Mercurial > repos > peterjc > align_back_trans

changeset 7:883842b81796 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"Update all the pico_galaxy tools on main Tool Shed"
author peterjc
date Fri, 16 Apr 2021 22:26:52 +0000
parents b27388e5a0bb
children
files tools/align_back_trans/README.rst tools/align_back_trans/align_back_trans.py tools/align_back_trans/align_back_trans.xml tools/align_back_trans/tool_dependencies.xml
diffstat 4 files changed, 57 insertions(+), 34 deletions(-) [+]
line wrap: on
line diff
--- a/tools/align_back_trans/README.rst	Mon Aug 21 06:26:14 2017 -0400
+++ b/tools/align_back_trans/README.rst	Fri Apr 16 22:26:52 2021 +0000
@@ -110,7 +110,7 @@
 
     $ planemo shed_upload --tar_only tools/align_back_trans/
     ...
-    $ tar -tzf shed_upload.tar.gz 
+    $ tar -tzf shed_upload.tar.gz
     test-data/demo_nucs.fasta
     test-data/demo_nucs_trailing_stop.fasta
     test-data/demo_prot_align.fasta
--- a/tools/align_back_trans/align_back_trans.py	Mon Aug 21 06:26:14 2017 -0400
+++ b/tools/align_back_trans/align_back_trans.py	Fri Apr 16 22:26:52 2021 +0000
@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-"""Back-translate a protein alignment to nucleotides
+"""Back-translate a protein alignment to nucleotides.
 
 This tool is a short Python script (using Biopython library functions) to
 load a protein alignment, and matching nucleotide FASTA file of unaligned
@@ -35,10 +35,12 @@
 
 
 def check_trans(identifier, nuc, prot, table):
-    """Returns nucleotide sequence if works (can remove trailing stop)"""
+    """Return nucleotide sequence, if works (can remove trailing stop)."""
     if len(nuc) % 3:
-        sys.exit("Nucleotide sequence for %s is length %i (not a multiple of three)"
-                 % (identifier, len(nuc)))
+        sys.exit(
+            "Nucleotide sequence for %s is length %i (not a multiple of three)"
+            % (identifier, len(nuc))
+        )
 
     p = str(prot).upper().replace("*", "X")
     t = str(nuc.translate(table)).upper().replace("*", "X")
@@ -48,9 +50,11 @@
             t = t[:-1]
             nuc = nuc[:-3]  # edit return value
     if len(t) != len(p):
-        err = ("Inconsistent lengths for %s, ungapped protein %i, "
-               "tripled %i vs ungapped nucleotide %i." %
-               (identifier, len(p), len(p) * 3, len(nuc)))
+        err = (
+            "Inconsistent lengths for %s, ungapped protein %i, "
+            "tripled %i vs ungapped nucleotide %i."
+            % (identifier, len(p), len(p) * 3, len(nuc))
+        )
         if t.endswith(p):
             err += "\nThere are %i extra nucleotides at the start." % (len(t) - len(p))
         elif t.startswith(p):
@@ -59,7 +63,8 @@
             # TODO - Calculate and report the number to trim at start and end?
             err += "\nHowever, protein sequence found within translated nucleotides."
         elif p[1:] in t:
-            err += "\nHowever, ignoring first amino acid, protein sequence found within translated nucleotides."
+            err += "\nHowever, ignoring first amino acid, protein sequence found "
+            "within translated nucleotides."
         sys.exit(err)
 
     if t == p:
@@ -69,9 +74,11 @@
         if str(nuc[0:3]).upper() in ambiguous_generic_by_id[table].start_codons:
             return nuc
         else:
-            sys.exit("Translation check failed for %s\n"
-                     "Would match if %s was a start codon (check correct table used)\n"
-                     % (identifier, nuc[0:3].upper()))
+            sys.exit(
+                "Translation check failed for %s\n"
+                "Would match if %s was a start codon (check correct table used)\n"
+                % (identifier, nuc[0:3].upper())
+            )
     else:
         # Allow * vs X here? e.g. internal stop codons
         m = "".join("." if x == y else "!" for (x, y) in zip(p, t))
@@ -81,13 +88,15 @@
             sys.stderr.write("Translation: %s\n" % t)
         else:
             for offset in range(0, len(p), 60):
-                sys.stderr.write("Protein:     %s\n" % p[offset:offset + 60])
-                sys.stderr.write("             %s\n" % m[offset:offset + 60])
-                sys.stderr.write("Translation: %s\n\n" % t[offset:offset + 60])
+                sys.stderr.write("Protein:     %s\n" % p[offset : offset + 60])
+                sys.stderr.write("             %s\n" % m[offset : offset + 60])
+                sys.stderr.write("Translation: %s\n\n" % t[offset : offset + 60])
         sys.exit("Translation check failed for %s\n" % identifier)
 
