- galaxy-commits - lists.galaxyproject.org

galaxy-dist commit 9f172e4713ed: Support query anchored and HTML 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 1286796719 -3600 # Node ID 9f172e4713edbf4d6a22f10ad01867710cce6b00 # Parent d8da4f7bb0f5e1d43b371e4e52fb688ad816e5bf Support query anchored and HTML output --- a/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml @@ -15,7 +15,7 @@ blastn $adv_opts.filter_query $adv_opts.strand -out $output1 --outfmt $out_format +$out_format -num_threads 8 ## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string ## Note -max_target_seqs overrides -num_descriptions and -num_alignments @@ -60,11 +60,16 @@ blastn </param><param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" /><param name="out_format" type="select" label="Output format"> - <option value="6">Tabular</option> - <option value="5">BLAST XML</option> - <option value="0">Pairwise text</option> + <option value="-outfmt 6" selected="True">Tabular</option> + <option value="-outfmt 5">BLAST XML</option> + <option value="-outfmt 0">Pairwise text</option> + <option value="-outfmt 0 -html">Pairwise HTML</option> + <option value="-outfmt 2">Query-anchored text</option> + <option value="-outfmt 2 -html">Query-anchored HTML</option> + <option value="-outfmt 4">Flat query-anchored text</option> + <option value="-outfmt 4 -html">Flat query-anchored HTML</option></param><conditional name="adv_opts"> @@ -102,10 +107,13 @@ blastn <outputs><data name="output1" format="tabular" label="${blast_type.value_label} on ${db_opts.db_opts_selector}"><change_format> - <when input="out_format" value="0" format="txt"/> - </change_format> - <change_format> - <when input="out_format" value="5" format="blastxml"/> + <when input="out_format" value="-outfmt 0" format="txt"/> + <when input="out_format" value="-outfmt 0 -html" format="html"/> + <when input="out_format" value="-outfmt 2" format="txt"/> + <when input="out_format" value="-outfmt 2 -html" format="html"/> + <when input="out_format" value="-outfmt 4" format="txt"/> + <when input="out_format" value="-outfmt 4 -html" format="html"/> + <when input="out_format" value="-outfmt 5" format="blastxml"/></change_format></data></outputs> @@ -147,7 +155,7 @@ Algorithms include blastn, megablast, an **Output format** -The default output of this tool is tabular, containing 12 columns: +Because Galaxy focuses on processing tabular data, the default output of this tool is tabular. This contains 12 columns: 1. Id of your sequence 2. GI of the database hit @@ -162,6 +170,14 @@ 10. End position in database hit 11. E-value 12. Bit score +The second option is BLAST XML output, which is designed to be parsed by another program, and is understood by other Galaxy tools. + +You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program). +The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website. +The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query. +The two query anchored outputs show a multiple sequence alignment between the query and all the matches, +and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences). + ------- **References** --- a/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml @@ -15,7 +15,7 @@ blastp $adv_opts.filter_query $adv_opts.matrix -out $output1 --outfmt $out_format +$out_format -num_threads 8 ## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string ## Note -max_target_seqs overrides -num_descriptions and -num_alignments @@ -55,11 +55,16 @@ blastp </param><param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" /><param name="out_format" type="select" label="Output format"> - <option value="6">Tabular</option> - <option value="5">BLAST XML</option> - <option value="0">Pairwise text</option> + <option value="-outfmt 6" selected="True">Tabular</option> + <option value="-outfmt 5">BLAST XML</option> + <option value="-outfmt 0">Pairwise text</option> + <option value="-outfmt 0 -html">Pairwise HTML</option> + <option value="-outfmt 2">Query-anchored text</option> + <option value="-outfmt 2 -html">Query-anchored HTML</option> + <option value="-outfmt 4">Flat query-anchored text</option> + <option value="-outfmt 4 -html">Flat query-anchored HTML</option></param><conditional name="adv_opts"> @@ -110,10 +115,13 @@ blastp <outputs><data name="output1" format="tabular" label="${blast_type.value_label} on ${db_opts.db_opts_selector}"><change_format> - <when input="out_format" value="0" format="txt"/> - </change_format> - <change_format> - <when input="out_format" value="5" format="blastxml"/> + <when input="out_format" value="-outfmt 0" format="txt"/> + <when input="out_format" value="-outfmt 0 -html" format="html"/> + <when input="out_format" value="-outfmt 2" format="txt"/> + <when input="out_format" value="-outfmt 2 -html" format="html"/> + <when input="out_format" value="-outfmt 4" format="txt"/> + <when input="out_format" value="-outfmt 4 -html" format="html"/> + <when input="out_format" value="-outfmt 5" format="blastxml"/></change_format></data></outputs> @@ -140,7 +148,7 @@ using the NCBI BLAST+ blastp command lin **Output format** -The default output of this tool is tabular, containing 12 columns: +Because Galaxy focuses on processing tabular data, the default output of this tool is tabular. This contains 12 columns: 1. Id of your sequence 2. GI of the database hit @@ -155,6 +163,14 @@ 10. End position in database hit 11. E-value 12. Bit score +The second option is BLAST XML output, which is designed to be parsed by another program, and is understood by other Galaxy tools. + +You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program). +The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website. +The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query. +The two query anchored outputs show a multiple sequence alignment between the query and all the matches, +and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences). + ------- **References** --- a/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml @@ -15,7 +15,7 @@ tblastx $adv_opts.strand $adv_opts.matrix -out $output1 --outfmt $out_format +$out_format -num_threads 8 ## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string ## Note -max_target_seqs overrides -num_descriptions and -num_alignments @@ -49,11 +49,16 @@ tblastx </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> - <option value="5">BLAST XML</option> - <option value="0">Pairwise text</option> + <option value="-outfmt 6" selected="True">Tabular</option> + <option value="-outfmt 5">BLAST XML</option> + <option value="-outfmt 0">Pairwise text</option> + <option value="-outfmt 0 -html">Pairwise HTML</option> + <option value="-outfmt 2">Query-anchored text</option> + <option value="-outfmt 2 -html">Query-anchored HTML</option> + <option value="-outfmt 4">Flat query-anchored text</option> + <option value="-outfmt 4 -html">Flat query-anchored HTML</option></param><conditional name="adv_opts"> @@ -100,10 +105,13 @@ tblastx <outputs><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> - <change_format> - <when input="out_format" value="5" format="blastxml"/> + <when input="out_format" value="-outfmt 0" format="txt"/> + <when input="out_format" value="-outfmt 0 -html" format="html"/> + <when input="out_format" value="-outfmt 2" format="txt"/> + <when input="out_format" value="-outfmt 2 -html" format="html"/> + <when input="out_format" value="-outfmt 4" format="txt"/> + <when input="out_format" value="-outfmt 4 -html" format="html"/> + <when input="out_format" value="-outfmt 5" format="blastxml"/></change_format></data></outputs> @@ -122,7 +130,7 @@ tblastx --><param name="evalue_cutoff" value="10.0" /><param name="filter_query" value="yes" /> - <param name="out_format" value="6" /> + <param name="out_format" value="-outfmt 6" /><output name="output1" file="megablast_wrapper_test1.out"/></test></tests> @@ -143,7 +151,7 @@ using the NCBI BLAST+ tblastx command li **Output format** -The default output of this tool is tabular, containing 12 columns: +Because Galaxy focuses on processing tabular data, the default output of this tool is tabular. This contains 12 columns: 1. Id of your sequence 2. GI of the database hit @@ -158,6 +166,14 @@ 10. End position in database hit 11. E-value 12. Bit score +The second option is BLAST XML output, which is designed to be parsed by another program, and is understood by other Galaxy tools. + +You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program). +The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website. +The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query. +The two query anchored outputs show a multiple sequence alignment between the query and all the matches, +and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences). + ------- **References** --- a/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @@ -15,7 +15,7 @@ blastx $adv_opts.strand $adv_opts.matrix -out $output1 --outfmt $out_format +$out_format -num_threads 8 ## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string ## Note -max_target_seqs overrides -num_descriptions and -num_alignments @@ -50,11 +50,16 @@ blastx </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> - <option value="5">BLAST XML</option> - <option value="0">Pairwise text</option> + <option