Commit 13451a12 authored by Hoogenboom, Jerry's avatar Hoogenboom, Jerry
Browse files

Dev version number, minor text corrections

parent fd596525
......@@ -479,7 +479,7 @@ TSSV
- Fixed incorrect calculation of tLeft, fLeft, rLeft, tRight and fRight
columns in the report output file when -T/--num-threads was set to 2 or
higher. The primary output of was unaffected.
higher. The primary output was unaffected.
- Added option '-T/--num-threads' (default: 1), which controls the number
......@@ -24,7 +24,7 @@ including tools for characterisation and filtering of PCR stutter artefacts and
other systemic noise, and for automatic detection of the alleles in a sample.
__version_info__ = ('1', '1', '1')
__version_info__ = ('1', '1', '2', 'dev1')
__version__ = '.'.join(__version_info__)
usage = __doc__.split("\n\n\n")
......@@ -937,12 +937,12 @@ def detect_sequence_format(seq):
# Special case.
return False
if PAT_SEQ_RAW.match(seq):
return 'raw'
return "raw"
if PAT_SEQ_TSSV.match(seq):
return 'tssv'
return "tssv"
if PAT_SEQ_ALLELENAME_STR.match(seq) or PAT_SEQ_ALLELENAME_MT.match(seq) \
return 'allelename'
return "allelename"
raise ValueError("Unrecognised sequence format")
......@@ -1568,11 +1568,11 @@ def regex_arg(value):
def add_allele_detection_args(parser):
group = parser.add_argument_group("allele detection options")
group.add_argument('-a', '--allelelist', metavar="ALLELEFILE",
group.add_argument("-a", "--allelelist", metavar="ALLELEFILE",
help="file containing a list of the true alleles of each sample "
"(e.g., obtained from allelefinder)")
group.add_argument('-c', '--annotation-column', metavar="COLNAME",
group.add_argument("-c", "--annotation-column", metavar="COLNAME",
help="name of a column in the sample files, which contains a value "
"beginning with 'ALLELE' for the true alleles of the sample")
......@@ -1580,11 +1580,11 @@ def add_allele_detection_args(parser):
def add_random_subsampling_args(parser):
group = parser.add_argument_group("random subsampling options (advanced)")
group.add_argument('-Q', '--limit-reads', metavar="N", type=pos_int_arg,
group.add_argument("-Q", "--limit-reads", metavar="N", type=pos_int_arg,
help="simulate lower sequencing depth by randomly dropping reads down "
"to this maximum total number of reads for each sample")
group.add_argument('-x', '--drop-samples', metavar="N", type=float,
group.add_argument("-x", "--drop-samples", metavar="N", type=float,
default=0, help="randomly drop this fraction of input samples")
......@@ -1595,7 +1595,7 @@ def add_sequence_format_args(parser, default_format=None, force=False,
if force:
group.add_argument('-F', '--sequence-format', metavar="FORMAT",
group.add_argument("-F", "--sequence-format", metavar="FORMAT",
choices=("raw", "tssv", "allelename"),
help="convert sequences to the specified format: one of "
......@@ -1603,10 +1603,10 @@ def add_sequence_format_args(parser, default_format=None, force=False,
"no conversion" if default_format is None else default_format)
+ ")")
if require_library:
parser.add_argument('library', metavar="LIBRARY", type=parse_library,
parser.add_argument("library", metavar="LIBRARY", type=parse_library,
help="library file with marker definitions")
group.add_argument('-l', '--library', metavar="LIBRARY",
group.add_argument("-l", "--library", metavar="LIBRARY",
help="library file for sequence format conversion")
......@@ -1618,13 +1618,13 @@ def add_input_output_args(parser, single_in=False, batch_support=False,
# Input file options group.
if not single_in:
# Multiple input files: positionals.
parser.add_argument('infiles', nargs='*', metavar="FILE",
parser.add_argument("infiles", nargs="*", metavar="FILE",
help="the sample data file(s) to process (default: read from "
elif not batch_support:
# Single input file and no batches: single positional.
parser.add_argument('infile', nargs='?', metavar="IN",
parser.add_argument("infile", nargs="?", metavar="IN",
help="the sample data file to process (default: read from stdin)")
......@@ -1632,7 +1632,7 @@ def add_input_output_args(parser, single_in=False, batch_support=False,
# option for batches, which are mutually exclusive.
mutex = parser.add_argument_group(
"input file options").add_mutually_exclusive_group()
mutex.add_argument('infile', nargs='?', metavar="IN",
mutex.add_argument("infile", nargs="?", metavar="IN",
help="single sample data file to process (default: read from "
......@@ -1647,10 +1647,10 @@ def add_input_output_args(parser, single_in=False, batch_support=False,
# Single input file with batch support: single positional and -o
# option for batches, which are mutually exclusive.
mutex = group.add_mutually_exclusive_group()
mutex.add_argument('outfile', nargs='?', metavar="OUT",
mutex.add_argument("outfile", nargs="?", metavar="OUT",
help="the file to write the output to (default: write to stdout)")
mutex.add_argument('-o', '--output', dest="outfiles", nargs="+",
mutex.add_argument("-o", "--output", dest="outfiles", nargs="+",
help="list of names of output files to match with input files "
"specified with -i/--input, or a format string to construct "
......@@ -1659,14 +1659,14 @@ def add_input_output_args(parser, single_in=False, batch_support=False,
((parser.prog.rsplit(" ", 1)[-1],)*2))
elif single_in:
# Single input file and no batch support: single positional.
parser.add_argument('outfile', nargs='?', metavar="OUT",
parser.add_argument("outfile", nargs="?", metavar="OUT",
help="the file to write the output to (default: write to stdout)")
elif batch_support:
# Multiple input files and batch support: use -o option.
# (This is multi-in, multi-out).
group.add_argument('-o', '--output', dest="outfiles", nargs="+",
group.add_argument("-o", "--output", dest="outfiles", nargs="+",
help="a single file name to write all output to (default: write "
......@@ -1676,13 +1676,13 @@ def add_input_output_args(parser, single_in=False, batch_support=False,
"'sampletag-%s.out'" % ((parser.prog.rsplit(" ", 1)[-1],)*2))
# Multiple input files and no batch support: use -o option.
group.add_argument('-o', '--output', dest="outfile", metavar="FILE",
group.add_argument("-o", "--output", dest="outfile", metavar="FILE",
help="file to write output to (default: write to stdout)")
if report_out:
group.add_argument('-R', '--report', metavar="FILE",
group.add_argument("-R", "--report", metavar="FILE",
help="file to write a report to (default: write to stderr)")
......@@ -1691,13 +1691,13 @@ def add_input_output_args(parser, single_in=False, batch_support=False,
group = parser.add_argument_group("sample tag parsing options",
"for details about REGEX syntax and capturing groups, check "
group.add_argument('-e', '--tag-expr', metavar="REGEX", type=regex_arg,
group.add_argument("-e", "--tag-expr", metavar="REGEX", type=regex_arg,
help="regular expression that captures (using one or more "
"capturing groups) the sample tags from the file names; by "
"default, the entire file name except for its extension (if "
"any) is captured")
group.add_argument('-f', '--tag-format', metavar="EXPR",
group.add_argument("-f", "--tag-format", metavar="EXPR",
help="format of the sample tags produced; a capturing group "
"reference like '\\n' refers to the n-th capturing group in "
......@@ -1789,7 +1789,7 @@ def get_input_output_files(args, single=False, batch_support=False):
# Link each output file to each input file.
# Treating files with the same sample tag as separate samples.
return ((tags[i], [infiles[i]], open(outfiles[i], 'w'))
return ((tags[i], [infiles[i]], open(outfiles[i], "w"))
for i in range(len(tags)))
if not single and batch_support:
......@@ -35,8 +35,8 @@ The allele list obtained from allelefinder should always be checked
carefully before using it as the input of various other tools operating
on reference samples. These tools rely heavily on the correctness of
this file to do their job. One may use the allelefinder report
(-R/--report output argument) and the blame tool to get a quick overview
of what might be wrong.
(-R/--report output argument) and the bganalyse tool to get a quick
overview of what might be wrong.
from errno import EPIPE
from ..lib import pos_int_arg, add_input_output_args, get_input_output_files, \
......@@ -24,8 +24,8 @@
Match background noise profiles (obtained from e.g., bgestimate) to
Ten new columns are added to the output giving, for each sequence, the
number of reads attributable to noise from other sequences (_noise
Eleven new columns are added to the output giving, for each sequence,
the number of reads attributable to noise from other sequences (_noise
columns) and the number of noise reads caused by the prescense of this
sequence (_add columns), as well as the resulting number of reads after
correction (_corrected columns: original minus _noise plus _add).
......@@ -41,6 +41,9 @@ predictions as opposed to direct observations;
'corrected_bgestimate'/'corrected_bghomstats', the sequence was present
in the noise profiles as a genuine allele and at least part of its noise
profile was based on direct observations.
Finally, the weight column gives the number of times that the noise
profile of that allele fitted in the sample.
import argparse, sys
#import numpy as np # Only imported when actually running this tool.
* Remove duplicate reads before alignment in TSSV: HUGE potential speedup.
* Group tools by function in the command line help and put Pipeline on top.
* Samplevis:
* Detect whether correction was performed; hide related columns if not.
......@@ -12,6 +13,16 @@ To-do:
be repainted between each chunk. One major issue with this is that user
input events may get scheduled between the chunks.
* Allow table filtering options to be specified for each marker separately.
* Pipeline:
* Add raw sequence output to ref-sample and case-sample analyses.
* Samplestats:
* Verify that Samplestats never treats "Other sequences" as the highest.
* Add capability to run Samplestats again on its own output.
* Add percentage-of-called-alleles columns.
* BGAnalyse:
* Add columns containing the sequence of the highest/lowest noise and the
sequence with the highest percentage recovery in every sample and marker.
* Add option for ignoring strands, operating on the total read counts instead.
* Add options for exporting data in CODIS format (and possibly others?).
* Add grouping, show/hide options, and target coverage for BGAnalyseVis to the
Vis tool.
......@@ -26,7 +37,7 @@ To-do:
variants are specified. The TSSV tool should always output the reference base
at these positions to comply with ethical regulations.
* Add options to Samplevis, Samplestats (and possibly other relevant tools) to
filter alleles by sequence length. The TSSV tool already supports this.
filter alleles by sequence length. The TSSV tool already supports this.
* Add visualisation with all markers in one graph ("samplesummaryvis"?).
* Add tool to analyse within-marker and between-marker coverage variation.
* Allow loading multiple files into HTML visualisations and provide prev/next
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment