[med-svn] [Git][med-team/fastaq][master] 7 commits: New upstream version 3.17.0
Sascha Steinbiss
gitlab at salsa.debian.org
Thu Feb 22 10:06:18 UTC 2018
Sascha Steinbiss pushed to branch master at Debian Med / fastaq
Commits:
e4dd7b7f by Sascha Steinbiss at 2018-02-22T10:22:16+01:00
New upstream version 3.17.0
- - - - -
2c37df60 by Sascha Steinbiss at 2018-02-22T10:22:17+01:00
Update upstream source from tag 'upstream/3.17.0'
Update to upstream version '3.17.0'
with Debian dir bd7c682b84a2f56d5b370c5d0512ad6d156cead9
- - - - -
28fd27b6 by Sascha Steinbiss at 2018-02-22T10:30:57+01:00
new upstream release
- - - - -
86c0d168 by Sascha Steinbiss at 2018-02-22T10:31:28+01:00
use secure format link in d/copyright
- - - - -
4f4862b5 by Sascha Steinbiss at 2018-02-22T10:55:58+01:00
bump Standards-Version
- - - - -
05de5782 by Sascha Steinbiss at 2018-02-22T10:56:29+01:00
remove patches that aren't applied anyway
- - - - -
6fdcce8f by Sascha Steinbiss at 2018-02-22T11:05:40+01:00
use dh11
- - - - -
10 changed files:
- debian/changelog
- debian/compat
- debian/control
- debian/copyright
- − debian/patches/delay-import-statements-for-manpage-creation.patch
- − debian/patches/series
- − debian/patches/spelling
- pyfastaq/sequences.py
- pyfastaq/tests/sequences_test.py
- setup.py
Changes:
=====================================
debian/changelog
=====================================
--- a/debian/changelog
+++ b/debian/changelog
@@ -1,3 +1,13 @@
+fastaq (3.17.0-1) unstable; urgency=medium
+
+ * New upstream release.
+ * Use secure format link in d/copyright.
+ * Bump Standards-Version.
+ * Drop unneeded patches.
+ * Use debhelper 11.
+
+ -- Sascha Steinbiss <satta at debian.org> Thu, 22 Feb 2018 10:22:55 +0100
+
fastaq (3.16.0-1) unstable; urgency=medium
[ Steffen Moeller ]
=====================================
debian/compat
=====================================
--- a/debian/compat
+++ b/debian/compat
@@ -1 +1 @@
-9
+11
=====================================
debian/control
=====================================
--- a/debian/control
+++ b/debian/control
@@ -5,7 +5,7 @@ Uploaders: Andreas Tille <tille at debian.org>,
Sascha Steinbiss <satta at debian.org>
Section: science
Priority: optional
-Build-Depends: debhelper (>= 9),
+Build-Depends: debhelper (>= 11),
dh-python,
python3,
python3-setuptools,
@@ -14,7 +14,7 @@ Build-Depends: debhelper (>= 9),
samtools,
help2man
X-Python3-Version: >= 3.2
-Standards-Version: 4.1.1
+Standards-Version: 4.1.3
Vcs-Browser: https://anonscm.debian.org/cgit/debian-med/fastaq.git
Vcs-Git: https://anonscm.debian.org/git/debian-med/fastaq.git
Homepage: https://github.com/sanger-pathogens/Fastaq
=====================================
debian/copyright
=====================================
--- a/debian/copyright
+++ b/debian/copyright
@@ -1,4 +1,4 @@
-Format: http://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
+Format: https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
Upstream-Name: Fastaq
Source: https://github.com/sanger-pathogens/Fastaq
=====================================
debian/patches/delay-import-statements-for-manpage-creation.patch deleted
=====================================
--- a/debian/patches/delay-import-statements-for-manpage-creation.patch
+++ /dev/null
@@ -1,774 +0,0 @@
-Description: Delay import of Fastaq modules by the python executables
- Man pages for this package are being automatically created with through the
- help2man wrapper called usage_to_man. help2man calls the python executables
- with the -h option and converts the usage into a man page.
- .
- The first step done by all the executables is the import of the modules deployed
- by this package. Since the package is not installed in the system at build time,
- the man pages would never be properly created.
- .
- This patch solves this problem by importing the modules in this package after
- the argument parsing code.
- .
- Upstream prefered to keep the code as it is for styling reasons, which is
- perfectly reasonable
- .
- fastaq (1.5.0-1) UNRELEASED; urgency=low
- .
- * Initial release (Closes: #766321)
-Author: Jorge Soares <j.s.soares at gmail.com>
-Index: fastaq/scripts/fastaq_capillary_to_pairs
-===================================================================
---- fastaq.orig/scripts/fastaq_capillary_to_pairs
-+++ fastaq/scripts/fastaq_capillary_to_pairs
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Given a fasta/q file of capillary reads, makes an interleaved file of read pairs (where more than read from same ligation, takes the longest read) and a file of unpaired reads. Replaces the .p1k/.q1k part of read names to denote fwd/rev reads with /1 and /2',
-@@ -9,4 +8,8 @@ parser = argparse.ArgumentParser(
- parser.add_argument('infile', help='Name of input fasta/q file')
- parser.add_argument('outprefix', help='Prefix of output files', metavar='outfiles prefix')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.capillary_to_pairs(options.infile, options.outprefix)
-Index: fastaq/scripts/fastaq_chunker
-===================================================================
---- fastaq.orig/scripts/fastaq_chunker
-+++ fastaq/scripts/fastaq_chunker
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Splits a multi fasta/q file into separate files. Splits sequences into chunks of a fixed size. Aims for chunk_size chunks in each file, but allows a little extra, so chunk can be up to (chunk_size + tolerance), to prevent tiny chunks made from the ends of sequences',
-@@ -12,6 +11,10 @@ parser.add_argument('chunk_size', type=i
- parser.add_argument('tolerance', type=int, help='Tolerance allowed in chunk size')
- parser.add_argument('--skip_all_Ns', action='store_true', help='Do not output any sequence that consists of all Ns')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.split_by_fixed_size(
- options.infile,
- options.outprefix,
-Index: fastaq/scripts/fastaq_count_sequences
-===================================================================
---- fastaq.orig/scripts/fastaq_count_sequences
-+++ fastaq/scripts/fastaq_count_sequences
-@@ -1,11 +1,14 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Counts the number of sequences in a fasta/q file',
- usage = '%(prog)s <fasta/q in>')
- parser.add_argument('infile', help='Name of input fasta/q file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- print(tasks.count_sequences(options.infile))
-Index: fastaq/scripts/fastaq_deinterleave
-===================================================================
---- fastaq.orig/scripts/fastaq_deinterleave
-+++ fastaq/scripts/fastaq_deinterleave
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Deinterleaves fasta/q file, so that reads are written alternately between two output files',
-@@ -11,4 +10,8 @@ parser.add_argument('infile', help='Name
- parser.add_argument('out_fwd', help='Name of output fasta/q file of forwards reads')
- parser.add_argument('out_rev', help='Name of output fasta/q file of reverse reads')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.deinterleave(options.infile, options.out_fwd, options.out_rev, fasta_out=options.fasta_out)
-Index: fastaq/scripts/fastaq_enumerate_names
-===================================================================
---- fastaq.orig/scripts/fastaq_enumerate_names
-+++ fastaq/scripts/fastaq_enumerate_names
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Renames sequences in a file, calling them 1,2,3... etc',
-@@ -12,6 +11,10 @@ parser.add_argument('--keep_suffix', act
- parser.add_argument('infile', help='Name of fasta/q file to be read')
- parser.add_argument('outfile', help='Name of output fasta/q file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.enumerate_names(options.infile,
- options.outfile,
- start_index=options.start_index,
-Index: fastaq/scripts/fastaq_expand_nucleotides
-===================================================================
---- fastaq.orig/scripts/fastaq_expand_nucleotides
-+++ fastaq/scripts/fastaq_expand_nucleotides
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Makes all combinations of sequences in input file by using all possibilities of redundant bases. e.g. ART could be AAT or AGT. Assumes input is nucleotides, not amino acids',
-@@ -9,6 +8,10 @@ parser = argparse.ArgumentParser(
- parser.add_argument('infile', help='Name of input file. Can be any of FASTA, FASTQ, GFF3, EMBL, GBK, Phylip')
- parser.add_argument('outfile', help='Name of output file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.expand_nucleotides(
- options.infile,
- options.outfile,
-Index: fastaq/scripts/fastaq_extend_gaps
-===================================================================
---- fastaq.orig/scripts/fastaq_extend_gaps
-+++ fastaq/scripts/fastaq_extend_gaps
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Extends the length of all gaps (and trims the start/end of sequences) in a fasta/q file. Does this by replacing a set number of bases either side of each gap with Ns. Any sequence that ends up as all Ns is lost',
-@@ -10,4 +9,8 @@ parser.add_argument('--trim_number', typ
- parser.add_argument('infile', help='Name of input fasta/q file')
- parser.add_argument('outfile', help='Name of output fasta/q file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.extend_gaps(options.infile, options.outfile, options.trim_number)
-Index: fastaq/scripts/fastaq_fasta_to_fastq
-===================================================================
---- fastaq.orig/scripts/fastaq_fasta_to_fastq
-+++ fastaq/scripts/fastaq_fasta_to_fastq
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Given a fasta and qual file, makes a fastq file',
-@@ -10,4 +9,8 @@ parser.add_argument('fasta', help='Name
- parser.add_argument('qual', help='Name of input quality scores file', metavar='qual in')
- parser.add_argument('outfile', help='Name of output fastq file', metavar='fastq out')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.fasta_to_fastq(options.fasta, options.qual, options.outfile)
-Index: fastaq/scripts/fastaq_filter
-===================================================================
---- fastaq.orig/scripts/fastaq_filter
-+++ fastaq/scripts/fastaq_filter
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Filters a fasta/q file by sequence length and/or by name matching a regular expression',
-@@ -14,6 +13,10 @@ parser.add_argument('-v', '--invert', ac
- parser.add_argument('infile', help='Name of fasta/q file to be filtered')
- parser.add_argument('outfile', help='Name of output fasta/q file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.filter(options.infile,
- options.outfile,
- minlength=options.min_length,
-Index: fastaq/scripts/fastaq_get_ids
-===================================================================
---- fastaq.orig/scripts/fastaq_get_ids
-+++ fastaq/scripts/fastaq_get_ids
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Gets IDs from each sequence in a fasta or fastq file',
-@@ -9,4 +8,8 @@ parser = argparse.ArgumentParser(
- parser.add_argument('infile', help='Name of input fasta/q file')
- parser.add_argument('outfile', help='Name of output file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.get_ids(options.infile, options.outfile)
-Index: fastaq/scripts/fastaq_get_seq_flanking_gaps
-===================================================================
---- fastaq.orig/scripts/fastaq_get_seq_flanking_gaps
-+++ fastaq/scripts/fastaq_get_seq_flanking_gaps
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Gets the sequences either side of gaps in a fasta/q file',
-@@ -11,4 +10,8 @@ parser.add_argument('--right', type=int,
- parser.add_argument('infile', help='Name of input fasta/q file')
- parser.add_argument('outfile', help='Name of output fasta/q file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.get_seqs_flanking_gaps(options.infile, options.outfile, options.left, options.right)
-Index: fastaq/scripts/fastaq_insert_or_delete_bases
-===================================================================
---- fastaq.orig/scripts/fastaq_insert_or_delete_bases
-+++ fastaq/scripts/fastaq_insert_or_delete_bases
-@@ -1,9 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--import sys
--import random
--from fastaq import sequences, utils, intervals
-
- parser = argparse.ArgumentParser(
- description = 'Deletes or inserts bases at given position(s) from a fasta/q file',
-@@ -16,6 +13,11 @@ parser.add_argument('-i','--insert', act
- parser.add_argument('--insert_range', help='Inserts random bases starting after position P in each sequence of the input file. Inserts start + (n-1)*step bases into sequence n.', metavar='P,start,step')
- options = parser.parse_args()
-
-+
-+import sys
-+import random
-+from fastaq import sequences, utils, intervals
-+
- test_ops = [int(x is not None) for x in [options.delete, options.insert, options.delete_range, options.insert_range]]
-
- if sum(test_ops) != 1:
-Index: fastaq/scripts/fastaq_interleave
-===================================================================