value="-outfmt 6" selected="True">Tabular</option> + <option value="-outfmt 5">BLAST XML</option> + <option value="-outfmt 0">Pairwise text</option> + <option value="-outfmt 0 -html">Pairwise HTML</option> + <option value="-outfmt 2">Query-anchored text</option> + <option value="-outfmt 2 -html">Query-anchored HTML</option> + <option value="-outfmt 4">Flat query-anchored text</option> + <option value="-outfmt 4 -html">Flat query-anchored HTML</option></param><conditional name="adv_opts"> @@ -103,10 +108,13 @@ blastx <outputs><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> - <change_format> - <when input="out_format" value="5" format="blastxml"/> + <when input="out_format" value="-outfmt 0" format="txt"/> + <when input="out_format" value="-outfmt 0 -html" format="html"/> + <when input="out_format" value="-outfmt 2" format="txt"/> + <when input="out_format" value="-outfmt 2 -html" format="html"/> + <when input="out_format" value="-outfmt 4" format="txt"/> + <when input="out_format" value="-outfmt 4 -html" format="html"/> + <when input="out_format" value="-outfmt 5" format="blastxml"/></change_format></data></outputs> @@ -133,7 +141,7 @@ using the NCBI BLAST+ blastx command lin **Output format** -The default output of this tool is tabular, containing 12 columns: +Because Galaxy focuses on processing tabular data, the default output of this tool is tabular. This contains 12 columns: 1. Id of your sequence 2. GI of the database hit @@ -148,6 +156,14 @@ 10. End position in database hit 11. E-value 12. Bit score +The second option is BLAST XML output, which is designed to be parsed by another program, and is understood by other Galaxy tools. + +You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program). +The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website. +The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query. +The two query anchored outputs show a multiple sequence alignment between the query and all the matches, +and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences). + ------- **References** --- a/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml @@ -14,7 +14,7 @@ tblastn $adv_opts.filter_query $adv_opts.matrix -out $output1 --outfmt $out_format +$out_format -num_threads 8 ## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string ## Note -max_target_seqs overrides -num_descriptions and -num_alignments @@ -50,11 +50,16 @@ tblastn </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> - <option value="5">BLAST XML</option> - <option value="0">Pairwise text</option> + <option value="-outfmt 6" selected="True">Tabular</option> + <option value="-outfmt 5">BLAST XML</option> + <option value="-outfmt 0">Pairwise text</option> + <option value="-outfmt 0 -html">Pairwise HTML</option> + <option value="-outfmt 2">Query-anchored text</option> + <option value="-outfmt 2 -html">Query-anchored HTML</option> + <option value="-outfmt 4">Flat query-anchored text</option> + <option value="-outfmt 4 -html">Flat query-anchored HTML</option></param><conditional name="adv_opts"> @@ -105,10 +110,13 @@ tblastn <outputs><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> - <change_format> - <when input="out_format" value="5" format="blastxml"/> + <when input="out_format" value="-outfmt 0" format="txt"/> + <when input="out_format" value="-outfmt 0 -html" format="html"/> + <when input="out_format" value="-outfmt 2" format="txt"/> + <when input="out_format" value="-outfmt 2 -html" format="html"/> + <when input="out_format" value="-outfmt 4" format="txt"/> + <when input="out_format" value="-outfmt 4 -html" format="html"/> + <when input="out_format" value="-outfmt 5" format="blastxml"/></change_format></data></outputs> @@ -135,7 +143,7 @@ using the NCBI BLAST+ tblastn command li **Output format** -The default output of this tool is tabular, containing 12 columns: +Because Galaxy focuses on processing tabular data, the default output of this tool is tabular. This contains 12 columns: 1. Id of your sequence 2. GI of the database hit @@ -150,6 +158,14 @@ 10. End position in database hit 11. E-value 12. Bit score +The second option is BLAST XML output, which is designed to be parsed by another program, and is understood by other Galaxy tools. + +You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program). +The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website. +The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query. +The two query anchored outputs show a multiple sequence alignment between the query and all the matches, +and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences). + ------- **References**

