[med-svn] [fastaq] 01/03: Imported Upstream version 3.10.1
Sascha Steinbiss
sascha-guest at moszumanska.debian.org
Mon Nov 16 19:20:24 UTC 2015
This is an automated email from the git hooks/post-receive script.
sascha-guest pushed a commit to branch master
in repository fastaq.
commit 3817361055b2a68787a63f52a7eb57a73d9457ad
Author: Sascha Steinbiss <sascha at steinbiss.name>
Date: Mon Nov 16 19:18:26 2015 +0000
Imported Upstream version 3.10.1
---
README.md | 1 -
pyfastaq/common.py | 2 +-
pyfastaq/runners/long_read_simulate.py | 49 ----------------------------------
pyfastaq/runners/to_tiling_bam.py | 3 ++-
scripts/fastaq | 1 -
setup.py | 2 +-
6 files changed, 4 insertions(+), 54 deletions(-)
diff --git a/README.md b/README.md
index af92b95..269ddc8 100644
--- a/README.md
+++ b/README.md
@@ -71,7 +71,6 @@ Available commands
| get_ids | Get the ID of each sequence |
| get_seq_flanking_gaps | Gets the sequences flanking gaps |
| interleave | Interleaves two files, output is alternating between fwd/rev reads |
-| long_read_simulate | Simulates long reads from reference |
| make_random_contigs | Make contigs of random sequence |
| merge | Converts multi sequence file to a single sequence |
| replace_bases | Replaces all occurences of one letter with another |
diff --git a/pyfastaq/common.py b/pyfastaq/common.py
index 63b3d84..b951f1c 100644
--- a/pyfastaq/common.py
+++ b/pyfastaq/common.py
@@ -1 +1 @@
-version = '3.10.0'
+version = '3.10.1'
diff --git a/pyfastaq/runners/long_read_simulate.py b/pyfastaq/runners/long_read_simulate.py
deleted file mode 100644
index ad8da23..0000000
--- a/pyfastaq/runners/long_read_simulate.py
+++ /dev/null
@@ -1,49 +0,0 @@
-import argparse
-from pyfastaq import tasks
-
-def run(description):
- parser = argparse.ArgumentParser(
- description = 'Simulates long reads from a sequence 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).',
- usage = 'fastaq long_read_simulate [options] <infile> <outfile>')
-
- parser.add_argument('infile', help='Name of input file')
- parser.add_argument('outfile', help='Name of output FASTA file')
-
- parser.add_argument('--method', help='How to sample the read positions and lengths. Choose from 1) "tiling", where reads of fixed length are taken at equal intervals from the reference. 2) "unfiform", where reads of fixed length taken at positions sampled uniformly. 3) "gamma", where reads lengths are taken from a gamma distribution, and positions sampled uniformly. [%(default)s]', default='tiling', choices=['tiling', 'uniform', 'gamma'], metavar='tiling|uniform|gamma')
- parser.add_argument('--seed', type=int, help='Seed for random number generator [default: use python\'s default]', metavar='INT')
- parser.add_argument('--qual', help='Write a file of fake quality scores called outfile.qual, all bases same quality [%(default)s]', metavar='INT')
- parser.add_argument('--fixed_read_length', type=int, help='Length of each read. Only applies if method is tile or uniform. [%(default)s]', default=20000, metavar='INT')
- parser.add_argument('--coverage', type=float, help='Read coverage. Only applies if method is gamma or uniform. [%(default)s]', default=2, metavar='FLOAT')
-
-
- tiling_group = parser.add_argument_group('tiling options')
- tiling_group.add_argument('--tile_step', type=int, help='Distance between start of each read [%(default)s]', default=10000, metavar='INT')
-
- gamma_group = parser.add_argument_group('gamma options')
- gamma_group.add_argument('--gamma_shape', type=float, help='Shape parameter of gamma distribution [%(default)s]', default=1.2, metavar='FLOAT')
- gamma_group.add_argument('--gamma_scale', type=float, help='Scale parameter of gamma distribution [%(default)s]', default=6000, metavar='FLOAT')
- gamma_group.add_argument('--gamma_min_length', type=int, help='Minimum read length [%(default)s]', default=20000, metavar='INT')
-
- ins_group = parser.add_argument_group('options to add insertions to reads')
- 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()
- tasks.make_long_reads(
- options.infile,
- options.outfile,
- method=options.method,
- fixed_read_length=options.fixed_read_length,
- coverage=options.coverage,
- tile_step=options.tile_step,
- gamma_shape=options.gamma_shape,
- gamma_scale=options.gamma_scale,
- gamma_min_length=options.gamma_min_length,
- seed=options.seed,
- ins_skip=options.ins_skip,
- ins_window=options.ins_window
- )
-
- if options.qual:
- tasks.fastaq_to_fake_qual(options.outfile, options.outfile + '.qual', q=options.qual)
diff --git a/pyfastaq/runners/to_tiling_bam.py b/pyfastaq/runners/to_tiling_bam.py
index ab37e65..df098c1 100644
--- a/pyfastaq/runners/to_tiling_bam.py
+++ b/pyfastaq/runners/to_tiling_bam.py
@@ -13,6 +13,7 @@ def run(description):
parser.add_argument('read_step', type=int, help='Distance between start of each read')
parser.add_argument('read_prefix', help='Prefix of read names')
parser.add_argument('outfile', help='Name of output BAM file')
+ parser.add_argument('--qual_char', help='Character to use for quality score [%(default)s]', default='I')
parser.add_argument('--read_group', help='Add the given read group ID to all reads [%(default)s]' ,default='42')
options = parser.parse_args()
@@ -56,7 +57,7 @@ def run(description):
end = len(seq) - 1
start = end - options.read_length + 1
- read = sequences.Fastq(options.read_prefix + ':' + seq.id + ':' + str(start + 1) + ':' + str(end + 1), seq[start:end+1], 'I' * (end - start + 1))
+ read = sequences.Fastq(options.read_prefix + ':' + seq.id + ':' + str(start + 1) + ':' + str(end + 1), seq[start:end+1], options.qual_char * (end - start + 1))
print ('\t'.join([read.id,
'0',
diff --git a/scripts/fastaq b/scripts/fastaq
index 3198b2d..b264517 100755
--- a/scripts/fastaq
+++ b/scripts/fastaq
@@ -17,7 +17,6 @@ tasks = {
'get_ids': 'Get the ID of each sequence',
'get_seq_flanking_gaps': 'Gets the sequences flanking gaps',
'interleave': 'Interleaves two files, output is alternating between fwd/rev reads',
- 'long_read_simulate': 'Simulates long reads from reference',
'make_random_contigs': 'Make contigs of random sequence',
'merge': 'Converts multi sequence file to a single sequence',
'replace_bases': 'Replaces all occurences of one letter with another',
diff --git a/setup.py b/setup.py
index 012b341..baa05ba 100644
--- a/setup.py
+++ b/setup.py
@@ -4,7 +4,7 @@ from setuptools import setup, find_packages
setup(
name='pyfastaq',
- version='3.10.0',
+ version='3.10.1',
description='Script to manipulate FASTA and FASTQ files, plus API for developers',
packages = find_packages(),
author='Martin Hunt',
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/debian-med/fastaq.git
More information about the debian-med-commit
mailing list