# HG changeset patch # User peterjc # Date 1374681201 14400 # Node ID 3b990ab4ae0495f1aa62cc13698776bf3c52ca9e # Parent 66d1ca92fb38143af99e8d48c0c2eeac19470553 Uploaded v0.0.6, auto-dependencies, RST, MIT diff -r 66d1ca92fb38 -r 3b990ab4ae04 tools/filters/seq_filter_by_id.py --- a/tools/filters/seq_filter_by_id.py Wed Apr 24 11:33:48 2013 -0400 +++ b/tools/filters/seq_filter_by_id.py Wed Jul 24 11:53:21 2013 -0400 @@ -29,8 +29,9 @@ (formerly the Scottish Crop Research Institute, SCRI), UK. All rights reserved. See accompanying text file for licence details (MIT/BSD style). -This is version 0.0.5 of the script, use -v or --version to get the version. +This is version 0.1.0 of the script, use -v or --version to get the version. """ +import os import sys def stop_err(msg, err=1): @@ -38,46 +39,72 @@ sys.exit(err) if "-v" in sys.argv or "--version" in sys.argv: - print "v0.0.5" + print "v0.1.0" sys.exit(0) #Parse Command Line -try: - tabular_file, cols_arg, in_file, seq_format, out_positive_file, out_negative_file = sys.argv[1:] -except ValueError: - stop_err("Expected six arguments (tab file, columns, in seq, seq format, out pos, out neg), got %i:\n%s" % (len(sys.argv)-1, " ".join(sys.argv))) -try: - columns = [int(arg)-1 for arg in cols_arg.split(",")] -except ValueError: - stop_err("Expected list of columns (comma separated integers), got %s" % cols_arg) -if min(columns) < 0: - stop_err("Expect one-based column numbers (not zero-based counting), got %s" % cols_arg) +if len(sys.argv) - 1 < 7 or len(sys.argv) % 2 == 1: + stop_err("Expected 7 or more arguments, 5 required " + "(in seq, seq format, out pos, out neg, logic) " + "then one or more pairs (tab file, columns), " + "got %i:\n%s" % (len(sys.argv)-1, " ".join(sys.argv))) +in_file, seq_format, out_positive_file, out_negative_file, logic = sys.argv[1:6] + +if not os.path.isfile(in_file): + stop_err("Missing input file %r" % in_file) if out_positive_file == "-" and out_negative_file == "-": stop_err("Neither output file requested") +if logic not in ["UNION", "INTERSECTION"]: + stop_err("Fifth agrument should be 'UNION' or 'INTERSECTION', not %r" % logic) +identifiers = [] +for i in range((len(sys.argv) - 6) // 2): + tabular_file = sys.argv[6+2*i] + cols_arg = sys.argv[7+2*i] + if not os.path.isfile(tabular_file): + stop_err("Missing tabular identifier file %r" % tabular_file) + try: + columns = [int(arg)-1 for arg in cols_arg.split(",")] + except ValueError: + stop_err("Expected list of columns (comma separated integers), got %r" % cols_arg) + if min(columns) < 0: + stop_err("Expect one-based column numbers (not zero-based counting), got %r" % cols_arg) + identifiers.append((tabular_file, columns)) -#Read tabular file and record all specified identifiers -ids = set() -handle = open(tabular_file, "rU") -if len(columns)>1: - #General case of many columns - for line in handle: - if line.startswith("#"): - #Ignore comments - continue - parts = line.rstrip("\n").split("\t") - for col in columns: - ids.add(parts[col]) - print "Using %i IDs from %i columns of tabular file" % (len(ids), len(columns)) -else: - #Single column, special case speed up - col = columns[0] - for line in handle: - if not line.startswith("#"): - ids.add(line.rstrip("\n").split("\t")[col]) - print "Using %i IDs from tabular file" % (len(ids)) -handle.close() +#Read tabular file(s) and record all specified identifiers +ids = None #Will be a set +for tabular_file, columns in identifiers: + file_ids = set() + handle = open(tabular_file, "rU") + if len(columns)>1: + #General case of many columns + for line in handle: + if line.startswith("#"): + #Ignore comments + continue + parts = line.rstrip("\n").split("\t") + for col in columns: + file_ids.add(parts[col]) + else: + #Single column, special case speed up + col = columns[0] + for line in handle: + if not line.startswith("#"): + file_ids.add(line.rstrip("\n").split("\t")[col]) + print "Using %i IDs from column %s in tabular file" % (len(file_ids), ", ".join(str(col+1) for col in columns)) + if ids is None: + ids = file_ids + if logic == "UNION": + ids.update(file_ids) + else: + ids.intersection_update(file_ids) + handle.close() +if len(identifiers) > 1: + if logic == "UNION": + print "Have %i IDs combined from %i tabular files" % (len(ids), len(identifiers)) + else: + print "Have %i IDs in common from %i tabular files" % (len(ids), len(identifiers)) def crude_fasta_iterator(handle): diff -r 66d1ca92fb38 -r 3b990ab4ae04 tools/filters/seq_filter_by_id.rst --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tools/filters/seq_filter_by_id.rst Wed Jul 24 11:53:21 2013 -0400 @@ -0,0 +1,120 @@ +Galaxy tool to filter FASTA, FASTQ or SFF sequences by ID +========================================================= + +This tool is copyright 2010-2013 by Peter Cock, The James Hutton Institute +(formerly SCRI, Scottish Crop Research Institute), UK. All rights reserved. +See the licence text below. + +This tool is a short Python script (using both the Galaxy and Biopython library +functions) which divides a FASTA, FASTQ, or SFF file in two, those sequences with +or without an ID present in the specified column(s) of a tabular file. Example uses +include filtering based on search results from a tool like NCBI BLAST before +assembly. + +This tool is available from the Galaxy Tool Shed at: + +* http://toolshed.g2.bx.psu.edu/view/peterjc/seq_filter_by_id + +See also sister tools: + +* http://toolshed.g2.bx.psu.edu/view/peterjc/seq_select_by_id +* http://toolshed.g2.bx.psu.edu/view/peterjc/seq_rename + + +Automated Installation +====================== + +This should be straightforward using the Galaxy Tool Shed, which should be +able to automatically install the dependency on Biopython, and then install +this tool and run its unit tests. + + +Manual Installation +=================== + +There are just two files to install to use this tool from within Galaxy: + +* seq_filter_by_id.py (the Python script) +* seq_filter_by_id.xml (the Galaxy tool definition) + +The suggested location is in the Galaxy folder tools/filters next to the tool +for calling sff_extract.py for converting SFF to FASTQ or FASTA + QUAL. + +You will also need to modify the tools_conf.xml file to tell Galaxy to offer the +tool. One suggested location is in the filters section. Simply add the line:: + + + +If you wish to run the unit tests, also add this to tools_conf.xml.sample +and move/copy the test-data files under Galaxy's test-data folder. Then:: + + $ ./run_functional_tests.sh -id seq_filter_by_id + +You will also need to install Biopython 1.54 or later. That's it. + + +History +======= + +======= ====================================================================== +Version Changes +------- ---------------------------------------------------------------------- +v0.0.1 - Initial version, combining three separate scripts for each file format. +v0.0.4 - Record script version when run from Galaxy. + - Faster FASTA code which preserves the original line wrapping. + - Basic unit test included. +v0.0.5 - Check for errors using Python script's return code. + - Cope with malformed FASTA entries without an identifier. +v0.0.6 - Link to Tool Shed added to help text and this documentation. + - Automated installation of the Biopython dependency. + - Use reStructuredText for this README file. + - Adopt standard MIT License. +======= ====================================================================== + + + +Developers +========== + +This script and related tools are being developed on the following hg branch: +http://bitbucket.org/peterjc/galaxy-central/src/tools + +This incorporates the previously used hg branch: +http://bitbucket.org/peterjc/galaxy-central/src/fasta_filter + +For making the "Galaxy Tool Shed" http://toolshed.g2.bx.psu.edu/ tarball use +the following command from the Galaxy root folder:: + + $ tar -czf seq_filter_by_id.tar.gz tools/filters/seq_filter_by_id.* test-data/k12_ten_proteins.fasta test-data/k12_hypothetical.fasta test-data/k12_hypothetical.tabular + +Check this worked:: + + $ tar -tzf seq_filter_by_id.tar.gz + filter/seq_filter_by_id.py + filter/seq_filter_by_id.rst + filter/seq_filter_by_id.xml + test-data/k12_ten_proteins.fasta + test-data/k12_hypothetical.fasta + test-data/k12_hypothetical.tabular + + +Licence (MIT) +============= + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in +all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN +THE SOFTWARE. diff -r 66d1ca92fb38 -r 3b990ab4ae04 tools/filters/seq_filter_by_id.txt --- a/tools/filters/seq_filter_by_id.txt Wed Apr 24 11:33:48 2013 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,89 +0,0 @@ -Galaxy tool to filter FASTA, FASTQ or SFF sequences by ID -========================================================= - -This tool is copyright 2010-2013 by Peter Cock, The James Hutton Institute -(formerly SCRI, Scottish Crop Research Institute), UK. All rights reserved. -See the licence text below. - -This tool is a short Python script (using both the Galaxy and Biopython library -functions) which divides a FASTA, FASTQ, or SFF file in two, those sequences with -or without an ID present in the specified column(s) of a tabular file. Example uses -include filtering based on search results from a tool like NCBI BLAST before -assembly. - - -Installation -============ - -There are just two files to install: - -* seq_filter_by_id.py (the Python script) -* seq_filter_by_id.xml (the Galaxy tool definition) - -The suggested location is in the Galaxy folder tools/filters next to the tool -for calling sff_extract.py for converting SFF to FASTQ or FASTA + QUAL. - -You will also need to modify the tools_conf.xml file to tell Galaxy to offer the -tool. One suggested location is in the filters section. Simply add the line: - - - -You will also need to install Biopython 1.54 or later. That's it. - - -History -======= - -v0.0.1 - Initial version, combining three separate scripts for each file format. -v0.0.4 - Record script version when run from Galaxy. - - Faster FASTA code which preserves the original line wrapping. - - Basic unit test included. -v0.0.5 - Check for errors using Python script's return code. - - Cope with malformed FASTA entries without an identifier. - - -Developers -========== - -This script and related tools are being developed on the following hg branch: -http://bitbucket.org/peterjc/galaxy-central/src/tools - -This incorporates the previously used hg branch: -http://bitbucket.org/peterjc/galaxy-central/src/fasta_filter - -For making the "Galaxy Tool Shed" http://toolshed.g2.bx.psu.edu/ tarball use -the following command from the Galaxy root folder: - -$ tar -czf seq_filter_by_id.tar.gz tools/filters/seq_filter_by_id.* test-data/k12_ten_proteins.fasta test-data/k12_hypothetical.fasta test-data/k12_hypothetical.tabular - -Check this worked: - -$ tar -tzf seq_filter_by_id.tar.gz -filter/seq_filter_by_id.py -filter/seq_filter_by_id.txt -filter/seq_filter_by_id.xml -test-data/k12_ten_proteins.fasta -test-data/k12_hypothetical.fasta -test-data/k12_hypothetical.tabular - - -Licence (MIT/BSD style) -======================= - -Permission to use, copy, modify, and distribute this software and its -documentation with or without modifications and for any purpose and -without fee is hereby granted, provided that any copyright notices -appear in all copies and that both those copyright notices and this -permission notice appear in supporting documentation, and that the -names of the contributors or copyright holders not be used in -advertising or publicity pertaining to distribution of the software -without specific prior permission. - -THE CONTRIBUTORS AND COPYRIGHT HOLDERS OF THIS SOFTWARE DISCLAIM ALL -WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED -WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO EVENT SHALL THE -CONTRIBUTORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT -OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS -OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE -OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE -OR PERFORMANCE OF THIS SOFTWARE. diff -r 66d1ca92fb38 -r 3b990ab4ae04 tools/filters/seq_filter_by_id.xml --- a/tools/filters/seq_filter_by_id.xml Wed Apr 24 11:33:48 2013 -0400 +++ b/tools/filters/seq_filter_by_id.xml Wed Jul 24 11:53:21 2013 -0400 @@ -1,8 +1,8 @@ - + from a tabular file seq_filter_by_id.py --version -seq_filter_by_id.py $input_tabular $columns $input_file $input_file.ext +seq_filter_by_id.py "$input_file" "$input_file.ext" #if $output_choice_cond.output_choice=="both" $output_pos $output_neg #elif $output_choice_cond.output_choice=="pos" @@ -10,6 +10,9 @@ #elif $output_choice_cond.output_choice=="neg" - $output_neg #end if +## TODO - Decide on best way to expose multiple ID files via the XML wrapper. +## Single tabular file, can call the Python script with either UNION or INTERSECTION +UNION "$input_tabular" "$columns" @@ -109,5 +112,7 @@ molecular biology and bioinformatics. Bioinformatics 25(11) 1422-3. http://dx.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/seq_filter_by_id