1 0

galaxy-dist commit 9bf65ebafa8f: Reduce whitespace in <command> tag (there are OS limits on command line length)
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 1286366018 -3600 # Node ID 9bf65ebafa8fc89115a5b42ebb9865ed99c1cf84 # Parent 6273161e76c33f807145d9b12eafa0a6e414bbf1 Reduce whitespace in <command> tag (there are OS limits on command line length) --- a/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml @@ -1,20 +1,21 @@ <tool id="ncbi_blastn_wrapper" name="NCBI BLAST+ blastn" version="0.0.1"><description>Search nucleotide database with nucleotide query sequence(s)</description><command> - blastn - -query "$query" +## The command is a Cheetah template which allows some Python based syntax. +## Lines starting hash hash are comments. Galaxy will turn newlines into spaces +blastn -query "$query" #if $db_opts.db_opts_selector == "db": - -db "$db_opts.database" + -db "$db_opts.database" #else: - -subject "$db_opts.subject" + -subject "$db_opts.subject" #end if - -task $blast_type - -evalue $evalue_cutoff - $adv_opts.filter_query - $adv_opts.strand - -out $output1 - -outfmt $out_format - -num_threads 8 +-task $blast_type +-evalue $evalue_cutoff +$adv_opts.filter_query +$adv_opts.strand +-out $output1 +-outfmt $out_format +-num_threads 8 </command><inputs><param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> --- a/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml @@ -1,20 +1,22 @@ <tool id="ncbi_blastp_wrapper" name="NCBI BLAST+ blastp" version="0.0.1"><description>Search protein database with protein query sequence(s)</description><command> - blastp - -query "$query" +## The command is a Cheetah template which allows some Python based syntax. +## Lines starting hash hash are comments. Galaxy will turn newlines into spaces +blastp +-query "$query" #if $db_opts.db_opts_selector == "db": - -db "$db_opts.database" + -db "$db_opts.database" #else: - -subject "$db_opts.subject" + -subject "$db_opts.subject" #end if - -task $blast_type - -evalue $evalue_cutoff - $adv_opts.filter_query - $adv_opts.matrix - -out $output1 - -outfmt $out_format - -num_threads 8 +-task $blast_type +-evalue $evalue_cutoff +$adv_opts.filter_query +$adv_opts.matrix +-out $output1 +-outfmt $out_format +-num_threads 8 </command><inputs><param name="query" type="data" format="fasta" label="Protein query sequence(s)"/> --- a/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml @@ -1,20 +1,22 @@ <tool id="ncbi_tblastx_wrapper" name="NCBI BLAST+ tblastx" version="0.0.1"><description>Search translated nucleotide database with translated nucleotide query sequence(s)</description><command> - tblastx - -query "$query" +## The command is a Cheetah template which allows some Python based syntax. +## Lines starting hash hash are comments. Galaxy will turn newlines into spaces +tblastx +-query "$query" #if $db_opts.db_opts_selector == "db": - -db "$db_opts.database" + -db "$db_opts.database" #else: - -subject "$db_opts.subject" + -subject "$db_opts.subject" #end if - -evalue $evalue_cutoff - $adv_opts.filter_query - $adv_opts.strand - $adv_opts.matrix - -out $output1 - -outfmt $out_format - -num_threads 8 +-evalue $evalue_cutoff +$adv_opts.filter_query +$adv_opts.strand +$adv_opts.matrix +-out $output1 +-outfmt $out_format +-num_threads 8 </command><inputs><param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> --- a/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @@ -1,20 +1,22 @@ <tool id="ncbi_blastx_wrapper" name="NCBI BLAST+ blastx" version="0.0.1"><description>Search protein database with translated nucleotide query sequence(s)</description><command> - blastx - -query "$query" +## The command is a Cheetah template which allows some Python based syntax. +## Lines starting hash hash are comments. Galaxy will turn newlines into spaces +blastx +-query "$query" #if $db_opts.db_opts_selector == "db": - -db "$db_opts.database" + -db "$db_opts.database" #else: - -subject "$db_opts.subject" + -subject "$db_opts.subject" #end if - -evalue $evalue_cutoff - $adv_opts.filter_query - $adv_opts.strand - $adv_opts.matrix - -out $output1 - -outfmt $out_format - -num_threads 8 +-evalue $evalue_cutoff +$adv_opts.filter_query +$adv_opts.strand +$adv_opts.matrix +-out $output1 +-outfmt $out_format +-num_threads 8 </command><inputs><param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> --- a/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml @@ -1,19 +1,21 @@ <tool id="ncbi_tblastn_wrapper" name="NCBI BLAST+ tblastn" version="0.0.1"><description>Search translated nucleotide database with protein query sequence(s)</description><command> - tblastn - -query "$query" +## The command is a Cheetah template which allows some Python based syntax. +## Lines starting hash hash are comments. Galaxy will turn newlines into spaces +tblastn +-query "$query" #if $db_opts.db_opts_selector == "db": - -db "$db_opts.database" + -db "$db_opts.database" #else: - -subject "$db_opts.subject" + -subject "$db_opts.subject" #end if - -evalue $evalue_cutoff - $adv_opts.filter_query - $adv_opts.matrix - -out $output1 - -outfmt $out_format - -num_threads 8 +-evalue $evalue_cutoff +$adv_opts.filter_query +$adv_opts.matrix +-out $output1 +-outfmt $out_format +-num_threads 8 </command><inputs><param name="query" type="data" format="fasta" label="Protein query sequence(s)"/>

1 0

galaxy-dist commit 6273161e76c3: Make BLOSUM62 the default with sensible sorting (tip from Ross Lazarus on mailing list)
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 1286293953 -3600 # Node ID 6273161e76c33f807145d9b12eafa0a6e414bbf1 # Parent dd7a3707f323bbf38689a24bfcb0b337c3494569 Make BLOSUM62 the default with sensible sorting (tip from Ross Lazarus on mailing list) --- a/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml @@ -63,9 +63,9 @@ <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" /><param name="matrix" type="select" label="Scoring matrix"> - <option value="-matrix BLOSUM62">BLOSUM62 (default)</option><option value="-matrix BLOSUM90">BLOSUM90</option><option value="-matrix BLOSUM80">BLOSUM80</option> + <option value="-matrix BLOSUM62" selected="true">BLOSUM62 (default)</option><option value="-matrix BLOSUM50">BLOSUM50</option><option value="-matrix BLOSUM45">BLOSUM45</option><option value="-matrix PAM250">PAM250</option> --- a/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml @@ -65,9 +65,9 @@ <option value="-strand minus">Minus (reverse complement)</option></param><param name="matrix" type="select" label="Scoring matrix"> - <option value="-matrix BLOSUM62">BLOSUM62 (default)</option><option value="-matrix BLOSUM90">BLOSUM90</option><option value="-matrix BLOSUM80">BLOSUM80</option> + <option value="-matrix BLOSUM62" selected="true">BLOSUM62 (default)</option><option value="-matrix BLOSUM50">BLOSUM50</option><option value="-matrix BLOSUM45">BLOSUM45</option><option value="-matrix PAM250">PAM250</option> --- a/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @@ -65,15 +65,16 @@ <option value="-strand minus">Minus (reverse complement)</option></param><param name="matrix" type="select" label="Scoring matrix"> - <option value="-matrix BLOSUM62">BLOSUM62 (default)</option><option value="-matrix BLOSUM90">BLOSUM90</option><option value="-matrix BLOSUM80">BLOSUM80</option> + <option value="-matrix BLOSUM62" selected="true">BLOSUM62 (default)</option><option value="-matrix BLOSUM50">BLOSUM50</option><option value="-matrix BLOSUM45">BLOSUM45</option><option value="-matrix PAM250">PAM250</option><option value="-matrix PAM70">PAM70</option><option value="-matrix PAM30">PAM30</option></param> + </when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml @@ -58,9 +58,9 @@ <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" /><param name="matrix" type="select" label="Scoring matrix"> - <option value="-matrix BLOSUM62">BLOSUM62 (default)</option><option value="-matrix BLOSUM90">BLOSUM90</option><option value="-matrix BLOSUM80">BLOSUM80</option> + <option value="-matrix BLOSUM62" selected="true">BLOSUM62 (default)</option><option value="-matrix BLOSUM50">BLOSUM50</option><option value="-matrix BLOSUM45">BLOSUM45</option><option value="-matrix PAM250">PAM250</option>

