Mercurial > repos > galaxyp > map_peptides_to_bed

changeset 0:51f8f9041724 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty
author galaxyp
date Mon, 25 Jan 2016 15:32:49 -0500
parents
children db90662d26f9
files map_peptides_to_bed.py map_peptides_to_bed.xml test-data/mapped_peptides.bed test-data/peptides.tsv test-data/translated_bed_sequences.bed tool_dependencies.xml
diffstat 6 files changed, 473 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/map_peptides_to_bed.py	Mon Jan 25 15:32:49 2016 -0500
@@ -0,0 +1,333 @@
+#!/usr/bin/env python
+"""
+#
+#------------------------------------------------------------------------------
+#                         University of Minnesota
+#         Copyright 2014, Regents of the University of Minnesota
+#------------------------------------------------------------------------------
+# Author:
+#
+#  James E Johnson
+#
+#------------------------------------------------------------------------------
+"""
+
+"""
+Input: list of protein_accessions, peptide_sequence
+       GFF3 with fasta 
+Output: GFF3 of peptides
+
+Filter: Must cross splice boundary
+  
+"""
+
+import sys,re,os.path
+import tempfile
+import optparse
+from optparse import OptionParser
+from Bio.Seq import reverse_complement, transcribe, back_transcribe, translate
+
+class BedEntry( object ):
+  def __init__(self, line):
+    self.line = line
+    try:
+      fields = line.rstrip('\r\n').split('\t')
+      (chrom,chromStart,chromEnd,name,score,strand,thickStart,thickEnd,itemRgb,blockCount,blockSizes,blockStarts) = fields[0:12]
+      seq = fields[12] if len(fields) > 12 else None
+      self.chrom = chrom
+      self.chromStart = int(chromStart)
+      self.chromEnd = int(chromEnd)
+      self.name = name
+      self.score = int(score)
+      self.strand = strand
+      self.thickStart = int(thickStart)
+      self.thickEnd = int(thickEnd)
+      self.itemRgb = itemRgb
+      self.blockCount = int(blockCount)
+      self.blockSizes = [int(x) for x in blockSizes.split(',')]
+      self.blockStarts = [int(x) for x in blockStarts.split(',')]
+      self.seq = seq
+    except Exception, e:
+      print >> sys.stderr, "Unable to read Bed entry" % e
+      exit(1)
+  def __str__(self):
+    return '%s\t%d\t%d\t%s\t%d\t%s\t%d\t%d\t%s\t%d\t%s\t%s%s' % (
+      self.chrom, self.chromStart, self.chromEnd, self.name, self.score, self.strand, self.thickStart, self.thickEnd, self.itemRgb, self.blockCount, 
+      ','.join([str(x) for x in self.blockSizes]), 
+      ','.join([str(x) for x in self.blockStarts]), 
+      '\t%s' % self.seq if self.seq else '')
+  def get_splice_junctions(self): 
+    splice_juncs = []
+    for i in range(self.blockCount  - 1):
+      splice_junc = "%s:%d_%d" % (self.chrom, self.chromStart + self.blockSizes[i], self.chromStart + self.blockStarts[i+1])
+      splice_juncs.append(splice_junc)
+    return splice_juncs
+  def get_exon_seqs(self):
+    exons = []
+    for i in range(self.blockCount):
+      # splice_junc = "%s:%d_%d" % (self.chrom, self.chromStart + self.blockSizes[i], self.chromStart + self.blockStarts[i+1])
+      exons.append(self.seq[self.blockStarts[i]:self.blockStarts[i] + self.blockSizes[i]])
