[med-svn] [Git][med-team/busco][upstream] New upstream version 4.1.4

[Nilesh Patra]

Nilesh Patra pushed to branch upstream at Debian Med / busco


Commits:
0dba4338 by Nilesh Patra at 2020-10-08T18:31:32+05:30
New upstream version 4.1.4
- - - - -


4 changed files:

- CHANGELOG
- README.md
- src/busco/BuscoTools.py
- src/busco/_version.py


Changes:

=====================================
CHANGELOG
=====================================
@@ -1,3 +1,6 @@
+4.1.4
+- Fix Augustus parsing bug
+
 4.1.3
 - Issue #296 fixed
 - Issue #305 fixed


=====================================
README.md
=====================================
@@ -1,6 +1,8 @@
 **BUSCOv4 - Benchmarking sets of Universal Single-Copy Orthologs.**
 
-######Note: v4.1.3 is the latest stable release. To access v5.beta clone this repository and checkout the v5 branch with `git checkout v5.beta`
+######Note: v4.1.4 is the latest stable release. To access v5.beta clone this repository and checkout the v5 branch with `git checkout v5.beta`
+
+######Note: A critical bug was discovered to have been introduced in v4.1.3. Any analysis on eukaryote genomes done with this version should be repeated with v4.1.4.
 
 For full documentation please consult the user guide: https://busco.ezlab.org/busco_userguide.html
 


=====================================
src/busco/BuscoTools.py
=====================================
@@ -512,7 +512,8 @@ class HMMERRunner(BaseRunner):
                 elif isinstance(self.input_sequences, list):
                     input_files = [f for f in self.input_sequences if os.path.basename(f).startswith(busco_id)]
                     for seq_filename in input_files:
-                        output_filename = os.path.basename(seq_filename).rpartition(".faa")[0] + ".out"
+                        filename_parts = os.path.basename(seq_filename).rpartition(".faa")
+                        output_filename = filename_parts[0] + ".out" + filename_parts[-1]
                         yield busco_id, seq_filename, output_filename
 
     @property
@@ -1931,38 +1932,50 @@ class AugustusRunner(BaseRunner):
 
             for line in f:
 
-                if aa_sequence_section and (line.startswith("# end gene") or "]" in line):
-                    aa_sequence_section = False
-                    completed_record = True
-                    if gene_id is not None:
-                        aa_sequence = "".join(aa_sequence_parts)
-                        nt_sequence = "".join(nt_sequence_parts)
-                        seq_record_aa = SeqRecord(Seq(aa_sequence.upper()), id=gene_id)
-                        seq_record_nt = SeqRecord(Seq(nt_sequence.upper()), id=gene_id)
-                        sequences_aa.append(seq_record_aa)
-                        sequences_nt.append(seq_record_nt)
-                        aa_sequence_parts = []
-                        nt_sequence_parts = []
-                        gene_id = None
-                    continue
-
-                if aa_sequence_section and line.startswith("# sequence of block"):
-                    aa_sequence_section = False
-                    continue
-
                 if aa_sequence_section:
-                    line = line.strip().lstrip("# ").rstrip("]")
-                    aa_sequence_parts.append(line)
-                    continue
+                    if "]" in line:
+                        line = line.strip().lstrip("# ").rstrip("]")
+                        aa_sequence_parts.append(line)
+                        aa_sequence_section = False
+                        completed_record = True
+                        if gene_id is not None:
+                            aa_sequence = "".join(aa_sequence_parts)
+                            nt_sequence = "".join(nt_sequence_parts)
+                            seq_record_aa = SeqRecord(Seq(aa_sequence.upper()), id=gene_id)
+                            seq_record_nt = SeqRecord(Seq(nt_sequence.upper()), id=gene_id)
+                            sequences_aa.append(seq_record_aa)
+                            sequences_nt.append(seq_record_nt)
+                            aa_sequence_parts = []
+                            nt_sequence_parts = []
+                            gene_id = None
+                        continue
+
+                    else:
+                        line = line.strip().lstrip("# ").rstrip("]")
+                        aa_sequence_parts.append(line)
+                        continue
 
                 if line.startswith("# protein"):
                     nt_sequence_section = False
                     aa_sequence_section = True
                     if "]" in line:
+                        line = line.strip().rstrip("]").split("[")
+                        aa_sequence_parts.append(line[1])
                         aa_sequence_section = False
                         completed_record = True
-                    line = line.strip().rstrip("]").split("[")
-                    aa_sequence_parts.append(line[1])
+                        if gene_id is not None:
+                            aa_sequence = "".join(aa_sequence_parts)
+                            nt_sequence = "".join(nt_sequence_parts)
+                            seq_record_aa = SeqRecord(Seq(aa_sequence.upper()), id=gene_id)
+                            seq_record_nt = SeqRecord(Seq(nt_sequence.upper()), id=gene_id)
+                            sequences_aa.append(seq_record_aa)
+                            sequences_nt.append(seq_record_nt)
+                            aa_sequence_parts = []
+                            nt_sequence_parts = []
+                            gene_id = None
+                    else:
+                        line = line.strip().rstrip("]").split("[")
+                        aa_sequence_parts.append(line[1])
                     continue
 
                 if nt_sequence_section:


=====================================
src/busco/_version.py
=====================================
@@ -6,4 +6,4 @@ Copyright (c) 2016-2020, Evgeny Zdobnov (ez at ezlab.org)
 Licensed under the MIT license. See LICENSE.md file.
 
 """
-__version__ = "4.1.3"
+__version__ = "4.1.4"



View it on GitLab: https://salsa.debian.org/med-team/busco/-/commit/0dba43385fbd72234a904d33da5092a9d5c7afe9

-- 
View it on GitLab: https://salsa.debian.org/med-team/busco/-/commit/0dba43385fbd72234a904d33da5092a9d5c7afe9
You're receiving this email because of your account on salsa.debian.org.


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://alioth-lists.debian.net/pipermail/debian-med-commit/attachments/20201008/aa1e4aad/attachment-0001.html>