1 0

galaxy-dist commit 477eb3cceae7: Updated a caption for consistency, removed an old comment
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 1285944657 -3600 # Node ID 477eb3cceae79d93be845a8540572033f208ae73 # Parent 36086d5bd8fa174ce88443eeeefec52b8fada5bd Updated a caption for consistency, removed an old comment --- a/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @@ -33,7 +33,7 @@ </when><when value="file"><param name="database" type="hidden" value="" /> - <param name="subject" type="data" format="fasta" label="Protein subject sequence(s)"/> + <param name="subject" type="data" format="fasta" label="Protein FASTA file to use as database"/></when></conditional><param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" /> --- a/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml @@ -59,7 +59,6 @@ </conditional></inputs><outputs> - <data name="output1" format="tabular" label="tblastn on ${db_opts.db_opts_selector}"><change_format><when input="out_format" value="0" format="txt"/>

1 0

galaxy-dist commit dd7a3707f323: Add -matrix option to BLASTP, BLASTX, TBLASTN and TBLASTX (doesn't apply to BLASTN)
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 1286293730 -3600 # Node ID dd7a3707f323bbf38689a24bfcb0b337c3494569 # Parent 1c8a5958c7481e53e862dbdf44d5367b6f3fc271 Add -matrix option to BLASTP, BLASTX, TBLASTN and TBLASTX (doesn't apply to BLASTN) --- a/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml @@ -11,6 +11,7 @@ -task $blast_type -evalue $evalue_cutoff $adv_opts.filter_query + $adv_opts.matrix -out $output1 -outfmt $out_format -num_threads 8 @@ -56,10 +57,21 @@ </param><when value="basic"><param name="filter_query" type="hidden" value="" /> + <param name="matrix" 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="matrix" type="select" label="Scoring matrix"> + <option value="-matrix BLOSUM62">BLOSUM62 (default)</option> + <option value="-matrix BLOSUM90">BLOSUM90</option> + <option value="-matrix BLOSUM80">BLOSUM80</option> + <option value="-matrix BLOSUM50">BLOSUM50</option> + <option value="-matrix BLOSUM45">BLOSUM45</option> + <option value="-matrix PAM250">PAM250</option> + <option value="-matrix PAM70">PAM70</option> + <option value="-matrix PAM30">PAM30</option> + </param></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml @@ -11,6 +11,7 @@ -evalue $evalue_cutoff $adv_opts.filter_query $adv_opts.strand + $adv_opts.matrix -out $output1 -outfmt $out_format -num_threads 8 @@ -53,6 +54,7 @@ <when value="basic"><param name="filter_query" type="hidden" value="" /><param name="strand" type="hidden" value="" /> + <param