+    if self.strand == '-':  #reverse complement
+      exons.reverse()
+      for i,s in enumerate(exons):
+        exons[i] = reverse_complement(s)
+    return exons
+  def get_spliced_seq(self):
+    seq = ''.join(self.get_exon_seqs())
+    return seq
+  def get_translation(self,sequence=None):
+    translation = None
+    seq = sequence if sequence else self.get_spliced_seq()
+    if seq:
+      seqlen = len(seq) / 3 * 3;
+      if seqlen >= 3:
+        translation = translate(seq[:seqlen])
+    return translation
+  def get_translations(self):
+    translations = []
+    seq = self.get_spliced_seq()
+    if seq:
+      for i in range(3):
+        translation = self.get_translation(sequence=seq[i:])
+        if translation:
+          translations.append(translation)
+    return translations
+  ## (start,end)
+  def get_subrange(self,tstart,tstop):
+    chromStart = self.chromStart
+    chromEnd = self.chromEnd
+    r = range(self.blockCount)
+    if self.strand == '-':
+      r.reverse()
+    bStart = 0
+    for x in r:
+      bEnd = bStart + self.blockSizes[x]
+      ## print >> sys.stderr, "%d chromStart: %d  chromEnd: %s  bStart: %s  bEnd: %d" % (x,chromStart,chromEnd,bStart,bEnd)
+      if bStart <= tstart < bEnd:
+        if self.strand == '+':
+          chromStart = self.chromStart + self.blockStarts[x] + (tstart - bStart)
+        else:
+          chromEnd = self.chromStart + self.blockStarts[x] + self.blockSizes[x] - (tstart - bStart)
+      if bStart <= tstop < bEnd:
+        if self.strand == '+':
+          chromEnd = self.chromStart + self.blockStarts[x] + (tstop - bStart)
+        else:
+          chromStart = self.chromStart + self.blockStarts[x] + self.blockSizes[x] - (tstop - bStart)
+      bStart += self.blockSizes[x]
+    return(chromStart,chromEnd)
+  #get the blocks for sub range
+  def get_blocks(self,chromStart,chromEnd):
+    tblockCount = 0
+    tblockSizes = []
+    tblockStarts = []
+    for x in range(self.blockCount):
+      bStart = self.chromStart + self.blockStarts[x]
+      bEnd = bStart + self.blockSizes[x]
+      if bStart > chromEnd:
+        break
+      if bEnd < chromStart:
+              continue
+      cStart = max(chromStart,bStart)
+      tblockStarts.append(cStart - chromStart)
+      tblockSizes.append(min(chromEnd,bEnd) - cStart)
+      tblockCount += 1
+      print >> sys.stderr, "tblockCount: %d  tblockStarts: %s  tblockSizes: %s" % (tblockCount,tblockStarts,tblockSizes)
+    return (tblockCount,tblockSizes,tblockStarts)
+    
+  ## [[start,end,seq,blockCount,blockSizes,blockStarts],[start,end,seq,blockCount,blockSizes,blockStarts],[start,end,seq,blockCount,blockSizes,blockStarts]]
+  ## filter: ignore translation if stop codon in first exon after ignore_left_bp
+  def get_filterd_translations(self,untrimmed=False,filtering=True,ignore_left_bp=0,ignore_right_bp=0):
+    translations = [None,None,None,None,None,None]
+    seq = self.get_spliced_seq()
+    ignore = (ignore_left_bp if self.strand == '+' else ignore_right_bp) / 3
+    block_sum = sum(self.blockSizes)
+    exon_sizes = self.blockSizes
+    if self.strand == '-':
+      exon_sizes.reverse()
