggggt gagacggtaa taccagttgg gactgttact gcgtttatag
+     8941 agcgacatga ttcgagtttc tcctgcgggt cgccctgcac aactcgcgga atccattctc
+     9001 cggcgaggta acgctgcagg gcaactgtcg aaaacatcca gcgcttgccg accttccgac
+     9061 caggcagcgc gccagccttc gctttcaggc gcaccgtttc agggtgcgcg ccgagcagcg
+     9121 cggcggcttg ttcgaggttc acggtgttca tcgggctatc tcccgagtgc gacgcggcgg
+     9181 ggggaggggc aaaacaactc gtggattcgt ggcatgccct gtttttcgtg cgtaaccaac
+     9241 tgattcttaa ggtttttgat tgccatcatt tgccatgaaa aacccgtggc actcccttcc
+     9301 gactcgtggc ctaaaaaata ggcagcgccc gcgactcgtg gcaaaacgcg cccgactcgt
+     9361 ggcatggcgt atcggtcaat tttcgcccct tccacgtatt ctttcttctt ctttttcaat
+     9421 gaattagaga gagaagagaa agggacggcg gcggccggcg caaaaaccgg actagtggca
+     9481 aaaacgcatc gactggtggc aattcgaatg cgattcatgg cggctctcgc ttcaagaatc
+     9541 aaagacttac gagcggacag ccccgaaaac cacgattcgc gtgcgctgcc tgcccgttcc
+     9601 ctgtggaaaa accggcccgc gcgccccctc tccctcaagg cccgcgtagt tgcccggccg
+     9661 tttcgactcg cgggggggac ggggggaagc gggcagcacg gcggccgcgt gacgacgtgc
+     9721 gccgattgct gcgcgcatcg acgcacgcac cggaaacccg aatacagggc cgctacgcgg
+     9781 ccggaatgaa tgagggaaga ggaacggccg cacggcggcc gtatcggctg agagcgggtc
+     9841 atgcgcgacc ccgctgctcg gtcgcgtcgg tggccaagtc ttcgcgaatg gacacgtgca
+     9901 gcccgaaggc ggccaggcgg tccagcgaaa tcggcgtgag gtacggcacg cggcgcgtgt
+     9961 agatgcgccg ctcgacttcc ttctcgccga ccacgacgcc ggcgtgcttg agttgcgcct
+    10021 tgaacacgcg atccgatttc accggcaggc cgttccattt gtcgcgcagt gcgctcgtgt
+    10081 gggcgatgtg gtccatcacg tggcccgtgc gcagcagcag gcagaactcg ccgtcgacca
+    10141 tgtcgaacgt gtacgggtgc ttgtagttgc cgccgtcgat ctccgacagc acggtttcca
+    10201 tgatccacac ccacggctcg cgatcggcgc tcgtctcggc gatgtggccg ttcatttcgg
+    10261 cgagcaggtc gcgcgggaag tccccttcgc tcgggtccat gccggcgaac tcgcacaggt
+    10321 agcgccaggc gagcgcgacg gccgcatagt tgccggccat ccgcttcgcg ccgtcgtcct
+    10381 cgccgctcgc gcggcagttg gccagcgcct tgtcgcgcag tgtcgcgtac tggtcggaca
+    10441 cggcgcgctt gtccaagccg gcgaggaatt cgagccactg gcgaaccggg aagcgcggca
+    10501 ggtcgtcggg catcagcggg ccgcgcttgc cggtcagcgt cgtccgcaca agcttgccga
+    10561 gcaggctgcg caccggaacg tcctcgccgg ccagcatcac gggcgcgcac aacaggtatt
+    10621 cggtcatgtc ggtcccgcgt cgtgttacgg tgtactggta gttctcctgc agcaggccga
+    10681 ccgccttgtc gatcacgtcc tgccggcgcg cggacagctc ttcccatccg accgggtggc
+    10741 tcgtgtggct gatgctggtc agcaggcgga actcggtctg cagcgactgc cccgagaaca
+    10801 tcgtgaacgc gagcgagcgt tcaagccgct tgatgagcgt cgacttaccg gcgcccttgt
+    10861 tcgcctggat cgtgatgtgc ggccagaagc cgagcaacgc cttcaggtgg ccgccgagcg
+    10921 cccacacgag cgggatcgtc gccgcgttct gcttgaacgt cgcctggtac gcggtaatga
+    10981 cgcggcgcgc gtcgctggcc gggccggtcg ggaaggtcag gttgtgatac gggcactgct
+    11041 tgtcggcttc ggtgaagtag cagtccggtc cctcgttgac gatcagacgg ccatcgcgcc
+    11101 aggcgagccc gacgaagttc gccgcctggc gtgcgccgag gtcggcgccg cgctccagga
+    11161 tgttgaccat gcgcttgaac ggcgccggcg cccagatcgg gccgaacttg ccccactggt
+    11221 cgacgttgtg gagctggtcg tcgagcatca cgcggcgcac gagctgcgcg ccgtggcgcg
+    11281 gcgcttggac cgatacggcg aaatagacgg tgggtgcctg gtcagcgtcg cccgtcatcg
+    11341 tcgacgtcgc gctcgccacg gacacgcggc taatgccggc gatgcggaag ccgcacaggt
+    11401 ccgtcatgac gggcgtttcg acgccgcttt cctcgttctt gtccatcttc gtgatgtagc
+    11461 tggtgaagtc cggccgcacg cggaaacgcc agtactgcgc gaagtcgtgc gacggcagga
+    11521 agatgcgcgg ccggccgcga cgcgtggcgt cgccggcgag gccggcgatg agccacggct
+    11581 cgagctggtc gagtgcgcgc tgcagatcgg ccgggccgcg cagttgcagg tagtcgttca
+    11641 cgtcgttgat cggcttgacg gctttctcgc cgtccgcgag gtcggcgaac caattcgcct
+    11701 ggtcgacgag cacggcgctg atgttcagtg ccgtcaaccg ttcgtagagc gcccaggcag
+    11761 cttccggccc gggccggcgg ccggcgcgcg ggtggccgtc cgcgaacggc tcgtcattgt
+    11821 ccaggcagat cacgacctgt ttgccgcgca ggaacgcgaa gtcgatgccg tcgacgttcg
+    11881 ccaggccgcg cagcgcgagc gcggccgcgc catggatcgc gcaggtgtcg atcgacagcg
+    11941 cattgatcgc gctttcgacg atgaacacgc gcttcgcctt gtcgagccgg cgaggatcgg
+    12001 cggtccagcc gtagcccgct ttgtcgccct gggtctgcgt cttgacgccg ccgttgagcg
+    12061 cgggatcgac gtagcgcatg tcgacggcga cgacgcgcgc gtcgcccggt gcgcgcacga
+    12121 tgaacgccgc ggccgggccg gcgtggccga cttcgccggc ggcgaccttc gagctggtcc
+    12181 aggtgttgaa gccgagcgag cgcgctgcga tcgccgcgtc gatcgcagcg gcggaaatgc
+    12241 cgcggccgcc gaggtattcg cgcacctggt cacgctcggc gaagcaccga tcggcgatgt
+    12301 attcgaccgt cgttttctcg cggcgctctg cgggcgcctg gcgatcgagc gggatgccgt
+    12361 atgcatcgtg caggtagcgc accgcgtcgg cgaccgtgcc gccgcgcgcg tgaatgacca
+    12421 ggtcgatgca cgagccgccg acgtcggcgc tatggtcgcg ccagccggtg ccgtgcttcg
+    12481 ggtgattcac gtagatcgac agtgacgggc ttttgtcgtc gtgctgcggc gagtggtata
+    12541 gcgcgcggtc gccgccgcgg ccgcgcttca agccgaggcg atcggcgagg tcgtgcaggt
+    12601 cgatgcgttg tttcagttcg tcgatcgagg ccatcgttat tgctgttggt gcagggaaag
+    12661 ggcggcaggg ttgccgggtg tcgcggggct gtcgacgagc gcgcggagcg cgccggccga
+    12721 cgcggggaag gcaagcgcaa ggcgatcgcc gaggacgctg acgaacaggg cgagcgcggc
+    12781 gatgcgttgc atgccgccgg gttcatggtc gaagcgaagc acgtcggcgg ctgccgcgat
+    12841 ggaagccgcg agcgcggcat cgtgaggggt agtcgtgtgc ttcatgcggc ggcgcctccg
+    12901 aggatgtcgt gatggttctg ttgcaggcgc tgaacggcgt gctgcagctc gtagcgcgag
+    12961 gtgatcgcct ggtcgagcat ggtgcgcagg cgcttgcggt tgcgttcgag attcgacgtc
+    13021 gcgttcgcga gggctgcggt acgcgtcgcg ccgtggccga tgcgcatgcc cgatatcagg
+    13081 tgcgtgacga cgcacttttc ggggtggccg tcgtgcaggt gcgactcggt gtgaataccg
+    13141 aatgcggcgc cggcatcgtt cgggatgaca acatgatcgc cggcgacggt gcgcaggccg
+    13201 gccgaagtca gcagttcgta gcggatggtg ggctcgttcg tcatcgtgtc agctccgcgg
+    13261 cggcacagac caggccagcg ctgcgaccag gacgaccatt gcgatgacgc cgatcacgaa
+    13321 agcgatcggc cgggcgagcc gaacgtcgaa caggcgcagc acgtcggcgg ctaggtagta
+    13381 gacgccggtg agagaaaggg aaagcatcag cagcacgccg atgctgaaaa cgtagggctt
+    13441 catgatgtgg ttccaggtga gtacgccggc ggccggcgcg ggcggatcag tcgaagtcgt
+    13501 tcgcggcgcg gcgcttcccg tcgatggcag gcaactcgga cgcgggttct cgatcgcgcc
+    13561 acacgttcgc cgtgcattcg aaggcgtggc gggcagccgg gcacagggcg tcgaaattcc
+    13621 cgaccatgcg caggcggcgc cacatcgcgc gcaggtctag gtcggtgagg ggcgcgcgca
+    13681 tcggatcagt gcagaacgat gggcgtcagg acaggcatgc cggcgtcggc gtcccaatga
+    13741 cagcccaaca cgtagccgag ccggcgggcg gtgccgacga acacgagcgg atcgatgtcg
+    13801 gcgcgccaca gtgcgcgcag gtattcgcgg cgcttgtcga gcgacaggca agtcggatcg
+    13861 aactgcatca cgacggcggt agaggcgagg gtggccatgc gatctccttt ttttgggcaa