 
-def sequence_back_translate(aligned_protein_record, unaligned_nucleotide_record, gap, table=0):
+def sequence_back_translate(
+    aligned_protein_record, unaligned_nucleotide_record, gap, table=0
+):
     """Back-translate a sequence."""
     # TODO - Separate arguments for protein gap and nucleotide gap?
     if not gap or len(gap) != 1:
@@ -99,20 +108,27 @@
         assert len(gap_codon) == 3
     else:
         from Bio.Alphabet import Gapped
+
         alpha = Gapped(alpha, gap)
         gap_codon = gap * 3
 
     ungapped_protein = aligned_protein_record.seq.ungap(gap)
     ungapped_nucleotide = unaligned_nucleotide_record.seq
     if table:
-        ungapped_nucleotide = check_trans(aligned_protein_record.id, ungapped_nucleotide, ungapped_protein, table)
+        ungapped_nucleotide = check_trans(
+            aligned_protein_record.id, ungapped_nucleotide, ungapped_protein, table
+        )
     elif len(ungapped_protein) * 3 != len(ungapped_nucleotide):
-        sys.exit("Inconsistent lengths for %s, ungapped protein %i, "
-                 "tripled %i vs ungapped nucleotide %i" %
-                 (aligned_protein_record.id,
-                  len(ungapped_protein),
-                  len(ungapped_protein) * 3,
-                  len(ungapped_nucleotide)))
+        sys.exit(
+            "Inconsistent lengths for %s, ungapped protein %i, "
+            "tripled %i vs ungapped nucleotide %i"
+            % (
+                aligned_protein_record.id,
+                len(ungapped_protein),
+                len(ungapped_protein) * 3,
+                len(ungapped_nucleotide),
+            )
+        )
 
     seq = []
     nuc = str(ungapped_nucleotide)
@@ -122,8 +138,10 @@
         else:
             seq.append(nuc[:3])
             nuc = nuc[3:]
-    assert not nuc, "Nucleotide sequence for %r longer than protein %r" \
-        % (unaligned_nucleotide_record.id, aligned_protein_record.id)
+    assert not nuc, "Nucleotide sequence for %r longer than protein %r" % (
+        unaligned_nucleotide_record.id,
+        aligned_protein_record.id,
+    )
 
     aligned_nuc = unaligned_nucleotide_record[:]  # copy for most annotation
     aligned_nuc.letter_annotation = {}  # clear this
@@ -132,7 +150,9 @@
     return aligned_nuc
 
 
-def alignment_back_translate(protein_alignment, nucleotide_records, key_function=None, gap=None, table=0):
+def alignment_back_translate(
+    protein_alignment, nucleotide_records, key_function=None, gap=None, table=0
+):
     """Thread nucleotide sequences onto a protein alignment."""
     # TODO - Separate arguments for protein and nucleotide gap characters?
     if gap is None:
@@ -149,8 +169,9 @@
                 nucleotide = nucleotide_records[key_function(protein.id)]
                 aligned.append(sequence_back_translate(protein, nucleotide, gap, table))
     except KeyError:
-        raise ValueError("Could not find nucleotide sequence for protein %r"
-                         % protein.id)
+        raise ValueError(
+            "Could not find nucleotide sequence for protein %r" % protein.id
+        )
 
     return MultipleSeqAlignment(aligned)
 
@@ -165,7 +186,8 @@
 elif len(sys.argv) == 6:
     align_format, prot_align_file, nuc_fasta_file, nuc_align_file, table = sys.argv[1:]
 else:
-    sys.exit("""This is a Python script for 'back-translating' a protein alignment,
+    sys.exit(
+        """This is a Python script for 'back-translating' a protein alignment,
 
 It requires three, four or five arguments:
 - alignment format (e.g. fasta, clustal),
@@ -185,7 +207,8 @@
 This script is available with sample data and a Galaxy wrapper here:
 https://github.com/peterjc/pico_galaxy/tree/master/tools/align_back_trans
 http://toolshed.g2.bx.psu.edu/view/peterjc/align_back_trans
-""")
+"""  # noqa: E501
+    )
 
 try:
     table = int(table)
--- a/tools/align_back_trans/align_back_trans.xml	Mon Aug 21 06:26:14 2017 -0400
+++ b/tools/align_back_trans/align_back_trans.xml	Fri Apr 16 22:26:52 2021 +0000
@@ -123,7 +123,7 @@
 
 Cock et al (2009). Biopython: freely available Python tools for computational
 molecular biology and bioinformatics. Bioinformatics 25(11) 1422-3.
-http://dx.doi.org/10.1093/bioinformatics/btp163 pmid:19304878.
+https://doi.org/10.1093/bioinformatics/btp163 pmid:19304878.
 
 This tool is available to install into other Galaxy Instances via the Galaxy
 Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/align_back_trans
--- a/tools/align_back_trans/tool_dependencies.xml	Mon Aug 21 06:26:14 2017 -0400
+++ b/tools/align_back_trans/tool_dependencies.xml	Fri Apr 16 22:26:52 2021 +0000
@@ -1,6 +1,6 @@
-<?xml version="1.0"?>
+<?xml version="1.0" ?>
 <tool_dependency>
     <package name="biopython" version="1.67">
-        <repository changeset_revision="a12f73c3b116" name="package_biopython_1_67" owner="biopython" toolshed="https://toolshed.g2.bx.psu.edu" />
+        <repository name="package_biopython_1_67" owner="biopython" toolshed="https://toolshed.g2.bx.psu.edu" changeset_revision="a12f73c3b116"/>
     </package>
-</tool_dependency>
+</tool_dependency>
\ No newline at end of file