+    splice_sites = [sum(exon_sizes[:x]) / 3 for x in range(1,len(exon_sizes))]
+    print >> sys.stderr, "splice_sites: %s" % splice_sites
+    junc = splice_sites[0] if len(splice_sites) > 0 else exon_sizes[0]
+    if seq:
+      for i in range(3):
+        translation = self.get_translation(sequence=seq[i:])
+        if translation:
+          tstart = 0
+          tstop = len(translation)
+          if not untrimmed:
+            tstart = translation.rfind('*',0,junc) + 1
+            stop = translation.find('*',junc)
+            tstop = stop if stop >= 0 else len(translation)
+          if filtering and tstart > ignore:
+            continue
+          trimmed = translation[tstart:tstop]
+          #get genomic locations for start and end 
+          offset = (block_sum - i) % 3
+          print >> sys.stderr, "tstart: %d  tstop: %d  offset: %d" % (tstart,tstop,offset)
+          if self.strand == '+':
+            chromStart = self.chromStart + i + (tstart * 3)
+            chromEnd = self.chromEnd - offset - (len(translation) - tstop) * 3
+          else:
+            chromStart = self.chromStart + offset + (len(translation) - tstop) * 3
+            chromEnd = self.chromEnd - i - (tstart * 3)
+          #get the blocks for this translation
+          tblockCount = 0 
+          tblockSizes = []
+          tblockStarts = []
+          for x in range(self.blockCount):
+            bStart = self.chromStart + self.blockStarts[x]
+            bEnd = bStart + self.blockSizes[x]
+            if bStart > chromEnd:
+              break
+            if bEnd < chromStart:
+              continue
+            cStart = max(chromStart,bStart)
+            tblockStarts.append(cStart - chromStart)
+            tblockSizes.append(min(chromEnd,bEnd) - cStart)
+            tblockCount += 1
+          print >> sys.stderr, "tblockCount: %d  tblockStarts: %s  tblockSizes: %s" % (tblockCount,tblockStarts,tblockSizes)
+          translations[i] = [chromStart,chromEnd,trimmed,tblockCount,tblockSizes,tblockStarts]
+    return translations
+  def get_seq_id(self,seqtype='unk:unk',reference='',frame=None):
+    ## Ensembl fasta ID format
+    # >ID SEQTYPE:STATUS LOCATION GENE TRANSCRIPT
+    # >ENSP00000328693 pep:splice chromosome:NCBI35:1:904515:910768:1 gene:ENSG00000158815:transcript:ENST00000328693 gene_biotype:protein_coding transcript_biotype:protein_coding
+    frame_name = ''
+    chromStart = self.chromStart
+    chromEnd = self.chromEnd
+    strand = 1 if self.strand == '+' else -1
+    if frame != None:
+      block_sum = sum(self.blockSizes)
+      offset = (block_sum - frame) % 3
+      frame_name = '_' + str(frame + 1)
+      if self.strand == '+':
+        chromStart += frame
+        chromEnd -= offset
+      else:
+        chromStart += offset
+        chromEnd -= frame
+    location = "chromosome:%s:%s:%s:%s:%s" % (reference,self.chrom,chromStart,chromEnd,strand)
+    seq_id = "%s%s %s %s" % (self.name,frame_name,seqtype,location)
+    return seq_id
+  def get_line(self, start_offset = 0, end_offset = 0):
+    if start_offset or end_offset:
+      s_offset = start_offset if start_offset else 0