+    13921 aaaaagcccc tcgcgccggt taggcacgat gcgaggggaa aacaggggaa aggggtttag
+    13981 gtcgctagac gggcagttcg agctgctcga cgagacgctc gcgcacgttt ggtgagagcg
+    14041 gcaggtgtag cgacagattc ggggtcgcgg acggcgacaa ggtgcgcgcg aactccatgt
+    14101 tcacgatgta ggtgtggccg cactcgacgt tgttgcactg gaaggtgact tcccggaagg
+    14161 tctgggacat ttcgcggctg ctgcgcgcgg tcgcgcgcgt gcggcagtgc gggcagcggt
+    14221 tcaggattcg catgtcggct tactccggac gaggtacaag gcgcggccgc ggccgttcat
+    14281 ctgcttggca gtgcggcgaa ggcggcgctt ggcgagccac tcgactgtcg cttctaggga
+    14341 gggcaggtcg tgcaaggtgc gcacgcgttc cagcacgtcg cggtcggcgt ccgagagggc
+    14401 aatttccgtg ctggtttcgg gcatcggtgg agctactcat tgttggcggt tcggtgcctt
+    14461 cgctcaggcg ccggcgcggt ccagaatcga ggtgttgcgt tcggcgagta cagcggtcgc
+    14521 ttcgcgcatc acgatgtcgc ggattagcac ggcgagttgc tcgccctggt agttcgcgag
+    14581 cgccgtgaga acggcctgct cgtagtcgtc gaagcggacg gtgtgcttgt tgttgcggat
+    14641 gcgcttggga tcgggataca tgcaggcttc tcaattcacg agcgggcgga acgggaacgt
+    14701 gggatggcgc gcagctcgct cgcgccgatg cggatcagct cgcgcgccat gctcgaaatc
+    14761 gagcgattgc gctgctcagc gagctgttcg agctcgtcgc gttccgtgga agtgagccgg
+    14821 acgtacacgg gcttgtccga cagggtgccg cgtggcgatc ggcgcgggcc tttggcggta
+    14881 gtcatggtcg gtatactttg ttggttagcc ttgcgttacg gtaaggctag tgtaatgagc
+    14941 aaaaaacgtc tcgtcaacga tattaggaaa attatgtctc aagtggggag tcgcttgcgg
+    15001 gaagagcgct tgcggatcgg actgagccag gacgaatttg ccgccgtggg cggtatcact
+    15061 cggcgttcac agtcggcgta tgaatcggac gagcggtcgc ccgatgcaag ctatctgtta
+    15121 ggcgtccgcg caatcggcgt cgatatttac tacgtgctga ccggcgagcg aatttccgcc
+    15181 gagcatggag caggcgaggt gaaagcagac agtgaggagg cagagttcct ggaggtatat
+    15241 cggcaactca acgagactgg caaagcgacc ttgcaatcgt tcattggtag cgttctaaat
+    15301 caggccatca tgctcaagac gggcacgcca cggcgcgcga agcgcctgcc ggagaaccgc
+    15361 cgcgcagcgc tcgacgagcg catggcggaa aacgtcgatc gtgcgatggc ggaaatcgag
+    15421 cgtttgcgcg ccgagcgggc tgcgaaggac ggaaagaagt agtccgggcg cgtcgtcgcg
+    15481 cgcgggccat tcttcacaca aacactgtat atccatccag tattgggtta gcatcttgaa
+    15541 agccggcgat gctggcgacg tggacggatt ccgaggcaac cacgtcgtgt tgagtgccgc
+    15601 cggtccgtga acgtgtttgt gagggaccag aagaatgagc atcgacatga agcacaacaa
+    15661 cggcgcggtc ggcgtgttga cggctgccga tcgtcacgcg gacgcacgcg ccggagcaac
+    15721 gggccggata cgattccgtt cggacctgac tggaagcgag cgcgatgttg cgcgcgctgc
+    15781 gatcgacgat gccatgcagt ctgtcggcca ggtgctcgaa gttgcgcttc aggcgatggg
+    15841 aaatcttcgt gttgcacgcg cggcgcttgg gcggtgcgac gacgggccgc caatccgtgc
+    15901 gaatatgaat gatcgctaca attcgtagtt gaccgtctcc catagcaagc aacctgaagc
+    15961 ccgccgtgtg cgggcttttt actttccgcc tttcttgaaa tgcgaccggt gccgctcggt
+    16021 cgtcggatcg tcgcgcattt cgaggtcgag cccggtcgtg aatccgccgt cactgtcgat
+    16081 ggtgtgcgtt gccttcttca cgagccacgc ggtttcgtcg atttcgggct tgaagcccga
+    16141 cagcgtgacc ggcatttcgg ggaacagatc ggcgcggccg cgcgcgagcg aatagcgcat
+    16201 cgtcgcctgg ctgcgctgca tgcgcttgaa ctcggcctgc gccgcggctc gcgcttcggc
+    16261 ctccgtcgcg tagtcctccg gcagcacctt cacattcttg ttgttctccc cgccaacgat
+    16321 gaccgacttc cgcttcgcct tgccgttcga atggtagtgc gcgcgcacgg ccgagtaatt
+    16381 ttcccgttcg gacacgtggt acgcatgctg gtcgccgctc gcgcgcgtca gattcaacac
+    16441 ctcgaacgat ttcccgctga cggtcttgcc ggtgccgatc ggcgtgaaga gcagccgcaa
+    16501 atccttgacg ttcatcactg cgtcgtagcg cttcgccagc cgcgtcagaa acgacatatc
+    16561 gctttcgtgg gtctggtcga tgtgcgcgat cacgatcttc gccagcgtgt ccgcgacggc
+    16621 gggcgtcagc ttgtagcggc cggcgatcgc gcgcacgatc gagccgatcg tctgcttgtg
+    16681 ccagctcttc tcacgacgct cctgcatgcc gttcgacatc gaggccgagc gtgcgcgcac
+    16741 ggtcagcgtg tcgggcgcgc cgctatgttc gaactcggtc acgacgaacg tgcccttgtc
+    16801 gacgagctgc tcgccggccc agccgatcga caccttgatt tcatcgccgc gcttgggcag
+    16861 cgccagatcg ccgcgcgagt cgtcgagcac caggtcgatc gtatccgcgt cgtcagagcg
+    16921 cgattccgtg agggtcagcg attcgagccg cggcaggaac cgccgcgaga tgtcccggcc
+    16981 gccgagcgtg atgcggtagt cggccatcgg ctcgacacgt tcgagccgat acacagcagc
+    17041 gttcgagtgt tcggtcgcgc gcgtcgtcat gccttcggct ccgcgttcgc tgcatcatcg
+    17101 gcttccgctt catcgataag cgccgcatcc tggtcgatgc gcagcgcgtc gtcgtcgacg
+    17161 cattcgagcg tcaacgtgaa ttcgatcctg cgcgcggtgc cttcgcgggt gaagtaacgt
+    17221 cgcgtttcgt cgagccctac gatgaggtac gcgccgtaga cggtcccgag accgtcgacc
+    17281 aacacgtacg cttcgccgac gtttgccatc tggacgagct ggtcgagcga cgcgctggtg
+    17341 ccgatttgat ccggcgcgat gaggccgtcg agcgtgatga catcgtcgcc ctggccggtg
+    17401 tactggcgag catcgcgcgc gccgatacgc gacttcttcg gatgcttcca gttccggcgg
+    17461 cgcttcagct cgtggaaggg ggcggtagtc aggctgaaca cgaattgatc cagcgacagc
+    17521 aacatgggac agatcctccg tgaatgtcag tcggacaggc gcgagccggc gcgcccacgc
+    17581 tgcgcgcgtt cgcgacgatc cagctcggcg gccacggcgc gggcgatcgc gcgcggatcg
+    17641 tcgccggcct gcgggtaaat gttgatgacg atcgacgcag gcgcggcggc cgatgcagac
+    17701 gatgttgcag ccggacccga tgccgcgatc ggcggccgcc gatcgattgg cacgagtggc
+    17761 gcggccgtcg acagcgcggg tgtgccgaac ccggttacgg cggccgtcgc aagcccgagc
+    17821 gccgcgcgcg cgacgccgcg ctgctctccc gccataccga gcgcggcccc ctcgccgacg
+    17881 aatccgccca gctcggcgaa cacgcggctc gggctgtgaa tgccgagctt ttccttgaac
+    17941 cacgtcacgg ttgagttcgc gacgttcgtg atggcctcct tcacggcgcc caggccgttc
+    18001 gtgatgccgt tgaccaggcc cgatatcagg ttggccccga attccgccat cttctcggcg
+    18061 accttggcgg ccacgacgat gatgttcgcg agccattcac caaagccccg gcccgcgttg
+    18121 ctggccttgt ccagactttc cttgctcgcg tcgaccggcc ccaacaggcg ggaaatccag
+    18181 tcccacacgc ccttgacggc atccatcagc caattgaagg cgggcttgag cggctcgaac
+    18241 atcgcgccga gcacaccgaa tacgcggctg aaaatcggcg cgagcggttg cagaccttcg
+    18301 gtcaagccct gccagaagcc ggagaagaac gccttgatcg gttcccaata tcggacgatg
+    18361 agcagcgcgg ccagcgcgat cccggtgatg acgaggccga ccgggttcat gagcgccaca
+    18421 cggccgacga acatcagcat ttgagcgagc ccgccgagcg cggcgccgac gcctttgatt
+    18481 gcgccgactg caccgccctt gatgagaccg cccgcaccct tgagcgcatc gaccgacatc
+    18541 ccggcgacgc cgcggttgcc cgcgtactgc cgtgcggcgg tccagcgcga gacgacggcc
+    18601 gcgcgcgacg cggccgcctg agcggcgacc gcgcgccaca cctgggcggt gtattgccga
+    18661 gcggcgacca gaccgtcttt catcgacgtg gctgccgtgc ggctccactg cgcgacggtc
+    18721 gacacggccg cgcggccggc ggctgggatg ccttcgcgca gcgttcgtgc ataaccgcgc
+    18781 aacgtcgcca aagccgtgcg tggcgatgat gccgaccagg cggcggccag ggcggtgcgc
+    18841 atgcgcgcgg cggtcgtgcg cacagcattg ccgacaacag agaaccggga agccgcaccc
+    18901 gacaaccgcc cgaagccgcc cgcgctcgca ccgagcgtgc gcgcgagaaa gccgccctga
+    18961 atgccgagcg tcgccatgct gaatcgcacg atcgcgagcg gcccgagaat gcccgcgagc
+    19021 acaatcgtga acgtccccat gacgacgagc agcgcggcga acgcggcgag cacggacaga
+    19081 atgaccttca ccgcggcgcc gtggcgctga atcaggccga tgaggccgac gagaatctcg
+    19141 cgggtcttgt cgagcgccgc gttgtacagc ggtgcgatgc gctcgccgat ctcgcggcgc
+    19201 aagtcgcggc ccttcgcgag caggtcgttt tccttgccct gcgtttgcag cgcagcgagc
+    19261 ttcgccgcgt cgtcgatgcc gtatgcgccg cggttgagct tttcgttctt gtgaatctgg
+    19321 tcgcgctgca tgtacatagt cgtgaacaga ttcgacgcag tccggttggt gaagatcgtc
+    19381 gaaatcatgt ctttcacctt gtccggatca gtgatcccct tcgcggccag cttcggcaga
+    19441 aacacctttt ccagccattc gagcggcgac gccttgaaca gatcgccgcc agtgagcgca
+    19501 ccgggcttga tttccttgat cgtgccgatt ttcgtatcga tgaccttttt tcggtcgagc
+    19561 agcccgagcg cgatcatctg gttcgctgca cgcttcgttg tcttgccctg gtacgcgttg
+    19621 ctgtacgcgg acatgaggcc ggtgccgacg ccgtggccgc ccatttcctg gatcagcggt
+    19681 tccatctggt aatagaacgc gtcctggcgc atctgtttcg ccgcgacgcc gcccgtctgg
+    19741 atgaagttgc gccattcgtc gccgccgacg cgcccgccgg tcgccgacag caccttctgc
+    19801 accatgttcg cttcgttctt gaacgtcgct tcgtctttcg tgccgccgcg cagctcgatc
+    19861 accttcagca tgttcatgaa tttctcttcg ttcgcgtgcg cgtcttccgc gccgaacagt
+    19921 gcttcgttgg cgaacttcat tttcgcgagc gttggcatga ccatctgcgc gtgatgctcg
+    19981 tccgcgaaga tcgacaacgc gtcgcgcatc agcgtcatgt tgtcggacgt gctgacgccc
+    20041 atcatgttca tcgcgcgtac gtacttctcg gcgtcctgcg ttgcttggtc gccgaggccg
+    20101 agcgccgtga tgcgcgctcg ttcgttcgtc attttcttgg cttcgtcaag cgtgccgccg
+    20161 aggccgccga gcatgcgcat gccagtagac cgggcggcgt agccgccgat tgccatcccg
+    20221 ccggctacgc cctgcatcgc ctgcatcttg ccgcgcgctg cggcgagctt tcgatcgcgt
+    20281 tccgtcagcg cttcgagctg gcgcgtctgc gcctgcatcg tggccgtcgt cgacgcgatg
+    20341 tttgagcgca gcgtgcgctc gtgctgtgcg aggttgcgcg tctcgatgcc ggcctgcgcg
+    20401 agccggccgc gcatctcgtc gacggcggcc gcctgctttt tctgctcggc gcgtaagcgt
+    20461 gacgctgcct ggcgtgcgcg cgccatgtcg gcgaccatct gcttcgtggg cgggccgaat
+    20521 gcgtgcagtg agccggcgag cgccttcacg ttggattgcg ccgcgccgag cttcttcgtg
+    20581 gtgtcggcga gcccggcgcg catttcgcgg aacgaggcga cagctttctg ttgcttgccc
+    20641 agttcggcaa gctcgccacg cgtcgccttc aacgactgcg cgagcccctt gttgctgttc
+    20701 agcatgttcc gtaagggctt cgtccagttg tcgaccatgt cgaacatgac gcgcagtttc
+    20761 agggcgttgt ccatcgttac tcgtgtccgc ttcgtatccg ggcgcgctcg cgccaatcca
+    20821 tcagctcaga aagggaaagg tcgtccatgt cacggggtgt ccagccgaac accgtcgcga
+    20881 catcggccat cgcgtcttct acgcgttcag ggattccatg ctcgctttca gcgccttcgg
+    20941 catcaaaaaa ccggcgaaga taccccccaa tgccacgagg tcggccgggt ccatcaacgt
+    21001 gacatccatc tcggtcagcg tcggcgtgct gatgcgaggc agcaccttgc gcagcgcgtc
+    21061 cacgtcgagg ttcacgagtg ccgcgagcga cgtgccgcgc aaggcgcctg cggacggctt
+    21121 cgcaagggtc acatgcgtga tggtctgctc gccgcgcacg atcggcgtgt cgaaggtgtg
+    21181 cgtgttggcc gcgatcgcgt cgagcacggc gccgccggtg gtggtgttgt tggtgtcgag
+    21241 ggtcgtcatg ttgcgtatcc tgatgatgat ctaaagggat gcccgcggcg tgcgcggggc
+    21301 gaagcgttac aggccgattg cctggcgcag accggcgagc aggtcgttac cgttgatctt
+    21361 ctcgatcatg ttgatgaaat ccatctcgat cagatcctgg ccgttgatgg acagcttgta
+    21421 gtagctggct gccgtcgtga ccttgaaatc ggtgtcttcc ttcggcttgg ccgtacccat
+    21481 gtcgatttcc ttgtggcgac cgcgcacgac gatttcgacg gaatcgtagg tcttcgaatc
+    21541 ctcgcgctgg tagccgccgg agaaacggag ctgcacgccg tcgtgcgtgg tgatgccgta
+    21601 catccgaatg acatcctcca tgaagccgcc gcaggtccat tcgagctgga tagcctcctg
+    21661 gccgaagtcg atcggaatcg ggccgctcat gccgccgccc tggtaatcct ccatctttcg
+    21721 tgacagcttc gggagctgga tttccttcgt ctcgccgacg aagttggtgc cgttgtgaaa
+    21781 caggttgaag cctttcagct tgcggggcat acccatgtgt ttgactcctg gttaggccga
+    21841 cacgcgcgag gcgaaatcgg cgagatagcg atcggtgatg cgctggcgca gcttcaggtt
+    21901 ttcgagcggc gggaccggcg tgtagtcgta gtcgatccac gtgccgcccg acgtcagctc
+    21961 gtcggtcgtg ttcggctccg ggtcgtacca ggcgccgccg ccgatcagct cgccgaccga
+    22021 gacttcgcgg cggaaccacg cgttgatgtt ctcgatgatg tcccgcgcgc gcgacgggtt
+    22081 gagcgggccg tcgacgacgc ccatttgttc ttcggcgatc gtgtcggcga tcacctgcgc
+    22141 cgaacgcgtg tagttctcga agaagaactt gccgtccgcg tcacacgtgc gcgagcccca
+    22201 gaagcggaag ccgttccggt tgacgagcgt ggtgacctgg ttctcgttca gataacccgc
+    22261 gtccgtcgcc gggtcttgca aatcccacga cacgtccgcg ctgatgccag tcacgccgtt
+    22321 gacgacgacg ttcgacagcg tcttgtgcca gccgatgtcg ttgtcgatct tcgcgcgcag
+    22381 gccggcggcg atcgccggtg ccgggatggt gacggtcgag ttcgtcacgt cgtcccagcc
+    22441 gagccagtcc ggccagatca ccatgatttc gcgttgaccg aactgcttgc ggtacgcgac
+    22501 cgcctcttcc ttcgtcttgc agccgtgcgc cgccacgtaa acgaacgcgc gcagcgactg
+    22561 cgcgatcgtc gcgaatgccg cggcgacggg ctgcgtgtcg aggccgggtg cgaccaggat
+    22621 gcgcggcttc acggcgagct tcccctgcgc cgccagcagc gccttcatgc cggtgtactt
+    22681 gccgtccggc gtgacggtgc cgatgacgtt cgtcgtcgtc tcggcttcgt cctttccgtc
+    22741 cgcgacgcgc acgacgacgg tgacgggctt cgtctgcttg ccgatcgcgt cgagcgtgcg
+    22801 gcgcagcgtg cccttcgtgc cggccttgcc gagcgcggcg atgacgttcg tcagcagcac
+    22861 cggcgtgtcg agcgggaacg tcgccgggtc ggcgtcggcg ccggtgcaga caatgccgag
+    22921 cacggccgtg gagaccgtgc gaatcggccg gccgccttcg ttaatttcga tgacgcgtac
+    22981 gccgtggtgg taatcctgcg gcatggtatg caactcctat atgtatacag gtgagaggaa
+    23041 acgggagagc ccgttgtcag gtcgatgcga tgggggccgg ttgttgcggt tcgatcggct
+    23101 cggtgggcgc cacgtatggc gcgggcgttg cgggccacgc cacggcatcc ggaaacgtgt
+    23161 cggtgttgat cgtggacacg agcgccatct ggtacgcgga ccaggctttg aagtagtagg
+    23221 tgccttcgtc atcgagcagg ccggcggcat acgcatcggc cttccctgcg ttcgcgcgcc
+    23281 gtgcgatttc catcagtcgt tcgaactcgg ccatcgcggc gtcgcgtttt tcgcgtgcga
+    23341 tcagctcggg cggcaccgtc catgcaccgt cgatccacgc atgacgcggc gacggtcgcg
+    23401 gctcggtggt cagttccaga tcgtcgggcg tcttgccagc gatcgcgatt tcgacgggct
+    23461 cgccggtgtc ggtgcggtag cagacgcgtc cgcggaagtc cggcagcagg aaccaagcgc
+    23521 cgtcacgata gaacggccag gtggtcggcg tgcgcggcgg cggcgcatcg atcgtcgcgg
+    23581 acgatggaat gagccagcgg ccgtcattgc gcggatcggc gtcgggctgg ctgctggtca
+    23641 ggtattcgcc ggtcgacggg ctgtagtggt gaatcagcat gtttcgaggt ccgtaagtta
+    23701 gtaggcgcgg atcatggcga gcagcgtgat gttgcgtggc cgtgcttcgt tgccgccgtc
+    23761 tgcgccgatc gtgattgcat gcgagtgggc gccggcccca ccgatgccga cgttgtggcc
+    23821 gtgattcccg gcatcgttca gccaaatgcc ggtgccgcgc cggtcggtcg tgccgttgta
+    23881 ctggccgtcg ttctccgtgt tgtatccgcc accggtcagt tgactcgatc cgccgctatc
+    23941 ggtgttgcgt gcgatcacga caaacgggtg atcgtgtcca ggatcgttca catagtgatt
+    24001 gtggttgccc tgcccgtctg tccaggccga gtgcgcgtga tcgccgacag cagcggcgga
+    24061 tgcgccgtgc gcgtgcgaac ggttctggtc gccctggtac gagccgatgg cgcgctgcgg
+    24121 atcgatgtcg ttacggccgt ctgcccaaca gcggatgaac tcgccgcgca tctcgggcag
+    24181 gcggaacgtc gtcgcgccgt caccggtcga gaagcaaccc cagcgaccgt tcagccattc
+    24241 ggcctcggac acgagcgcgc cgcttgcctg agcgtaggcc cacagcgccg gatagtcggc
+    24301 gcgattcacg aggacaccgt tggctttgag gaaaccggcg cgcgccaatg tgcggggttc
+    24361 gaagacaatc tggccgacag tcacggtcga aatcgcagac agcacccatt ccgtcgtcgc
+    24421 caggcgcgtc gagcgatcgc cctgcggtgg cgtcggacct tggacgggtc gttcgaagtt
+    24481 cgttccactc ggcgtgaatg tcacctgggg gagcgagttg cacgtgatcc cgaacgaacc
+    24541 atctgcgatg tgataaaggc ccgtgtccgg cgctccgtcg ttttggaacg tgagcgaagg
+    24601 agaaccggca ctaccttccg acaggaaaat acgcttgccc ggatcgaacc acacgtccgc
+    24661 ggacatcgtt ccgcctttca ggcgatcgag tggcgtcacg ttgcccgagt gccacacggg
+    24721 ctttccgtcg acacggagcg aatggtcgga cgtgaagtat tggaacgagc ccgcgttgcc
+    24781 gccccaccag ccgacagaat tggggttgcc gtagaagtag ccgtcgatgg gacccagacg
+    24841 catacgtccc tcggatacgg cattgccaat cgtcagttcg ccgcgaatgt tgacgttgcc
+    24901 gccgagcgtc gcacccgacc ccagatcgtc gattctgacg aagccggatt cgagattcca
+    24961 tgcaaacgga cggaagtcgt tgaacgtgcc atccgggtca cccttcttcg tcgacagcag
+    25021 atagacgttc gtcccgtcat ttcgaaaaaa tgcaccgtag ccgccacacg ttgctcgaaa
+    25081 atgcgcaccg cctgcgtcca tttctcgcga ggttaagccc cccttgaacg tggcgcttcc
+    25141 cccggcttgg atcgcgttgc ggccatcgtc gccgacatcg ccgacgagca ggcgcttcgg
+    25201 aagtgaaaag acctgcgtgc ttcggtcgac gcgaaacgct gggaactgcg tgacgccatc
+    25261 gtcgtcgaac gcgttcaatc cgaagttgtt gccggcattt ccgccggtgg tagcgccatc
+    25321 tcgcttgaac agagaccacc gcaccttccc gccatcggca aagaacagtg tcgagaaact
+    25381 gccggcgccg ccgtcgattg aaacggcctt cgaatagctg gtgccttcgg tgacggtatt
+    25441 gccaccgacc agaagccgtg agccgccgtc gtcgttcttc acgtcgccga tgagaacgcg
+    25501 gccgccgtag gtgatgcgta cggcgcgcgc ctggtacccg tctgtctggg tgtcgttggc
+    25561 cgttttgttg agccagatat cgaggtactc gcgcccccac gcaccgccgt cgaaccccga
+    25621 ccggaccgtc gcgattagac gggtgccagt gtcgacgttg ttaccgccga acgtgccata
+    25681 caggcgaacc cgaccctcgc ggccggtctt accggacggt gggcgaatcg tgacgtgcgc
+    25741 ggcgtccggg cccgcgtcga actccgcgac gacggggccg gtaaatttcg cgccagtcag
+    25801 cgcggcgtac cgggctgcgg cagtcttcgg cgtgatggcg cgcgagtcgt ccgcgcccgc
+    25861 gtcgacttcg gcctgcgtgg cgagttctac gacgcccttg cgttcggtcg tcgccggcgg
+    25921 attcagaaac gtggccgggc caaactgaag ctgcgccgcg tcgatcgacg cgaacacgat
+    25981 gtcgctcgcg agcagcagca tggcggccgg cgacttttca agaatgggcg tgctctgcac
+    26041 gtagacaccg aacaacacgc cgttgtccag gtacaggccg tacgcgtaca acgtgtactg
+    26101 gtcgttcgtg tcgtcctgga tgacgacgtg cacggtgtcc ggcgcgacgt tttcgccgcc
+    26161 gaacgtcgtc acacgcttgc gctcgttcgg cagggtcttc atgcccttgt cgaacgcgaa
+    26221 cgcggcggtg ccgagaccga tttcggcgac gcggcgcgac gtgatgccgg tgttacccgc
+    26281 ggcgacgagc gctgcgcggc cggcgtcggt gatttgaatc aggtttccag ccatattcag
+    26341 gtatccgaga gggacaggcg gcaatagacc gcggcgcgcg cgccggcgcc gacgcgctgc
+    26401 gtgccggtct cgccaaagcc ctgcttgaag atgtagtgcg cggtaccgcg cttcgcgcga
+    26461 tcgacttccg cgcggatgtc ggcgacgtac tcggcggtcg cgggcacgcc gtcgcggctg
+    26521 ccgaccgtca gcacgatctc gaacgtgccg ggcttgccgc gtggcgtcat ctcgaaccac
+    26581 tcgcgcatcg ccacgttcgc gccgaacgac gcgcagacct ggcgcacggc ctcggccgtg
+    26641 cccttgatcc gggcaatgcg gatagcggtc ttcacgcgcg cgcgcttgac ctgctcgggc
+    26701 cagtagtctt tccaggtctc gacgccgacg tgccaggcga gccagggcag gaaggccagc
+    26761 gggattgcgt ccgggtccat cagcgtgccg atgtcgaccg ggatgccgct gattcgcgcg
+    26821 ttggtctcgg ccaagcgccg ctcgagcgcg gtcgcgttcg ggggcagcaa cgagggcatc
+    26881 ggcctattca tccgcgaccc cgccgtcgat cagctcgatt cctgtgcagt agggcgcctg
+    26941 ctcgcccgtc acggcgacgc cgccggccgg cgagtcgagc aataccttct gcacgcccgc
+    27001 cacgcgcatt gccgcgtgca ggccgtcgac cgtcacttcc atgccgatgc ggtgcatgtc
+    27061 ggcggcaaac ttcgccgtgc gcttgttcgc ttccgcgagc gcgaccgcgc gatccgggcc
+    27121 ggagaagaat cgcagcgtcg agcggatcgc gtagcgcacg atttttgcgc tttgcacgat
+    27181 cacttcatcg gtctgcggcc gcttgccttc cagattcttc ttcacgatct cgatcagctc
+    27241 ggcgctcgcg gtgccgtcac cttcgcgcga caggatcgtg acgaccatca cgcacggttc
+    27301 cgggctgaac gcggcggcgg acagcacgcg gccatcggcc gaacgcgcat ggaacacgta
+    27361 cgcttcttca ggaccggcga cggagaagcc gcgcggcgcg agctgcacgc gctcgcgcag
+    27421 gctgtcgtcg tcttcgtaga ccggatctac gccgttttca ggatcgccgg ccgagatgac
+    27481 caggcgttcc acgtcgaaga gggcggcgat gtgttcgagc gtcgtgccgc gtgcatatgc
+    27541 gagcaggatg ccgcgggcct tgtcgttgat gagctggcgc agcagcactt cgcgataggc
+    27601 gttttcttgc aacgatcgcg tcaacggttc ggattcgagc gcgagcgtcg cggcgatctc
+    27661 ggcgcgttgg tcggccgggt atagggaaat gagccgcgcc ttgcgttcag caaagaccgt
+    27721 ttcgaagtcg agcgggtcga cgatatcggg cgccggcagt tgcgacaggt cgatcggcgt
+    27781 cgttctcatg cgctgactcc tttcgacacg ggcacgcgca gcgatacggg ctcgtcgcgc
+    27841 tcgtcggtcc atccttcgat gtcgacgagc tgctgaccgg cgaacgcctc atcggtatcc
+    27901 gccacgagtt gcacgcgggt gatggtcaga cgcggctccc agcgcatcag cgcggcagcg
+    27961 gcggccgcat acaggcgaat gcgcgtcgcg ccattggtcg gtgcgtcgat caggtccggc
+    28021 agttccgagc cgaacgaacg gcgctggatg cacgagccga gcggggtcgt cagaatccgg
+    28081 ccgatcgact gcgacaggtg ttcgatgccc gaaatcgcgc gaccggtaac ggcgttcatg
+    28141 cccttcatgc gccaccccgg atcggcttcg acgtaacggc gaattcgccc tgcgcctggt
+    28201 gcgggtgatt gatgaggctg acgccgcctg cgcgcacgtc gccggtgagg tctgcactgc
+    28261 cgtcgatctt catcacggcg ccgccgtcgc cgcccttgcc ggtcataccg gattcgaacg
+    28321 tgagcgggcc tttcacggtc agcgatttcg tcacggtcgc gtcaccgtcg agcaggatgt
+    28381 gctcggcctg cacggtcgcg tccttcgtct gcacgacgac ggcgcccggt gcgacaacgc
+    28441 gtacggtcgc gccggccggc agcgcggccg tcagcgcgtg cgccgcgtgg tcgtagctga
+    28501 cgcgcgcgcc gtccgcgtag atgcgggtgt gggtgttcgg ggagttgtct ggtgccggcg
+    28561 cggcgtccga gtagaggccg cgcagggcga ctgcctgcgc gaagtcgccc atcgggccga
+    28621 gcagcacaac ctgctcgccc tttgtcggcg gaagccattc gcgcgtgctg ccagccgccg
+    28681 gcgtgagcca gggaatccag ttggtttgca ggccgtcgtc ggcggattcg ccgaccgcga
+    28741 cgcgacagag gcccgtgccg tagtcgacat cgagaatcga gcccttgcgc acggcgttgc
+    28801 gtgcctgccg ttgaatttcg ttcgcatcca tgccgaccat gttgccggcc gtcctcgcgt
+    28861 gacgcgagcg aatgcaaatg tcgtgctcgc gggtacagca tgctcgtcgc gcgcgcgagc
+    28921 aaacgtgagt cgacaatcgg cattacgcgc tcaacgacgt ggtttgcaca cgtcgcgagt
+    28981 gtccctttca cgctgcctct gaaccatgac gattcacatt tccgacgccg cgcccgcggc
+    29041 cgacattgcc ccaatgctca accagcttca tcgtgtcgat gcactcgcat tggcgcgcac
+    29101 actgccggat cagtccgtcg acctggtgtt caccgatccc ccgtacgcat cgggcggctt
+    29161 gcacctgtcc gcacgaacgc gcgcaccgag ccagaagtac atcaacagcg acacgaaggc
+    29221 ggtctatacc gacttcgaag gcgataacat ggatcaacgc gcctgggcgt tctggtgcca
+    29281 tgcctggctg accgagtgtc gccgtgcgat gaagcccggc gcgctactcg tttgcttcat
+    29341 cgactggcgc cagctcgcga cgttgacgga cgtggtgcag gcggccggcc tgacgctgcg
+    29401 cggcatcgcc gtatgggaca aaacgccagg tcgtacccgg ccgcgtcgag gcgggttcgc
+    29461 gcaacaggcc gaattcatcg tatgggcgag ccgcgggccg atgaacgata gcgacgtgta
+    29521 cctgccgggc gtgtttccga cgcggctggc gctgccgaag caacacgtca cggaaaagcc
+    29581 gatcgagctg gcacgcgacg tggtgcgcct ggtgcccgat ggcggcgtcg tgtgcgacct
+    29641 gttcgccggt tccgggacgt tcctggtcgc cgcccgcgaa gccggcctgc agtgggtcgg
+    29701 atgtgagacg agccaggcgt atcacgcgat cgcgtcgacg cgcctggctg ccgtgaatga
+    29761 ttcagcggtt gaggtagcgt agcagccggt cgcgcacgag ttcgcgatcg actgagctga
+    29821 agccgagcac gacgcgaacc ggatactgcg cgagcgggcc gcccggttcg acgggggcct
+    29881 tctggccttc ctggtgaacg cgcacgatgc gcgacaggcg gtcgtcgaag ccgatcgcaa
+    29941 gccccgtgtc gtcgacatcg atccgcagat agcgggcggt gcgcagcttg cgaaacatcg
+    30001 cctgccgctt gatgcggccg accttggcgc gcaagccctt gccgcccttc ttgatcttgc
+    30061 gcggcacgta cgcgctgccg tccgggtttt gctgcgcggc gacgcgcgac tgctgcgcgc
+    30121 ggcgcatatc gcgccccagc tcgcggaata gtcgccgacg agctgccggc gccagcttcg
+    30181 cgagcagccc gccggcccac ttctcaagtg cacgcagttc gtcgtccatc acaccaccca
+    30241 atgttcgtcc gcgtcgtcga cgtgttcgac cgtgcggcgg ccgtcgtcgt ccgtaccgac
+    30301 tacaacgctt tctgtaagtt tcagcttgat cgcgaggtcg acggcatcgt tggcgaggat
+    30361 gtcggcgatg aacgtcatcc catcgcggcg ctggtcggcg ttggtcacga ggtcgggctg
+    30421 gtttgcgcgc gcccattcga cgacggcgat catcacgtcg tcggcgctgc cgatgaagtc
+    30481 gcggatgaga atctcgcact cgtaccggta ttcgaacgac ggcgtgcgtg tgccggtcgc
+    30541 gacgatgtgg ccgtcgttga tgaagacgac gagcaggtcg ggcgcagcgg cgagctgcgg
+    30601 aagcgcagcg acgagcgcgg cgcgcaggct gttcggttta atcatgggcg ggggcctgcc
+    30661 ggttcggctg actgcgcgcc tggcactcgg ccaccatgtc gacttcggcc gcacagcgcg
+    30721 cccatgccgc ccgcgcgatg gtcagcgcgt cgctcagatc accgttcgtc tgcgggtgag
+    30781 ctgccggcag cgcgcaccgg gtcaccgtcg cgcacgcgtt gagcgtaatc gtcggcgccg
+    30841 gtgagggcgg ggctgctgtg caggcgcaca acgtcgtcag gcaggcgagc agtagcccac
+    30901 gcgcgaacgg cttcgttctc atcgacgagt ctccggagtt gcgattgata cgcggcgagc
+    30961 gtcgcgtcga ccgcgccgcg tgtgcggtcg agctgcgcgc gctgcaggtc tttctcgcgg
+    31021 gcgtccgtga gcagccggcc gatgattgcg tcgcgcgcac ccacgtcctg tttcgcctgg
+    31081 cgggcggcat cctgtgccgt ggcgaggcgt ccctgcagcg cgcgcacata ttgcgcgccg
+    31141 gcgaccgccg cgacgagcac cgcgagcgcc agccagaagc gaacgcccgg catgttcacg
+    31201 cggccgcctt cgcgccggcg tagcgttcgt acgcctgggc gagcttcgcg tcgtacaggt
+    31261 tgcgggcata gtccgggccg ttgtaaccct tcgcgaacgc cgcccacttc cggttcttca
+    31321 gcgcggacag cagcgacgag tcagccgcga cgaagcgcac gaacccgtcg agctggtcgc
+    31381 cctcgctcgt ctccatccgc gcgacgaact cgtcgatgct cgcgtagccg aggcgcttcc
+    31441 agtggtagcc catcacctgg aacgcgcccc agctcgccga ttcgtaggcc gatgccgcgt
+    31501 ggacgcgcgc ggcggtgtcg agccgcacgt attcggcggc gccgccctgg tagccgcccg
+    31561 gcttctggtt gacgacgttc gggaacagca gcgagtagtg gacggcgtca ttcgcgccga
+    31621 tgctgtcgac gagctgccga tacatgacat gccgctcgaa caggatcacg ggccgtccgt
+    31681 ccgccagaaa ccccgagccg cgtgattcca cttcgttgac ggcgcgcacg catgcgggcg
+    31741 acacgccgag cttgtccgcg gcgcgcgcga tgtccgcttc cgtcaggtgt ttgcggtcgc
+    31801 gctggccggc cgacagcacg gcgtacgtgt tcgggccggc gatcccatcg acgacgatcc
+    31861 cggccgcggc ctggagcgcc ttcaccgctt gctcggtcgc ttcgtcgtac aggtgggaca
+    31921 cgtcgagcgc gtagccggcg cgggcgagac gttgctgcag cagaccgact tccgcgccgc
+    31981 ggtcgttgaa acggaggata ttcatgattc gttgctccgg agaaggcgcg cgacgttccc
+    32041 gcgcgcgagg tacacaaaca gggccagcaa tacggcctgt acggcctgga agaagccgac
+    32101 cggtttcggg tggatgagca gctcgattgc cgagccgccg gaaatcgcga cgatcagcca
+    32161 ggccgtccag gcgacgtgcg aacggtgccg cgcgccgttc ttccggtagg tcagcacgcg
+    32221 caggatgacg gcgaggtgcg cggcgagtgc gaccagggca aacgacaggt gcatgtcatt
+    32281 tccccctgcg gatcagcgcg ccgaagtcga tatccttcac gcgctccatc agcgtcagcg
+    32341 tgaccgtgat gacgagcgcg gcggcgaaga acgcggcgac gcccgacgag cggaccggca
+    32401 cgatgtgggt gatttccggc gcggcgagat aacccatcac gagcgagatg agcatgtacg
+    32461 cggcgcgccg gccgatgccg aggtctttcg aggtgacgac gacaagcgcc gcgccggcga
+    32521 acgcgccaat cagcgcgtcg ccgtcgatgc ccggcgcgat gccggccagg ccgatcgcgg
+    32581 cggccagcgc tgcggcggta gtggtgttcg gttcagccat tcggacaatt ccaggtcagt
+    32641 caaacagttg caggaggggc ttcgtctgct cgatcgtgtt cagctcgggc atgtcgacga
+    32701 cggttcccat cggcagcacg acgcccagct cggcgaggcc gggattggct tccaggaccg
+    32761 cttcgacggt gccggccgtg ctggcgtagt ggcgccagca aacggcgtcg agcgtttcac
+    32821 cctgaagcgt ggagactttc atcagatcag ctcaaccgtc gagcgcgcga cgcccagaat
+    32881 gtcgctgatg gcccaccgcg cgttgcggcg cgactcgtcg acggttacgg ccagctcggc
+    32941 cgctacctgt ccgccgctct tcgtcgaatc gaagccgcgg tatttctccg tcacatccgc
+    33001 atgcgccagg tggtagaccg cgcgccggta acggaacaca tgcacggatt cgccgtcgac
+    33061 acgctcggcc ggcacgtcgg caagcgaacc cgcgcccgct gtccgctgcc gcgcgcgcca
+    33121 cgcggccagc tcgtcgttga cggtcagcat ggcgtcgcgc gcggcgtggc gcaggcgttc
+    33181 gcgcgtcacg gtgccgtcca ggcgcatcgc gtcgcgcagc gccgacaggt cgatgtccgg
+    33241 gaagaagccg tcgttcgtca gcgtgccgtc gatcggcgac gccgcgacgg caggcgcagc
+    33301 agtggcaacg aaactgttca tggtcgattc ggggagtgat ggcggtggac cgaaggtcag
+    33361 ggcctgtgtc cgtcaggcgt tgggccgtgc cttcggtgtc gccatgccgg ggtgggctct
+    33421 ttacgtgcct tcggcgccgt cgccctgacg gcccgtggct tcgatcagct tcgagagccg
+    33481 atcgatgtcc tttttcacgc cgacgcgatc gttcaacgat agcgcgcggc gcagatagtc
+    33541 gagggcgcgc ggcgggtcgg cttcctgtac ggcgtagccg agcgccttgc agagcttcgc
+    33601 gcgcacctgg tcgtgcatgt ccgcttcggc cgtcagctcg tcgaccagct ccaggctggc
+    33661 ggcttcgaac gtgctgcgct ccaggaacgc ggccagcgcg gcatcggcga actgttcggc
+    33721 gacgacggag gcgagcgacc gttcgaactg gtcgggcagc gcgagaccgt gcgtgagcgc
+    33781 gtaggcggcg atcgcgagcg caccgtcgta gtcgccggcg tcgatgcgcc agaccatgac
+    33841 cgtcacgagt acgtcgtcct gggcgccgcg gccgccgttc aacacgcccg ccacgtagtc
+    33901 ggcgtactcc ggcagcaact tccgcttcag ttcgaccttg cgggcgaccg actgcacgcc
+    33961 cttcagggcg cggcggtcgg ccgcgagctt cgcgagcatc agctcgtacg gcgtcgcacc
+    34021 ggccatcgtc tgaccaggcg cagtcgcggc cgccgcgcgg gcggccgaca cacgcgcgaa
+    34081 gtgcgcgcga gcgggcgtgt tgatcgtcat gccgccacca gctcgatgtt ttccgcgacg
+    34141 cagccgcaac cgaagtcttc gacgacatac gcgtcgttcg acgattcgta gttctcgatt
+    34201 tggtcgcgct tcgggttgtc gatcagcgag cgacggcgtg caccttcctg gaagtagatc
+    34261 gacaggtttt ccagcttcgt caccatcatc gcgcgcttcg ggaagaacgg cacacgcacg
+    34321 gccggcaggt tgccgatgcg cttctggctg acgatcaggt cggccgcgag ctgctcggtc
+    34381 ggtgcctgcg ccgtgttgac gatcgggaaa tacttgtcgt gcagcagctc gcggccgcag
+    34441 atcacgacga ggcccgtatc ttcctggaac cacgggtcga tcatcgacga cacgatgtcc
+    34501 atcacgagcg cgtcgaggtt cacatagtcg ccgcccttac cgacgagcac cttgccggct
+    34561 tccttcgcac cttcgtgcag cacgcggtgc cctgcgcggt cgcgatactg ttgcagccag
+    34621 ccgatattca cgtcctgcaa cagcgggttc gccgctttgt ccgtcgacag cgccgcctta
+    34681 acgccattcc agccgatcat gatccggtcg agcgcggact ggttgaggat cacgttgcgg
+    34741 atgcgctgct ggaagtcggg gaatttcgcc caggcgtcga gcttgcggta cgtaatggcc
+    34801 gtgtcgtagt cggttttttc gcagcggtag cggttgctat cgagcgcggt cgggtcgatc
+    34861 ggctgacgtt cagccttcgt cgtgtcggtg cggctcgcga tcggaccgga taccgacagg
+    34921 ccgagctttt cgccttccag ttcggtcacg ggcaggatgt tgatgctctt caggaatgcg
+    34981 ctcgattcct gcatcttggt ttcgagtgtt tgctggacgg acggctcgac ggcgaatttc
+    35041 tgcgacacgt cgtcggtgtc gttgagcttg gcaatttgcg cggcgtactt acggtacgcc
+    35101 tggcgcgttt ccttcttcat gagttgggtt ctccggggtg tgagcgtgga agggatcagc
+    35161 agtcggtcac gagctcgccg gtcgagccgg tcgacggctg gcgccgcggt gcgccgttat
+    35221 cggttgccga cagcttcgcg gtcagtgctt cgacggcggc gaccgcttcg tcggcacgct
+    35281 tcttcgcggc ggccgcgtct tgctgcgcgg cggtcaggtc gacgcgcagc gcggcgacat
+    35341 cgcggccctg ctgactcgcg aacccggcga tctcttcgac tgcgtggcgc acgtcagcat
+    35401 cacgttggtc gtccgtcgag cgattgcgcg cgaacatgcc tttgacgatg gagagcaggc
+    35461 tcgtcgattc gggttcgcct tcgaactcga tcgacgtttc gcacgcggcc gagaacaggt
+    35521 tgttcgaacg gcgcgccgcg aattgcagtg cttcggtgcc gaggctcgcc gggtcgtcgg
+    35581 tcgcggccag gccgaccaga tacgcttcgc cgatgtcggc gaagtcgggg ttgacttcga
+    35641 tcgatgtgaa aaccttctgg cgcttcttcg acagcgcgac cagctcgtcg gtcggatcga
+    35701 gctgcgcgta cagccccatc ttgcctttca gcgggccgtc ttcgatctcg gatgccttca
+    35761 gcgcgatcac atcgccatac gcgccgaacg ggttggttgc cgagagcggc gcccatccct
+    35821 tcaggtgctc gatattgaga cgcgcgccgt acagttcgcg gttgtagttc ttcgccatct
+    35881 gcgtgagcca ttcgcgcttg atctcgcgac cgtcgacagt cgcaccttcg accgcgacgc
+    35941 ggaaaaactt cgttttgttg gttgccatag agagaggtcg aaccgtgggt cagtgaatgt
+    36001 ggttctcatg ttcgaccttc acgcgctacg gctcaacgag cggcgtgtgt tgctcgcacg
+    36061 ggtacgtagt gcttcgcgtg atcgcgcgcg cgcgtcgccc tacgcttgcc gcatgctcga
+    36121 aacgacaaat ccaattcaac gcgaagcgaa cgtgcgacag atcgcgcgct cgctctactg
+    36181 gcaaggctgg cgcatctcgt cgatcgcacg gcatctcgaa ctgaagcccg cgaccgtggc
+    36241 gtcgtggtgc cgtcgcgaca agtggaaaga cgcaacgccg atcgagcgca tcgaggcggc
+    36301 ggccgaaacg cgcctgatgg tcctgattgc gaaggacaag aaggacggcg cggactacaa
+    36361 ggaaatcgac ctgctcggcc ggcagattga gcggctcgcg cgcgtgcaga aatacgggga
+    36421 gacggggaag gaaggcgacc tgaaccccaa catcgccgcg cgcaatgccg ggccgaagcg
+    36481 caagccgccg cgcaacgaaa tcagcgagga acagcacgag cggatcgtgg cggcgttccg
+    36541 cgaatcgctg ttcgactacc agaaggtctg gtatcgcaat ggcgatcaac gcacgcgcaa
+    36601 catcctgaag tcacggcaga tcggcgcgac ttggtatttc tcgcgcgaag cgttcgtcga
+    36661 cgcgctcgaa accggccgca atcagatttt tctgtcggcc agcaaggcgc aggcgcacgt
+    36721 cttcaaacag tacatcgcgc agttcgcgcg tgacgcggcc gacgtggaac tgaccggcga
+    36781 tccgatcatc ctgccgaacg gcgcgattct gtatttcctg gggacgaacg cgcgcacggc
+    36841 gcagtcgtat cacggcaatt tctatttcga cgaatacttc tgggttccga agtttcgcga
+    36901 gctgaacaag gtcgcgtcgg gcatggcgat gcacaagcgc tggcgcaaga cctacttcag
+    36961 cacgccgtcg agcatcacgc atgaggcgta tgcgttctgg agcggcgcgc acgcgaaccg
+    37021 cggccgcgca gccgccgatc gtatccagat cgacacgagc cacgaagcgc tcgtgcgcgg
+    37081 catgctgggc gaggacgcac agtggcgcca gatcgtgacg attctggatg cgatggcggg
+    37141 cggctgcgac ctgttcgaca tcgacgagct gcgccgcgaa tacagcgccg aggaattcgc
+    37201 caatctgctg atgtgcgcgt tcatcgatga ttcgctgtcg gtgttcaagc tggccgagct
+    37261 gcagcgctgc atggtcgact cgtgggagga atgggccgac gacttctcgc cgctgctgct
+    37321 gcgcccgttc ggctatcgcg aggtatgggt tggctacgat ccggcgctga ctggcgactc
+    37381 ggccggcctg gtcgtcgtgg cgccgccgcg ggtcgagggt ggggcgtttc gcgtgctcga
+    37441 acgtcatcag ttccgcggta acgacttcga ggaacaggcc gcggcgatcg agcagatcac
+    37501 gcagcgctac aacgtcggct acatcgcgat cgacacgaca ggcatggggc agggggtcta
+    37561 tcagctcgtg cgcaagttct acccggccgt cgtcgcgttg aactactcgc ccgaggtgaa
+    37621 aactcgcctc gtgctgaaag ggcaatccgt tatccgcaat ggccgcctgc aattcgacgc
+    37681 gggctggacc gacctggccg ctgccttcat ggcgatcaaa cagaccatga cgccgagcgg
+    37741 tcgacagacg acgttcacgg ctgaccggaa cgacgagacc ggtcacgcgg atctagcgtg
+    37801 ggcctgcctg cacgcgatcg accgcgaacc gctcgccggc ggcgacatca attcttcatc
+    37861 tttcacggag ttctattcat gagcaagcgc cgatcgcgcg cgccgcgcac gttcgcggcc
+    37921 gcgccggatt cgggcgccgc cggcgccgcg ccggcgcgcg ccgaggtctt caccttcgac
+    37981 gatcccacgc cggtcatgaa ccgggcggag attctcgatt acgtcgaatg ctggtcgaac
+    38041 ggcgattggt tcgagccgcc tgtcagcttc gccggcctgg cgaaatcgtt tcgcgcgagc
+    38101 acgcaccaca gctcggcgct gtacttcaag gcgaacgtgc tggcgtcgac attccggccg
+    38161 cacaagtggc tgtcgcggca cgcgttcgaa cggtgggcgc tcgattttct gacgttcggc
+    38221 aacggctacc tggaacgccg ccgcaatcag ctcggcgaca cgctgcgact cgaaccagcc
+    38281 ctggcgaaat acacgcggcg caaggcagat ttcagcggct tcgtgtacgt gaacggctgg
+    38341 caggacaagc acgagttcga gccgggcagc gtgttccagc tcatgcgacc ggacatcaac
+    38401 caggaggtgt acggcctgcc cgaatatctc agctcgcttc actcggcgtg gctgaacgaa
+    38461 tcgtcgacgt tgttccggcg gaagtactac gaaaacggga gccacgccgg cttcatcctc
+    38521 tacatgaccg acgcggcgca gaaacaggag gatgtcgaca acatgcgcac ggcgttgaag
+    38581 aacgcaaagg ggccgggcaa tttccgcaac gtgttcatgt acgcgccggg cgggaagaag
+    38641 gacggcatcc agctcattcc cgtgtcggag gtcgcggcga aggacgagtt cttcaacatc
+    38701 aagaacgtga cgcgcgacga cctgctcgcc gcgcatcgcg tgccgccgca actgctcggc
+    38761 atcgtgccga gcaactcggg gggcttcggc acgccggaca ccgcggcgcg cgtgttcggc
+    38821 cggaacgaaa tcaagccact gcaggcgcgc ttcgccgagc tgaatgactg gctcggcgaa
+    38881 gaggtcgtgt cgttcgacga ttacgagatt ccgccggttc cggcggccga gtagcgcacg
+    38941 cggcgattcg aagtcatgcg gcagggccgc gcaccgggca accgggcgcg gccctttttg
+    39001 cgtttggggc cggcgcgatt agaggggcta cagcggcttg gccgtccgca gggtgcgcaa
+    39061 gggtcggacg ccgcaaggcg ggagccgcag cgagcctgtc gtccggccgt gcagggtgtc
+    39121 ccgcggggtg gggagggggc agggaggccc gcgccgcgcc cgccgctgcg cggtcccctc
+    39181 cccgcc
+//
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_renumber_gbk/test-data/renumbered.tsv	Fri Jun 17 13:13:47 2022 +0000
@@ -0,0 +1,166 @@
+NODE_2_length_39186_cov_113.152335	RBS:CPT_NODE_2_length_39186_cov_113.152335_011	[Removed: RBS did not both fall within boundary of gene and share a boundary with a gene]
+NODE_2_length_39186_cov_113.152335	RBS:CPT_NODE_2_length_39186_cov_113.152335_027	[Removed: RBS did not both fall within boundary of gene and share a boundary with a gene]
+NODE_2_length_39186_cov_113.152335	RBS:CPT_NODE_2_length_39186_cov_113.152335_027	[Removed: RBS did not both fall within boundary of gene and share a boundary with a gene]
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_001	MS105_0000000001
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_001	MS105_0000000001
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_001	MS105_0000000001
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_002	MS105_0000000002
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_002	MS105_0000000002
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_002	MS105_0000000002
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_003	MS105_0000000003
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_003	MS105_0000000003
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_003	MS105_0000000003
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_004	MS105_0000000004
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_004	MS105_0000000004
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_004	MS105_0000000004
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_005	MS105_0000000005
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_005	MS105_0000000005
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_005	MS105_0000000005
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_006	MS105_0000000006
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_006	MS105_0000000006
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_006	MS105_0000000006
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_007	MS105_0000000007
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_007	MS105_0000000007
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_007	MS105_0000000007
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_008	MS105_0000000008
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_008	MS105_0000000008
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_008	MS105_0000000008
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_009	MS105_0000000009
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_009	MS105_0000000009
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_009	MS105_0000000009
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_010	MS105_0000000010
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_010	MS105_0000000010
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_010	MS105_0000000010
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_011	MS105_0000000011
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_011	MS105_0000000011
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_012	MS105_0000000012
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_012	MS105_0000000012
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_012	MS105_0000000012
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_013	MS105_0000000013
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_013	MS105_0000000013
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_013	MS105_0000000013
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_014	MS105_0000000014
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_014	MS105_0000000014
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_014	MS105_0000000014
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_015	MS105_0000000015
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_015	MS105_0000000015
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_015	MS105_0000000015
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_016	MS105_0000000016
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_016	MS105_0000000016
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_016	MS105_0000000016
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_017	MS105_0000000017
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_017	MS105_0000000017
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_017	MS105_0000000017
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_018	MS105_0000000018
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_018	MS105_0000000018
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_019	MS105_0000000019
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_019	MS105_0000000019
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_019	MS105_0000000019
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_020	MS105_0000000020
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_020	MS105_0000000020
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_020	MS105_0000000020
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_021	MS105_0000000021
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_021	MS105_0000000021
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_021	MS105_0000000021
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_022	MS105_0000000022
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_022	MS105_0000000022
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_022	MS105_0000000022
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_023	MS105_0000000023
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_023	MS105_0000000023
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_023	MS105_0000000023
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_024	MS105_0000000024
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_024	MS105_0000000024
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_024	MS105_0000000024
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_025	MS105_0000000025
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_025	MS105_0000000025
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_025	MS105_0000000025
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_026	MS105_0000000026
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_026	MS105_0000000026
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_026	MS105_0000000026
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_027	MS105_0000000027
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_027	MS105_0000000027
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_027	MS105_0000000027
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_027	MS105_0000000027
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_028	MS105_0000000028
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_028	MS105_0000000028
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_028	MS105_0000000028
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_029	MS105_0000000029
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_029	MS105_0000000029
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_029	MS105_0000000029
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_030	MS105_0000000030
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_030	MS105_0000000030
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_030	MS105_0000000030
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_031	MS105_0000000031
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_031	MS105_0000000031
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_031	MS105_0000000031
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_032	MS105_0000000032
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_032	MS105_0000000032
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_032	MS105_0000000032
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_033	MS105_0000000033
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_033	MS105_0000000033
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_033	MS105_0000000033
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_034	MS105_0000000034
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_034	MS105_0000000034
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_034	MS105_0000000034
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_035	MS105_0000000035
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_035	MS105_0000000035
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_035	MS105_0000000035
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_036	MS105_0000000036
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_036	MS105_0000000036
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_036	MS105_0000000036
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_037	MS105_0000000037
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_037	MS105_0000000037
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_037	MS105_0000000037
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_038	MS105_0000000038
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_038	MS105_0000000038
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_038	MS105_0000000038
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_039	MS105_0000000039
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_039	MS105_0000000039
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_039	MS105_0000000039
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_040	MS105_0000000040
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_040	MS105_0000000040
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_040	MS105_0000000040
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_041	MS105_0000000041
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_041	MS105_0000000041
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_041	MS105_0000000041
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_042	MS105_0000000042
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_042	MS105_0000000042
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_042	MS105_0000000042
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_043	MS105_0000000043
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_043	MS105_0000000043
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_043	MS105_0000000043
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_044	MS105_0000000044
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_044	MS105_0000000044
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_044	MS105_0000000044
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_045	MS105_0000000045
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_045	MS105_0000000045
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_045	MS105_0000000045
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_046	MS105_0000000046
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_046	MS105_0000000046
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_046	MS105_0000000046
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_047	MS105_0000000047
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_047	MS105_0000000047
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_047	MS105_0000000047
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_048	MS105_0000000048
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_048	MS105_0000000048
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_048	MS105_0000000048
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_049	MS105_0000000049
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_049	MS105_0000000049
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_049	MS105_0000000049
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_050	MS105_0000000050
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_050	MS105_0000000050
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_051	MS105_0000000051
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_051	MS105_0000000051
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_051	MS105_0000000051
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_052	MS105_0000000052
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_052	MS105_0000000052
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_052	MS105_0000000052
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_053	MS105_0000000053
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_053	MS105_0000000053
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_053	MS105_0000000053
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_054	MS105_0000000054
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_054	MS105_0000000054
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_054	MS105_0000000054
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_055	MS105_0000000055
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_055	MS105_0000000055
+NODE_2_length_39186_cov_113.152335	CPT_NODE_2_length_39186_cov_113.152335_055	MS105_0000000055