- galaxy-commits - lists.galaxyproject.org

galaxy-dist commit 8979b429d769: Adding a Python script for converting BLAST XML to 12 column tabular
by commits-noreply＠bitbucket.org 20 Nov '10

20 Nov '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User peterjc <p.j.a.cock(a)googlemail.com> # Date 1286551276 -3600 # Node ID 8979b429d7691f4121afb368a05e6b9d0ea40706 # Parent b2906cd2d484a25f80134f432b7c36ed18747bb5 Adding a Python script for converting BLAST XML to 12 column tabular --- /dev/null +++ b/tools/ncbi_blast_plus/blastxml_to_tabular.xml @@ -0,0 +1,41 @@ +<tool id="blastxml_to_tabular" name="BLAST XML to tabular" version="0.0.1"> + <description>Convert BLAST XML output to tabular</description> + <command interpreter="python"> + blastxml_to_tabular.py $blastxml_file $tabular_file + </command> + <inputs> + <param name="blastxml_file" type="data" format="blastxml" label="BLAST results as XML"/> + </inputs> + <outputs> + <data name="tabular_file" format="tabular" label="BLAST results as tabular" /> + </outputs> + <requirements> + </requirements> + <tests> + </tests> + <help> + +**What it does** + +NCBI BLAST+ (and the older NCBI 'legacy' BLAST) can output in a range of formats including +tabular and a more detailed XML format. A complex workflow may need both the XML and the +tabular output. + +This tool takes the BLAST XML output and converts it into the 12 column tabular equivalent: + +1. Id of your sequence +2. GI of the database hit +3. % identity +4. Alignment length +5. # mismatches +6. # gaps +7. Start position in your sequence +8. End position in your sequence +9. Start position in database hit +10. End position in database hit +11. E-value +12. Bit score + + + </help> +</tool> --- /dev/null +++ b/tools/ncbi_blast_plus/blastxml_to_tabular.py @@ -0,0 +1,123 @@ +#!/usr/bin/env python +"""Convert a BLAST XML file to 12 column tabular output + +Takes two command line options, input BLAST XML filename and output tabular +BLAST filename. + +The 12 colums output are 'qseqid sseqid pident length mismatch gapopen qstart +qend sstart send evalue bitscore' which mean: + + * qseqid - Query Seq-id + * sseqid - Subject Seq-id + * pident - Percentage of identical matches + * length - Alignment length + * mismatch - Number of mismatches + * gapopen - Number of gap openings + * qstart - Start of alignment in query + * qend - End of alignment in query + * sstart - Start of alignment in subject + * send - End of alignment in subject + * evalue - Expect value + * bitscore - Bit score + +Most of these fields are given explicitly in the XML file, others some like +the percentage identity and the number of gap openings must be calculated. + +This script attempts to produce idential output to what BLAST+ would have done. +However, check this with "diff -b ..." since BLAST+ sometimes includes an extra +space character (probably a bug). +""" +import sys + +#Parse Command Line +in_file, out_file = sys.argv[1:] + +assert sys.version_info[:2] >= ( 2, 4 ) +if sys.version_info[:2] >= ( 2, 5 ): + import xml.etree.cElementTree as cElementTree +else: + import cElementTree + +def stop_err( msg ): + sys.stderr.write("%s\n" % msg) + sys.exit(1) + +tags = ["Hsp_identity", + "Hsp_align-len", + "Hsp_gaps", + "Hsp_query-from", + "Hsp_query-to", + "Hsp_hit-from", + "Hsp_hit-to", + "Hsp_evalue", + "Hsp_bit-score"] + +# get an iterable +try: + context = cElementTree.iterparse(in_file, events=("start", "end")) +except: + stop_err("Invalid data format.") +# turn it into an iterator +context = iter(context) +# get the root element +try: + event, root = context.next() +except: + stop_err( "Invalid data format." ) + +outfile = open(out_file, 'w') +for event, elem in context: + # for every <Iteration> tag + if event == "end" and elem.tag == "Iteration": + qseqid = elem.findtext("Iteration_query-def").split(None,1)[0] + # for every <Hit> within <Iteration> + for hit in elem.findall("Iteration_hits/Hit/"): + sseqid = hit.findtext("Hit_id").split(None,1)[0] + # for every <Hsp> within <Hit> + for hsp in hit.findall("Hit_hsps/Hsp"): + identity = hsp.findtext("Hsp_identity") + length = hsp.findtext("Hsp_align-len") + pident = "%0.2f" % (100*float(identity)/float(length)) + + q_seq = hsp.findtext("Hsp_qseq") + h_seq = hsp.findtext("Hsp_hseq") + assert len(q_seq) == len(h_seq) == int(length) + gapopen = str(len(q_seq.replace('-', ' ').split())-1 + \ + len(h_seq.replace('-', ' ').split())-1) + mismatch = str(len(q_seq) - sum(1 for q,h in zip(q_seq, h_seq) \ + if q == h or q == "-" or h == "-")) + assert int(identity) == sum(1 for q,h in zip(q_seq, h_seq) if q == h) + + evalue = hsp.findtext("Hsp_evalue") + if evalue == "0": + evalue = "0.0" + else: + evalue = "%0.0e" % float(evalue) + + bitscore = float(hsp.findtext("Hsp_bit-score")) + if bitscore < 100: + #Seems to show one decimal place for lower scores + bitscore = "%0.1f" % bitscore + else: + #Note BLAST does not round to nearest int, it truncates + bitscore = "%i" % bitscore + + values = [qseqid, + sseqid, + pident, + length, #hsp.findtext("Hsp_align-len") + mismatch, + gapopen, + hsp.findtext("Hsp_query-from"), #qstart, + hsp.findtext("Hsp_query-to"), #qend, + hsp.findtext("Hsp_hit-from"), #sstart, + hsp.findtext("Hsp_hit-to"), #send, + evalue, #hsp.findtext("Hsp_evalue") in scientific notation + bitscore, #hsp.findtext("Hsp_bit-score") rounded + ] + #print "\t".join(values) + outfile.write("\t".join(values) + "\n") + # prevents ElementTree from growing large datastructure + root.clear() + elem.clear() +outfile.close()

1 0

galaxy-dist commit 55f909b601c4: Use the data_column type (great except on empty tabular files)
by commits-noreply＠bitbucket.org 20 Nov '10

20 Nov '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User peterjc <p.j.a.cock(a)googlemail.com> # Date 1285874190 -3600 # Node ID 55f909b601c49dc0bb53f4fee538605df04d19f4 # Parent 5498ff5b31ac871c7d22df60146fd96c61b74aab Use the data_column type (great except on empty tabular files) --- a/tools/ncbi_blast_plus/blast_filter_fasta.xml +++ b/tools/ncbi_blast_plus/blast_filter_fasta.xml @@ -5,9 +5,7 @@ </command><inputs><param name="blast_file" type="data" format="tabular" label="Tabular BLAST output"/> - <param name="blast_col" type="integer" value="1" label="Column containing FASTA identifiers"> - <validator type="in_range" min="1" /> - </param> + <param name="blast_col" type="data_column" data_ref="blast_file" numerical="true" value="1" label="Column containing FASTA identifiers" /><param name="in_file" type="data" format="fasta" label="BLAST query FASTA file"/></inputs><outputs>

1 0

galaxy-dist commit 34794995b12f: Adding simple python script to split a FASTA file into those sequence with/without BLAST hits using tabular output
by commits-noreply＠bitbucket.org 20 Nov '10

20 Nov '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User peterjc <p.j.a.cock(a)googlemail.com> # Date 1285681430 -3600 # Node ID 34794995b12f700d50c12bb013431c882dca9c10 # Parent 5244ad54bebadf57e8bede36643afa49c58ac579 Adding simple python script to split a FASTA file into those sequence with/without BLAST hits using tabular output --- a/tool_conf.xml.sample +++ b/tool_conf.xml.sample @@ -265,6 +265,7 @@ <section name="NCBI BLAST+" id="ncbi_blast_plus_tools"><tool file="ncbi_blast_plus/ncbi_blastn_wrapper.xml" /><tool file="ncbi_blast_plus/ncbi_blastp_wrapper.xml" /> + <tool file="ncbi_blast_plus/blast_filter_fasta.xml" /></section><section name="NGS: Mapping" id="solexa_tools"><tool file="sr_mapping/lastz_wrapper.xml" /> --- /dev/null +++ b/tools/ncbi_blast_plus/blast_filter_fasta.py @@ -0,0 +1,34 @@ +#!/usr/bin/env python +"""Filter a FASTA file using tabular BLAST output. + +Takes four command line options, tabular BLAST filename, input FASTA filename, +and two output FASTA filenames (for records with and without any BLAST hits). +""" +#TODO - Option to define which column to use for ID? + +import sys +from galaxy_utils.sequence.fasta import fastaReader, fastaWriter + +#Parse Command Line +blast_file, in_file, out_positive_file, out_negative_file = sys.argv[1:] + +#Read tabular BLAST file and record all queries with hit(s) +ids = set() +blast_handle = open(blast_file, "rU") +for line in blast_handle: + ids.add(line.split("\t")[0]) +blast_handle.close() + +#Write filtered FASTA file based on IDs from BLAST file +reader = fastaReader(open(in_file, "rU")) +positive_writer = fastaWriter(open(out_positive_file, "w")) +negative_writer = fastaWriter(open(out_negative_file, "w")) +for record in reader: + #The [1:] is because the fastaReader leaves the > on the identifer. + if record.identifier and record.identifier.split()[0][1:] in ids: + positive_writer.write(record) + else: + negative_writer.write(record) +positive_writer.close() +negative_writer.close() +reader.close() --- /dev/null +++ b/tools/ncbi_blast_plus/blast_filter_fasta.xml @@ -0,0 +1,26 @@ +<tool id="blast_filter_fasta" name="BLAST filter FASTA file" version="0.0.1"> + <description>Divide a FASTA file based on BLAST hits</description> + <command interpreter="python"> + blast_filter_fasta.py $blast_file $in_file $out_positive_file $out_negative_file + </command> + <inputs> + <param name="blast_file" type="data" format="tabular" label="Tabular BLAST output"/> + <param name="in_file" type="data" format="fasta" label="BLAST query FASTA file"/> + </inputs> + <outputs> + <data name="out_positive_file" format="fasta" label="Sequences with BLAST hits" /> + <data name="out_negative_file" format="fasta" label="Sequences without BLAST hits" /> + </outputs> + <requirements> + </requirements> + <tests> + </tests> + <help> + +**What it does** + +Takes a multi-sequence FASTA and the tabular output of running BLAST on it, and +divides the FASTA file in two: those sequence with a BLAST hit, and those without. + + </help> +</tool>

1 0

galaxy-dist commit ad83deba6458: Adding blastx and tblastx wrappers, tidying
by commits-noreply＠bitbucket.org 20 Nov '10

20 Nov '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User peterjc <p.j.a.cock(a)googlemail.com> # Date 1285688573 -3600 # Node ID ad83deba645811d8b9509a6e3c58e986ffa89e3b # Parent 92bb0d0d7e9058bc4b6b43eaa015349241bc13e0 Adding blastx and tblastx wrappers, tidying --- a/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml @@ -12,8 +12,8 @@ -num_threads 8 </command><inputs> - <param name="query" type="data" format="fasta" label="Query sequence(s)"/> - <param name="database" type="select" display="radio" label="Nucelotide BLAST database"> + <param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> + <param name="database" type="select" display="radio" label="Nucleotide BLAST database"><options from_file="blastdb.loc"><column name="name" index="0"/><column name="value" index="1"/> @@ -26,13 +26,6 @@ <option value="dc-megablast">dc-megablast</option><option value="vecscreen">vecscreen</option></param> - <param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" /><param name="out_format" type="select" label="Output format"><option value="6">Tabular</option> @@ -89,19 +82,22 @@ .. class:: warningmark -**Note**. Database searches may take substantial amount of time. For large input datasets it is advisable to allow overnight processing. +**Note**. Database searches may take substantial amount of time. +For large input datasets it is advisable to allow overnight processing. ----- **What it does** -This tool runs NCBI BLAST+ blastn tool (which include *megablast*). +Search a *nucleotide database* using a *nucleotide query*, +using the NCBI BLAST+ blastn command line tool. +Algorithms include blastn, megablast, and discontiguous megablast. ----- **Output format** -The default Output of this tool is tabular, containing 12 columns: +The default output of this tool is tabular, containing 12 columns: 1. Id of your sequence 2. GI of the database hit --- a/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml @@ -11,7 +11,7 @@ -num_threads 8 </command><inputs> - <param name="query" type="data" format="fasta" label="Query sequence(s)"/> + <param name="query" type="data" format="fasta" label="Protein query sequence(s)"/><param name="database" type="select" display="radio" label="Nucelotide BLAST database"><options from_file="blastdb.loc"><column name="name" index="0"/> @@ -60,19 +60,21 @@ .. class:: warningmark -**Note**. Database searches may take substantial amount of time. For large input datasets it is advisable to allow overnight processing. +**Note**. Database searches may take substantial amount of time. +For large input datasets it is advisable to allow overnight processing. ----- **What it does** -This tool runs NCBI BLAST+ tblastn tool. +Search a *translated nucleotide database* using a *protein query*, +using the NCBI BLAST+ tblastn command line tool. ----- **Output format** -The default Output of this tool is tabular, containing 12 columns: +The default output of this tool is tabular, containing 12 columns: 1. Id of your sequence 2. GI of the database hit --- a/tool_conf.xml.sample +++ b/tool_conf.xml.sample @@ -264,8 +264,10 @@ --><section name="NCBI BLAST+" id="ncbi_blast_plus_tools"><tool file="ncbi_blast_plus/ncbi_blastn_wrapper.xml" /> + <tool file="ncbi_blast_plus/ncbi_blastp_wrapper.xml" /> + <tool file="ncbi_blast_plus/ncbi_blastx_wrapper.xml" /><tool file="ncbi_blast_plus/ncbi_tblastn_wrapper.xml" /> - <tool file="ncbi_blast_plus/ncbi_blastp_wrapper.xml" /> + <tool file="ncbi_blast_plus/ncbi_tblastx_wrapper.xml" /><tool file="ncbi_blast_plus/blast_filter_fasta.xml" /></section><section name="NGS: Mapping" id="solexa_tools"> --- /dev/null +++ b/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml @@ -0,0 +1,112 @@ +<tool id="ncbi_tblastx_wrapper" name="NCBI BLAST+ tblastx" version="0.0.1"> + <description>Search translated nucleotide database with translated nucleotide query sequence(s)</description> + <command> + tblastx + -query "$query" + -db "$database" + -evalue $evalue_cutoff + -seg $adv_opts.filter_query + -out $output1 + -outfmt $out_format + -num_threads 8 + </command> + <inputs> + <param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> + <param name="database" type="select" display="radio" label="Nucelotide BLAST database"> + <options from_file="blastdb.loc"> + <column name="name" index="0"/> + <column name="value" index="1"/> + </options> + </param> + <param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" /> + <param name="out_format" type="select" label="Output format"> + <option value="6">Tabular</option> + <option value="5">BLAST XML</option> + <option value="0">Pairwise text</option> +  + </param> + <conditional name="adv_opts"> + <param name="adv_opts_selector" type="select" label="Advanced Options"> + <option value="basic" selected="True">Hide Advanced Options</option> + <option value="advanced">Show Advanced Options</option> + </param> + <when value="basic"> + <param name="filter_query" type="hidden" value="yes" /> + </when> + <when value="advanced"> + <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="yes" falsevalue="no" checked="true" /> + </when> + </conditional> + </inputs> + <outputs> +  + <data name="output1" format="tabular" label="tblastx on ${database.value_label}"> + <change_format> + <when input="out_format" value="0" format="txt"/> + </change_format> + <change_format> + <when input="out_format" value="5" format="blastxml"/> + </change_format> + </data> + </outputs> + <requirements> + <requirement type="binary">blastn</requirement> + </requirements> + <tests> + <test> + <param name="input_query" value="megablast_wrapper_test1.fa" ftype="fasta"/> +  + <param name="database" value="phiX" /> + <param name="blast_type" value="megablast" /> +  + <param name="evalue_cutoff" value="10.0" /> + <param name="filter_query" value="yes" /> + <param name="out_format" value="6" /> + <output name="output1" file="megablast_wrapper_test1.out"/> + </test> + </tests> + <help> + +.. class:: warningmark + +**Note**. Database searches may take substantial amount of time. For large input datasets it is advisable to allow overnight processing. + +----- + +**What it does** + +Search a *translated nucleotide database* using a *protein query*, +using the NCBI BLAST+ tblastx command line tool. + +----- + +**Output format** + +The default output of this tool is tabular, containing 12 columns: + +1. Id of your sequence +2. GI of the database hit +3. % identity +4. Alignment length +5. # mismatches +6. # gaps +7. Start position in your sequence +8. End position in your sequence +9. Start position in database hit +10. End position in database hit +11. E-value +12. Bit score + +------- + +**References** + +Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402. + + </help> +</tool> --- /dev/null +++ b/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @@ -0,0 +1,99 @@ +<tool id="ncbi_blastx_wrapper" name="NCBI BLAST+ blastx" version="0.0.1"> + <description>Search protein database with translated nucleotide query sequence(s)</description> + <command> + blastx + -query "$query" + -db "$database" + -evalue $evalue_cutoff + -seg $adv_opts.filter_query + -out $output1 + -outfmt $out_format + -num_threads 8 + </command> + <inputs> + <param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> + <param name="database" type="select" display="radio" label="Protein BLAST database"> + <options from_file="blastdb_p.loc"> + <column name="name" index="0"/> + <column name="value" index="1"/> + </options> + </param> + <param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" /> + <param name="out_format" type="select" label="Output format"> + <option value="6">Tabular</option> + <option value="5">BLAST XML</option> + <option value="0">Pairwise text</option> +  + </param> + <conditional name="adv_opts"> + <param name="adv_opts_selector" type="select" label="Advanced Options"> + <option value="basic" selected="True">Hide Advanced Options</option> + <option value="advanced">Show Advanced Options</option> + </param> + <when value="basic"> + <param name="filter_query" type="hidden" value="yes" /> + </when> + <when value="advanced"> + <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="yes" falsevalue="no" checked="true" /> + </when> + </conditional> + </inputs> + <outputs> +  + <data name="output1" format="tabular" label="blastx on ${database.value_label}"> + <change_format> + <when input="out_format" value="0" format="txt"/> + </change_format> + <change_format> + <when input="out_format" value="5" format="blastxml"/> + </change_format> + </data> + </outputs> + <requirements> + <requirement type="binary">blastn</requirement> + </requirements> + <tests> + </tests> + <help> + +.. class:: warningmark + +**Note**. Database searches may take substantial amount of time. +For large input datasets it is advisable to allow overnight processing. + +----- + +**What it does** + +Search a *protein database* using a *translated nucleotide query*, +using the NCBI BLAST+ blastx command line tool. + +----- + +**Output format** + +The default output of this tool is tabular, containing 12 columns: + +1. Id of your sequence +2. GI of the database hit +3. % identity +4. Alignment length +5. # mismatches +6. # gaps +7. Start position in your sequence +8. End position in your sequence +9. Start position in database hit +10. End position in database hit +11. E-value +12. Bit score + +------- + +**References** + +Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402. + + </help> +</tool> --- a/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml @@ -12,7 +12,7 @@ -num_threads 8 </command><inputs> - <param name="query" type="data" format="fasta" label="Query sequence(s)"/> + <param name="query" type="data" format="fasta" label="Protein query sequence(s)"/><param name="database" type="select" display="radio" label="Protein BLAST database"><options from_file="blastdb_p.loc"><column name="name" index="0"/> @@ -23,13 +23,6 @@ <option value="blastp">blastp</option><option value="blastp-short">blastp-short</option></param> - <param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" /><param name="out_format" type="select" label="Output format"><option value="6">Tabular</option> @@ -72,19 +65,21 @@ .. class:: warningmark -**Note**. Database searches may take substantial amount of time. For large input datasets it is advisable to allow overnight processing. +**Note**. Database searches may take substantial amount of time. +For large input datasets it is advisable to allow overnight processing. ----- **What it does** -This runs the command line NCBI BLAST+ blastp tool. +Search a *protein database* using a *protein query*, +using the NCBI BLAST+ blastp command line tool. ----- **Output format** -The default Output of this tool is tabular, containing 12 columns: +The default output of this tool is tabular, containing 12 columns: 1. Id of your sequence 2. GI of the database hit

1 0

galaxy-dist commit 6c1d520f25d4: Don't default to setting seg/dust explicitly (allow BLAST+ to use its own defaults)
by commits-noreply＠bitbucket.org 20 Nov '10

20 Nov '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User peterjc <p.j.a.cock(a)googlemail.com> # Date 1285930037 -3600 # Node ID 6c1d520f25d44f80de926285cbd927bc35f69a6a # Parent aa7f4bdc2eab6be57fc1311137ce423eb39750cd Don't default to setting seg/dust explicitly (allow BLAST+ to use its own defaults) --- a/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml @@ -6,7 +6,7 @@ -db "$database" -task $blast_type -evalue $evalue_cutoff - -dust $adv_opts.filter_query + $adv_opts.filter_query -out $output1 -outfmt $out_format -num_threads 8 @@ -41,10 +41,11 @@ <option value="advanced">Show Advanced Options</option></param><when value="basic"> - <param name="filter_query" type="hidden" value="yes" /> + <param name="filter_query" type="hidden" value="" /></when><when value="advanced"> - <param name="filter_query" type="boolean" label="Filter out low complexity regions (with DUST)" truevalue="yes" falsevalue="no" checked="true" /> +  + <param name="filter_query" type="boolean" label="Filter out low complexity regions (with DUST)" truevalue="-dust yes" falsevalue="-dust no" checked="true" /></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml @@ -6,7 +6,7 @@ -db "$database" -task $blast_type -evalue $evalue_cutoff - -seg $adv_opts.filter_query + $adv_opts.filter_query -out $output1 -outfmt $out_format -num_threads 8 @@ -38,10 +38,11 @@ <option value="advanced">Show Advanced Options</option></param><when value="basic"> - <param name="filter_query" type="hidden" value="yes" /> + <param name="filter_query" type="hidden" value="" /></when><when value="advanced"> - <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="yes" falsevalue="no" checked="true" /> +  + <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" /></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml @@ -5,7 +5,7 @@ -query "$query" -db "$database" -evalue $evalue_cutoff - -seg $adv_opts.filter_query + $adv_opts.filter_query -out $output1 -outfmt $out_format -num_threads 8 @@ -33,10 +33,11 @@ <option value="advanced">Show Advanced Options</option></param><when value="basic"> - <param name="filter_query" type="hidden" value="yes" /> + <param name="filter_query" type="hidden" value="" /></when><when value="advanced"> - <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="yes" falsevalue="no" checked="true" /> +  + <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" /></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @@ -5,7 +5,7 @@ -query "$query" -db "$database" -evalue $evalue_cutoff - -seg $adv_opts.filter_query + $adv_opts.filter_query -out $output1 -outfmt $out_format -num_threads 8 @@ -33,10 +33,11 @@ <option value="advanced">Show Advanced Options</option></param><when value="basic"> - <param name="filter_query" type="hidden" value="yes" /> + <param name="filter_query" type="hidden" value="" /></when><when value="advanced"> - <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="yes" falsevalue="no" checked="true" /> +  + <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" /></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml @@ -5,7 +5,7 @@ -query "$query" -db "$database" -evalue $evalue_cutoff - -seg $adv_opts.filter_query + $adv_opts.filter_query -out $output1 -outfmt $out_format -num_threads 8 @@ -33,10 +33,11 @@ <option value="advanced">Show Advanced Options</option></param><when value="basic"> - <param name="filter_query" type="hidden" value="yes" /> + <param name="filter_query" type="hidden" value="" /></when><when value="advanced"> - <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="yes" falsevalue="no" checked="true" /> +  + <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" /></when></conditional></inputs>

1 0

galaxy-dist commit 5176fa11ef2f: Add -strand as adv opt to blastn, blastx and tblastx wrappers
by commits-noreply＠bitbucket.org 20 Nov '10

20 Nov '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User peterjc <p.j.a.cock(a)googlemail.com> # Date 1285931141 -3600 # Node ID 5176fa11ef2f45df4a7bb0b82f2ca0871aaf2465 # Parent 6c1d520f25d44f80de926285cbd927bc35f69a6a Add -strand as adv opt to blastn, blastx and tblastx wrappers --- a/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml @@ -7,6 +7,7 @@ -task $blast_type -evalue $evalue_cutoff $adv_opts.filter_query + $adv_opts.strand -out $output1 -outfmt $out_format -num_threads 8 @@ -42,10 +43,16 @@ </param><when value="basic"><param name="filter_query" type="hidden" value="" /> + <param name="strand" type="hidden" value="" /></when><when value="advanced"><param name="filter_query" type="boolean" label="Filter out low complexity regions (with DUST)" truevalue="-dust yes" falsevalue="-dust no" checked="true" /> + <param name="strand" type="select" label="Query strand(s) to search against database/subject"> + <option value="-strand both">Both</option> + <option value="-strand plus">Plus (forward)</option> + <option value="-strand minus">Minus (reverse complement)</option> + </param></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @@ -6,6 +6,7 @@ -db "$database" -evalue $evalue_cutoff $adv_opts.filter_query + $adv_opts.strand -out $output1 -outfmt $out_format -num_threads 8 @@ -34,10 +35,16 @@ </param><when value="basic"><param name="filter_query" type="hidden" value="" /> + <param name="strand" type="hidden" value="" /></when><when value="advanced"><param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" /> + <param name="strand" type="select" label="Query strand(s) to search against database/subject"> + <option value="-strand both">Both</option> + <option value="-strand plus">Plus (forward)</option> + <option value="-strand minus">Minus (reverse complement)</option> + </param></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml @@ -6,6 +6,7 @@ -db "$database" -evalue $evalue_cutoff $adv_opts.filter_query + $adv_opts.strand -out $output1 -outfmt $out_format -num_threads 8 @@ -34,10 +35,16 @@ </param><when value="basic"><param name="filter_query" type="hidden" value="" /> + <param name="strand" type="hidden" value="" /></when><when value="advanced"><param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" /> + <param name="strand" type="select" label="Query strand(s) to search against database/subject"> + <option value="-strand both">Both</option> + <option value="-strand plus">Plus (forward)</option> + <option value="-strand minus">Minus (reverse complement)</option> + </param></when></conditional></inputs>

1 0

galaxy-dist commit 92bb0d0d7e90: Adding basic tblastn wrapper
by commits-noreply＠bitbucket.org 20 Nov '10

20 Nov '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User peterjc <p.j.a.cock(a)googlemail.com> # Date 1285685499 -3600 # Node ID 92bb0d0d7e9058bc4b6b43eaa015349241bc13e0 # Parent 34794995b12f700d50c12bb013431c882dca9c10 Adding basic tblastn wrapper --- a/tool_conf.xml.sample +++ b/tool_conf.xml.sample @@ -264,6 +264,7 @@ --><section name="NCBI BLAST+" id="ncbi_blast_plus_tools"><tool file="ncbi_blast_plus/ncbi_blastn_wrapper.xml" /> + <tool file="ncbi_blast_plus/ncbi_tblastn_wrapper.xml" /><tool file="ncbi_blast_plus/ncbi_blastp_wrapper.xml" /><tool file="ncbi_blast_plus/blast_filter_fasta.xml" /></section> --- /dev/null +++ b/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml @@ -0,0 +1,97 @@ +<tool id="ncbi_tblastn_wrapper" name="NCBI BLAST+ tblastn" version="0.0.1"> + <description>Search translated nucleotide database with protein query sequence(s)</description> + <command> + tblastn + -query "$query" + -db "$database" + -evalue $evalue_cutoff + -seg $adv_opts.filter_query + -out $output1 + -outfmt $out_format + -num_threads 8 + </command> + <inputs> + <param name="query" type="data" format="fasta" label="Query sequence(s)"/> + <param name="database" type="select" display="radio" label="Nucelotide BLAST database"> + <options from_file="blastdb.loc"> + <column name="name" index="0"/> + <column name="value" index="1"/> + </options> + </param> + <param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" /> + <param name="out_format" type="select" label="Output format"> + <option value="6">Tabular</option> + <option value="5">BLAST XML</option> + <option value="0">Pairwise text</option> +  + </param> + <conditional name="adv_opts"> + <param name="adv_opts_selector" type="select" label="Advanced Options"> + <option value="basic" selected="True">Hide Advanced Options</option> + <option value="advanced">Show Advanced Options</option> + </param> + <when value="basic"> + <param name="filter_query" type="hidden" value="yes" /> + </when> + <when value="advanced"> + <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="yes" falsevalue="no" checked="true" /> + </when> + </conditional> + </inputs> + <outputs> +  + <data name="output1" format="tabular" label="tblastn on ${database.value_label}"> + <change_format> + <when input="out_format" value="0" format="txt"/> + </change_format> + <change_format> + <when input="out_format" value="5" format="blastxml"/> + </change_format> + </data> + </outputs> + <requirements> + <requirement type="binary">blastn</requirement> + </requirements> + <tests> + </tests> + <help> + +.. class:: warningmark + +**Note**. Database searches may take substantial amount of time. For large input datasets it is advisable to allow overnight processing. + +----- + +**What it does** + +This tool runs NCBI BLAST+ tblastn tool. + +----- + +**Output format** + +The default Output of this tool is tabular, containing 12 columns: + +1. Id of your sequence +2. GI of the database hit +3. % identity +4. Alignment length +5. # mismatches +6. # gaps +7. Start position in your sequence +8. End position in your sequence +9. Start position in database hit +10. End position in database hit +11. E-value +12. Bit score + +------- + +**References** + +Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402. + + </help> +</tool>

1 0

galaxy-dist commit 5244ad54beba: Make descriptions more concise (don't need to repeat infor from name)
by commits-noreply＠bitbucket.org 20 Nov '10

20 Nov '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User peterjc <p.j.a.cock(a)googlemail.com> # Date 1285670784 -3600 # Node ID 5244ad54bebadf57e8bede36643afa49c58ac579 # Parent 6dd6224f571deb34c01c7fd0c3c4daccf948eda1 Make descriptions more concise (don't need to repeat infor from name) --- a/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml @@ -1,5 +1,5 @@ <tool id="ncbi_blastn_wrapper" name="NCBI BLAST+ blastn" version="0.0.1"> - <description>Use NCBI BLAST+ tool to search a nucleotide database with nucleotide query sequence(s)</description> + <description>Search nucleotide database with nucleotide query sequence(s)</description><command> blastn -query "$query" --- a/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml @@ -1,5 +1,5 @@ <tool id="ncbi_blastp_wrapper" name="NCBI BLAST+ blastp" version="0.0.1"> - <description>Use NCBI BLAST+ tool to search a protein database with protein query sequence(s)</description> + <description>Search protein database with protein query sequence(s)</description><command> blastp -query "$query"

1 0

galaxy-dist commit 36086d5bd8fa: Support -db (database) or -subject (FASTA file)
by commits-noreply＠bitbucket.org 20 Nov '10

20 Nov '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User peterjc <p.j.a.cock(a)googlemail.com> # Date 1285940235 -3600 # Node ID 36086d5bd8fa174ce88443eeeefec52b8fada5bd # Parent 5176fa11ef2f45df4a7bb0b82f2ca0871aaf2465 Support -db (database) or -subject (FASTA file) --- a/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml @@ -3,7 +3,11 @@ <command> blastn -query "$query" - -db "$database" +#if $db_opts.db_opts_selector == "db": + -db "$db_opts.database" +#else: + -subject "$db_opts.subject" +#end if -task $blast_type -evalue $evalue_cutoff $adv_opts.filter_query @@ -14,12 +18,25 @@ </command><inputs><param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> - <param name="database" type="select" display="radio" label="Nucleotide BLAST database"> - <options from_file="blastdb.loc"> - <column name="name" index="0"/> - <column name="value" index="1"/> - </options> - </param> + <conditional name="db_opts"> + <param name="db_opts_selector" type="select" label="Subject database/sequences"> + <option value="db" selected="True">BLAST Database</option> + <option value="file">FASTA file</option> + </param> + <when value="db"> + <param name="database" type="select" display="radio" label="Nucleotide BLAST database"> + <options from_file="blastdb.loc"> + <column name="name" index="0"/> + <column name="value" index="1"/> + </options> + </param> + <param name="subject" type="hidden" value="" /> + </when> + <when value="file"> + <param name="database" type="hidden" value="" /> + <param name="subject" type="data" format="fasta" label="Nucleotide FASTA file to use as database"/> + </when> + </conditional><param name="blast_type" type="select" display="radio" label="Type of BLAST"><option value="megablast">megablast</option><option value="blastn">blastn</option> @@ -57,8 +74,7 @@ </conditional></inputs><outputs> -  - <data name="output1" format="tabular" label="${blast_type.value_label} on ${database.value_label}"> + <data name="output1" format="tabular" label="${blast_type.value_label} on ${db_opts.db_opts_selector}"><change_format><when input="out_format" value="0" format="txt"/></change_format> --- a/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml @@ -3,7 +3,11 @@ <command> blastp -query "$query" - -db "$database" +#if $db_opts.db_opts_selector == "db": + -db "$db_opts.database" +#else: + -subject "$db_opts.subject" +#end if -task $blast_type -evalue $evalue_cutoff $adv_opts.filter_query @@ -13,12 +17,25 @@ </command><inputs><param name="query" type="data" format="fasta" label="Protein query sequence(s)"/> - <param name="database" type="select" display="radio" label="Protein BLAST database"> - <options from_file="blastdb_p.loc"> - <column name="name" index="0"/> - <column name="value" index="1"/> - </options> - </param> + <conditional name="db_opts"> + <param name="db_opts_selector" type="select" label="Subject database/sequences"> + <option value="db" selected="True">BLAST Database</option> + <option value="file">FASTA file</option> + </param> + <when value="db"> + <param name="database" type="select" display="radio" label="Protein BLAST database"> + <options from_file="blastdb_p.loc"> + <column name="name" index="0"/> + <column name="value" index="1"/> + </options> + </param> + <param name="subject" type="hidden" value="" /> + </when> + <when value="file"> + <param name="database" type="hidden" value="" /> + <param name="subject" type="data" format="fasta" label="Protein FASTA file to use as database"/> + </when> + </conditional><param name="blast_type" type="select" display="radio" label="Type of BLAST"><option value="blastp">blastp</option><option value="blastp-short">blastp-short</option> @@ -47,8 +64,7 @@ </conditional></inputs><outputs> -  - <data name="output1" format="tabular" label="${blast_type.value_label} on ${database.value_label}"> + <data name="output1" format="tabular" label="${blast_type.value_label} on ${db_opts.db_opts_selector}"><change_format><when input="out_format" value="0" format="txt"/></change_format> --- a/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml @@ -3,7 +3,11 @@ <command> tblastx -query "$query" - -db "$database" +#if $db_opts.db_opts_selector == "db": + -db "$db_opts.database" +#else: + -subject "$db_opts.subject" +#end if -evalue $evalue_cutoff $adv_opts.filter_query $adv_opts.strand @@ -13,12 +17,25 @@ </command><inputs><param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> - <param name="database" type="select" display="radio" label="Nucelotide BLAST database"> - <options from_file="blastdb.loc"> - <column name="name" index="0"/> - <column name="value" index="1"/> - </options> - </param> + <conditional name="db_opts"> + <param name="db_opts_selector" type="select" label="Subject database/sequences"> + <option value="db" selected="True">BLAST Database</option> + <option value="file">FASTA file</option> + </param> + <when value="db"> + <param name="database" type="select" display="radio" label="Nucleotide BLAST database"> + <options from_file="blastdb.loc"> + <column name="name" index="0"/> + <column name="value" index="1"/> + </options> + </param> + <param name="subject" type="hidden" value="" /> + </when> + <when value="file"> + <param name="database" type="hidden" value="" /> + <param name="subject" type="data" format="fasta" label="Nucleotide FASTA file to use as database"/> + </when> + </conditional><param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" /><param name="out_format" type="select" label="Output format"><option value="6">Tabular</option> @@ -49,8 +66,7 @@ </conditional></inputs><outputs> -  - <data name="output1" format="tabular" label="tblastx on ${database.value_label}"> + <data name="output1" format="tabular" label="tblastx on ${db_opts.db_opts_selector}"><change_format><when input="out_format" value="0" format="txt"/></change_format> --- a/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @@ -3,7 +3,11 @@ <command> blastx -query "$query" - -db "$database" +#if $db_opts.db_opts_selector == "db": + -db "$db_opts.database" +#else: + -subject "$db_opts.subject" +#end if -evalue $evalue_cutoff $adv_opts.filter_query $adv_opts.strand @@ -13,12 +17,25 @@ </command><inputs><param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> - <param name="database" type="select" display="radio" label="Protein BLAST database"> - <options from_file="blastdb_p.loc"> - <column name="name" index="0"/> - <column name="value" index="1"/> - </options> - </param> + <conditional name="db_opts"> + <param name="db_opts_selector" type="select" label="Subject database/sequences"> + <option value="db" selected="True">BLAST Database</option> + <option value="file">FASTA file</option> + </param> + <when value="db"> + <param name="database" type="select" display="radio" label="Protein BLAST database"> + <options from_file="blastdb_p.loc"> + <column name="name" index="0"/> + <column name="value" index="1"/> + </options> + </param> + <param name="subject" type="hidden" value="" /> + </when> + <when value="file"> + <param name="database" type="hidden" value="" /> + <param name="subject" type="data" format="fasta" label="Protein subject sequence(s)"/> + </when> + </conditional><param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" /><param name="out_format" type="select" label="Output format"><option value="6">Tabular</option> @@ -49,8 +66,7 @@ </conditional></inputs><outputs> -  - <data name="output1" format="tabular" label="blastx on ${database.value_label}"> + <data name="output1" format="tabular" label="blastx on ${db_opts.db_opts_selector}"><change_format><when input="out_format" value="0" format="txt"/></change_format> --- a/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml @@ -3,7 +3,11 @@ <command> tblastn -query "$query" - -db "$database" +#if $db_opts.db_opts_selector == "db": + -db "$db_opts.database" +#else: + -subject "$db_opts.subject" +#end if -evalue $evalue_cutoff $adv_opts.filter_query -out $output1 @@ -12,12 +16,25 @@ </command><inputs><param name="query" type="data" format="fasta" label="Protein query sequence(s)"/> - <param name="database" type="select" display="radio" label="Nucelotide BLAST database"> - <options from_file="blastdb.loc"> - <column name="name" index="0"/> - <column name="value" index="1"/> - </options> - </param> + <conditional name="db_opts"> + <param name="db_opts_selector" type="select" label="Subject database/sequences"> + <option value="db" selected="True">BLAST Database</option> + <option value="file">FASTA file</option> + </param> + <when value="db"> + <param name="database" type="select" display="radio" label="Nucleotide BLAST database"> + <options from_file="blastdb.loc"> + <column name="name" index="0"/> + <column name="value" index="1"/> + </options> + </param> + <param name="subject" type="hidden" value="" /> + </when> + <when value="file"> + <param name="database" type="hidden" value="" /> + <param name="subject" type="data" format="fasta" label="Nucleotide FASTA file to use as database"/> + </when> + </conditional><param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" /><param name="out_format" type="select" label="Output format"><option value="6">Tabular</option> @@ -43,7 +60,7 @@ </inputs><outputs> - <data name="output1" format="tabular" label="tblastn on ${database.value_label}"> + <data name="output1" format="tabular" label="tblastn on ${db_opts.db_opts_selector}"><change_format><when input="out_format" value="0" format="txt"/></change_format>

1 0

galaxy-dist commit 5498ff5b31ac: Allow filter to pick ID column
by commits-noreply＠bitbucket.org 20 Nov '10

20 Nov '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User peterjc <p.j.a.cock(a)googlemail.com> # Date 1285873215 -3600 # Node ID 5498ff5b31ac871c7d22df60146fd96c61b74aab # Parent ad83deba645811d8b9509a6e3c58e986ffa89e3b Allow filter to pick ID column --- a/tools/ncbi_blast_plus/blast_filter_fasta.py +++ b/tools/ncbi_blast_plus/blast_filter_fasta.py @@ -1,22 +1,26 @@ #!/usr/bin/env python -"""Filter a FASTA file using tabular BLAST output. +"""Filter a FASTA file using tabular output, e.g. from BLAST. -Takes four command line options, tabular BLAST filename, input FASTA filename, -and two output FASTA filenames (for records with and without any BLAST hits). +Takes five command line options, tabular BLAST filename, ID column number +(using one based counting), input FASTA filename, and two output FASTA +filenames (for records with and without any BLAST hits). + +In the default NCBI BLAST+ tabular output, the query sequence ID is in column +one, and the ID of the match from the database is in column two. """ -#TODO - Option to define which column to use for ID? - import sys from galaxy_utils.sequence.fasta import fastaReader, fastaWriter #Parse Command Line -blast_file, in_file, out_positive_file, out_negative_file = sys.argv[1:] +blast_file, blast_col, in_file, out_positive_file, out_negative_file = sys.argv[1:] +blast_col = int(blast_col)-1 +assert blast_col >= 0 #Read tabular BLAST file and record all queries with hit(s) ids = set() blast_handle = open(blast_file, "rU") for line in blast_handle: - ids.add(line.split("\t")[0]) + ids.add(line.split("\t")[blast_col]) blast_handle.close() #Write filtered FASTA file based on IDs from BLAST file --- a/tools/ncbi_blast_plus/blast_filter_fasta.xml +++ b/tools/ncbi_blast_plus/blast_filter_fasta.xml @@ -1,10 +1,13 @@ <tool id="blast_filter_fasta" name="BLAST filter FASTA file" version="0.0.1"><description>Divide a FASTA file based on BLAST hits</description><command interpreter="python"> - blast_filter_fasta.py $blast_file $in_file $out_positive_file $out_negative_file + blast_filter_fasta.py $blast_file $blast_col $in_file $out_positive_file $out_negative_file </command><inputs><param name="blast_file" type="data" format="tabular" label="Tabular BLAST output"/> + <param name="blast_col" type="integer" value="1" label="Column containing FASTA identifiers"> + <validator type="in_range" min="1" /> + </param><param name="in_file" type="data" format="fasta" label="BLAST query FASTA file"/></inputs><outputs> @@ -19,8 +22,12 @@ **What it does** -Takes a multi-sequence FASTA and the tabular output of running BLAST on it, and -divides the FASTA file in two: those sequence with a BLAST hit, and those without. +Typical use would be to take a multi-sequence FASTA and the tabular output of +running BLAST on it, and divides the FASTA file in two: those sequence with a +BLAST hit, and those without. + +In the default NCBI BLAST+ tabular output, the query sequence ID is in column +one, and the ID of the match from the database is in column two. </help></tool>

1 0