+      e_offset = end_offset if end_offset else 0
+      if s_offset > self.chromStart:
+        s_offset = self.chromStart
+      chrStart = self.chromStart - s_offset
+      chrEnd = self.chromEnd + e_offset
+      blkSizes = self.blockSizes
+      blkSizes[0] += s_offset
+      blkSizes[-1] += e_offset
+      blkStarts = self.blockStarts
+      for i in range(1,self.blockCount):
+        blkStarts[i] += s_offset
+      items = [str(x) for x in [self.chrom,chrStart,chrEnd,self.name,self.score,self.strand,self.thickStart,self.thickEnd,self.itemRgb,self.blockCount,','.join([str(x) for x in blkSizes]),','.join([str(x) for x in blkStarts])]]
+      return '\t'.join(items) + '\n'
+    return self.line
+
+def __main__():
+  #Parse Command Line
+  parser = optparse.OptionParser()
+  parser.add_option( '-t', '--translated_bed', dest='translated_bed', default=None, help='A bed file with added 13th column having a translation'  )
+  parser.add_option( '-i', '--input', dest='input', default=None, help='Tabular file with peptide_sequence column' )
+  parser.add_option( '-p', '--peptide_column', type='int', dest='peptide_column', default=1, help='column ordinal with peptide sequence' )
+  parser.add_option( '-n', '--name_column', type='int', dest='name_column', default=None, help='column ordinal with protein name' )
+  parser.add_option( '-s', '--start_column', type='int', dest='start_column', default=None, help='column with peptide start position in protein' )
+  parser.add_option( '-B', '--bed', dest='bed', default=None, help='Output a bed file with added 13th column having translation'  )
+  ## parser.add_option( '-G', '--gff3', dest='gff', default=None, help='Output translations to a GFF3 file'  )
+  ## parser.add_option( '-f', '--fasta', dest='fasta', default=None, help='Protein fasta'  )
+  parser.add_option( '-T', '--gffTags', dest='gffTags', action='store_true', default=False, help='Add #gffTags to bed output for IGV'  )
+  parser.add_option( '-d', '--debug', dest='debug', action='store_true', default=False, help='Turn on wrapper debugging to stderr'  )
+  (options, args) = parser.parse_args()
+  # Input files
+  if options.input != None:
+    try:
+      inputPath = os.path.abspath(options.input)
+      inputFile = open(inputPath, 'r')
+    except Exception, e:
+      print >> sys.stderr, "failed: %s" % e
+      exit(2)
+  else:
+    inputFile = sys.stdin
+  inputBed = None
+  if options.translated_bed != None:
+    inputBed = open(os.path.abspath(options.translated_bed),'r')
+  peptide_column = options.peptide_column - 1
+  name_column = options.name_column - 1 if options.name_column else None 
+  start_column = options.start_column - 1 if options.start_column else None 
+  # Read in peptides
+  # peps[prot_name] = [seq]
+  prot_peps = dict()
+  unassigned_peps = set()
+  try:
+    for i, line in enumerate( inputFile ):
+      ## print >> sys.stderr, "%3d\t%s" % (i,line)
+      if line.startswith('#'):
+        continue
+      fields = line.rstrip('\r\n').split('\t')
+      ## print >> sys.stderr, "%3d\t%s" % (i,fields)
+      if peptide_column < len(fields): 
+        peptide = fields[peptide_column]
+        prot_name = fields[name_column] if name_column is not None and name_column < len(fields) else None
+        if prot_name:
+          offset = fields[start_column] if start_column is not None and start_column < len(fields) else -1
+          if prot_name not in prot_peps:
+            prot_peps[prot_name] = dict()
+          prot_peps[prot_name][peptide] = offset
+        else:
+          unassigned_peps.add(peptide)  
+    if options.debug:
+      print >> sys.stderr, "prot_peps: %s" % prot_peps
+      print >> sys.stderr, "unassigned_peps: %s" % unassigned_peps
+  except Exception, e:
+    print >> sys.stderr, "failed: Error reading %s - %s" % (options.input if options.input else 'stdin',e)
+    exit(1)
+  # Output files
+  bed_fh = None
+  ## gff_fh = None
+  ## gff_fa_file = None
+  gff_fa = None
+  outFile = None
+  if options.bed:
+    bed_fh = open(options.bed,'w')
+    bed_fh.write('track name="%s" type=bedDetail description="%s" \n' % ('novel_junction_peptides','test'))
+    if options.gffTags:
+      bed_fh.write('#gffTags\n')
+  ## if options.gff:
+  ##   gff_fh = open(options.gff,'w')
+  ##   gff_fh.write("##gff-version 3.2.1\n")
+  ##   if options.reference:
+  ##    gff_fh.write("##genome-build %s %s\n" % (options.refsource if options.refsource else 'unknown', options.reference))
+  try:
+    for i, line in enumerate( inputBed ):
+      ## print >> sys.stderr, "%3d:\t%s" % (i,line)
+      if line.startswith('track'):
+        continue
+      entry = BedEntry(line)
+      if entry.name in prot_peps:
+        for (peptide,offset) in prot_peps[entry.name].iteritems():
+          if offset < 0:
+            offset = entry.seq.find(peptide)
+            if options.debug:
+              print >> sys.stderr, "%s\t%s\t%d\t%s\n" % (entry.name, peptide,offset,entry.seq)
+          if offset >= 0:
+            tstart = offset * 3
+            tstop = tstart + len(peptide) * 3
+            if options.debug:
+              print >> sys.stderr, "%d\t%d\t%d" % (offset,tstart,tstop)
+            (pepStart,pepEnd) = entry.get_subrange(tstart,tstop)
+            if options.debug:
+              print >> sys.stderr, "%d\t%d\t%d" % (offset,pepStart,pepEnd)
+            if bed_fh:
+              entry.thickStart = pepStart
+              entry.thickEnd = pepEnd
+              bedfields = str(entry).split('\t')
+              if options.gffTags:
+                bedfields[3] = "ID=%s;Name=%s" % (entry.name,peptide) 
+              bed_fh.write("%s\t%s\t%s\n" % ('\t'.join(bedfields[:12]),peptide,entry.seq))
+  except Exception, e:
+    print >> sys.stderr, "failed: Error reading %s - %s" % (options.input if options.input else 'stdin',e)
+
+if __name__ == "__main__" : __main__()
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/map_peptides_to_bed.xml	Mon Jan 25 15:32:49 2016 -0500
@@ -0,0 +1,68 @@
+<tool id="map_peptides_to_bed" name="Map peptides to a bed file" version="0.1.0">
+    <requirements>
+        <requirement type="package" version="1.62">biopython</requirement>
+    </requirements>
+    <stdio>
+        <exit_code range="1:" />
+    </stdio>
+    <command interpreter="python"><![CDATA[
+        map_peptides_to_bed.py 
+          --translated_bed="$translated_bed" 
+          --input="$input" 
+          #if $peptide_column:
+            --peptide_column=$peptide_column 
+          #end if
+          #if $name_column:
+            --name_column=$name_column
+          #end if
+          #if $start_column:
+            --start_column=$start_column
+          #end if
+          $gffTags
+          --bed="$mapped_peptides"
+    ]]></command>
+    <inputs>
+        <param name="translated_bed" type="data" format="bed" label="Translated bed with IDs to match in the input" help=""/>
+        <param name="input" type="data" format="tabular" label="Identified Peptides" help=""/>
+        <param name="peptide_column" type="data_column" data_ref="input" label="peptide column" optional="true" 
+               help="Defaults to first column"/>
+        <param name="name_column" type="data_column" data_ref="input" label="protein name column" optional="true" 
+               help="The name in this column must match the name column in the Translate bed"/>
+        <param name="start_column" type="data_column" data_ref="input" label="peptide offset column" optional="true" 
+               help="The offset in AnimoAcids of the peptide from the start of the protein sequence"/>
+        <param name="gffTags" type="boolean" truevalue="--gffTags" falsevalue="" checked="true" label="Use #gffTags in output" help=""/>
+    </inputs>
+    <outputs>
+        <data name="mapped_peptides" format="bed" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="translated_bed" type="data" ftype="bed" value="translated_bed_sequences.bed"/>
+            <param name="input" type="data" ftype="tabular" value="peptides.tsv"/>
+            <param name="peptide_column" value="2"/>
+            <param name="name_column" value="1"/>
+            <output name="mapped_peptides" file="mapped_peptides.bed"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+        Usage: map_peptides_to_bed.py [options]
+
+Options:
+  -h, --help            show this help message and exit
+  -t TRANSLATED_BED, --translated_bed=TRANSLATED_BED
+                        A bed file with added 13th column having a translation
+  -i INPUT, --input=INPUT
+                        Tabular file with peptide_sequence column
+  -p PEPTIDE_COLUMN, --peptide_column=PEPTIDE_COLUMN
+                        column ordinal with peptide sequence
+  -n NAME_COLUMN, --name_column=NAME_COLUMN
+                        column ordinal with protein name
+  -s START_COLUMN, --start_column=START_COLUMN
+                        column with peptide start position in protein
+  -B BED, --bed=BED     Output a bed file with added 13th column having
+                        translation
+  -T, --gffTags         Add #gffTags to bed output for IGV
+  -d, --debug           Turn on wrapper debugging to stderr
+
+    ]]></help>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/mapped_peptides.bed	Mon Jan 25 15:32:49 2016 -0500
@@ -0,0 +1,27 @@
+track name="novel_junction_peptides" type=bedDetail description="test" 
+#gffTags
+15	40902460	40907575	ID=JUNC00019210_2;Name=RNGRNKKLEDNYCEIT	1	+	40902484	40907575	255,0,0	2	35,37	0,5078	RNGRNKKLEDNYCEIT	SYENSEKVRNGRNKKLEDNYCEIT