---- fastaq.orig/scripts/fastaq_interleave
-+++ fastaq/scripts/fastaq_interleave
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Interleaves two fasta/q files, so that reads are written alternately first/second in output file',
-@@ -10,4 +9,8 @@ parser.add_argument('infile_1', help='Na
- parser.add_argument('infile_2', help='Name of second input fasta/q file')
- parser.add_argument('outfile', help='Name of output fasta/q file of interleaved reads')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.interleave(options.infile_1, options.infile_2, options.outfile)
-Index: fastaq/scripts/fastaq_long_read_simulate
-===================================================================
---- fastaq.orig/scripts/fastaq_long_read_simulate
-+++ fastaq/scripts/fastaq_long_read_simulate
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Simulates long reads from a fasta/q file. Can optionally make insertions into the reads, like pacbio does. If insertions made, coverage calculation is done before the insertions (so total read length may appear longer then expected).',
-@@ -29,8 +28,11 @@ ins_group = parser.add_argument_group('o
- ins_group.add_argument('--ins_skip', type=int, help='Insert a random base every --skip bases plus or minus --ins_window. If this option is used, must also use --ins_window.', metavar='INT')
- ins_group.add_argument('--ins_window', type=int, help='See --ins_skip. If this option is used, must also use --ins_skip.', metavar='INT')
-
--
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.make_long_reads(
- options.infile,
- options.outfile,
-Index: fastaq/scripts/fastaq_make_random_contigs
-===================================================================
---- fastaq.orig/scripts/fastaq_make_random_contigs
-+++ fastaq/scripts/fastaq_make_random_contigs
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Makes a multi-fasta file of random sequences, all of the same length. Each base has equal chance of being A,C,G or T',
-@@ -14,6 +13,10 @@ parser.add_argument('contigs', type=int,
- parser.add_argument('length', type=int, help='Length of each contig')
- parser.add_argument('outfile', help='Name of output file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.make_random_contigs(
- options.contigs,
- options.length,
-Index: fastaq/scripts/fastaq_merge
-===================================================================
---- fastaq.orig/scripts/fastaq_merge
-+++ fastaq/scripts/fastaq_merge
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Converts multi fasta/q file to single sequence file, preserving original order of sequences',
-@@ -10,6 +9,10 @@ parser.add_argument('infile', help='Name
- parser.add_argument('outfile', help='Name of output file')
- parser.add_argument('-n', '--name', help='Name of sequence in output file [%(default)s]', default='union')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.merge_to_one_seq(
- options.infile,
- options.outfile,
-Index: fastaq/scripts/fastaq_replace_bases
-===================================================================
---- fastaq.orig/scripts/fastaq_replace_bases
-+++ fastaq/scripts/fastaq_replace_bases
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Replaces all occurences of one letter with another in a fasta/q file',
-@@ -11,4 +10,8 @@ parser.add_argument('outfile', help='Nam
- parser.add_argument('old', help='Base to be replaced')
- parser.add_argument('new', help='Replace with this letter')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.replace_bases(options.infile, options.outfile, options.old, options.new)
-Index: fastaq/scripts/fastaq_reverse_complement
-===================================================================
---- fastaq.orig/scripts/fastaq_reverse_complement
-+++ fastaq/scripts/fastaq_reverse_complement
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Reverse complements all sequences in a fasta/q file',
-@@ -9,4 +8,8 @@ parser = argparse.ArgumentParser(
- parser.add_argument('infile', help='Name of input fasta/q file')
- parser.add_argument('outfile', help='Name of output fasta/q file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.reverse_complement(options.infile, options.outfile)
-Index: fastaq/scripts/fastaq_scaffolds_to_contigs
-===================================================================
---- fastaq.orig/scripts/fastaq_scaffolds_to_contigs
-+++ fastaq/scripts/fastaq_scaffolds_to_contigs
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Creates a file of contigs from a file of scaffolds - i.e. breaks at every gap in the input',
-@@ -10,4 +9,7 @@ parser.add_argument('--number_contigs',
- parser.add_argument('infile', help='Name of input fasta/q file')
- parser.add_argument('outfile', help='Name of output contigs file')
- options = parser.parse_args()
-+
-+from fastaq import tasks
-+
- tasks.scaffolds_to_contigs(options.infile, options.outfile, number_contigs=options.number_contigs)
-Index: fastaq/scripts/fastaq_search_for_seq
-===================================================================
---- fastaq.orig/scripts/fastaq_search_for_seq
-+++ fastaq/scripts/fastaq_search_for_seq
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Searches for an exact match on a given string and its reverese complement, in every sequences of a fasta/q file. Case insensitive. Guaranteed to find all hits',
-@@ -10,4 +9,7 @@ parser.add_argument('infile', help='Name
- parser.add_argument('outfile', help='Name of outputfile. Tab-delimited output: sequence name, position, strand')
- parser.add_argument('search_string', help='String to search for in the sequences')
- options = parser.parse_args()
-+
-+from fastaq import tasks
-+
- tasks.search_for_seq(options.infile, options.outfile, options.search_string)
-Index: fastaq/scripts/fastaq_sequence_trim
-===================================================================
---- fastaq.orig/scripts/fastaq_sequence_trim
-+++ fastaq/scripts/fastaq_sequence_trim
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Trims sequences off the start of all sequences in a pair of fasta/q files, whenever there is a perfect match. Only keeps a read pair if both reads of the pair are at least a minimum length after any trimming',
-@@ -14,6 +13,10 @@ parser.add_argument('outfile_1', help='N
- parser.add_argument('outfile_2', help='Name of output reverse fasta/q file', metavar='out_2')
- parser.add_argument('trim_seqs', help='Name of fasta/q file of sequences to search for at the start of each input sequence', metavar='trim_seqs')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.sequence_trim(
- options.infile_1,
- options.infile_2,
-Index: fastaq/scripts/fastaq_split_by_base_count
-===================================================================
---- fastaq.orig/scripts/fastaq_split_by_base_count
-+++ fastaq/scripts/fastaq_split_by_base_count
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Splits a multi fasta/q file into separate files. Does not split sequences. Puts up to max_bases into each split file. The exception is that any sequence longer than max_bases is put into its own file.',
-@@ -12,4 +11,8 @@ parser.add_argument('max_bases', type=in
- parser.add_argument('--max_seqs', type=int, help='Max number of sequences in each output split file [no limit]', metavar='INT')
-
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.split_by_base_count(options.infile, options.outprefix, options.max_bases, options.max_seqs)
-Index: fastaq/scripts/fastaq_strip_illumina_suffix
-===================================================================
---- fastaq.orig/scripts/fastaq_strip_illumina_suffix
-+++ fastaq/scripts/fastaq_strip_illumina_suffix
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Strips /1 or /2 off the end of every read name in a fasta/q file',
-@@ -9,4 +8,8 @@ parser = argparse.ArgumentParser(
- parser.add_argument('infile', help='Name of input fasta/q file')
- parser.add_argument('outfile', help='Name of output fasta/q file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.strip_illumina_suffix(options.infile, options.outfile)
-Index: fastaq/scripts/fastaq_to_fake_qual
-===================================================================
---- fastaq.orig/scripts/fastaq_to_fake_qual
-+++ fastaq/scripts/fastaq_to_fake_qual
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Makes fake quality scores file from a fasta/q file',
-@@ -10,6 +9,10 @@ parser.add_argument('infile', help='Name
- parser.add_argument('outfile', help='Name of output file')
- parser.add_argument('-q', '--qual', type=int, help='Quality score to assign to all bases [%(default)s]', default=40)
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.fastaq_to_fake_qual(
- options.infile,
- options.outfile,
-Index: fastaq/scripts/fastaq_to_fasta
-===================================================================
---- fastaq.orig/scripts/fastaq_to_fasta
-+++ fastaq/scripts/fastaq_to_fasta
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Converts sequence file to FASTA format',
-@@ -11,6 +10,10 @@ parser.add_argument('outfile', help='Nam
- parser.add_argument('-l', '--line_length', type=int, help='Number of bases on each sequence line of output file [%(default)s]', default=60)
- parser.add_argument('-s', '--strip_after_whitespace', action='store_true', help='Remove everything after first whitesapce in every sequence name')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.to_fasta(
- options.infile,
- options.outfile,
-Index: fastaq/scripts/fastaq_to_mira_xml
-===================================================================
---- fastaq.orig/scripts/fastaq_to_mira_xml
-+++ fastaq/scripts/fastaq_to_mira_xml
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Creates an xml file from a fasta/q file of reads, for use with Mira assembler',
-@@ -9,4 +8,8 @@ parser = argparse.ArgumentParser(
- parser.add_argument('infile', help='Name of input fasta/q file')
- parser.add_argument('xml_out', help='Name of output xml file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.fastaq_to_mira_xml(options.infile, options.xml_out)
-Index: fastaq/scripts/fastaq_to_orfs_gff
-===================================================================
---- fastaq.orig/scripts/fastaq_to_orfs_gff
-+++ fastaq/scripts/fastaq_to_orfs_gff
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Writes a GFF file of open reading frames from a fasta/q file',
-@@ -10,4 +9,8 @@ parser.add_argument('--min_length', type
- parser.add_argument('infile', help='Name of input fasta/q file')
- parser.add_argument('gff_out', help='Name of output gff file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.fastaq_to_orfs_gff(options.infile, options.gff_out, min_length=options.min_length)
-Index: fastaq/scripts/fastaq_to_perfect_reads
-===================================================================
---- fastaq.orig/scripts/fastaq_to_perfect_reads
-+++ fastaq/scripts/fastaq_to_perfect_reads
-@@ -1,10 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--import random
--from math import floor, ceil
--from fastaq import sequences, utils
--import sys
-
- parser = argparse.ArgumentParser(
- description = 'Makes perfect paired end fastq reads from a fasta/q file, with insert sizes sampled from a normal distribution. Read orientation is innies. Output is an interleaved fastq file.',
-@@ -20,6 +16,12 @@ parser.add_argument('--no_n', action='st
- parser.add_argument('--seed', type=int, help='Seed for random number generator. Default is to use python\'s default', default=None, metavar='INT')
- options = parser.parse_args()
-
-+
-+import random
-+from math import floor, ceil
-+from fastaq import sequences, utils
-+import sys
-+
- random.seed(a=options.seed)
-
- seq_reader = sequences.file_reader(options.infile)
-Index: fastaq/scripts/fastaq_to_random_subset
-===================================================================
---- fastaq.orig/scripts/fastaq_to_random_subset
-+++ fastaq/scripts/fastaq_to_random_subset
-@@ -1,9 +1,6 @@
- #!/usr/bin/env python3
-
--import sys
- import argparse
--import random
--from fastaq import sequences, utils
-
- parser = argparse.ArgumentParser(
- description = 'Takes a random subset of reads from a fasta/q file and optionally the corresponding read ' +
-@@ -15,6 +12,11 @@ parser.add_argument('outfile', help='Nam
- parser.add_argument('probability', type=int, help='Probability of keeping any given read (pair) in [0,100]', metavar='INT')
- options = parser.parse_args()
-
-+
-+import sys
-+import random
-+from fastaq import sequences, utils
-+
- seq_reader = sequences.file_reader(options.infile)
- fout = utils.open_file_write(options.outfile)
-
-Index: fastaq/scripts/fastaq_to_tiling_bam
-===================================================================
---- fastaq.orig/scripts/fastaq_to_tiling_bam
-+++ fastaq/scripts/fastaq_to_tiling_bam
-@@ -1,9 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--import sys
--import os
--from fastaq import sequences, utils
-
- parser = argparse.ArgumentParser(
- description = 'Takes a fasta/q file. Makes a BAM file containing perfect (unpaired) reads tiling the whole genome',
-@@ -17,6 +14,11 @@ parser.add_argument('outfile', help='Nam
- parser.add_argument('--read_group', help='Add the given read group ID to all reads [%(default)s]' ,default='42')
- options = parser.parse_args()
-
-+
-+import sys
-+import os
-+from fastaq import sequences, utils
-+
- # make a header first - we need to add the @RG line to the default header made by samtools
- tmp_empty_file = options.outfile + '.tmp.empty'
- f = utils.open_file_write(tmp_empty_file)
-Index: fastaq/scripts/fastaq_to_unique_by_id
-===================================================================
---- fastaq.orig/scripts/fastaq_to_unique_by_id
-+++ fastaq/scripts/fastaq_to_unique_by_id
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Removes duplicate sequences from a fasta/q file, based on their names. If the same name is found more than once, then the longest sequence is kept. Order of sequences is preserved in output',
-@@ -9,4 +8,8 @@ parser = argparse.ArgumentParser(
- parser.add_argument('infile', help='Name of input fasta/q file')
- parser.add_argument('outfile', help='Name of output fasta/q file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.to_unique_by_id(options.infile, options.outfile)
-Index: fastaq/scripts/fastaq_translate
-===================================================================
---- fastaq.orig/scripts/fastaq_translate
-+++ fastaq/scripts/fastaq_translate
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Translates all sequences in a fasta or fastq file. Output is always fasta format',
-@@ -10,4 +9,8 @@ parser.add_argument('--frame', type=int,
- parser.add_argument('infile', help='Name of fasta/q file to be translated', metavar='in.fasta/q')
- parser.add_argument('outfile', help='Name of output fasta file', metavar='out.fasta')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.translate(options.infile, options.outfile, frame=options.frame)
-Index: fastaq/scripts/fastaq_trim_Ns_at_end
-===================================================================
---- fastaq.orig/scripts/fastaq_trim_Ns_at_end
-+++ fastaq/scripts/fastaq_trim_Ns_at_end
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Trims any Ns off each sequence in a fasta/q file. Does nothing to gaps in the middle, just trims the ends',
-@@ -9,4 +8,8 @@ parser = argparse.ArgumentParser(
- parser.add_argument('infile', help='Name of input fasta/q file')
- parser.add_argument('outfile', help='Name of output fasta/q file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.trim_Ns_at_end(options.infile, options.outfile)
-Index: fastaq/scripts/fastaq_trim_ends
-===================================================================
---- fastaq.orig/scripts/fastaq_trim_ends
-+++ fastaq/scripts/fastaq_trim_ends
-@@ -1,7 +1,6 @@
- #!/usr/bin/env python3
-
- import argparse
--from fastaq import tasks
-
- parser = argparse.ArgumentParser(
- description = 'Trims set number of bases off each sequence in a fasta/q file',
-@@ -11,4 +10,8 @@ parser.add_argument('start_trim', type=i
- parser.add_argument('end_trim', type=int, help='Number of bases to trim off end')
- parser.add_argument('outfile', help='Name of output fasta/q file')
- options = parser.parse_args()
-+
-+
-+from fastaq import tasks
-+
- tasks.trim(options.infile, options.outfile, options.start_trim, options.end_trim)
=====================================
debian/patches/series deleted
=====================================
--- a/debian/patches/series
+++ /dev/null
@@ -1 +0,0 @@
-#delay-import-statements-for-manpage-creation.patch
=====================================
debian/patches/spelling deleted
=====================================
--- a/debian/patches/spelling
+++ /dev/null
@@ -1,13 +0,0 @@
-Description: spelling
-Author: Sascha Steinbiss <satta at debian.org>
---- a/pyfastaq/runners/make_random_contigs.py
-+++ b/pyfastaq/runners/make_random_contigs.py
-@@ -9,7 +9,7 @@
- parser.add_argument('--name_by_letters', action='store_true', help='Name the contigs A,B,C,... will start at A again if you get to Z')
- parser.add_argument('--prefix', help='Prefix to add to start of every sequence name', default='')
- parser.add_argument('--seed', type=int, help='Seed for random number generator. Default is to use python\'s default', default=None)
-- parser.add_argument('contigs', type=int, help='Nunber of contigs to make')
-+ parser.add_argument('contigs', type=int, help='Number of contigs to make')
- parser.add_argument('length', type=int, help='Length of each contig')
- parser.add_argument('outfile', help='Name of output file')
- options = parser.parse_args()
=====================================
pyfastaq/sequences.py
=====================================
--- a/pyfastaq/sequences.py
+++ b/pyfastaq/sequences.py
@@ -1,9 +1,8 @@
import copy
import re
-import string
import random
import itertools
-
+from collections import Counter
from pyfastaq import utils, intervals, genetic_codes
class Error (Exception): pass
@@ -465,6 +464,47 @@ class Fasta:
'''Returns a Fasta sequence, translated into amino acids. Starts translating from 'frame', where frame expected to be 0,1 or 2'''
return Fasta(self.id, ''.join([genetic_codes.codes[genetic_code].get(self.seq[x:x+3].upper(), 'X') for x in range(frame, len(self)-1-frame, 3)]))
+ def gc_content(self, as_decimal=True):
+ """Returns the GC content for the sequence.
+ Notes:
+ This method ignores N when calculating the length of the sequence.
+ It does not, however ignore other ambiguous bases. It also only
+ includes the ambiguous base S (G or C). In this sense the method is
+ conservative with its calculation.
+
+ Args:
+ as_decimal (bool): Return the result as a decimal. Setting to False
+ will return as a percentage. i.e for the sequence GCAT it will
+ return 0.5 by default and 50.00 if set to False.
+
+ Returns:
+ float: GC content calculated as the number of G, C, and S divided
+ by the number of (non-N) bases (length).
+
+ """
+ gc_total = 0.0
+ num_bases = 0.0
+ n_tuple = tuple('nN')
+ accepted_bases = tuple('cCgGsS')
+
+ # counter sums all unique characters in sequence. Case insensitive.
+ for base, count in Counter(self.seq).items():
+
+ # dont count N in the number of bases
+ if base not in n_tuple:
+ num_bases += count
+
+ if base in accepted_bases: # S is a G or C
+ gc_total += count
+
+ gc_content = gc_total / num_bases
+
+ if not as_decimal: # return as percentage
+ gc_content *= 100
+
+ return gc_content
+
+
class Embl(Fasta):
'''Exactly the same as Fasta, but reading seqs from a file works differently'''
=====================================
pyfastaq/tests/sequences_test.py
=====================================
--- a/pyfastaq/tests/sequences_test.py
+++ b/pyfastaq/tests/sequences_test.py
@@ -520,6 +520,19 @@ class TestFasta(unittest.TestCase):
fa = sequences.Fasta('name', 'A')
fa.split_capillary_id()
+ def test_gc_content(self):
+ """Test GC content calculation works as expected"""
+ tests = [
+ (sequences.Fasta('ID', 'cgCG'), 1.0),
+ (sequences.Fasta('ID', 'tTaA'), 0.0),
+ (sequences.Fasta('ID', 'GCAT'), 0.5),
+ (sequences.Fasta('ID', 'GCATNN'), 0.5),
+ (sequences.Fasta('ID', 'GCATNNS'), 0.6),
+ (sequences.Fasta('ID', 'GCATNNSK'), 0.5)
+ ]
+ for test, answer in tests:
+ self.assertAlmostEqual(test.gc_content(), answer)
+ self.assertAlmostEqual(test.gc_content(as_decimal=False), answer * 100)
class TestEmbl(unittest.TestCase):
def test_get_id_from_header_line(self):
=====================================
setup.py
=====================================
--- a/setup.py
+++ b/setup.py
@@ -4,7 +4,7 @@ from setuptools import setup, find_packages
setup(
name='pyfastaq',
- version='3.16.0',
+ version='3.17.0',
description='Script to manipulate FASTA and FASTQ files, plus API for developers',
packages = find_packages(),
author='Martin Hunt',
View it on GitLab: https://salsa.debian.org/med-team/fastaq/compare/ccbb92dfb5122196c131da85bdd6020a7fd3b6a5...6fdcce8fea8a68d9b85702790b9de62b359a0e22
---
View it on GitLab: https://salsa.debian.org/med-team/fastaq/compare/ccbb92dfb5122196c131da85bdd6020a7fd3b6a5...6fdcce8fea8a68d9b85702790b9de62b359a0e22
You're receiving this email because of your account on salsa.debian.org.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alioth.debian.org/pipermail/debian-med-commit/attachments/20180222/3e886997/attachment-0001.html>
More information about the debian-med-commit
mailing list