+15	40902460	40907575	ID=JUNC00019210_2;Name=SYENSEKVR	1	+	40902460	40902487	255,0,0	2	35,37	0,5078	SYENSEKVR	SYENSEKVRNGRNKKLEDNYCEIT
+15	40902461	40907549	ID=JUNC00019210_3;Name=KIVRKSEMEGI	1	+	40902467	40907543	255,0,0	2	34,11	0,5077	KIVRKSEMEGI	HMKIVRKSEMEGIRN
+9	17406	18053	ID=JUNC00000003_1;Name=LDPLAGAVTKTHV	1	-	17421	17460	255,0,0	2	73,26	0,621	LDPLAGAVTKTHV	APWTSGPCRYKKYVFLDPLAGAVTKTHVMLGAE
+9	17406	18053	ID=JUNC00000003_1;Name=LDPLAGAVTKTHVMLGAE	1	-	17406	17460	255,0,0	2	73,26	0,621	LDPLAGAVTKTHVMLGAE	APWTSGPCRYKKYVFLDPLAGAVTKTHVMLGAE
+9	17406	18053	ID=JUNC00000003_1;Name=APWTSGPCRYKKYVF	1	-	17460	18053	255,0,0	2	73,26	0,621	APWTSGPCRYKKYVF	APWTSGPCRYKKYVFLDPLAGAVTKTHVMLGAE
+9	17404	18051	ID=JUNC00000003_3;Name=CLPGPPGWCCNKDPCDAGGRD	1	-	17404	17467	255,0,0	2	75,24	0,623	CLPGPPGWCCNKDPCDAGGRD	PLDERALQVQEVCLPGPPGWCCNKDPCDAGGRD
+9	17404	18051	ID=JUNC00000003_3;Name=PLDERALQVQEVCLPG	1	-	17455	18051	255,0,0	2	75,24	0,623	PLDERALQVQEVCLPG	PLDERALQVQEVCLPGPPGWCCNKDPCDAGGRD
+8	27369376	27370079	ID=JUNC00000874_2;Name=PTSCNPSDMSHGYVTVKGYHKAKATHRGPWLVA	1	+	27369376	27370079	255,0,0	2	51,48	0,655	PTSCNPSDMSHGYVTVKGYHKAKATHRGPWLVA	PTSCNPSDMSHGYVTVKGYHKAKATHRGPWLVA
+8	27369376	27370079	ID=JUNC00000874_2;Name=DMSHGYVTVKGYHKA	1	+	27369397	27370046	255,0,0	2	51,48	0,655	DMSHGYVTVKGYHKA	PTSCNPSDMSHGYVTVKGYHKAKATHRGPWLVA
+7	148909514	148910831	ID=JUNC00002152_1;Name=DQQDLADRDIPTDPNSGENKSLSSQHMTFCHGS	1	+	148909514	148910831	255,0,0	2	60,39	0,1278	DQQDLADRDIPTDPNSGENKSLSSQHMTFCHGS	DQQDLADRDIPTDPNSGENKSLSSQHMTFCHGS
+7	148909514	148910831	ID=JUNC00002152_1;Name=DLADRDIPTDP	1	+	148909523	148909556	255,0,0	2	60,39	0,1278	DLADRDIPTDP	DQQDLADRDIPTDPNSGENKSLSSQHMTFCHGS
+7	148909515	148910811	ID=JUNC00002152_2;Name=IWQTEIFPRI	1	+	148909524	148909554	255,0,0	2	59,19	0,1277	IWQTEIFPRI	ISRIWQTEIFPRIPIQVRTRVSHLST
+7	148909515	148910811	ID=JUNC00002152_2;Name=IFPRIPIQVRTRVSHL	1	+	148909539	148910805	255,0,0	2	59,19	0,1277	IFPRIPIQVRTRVSHL	ISRIWQTEIFPRIPIQVRTRVSHLST
+6	41766614	41767580	ID=JUNC00002625_1;Name=LKDSGGLAVIIERRLGSMSSLT	1	-	41766614	41767580	255,0,0	2	53,13	0,953	LKDSGGLAVIIERRLGSMSSLT	LKDSGGLAVIIERRLGSMSSLT
+6	41766614	41767580	ID=JUNC00002625_1;Name=DSGGLAVIIERR	1	-	41766638	41767574	255,0,0	2	53,13	0,953	DSGGLAVIIERR	LKDSGGLAVIIERRLGSMSSLT
+6	41766614	41767580	ID=JUNC00002625_1;Name=GLAVIIERRLGSMSS	1	-	41766620	41766665	255,0,0	2	53,13	0,953	GLAVIIERRLGSMSS	LKDSGGLAVIIERRLGSMSSLT
+6	41766612	41767578	ID=JUNC00002625_3;Name=KRFRWSGRNHREKIGVHVVFDQ	1	-	41766612	41767578	255,0,0	2	55,11	0,955	KRFRWSGRNHREKIGVHVVFDQ	KRFRWSGRNHREKIGVHVVFDQ
+6	41766612	41767578	ID=JUNC00002625_3;Name=FRWSGR	1	-	41766654	41767572	255,0,0	2	55,11	0,955	FRWSGR	KRFRWSGRNHREKIGVHVVFDQ
+6	41766612	41767578	ID=JUNC00002625_3;Name=NHREKIGVHVVFD	1	-	41766615	41766654	255,0,0	2	55,11	0,955	NHREKIGVHVVFD	KRFRWSGRNHREKIGVHVVFDQ
+6	84856497	84862316	ID=JUNC00002772_1;Name=LKMKSEAVMNQFENSMRRYL	1	-	84856497	84862316	255,0,0	2	7,53	0,5766	LKMKSEAVMNQFENSMRRYL	LKMKSEAVMNQFENSMRRYL
+6	84856497	84862316	ID=JUNC00002772_1;Name=MNQFENSMRRYL	1	-	84856497	84862292	255,0,0	2	7,53	0,5766	MNQFENSMRRYL	LKMKSEAVMNQFENSMRRYL
+6	84856497	84862316	ID=JUNC00002772_1;Name=LKMKSEAVMNQFEN	1	-	84862274	84862316	255,0,0	2	7,53	0,5766	LKMKSEAVMNQFEN	LKMKSEAVMNQFENSMRRYL
+6	84856497	84862316	ID=JUNC00002772_1;Name=LKMKSEAV	1	-	84862292	84862316	255,0,0	2	7,53	0,5766	LKMKSEAV	LKMKSEAVMNQFENSMRRYL
+6	84856497	84862316	ID=JUNC00002772_1;Name=KSEAVMNQFENSMR	1	-	84862265	84862307	255,0,0	2	7,53	0,5766	KSEAVMNQFENSMR	LKMKSEAVMNQFENSMRRYL
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/peptides.tsv	Mon Jan 25 15:32:49 2016 -0500
@@ -0,0 +1,25 @@
+JUNC00019210_2	RNGRNKKLEDNYCEIT
+JUNC00019210_2	SYENSEKVR
+JUNC00019210_3	KIVRKSEMEGI
+JUNC00000003_1	LDPLAGAVTKTHVMLGAE
+JUNC00000003_1	APWTSGPCRYKKYVF
+JUNC00000003_1	LDPLAGAVTKTHV
+JUNC00000003_3	PLDERALQVQEVCLPG
+JUNC00000003_3	CLPGPPGWCCNKDPCDAGGRD
+JUNC00000874_2	PTSCNPSDMSHGYVTVKGYHKAKATHRGPWLVA
+JUNC00000874_2	DMSHGYVTVKGYHKA
+JUNC00002152_1	DQQDLADRDIPTDPNSGENKSLSSQHMTFCHGS
+JUNC00002152_1	DLADRDIPTDP
+JUNC00002152_2	IWQTEIFPRI
+JUNC00002152_2	IFPRIPIQVRTRVSHL
+JUNC00002625_1	LKDSGGLAVIIERRLGSMSSLT
+JUNC00002625_1	GLAVIIERRLGSMSS
+JUNC00002625_1	DSGGLAVIIERR
+JUNC00002625_3	FRWSGR
+JUNC00002625_3	KRFRWSGRNHREKIGVHVVFDQ
+JUNC00002625_3	NHREKIGVHVVFD
+JUNC00002772_1	LKMKSEAVMNQFENSMRRYL
+JUNC00002772_1	LKMKSEAVMNQFEN
+JUNC00002772_1	LKMKSEAV
+JUNC00002772_1	MNQFENSMRRYL
+JUNC00002772_1	KSEAVMNQFENSMR
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/translated_bed_sequences.bed	Mon Jan 25 15:32:49 2016 -0500
@@ -0,0 +1,14 @@
+track name="novel_junctioni_translations" description="test" 
+15	40902460	40907575	JUNC00019210_2	1	+	40902460	40907575	255,0,0	2	35,37	0,5078	SYENSEKVRNGRNKKLEDNYCEIT
+15	40902461	40907549	JUNC00019210_3	1	+	40902461	40907549	255,0,0	2	34,11	0,5077	HMKIVRKSEMEGIRN
+9	17406	18053	JUNC00000003_1	1	-	17406	18053	255,0,0	2	73,26	0,621	APWTSGPCRYKKYVFLDPLAGAVTKTHVMLGAE
+9	17438	18052	JUNC00000003_2	1	-	17438	18052	255,0,0	2	41,25	0,589	PPGRAGPAGTRSMSSWTPWLVL
+9	17404	18051	JUNC00000003_3	1	-	17404	18051	255,0,0	2	75,24	0,623	PLDERALQVQEVCLPGPPGWCCNKDPCDAGGRD
+8	27369376	27370079	JUNC00000874_2	1	+	27369376	27370079	255,0,0	2	51,48	0,655	PTSCNPSDMSHGYVTVKGYHKAKATHRGPWLVA
+7	99077597	99079392	JUNC00001897_1	1	+	99077597	99079392	255,0,0	2	64,35	0,1760	HLLSLFFQLGVHICIPNFRNNSVSHCTQLRVLL
+7	99077598	99079360	JUNC00001897_2	1	+	99077598	99079360	255,0,0	2	63,3	0,1759	IYCLYFSNLVCISVYPTSEITV
+7	148909514	148910831	JUNC00002152_1	1	+	148909514	148910831	255,0,0	2	60,39	0,1278	DQQDLADRDIPTDPNSGENKSLSSQHMTFCHGS
+7	148909515	148910811	JUNC00002152_2	1	+	148909515	148910811	255,0,0	2	59,19	0,1277	ISRIWQTEIFPRIPIQVRTRVSHLST
+6	41766614	41767580	JUNC00002625_1	1	-	41766614	41767580	255,0,0	2	53,13	0,953	LKDSGGLAVIIERRLGSMSSLT
+6	41766612	41767578	JUNC00002625_3	1	-	41766612	41767578	255,0,0	2	55,11	0,955	KRFRWSGRNHREKIGVHVVFDQ
+6	84856497	84862316	JUNC00002772_1	1	-	84856497	84862316	255,0,0	2	7,53	0,5766	LKMKSEAVMNQFENSMRRYL
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Mon Jan 25 15:32:49 2016 -0500
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="biopython" version="1.62">
+        <repository changeset_revision="f06c96348778" name="package_biopython_1_62" owner="biopython" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>