name="matrix" type="hidden" value="" /></when><when value="advanced"> @@ -62,6 +64,16 @@ <option value="-strand plus">Plus (forward)</option><option value="-strand minus">Minus (reverse complement)</option></param> + <param name="matrix" type="select" label="Scoring matrix"> + <option value="-matrix BLOSUM62">BLOSUM62 (default)</option> + <option value="-matrix BLOSUM90">BLOSUM90</option> + <option value="-matrix BLOSUM80">BLOSUM80</option> + <option value="-matrix BLOSUM50">BLOSUM50</option> + <option value="-matrix BLOSUM45">BLOSUM45</option> + <option value="-matrix PAM250">PAM250</option> + <option value="-matrix PAM70">PAM70</option> + <option value="-matrix PAM30">PAM30</option> + </param></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @@ -11,6 +11,7 @@ -evalue $evalue_cutoff $adv_opts.filter_query $adv_opts.strand + $adv_opts.matrix -out $output1 -outfmt $out_format -num_threads 8 @@ -53,6 +54,7 @@ <when value="basic"><param name="filter_query" type="hidden" value="" /><param name="strand" type="hidden" value="" /> + <param name="matrix" type="hidden" value="" /></when><when value="advanced"> @@ -62,6 +64,16 @@ <option value="-strand plus">Plus (forward)</option><option value="-strand minus">Minus (reverse complement)</option></param> + <param name="matrix" type="select" label="Scoring matrix"> + <option value="-matrix BLOSUM62">BLOSUM62 (default)</option> + <option value="-matrix BLOSUM90">BLOSUM90</option> + <option value="-matrix BLOSUM80">BLOSUM80</option> + <option value="-matrix BLOSUM50">BLOSUM50</option> + <option value="-matrix BLOSUM45">BLOSUM45</option> + <option value="-matrix PAM250">PAM250</option> + <option value="-matrix PAM70">PAM70</option> + <option value="-matrix PAM30">PAM30</option> + </param></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml @@ -10,6 +10,7 @@ #end if -evalue $evalue_cutoff $adv_opts.filter_query + $adv_opts.matrix -out $output1 -outfmt $out_format -num_threads 8 @@ -51,10 +52,21 @@ </param><when value="basic"><param name="filter_query" type="hidden" value="" /> + <param name="matrix" 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="matrix" type="select" label="Scoring matrix"> + <option value="-matrix BLOSUM62">BLOSUM62 (default)</option> + <option value="-matrix BLOSUM90">BLOSUM90</option> + <option value="-matrix BLOSUM80">BLOSUM80</option> + <option value="-matrix BLOSUM50">BLOSUM50</option> + <option value="-matrix BLOSUM45">BLOSUM45</option> + <option value="-matrix PAM250">PAM250</option> + <option value="-matrix PAM70">PAM70</option> + <option value="-matrix PAM30">PAM30</option> + </param></when></conditional></inputs>

1 0

galaxy-dist commit b2906cd2d484: Add -word_size as an advanced argument (ideally would be an optional integer with validation)
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 1286538540 -3600 # Node ID b2906cd2d484a25f80134f432b7c36ed18747bb5 # Parent b0286178f81dfcfbfd03e64b2b4fdb347ee75607 Add -word_size as an advanced argument (ideally would be an optional integer with validation) --- a/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml @@ -22,6 +22,9 @@ blastn #if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0): -max_target_seqs $adv_opts.max_hits #end if +#if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0): +-word_size $adv_opts.word_size +#end if </command><inputs><param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> @@ -72,6 +75,7 @@ blastn <param name="filter_query" type="hidden" value="" /><param name="strand" type="hidden" value="" /><param name="max_hits" type="hidden" value="" /> + <param name="word_size" type="hidden" value="" /></when><when value="advanced"> @@ -82,7 +86,11 @@ blastn <option value="-strand minus">Minus (reverse complement)</option></param> - <param name="max_hits" type="integer" value="0" lable="Maximum hits to show" help="Use zero for default limits"> + <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits"> + <validator type="in_range" min="0" /> + </param> +  + <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 4."><validator type="in_range" min="0" /></param></when> --- a/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml @@ -22,6 +22,9 @@ blastp #if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0): -max_target_seqs $adv_opts.max_hits #end if +#if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0): +-word_size $adv_opts.word_size +#end if </command><inputs><param name="query" type="data" format="fasta" label="Protein query sequence(s)"/> @@ -66,6 +69,7 @@ blastp <param name="filter_query" type="hidden" value="" /><param name="matrix" type="hidden" value="" /><param name="max_hits" type="hidden" value="" /> + <param name="word_size" type="hidden" value="" /></when><when value="advanced"> @@ -81,7 +85,11 @@ blastp <option value="-matrix PAM30">PAM30</option></param> - <param name="max_hits" type="integer" value="0" lable="Maximum hits to show" help="Use zero for default limits"> + <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits"> + <validator type="in_range" min="0" /> + </param> +  + <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2."><validator type="in_range" min="0" /></param></when> --- a/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml @@ -22,6 +22,9 @@ tblastx #if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0): -max_target_seqs $adv_opts.max_hits #end if +#if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0): +-word_size $adv_opts.word_size +#end if </command><inputs><param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> @@ -63,6 +66,7 @@ tblastx <param name="strand" type="hidden" value="" /><param name="matrix" type="hidden" value="" /><param name="max_hits" type="hidden" value="" /> + <param name="word_size" type="hidden" value="" /></when><when value="advanced"> @@ -86,6 +90,10 @@ tblastx <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits"><validator type="in_range" min="0" /></param> +  + <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2."> + <validator type="in_range" min="0" /> + </param></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @@ -22,6 +22,9 @@ blastx #if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0): -max_target_seqs $adv_opts.max_hits #end if +#if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0): +-word_size $adv_opts.word_size +#end if </command><inputs><param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> @@ -63,6 +66,7 @@ blastx <param name="strand" type="hidden" value="" /><param name="matrix" type="hidden" value="" /><param name="max_hits" type="hidden" value="" /> + <param name="word_size" type="hidden" value="" /></when><when value="advanced"> @@ -83,7 +87,11 @@ blastx <option value="-matrix PAM30">PAM30</option></param> - <param name="max_hits" type="integer" value="0" lable="Maximum hits to show" help="Use zero for default limits"> + <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits"> + <validator type="in_range" min="0" /> + </param> +  + <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2."><validator type="in_range" min="0" /></param></when> --- a/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml @@ -21,6 +21,9 @@ tblastn #if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0): -max_target_seqs $adv_opts.max_hits #end if +#if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0): +-word_size $adv_opts.word_size +#end if </command><inputs><param name="query" type="data" format="fasta" label="Protein query sequence(s)"/> @@ -61,6 +64,7 @@ tblastn <param name="filter_query" type="hidden" value="" /><param name="matrix" type="hidden" value="" /><param name="max_hits" type="hidden" value="" /> + <param name="word_size" type="hidden" value="" /></when><when value="advanced"> @@ -76,7 +80,11 @@ tblastn <option value="-matrix PAM30">PAM30</option></param> - <param name="max_hits" type="integer" value="0" lable="Maximum hits to show" help="Use zero for default limits"> + <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits"> + <validator type="in_range" min="0" /> + </param> +  + <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2."><validator type="in_range" min="0" /></param></when>

1 0

galaxy-dist commit f5f74df868f1: Comment out blastn vecscreen as not supported
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 1286381298 -3600 # Node ID f5f74df868f1dfb369ec723ef2cb9f0926eaa760 # Parent c4c2b6eea3e11ee8a024b32f58419f7b1d36f114 Comment out blastn vecscreen as not supported --- a/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml @@ -49,7 +49,10 @@ blastn <option value="blastn">blastn</option><option value="blastn-short">blastn-short</option><option value="dc-megablast">dc-megablast</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">

1 0

galaxy-dist commit 1c8a5958c748: Use dropdown (default) rather than radio for BLAST databases as could be lots of them
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 1285945041 -3600 # Node ID 1c8a5958c7481e53e862dbdf44d5367b6f3fc271 # Parent 477eb3cceae79d93be845a8540572033f208ae73 Use dropdown (default) rather than radio for BLAST databases as could be lots of them --- a/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml @@ -24,7 +24,7 @@ <option value="file">FASTA file</option></param><when value="db"> - <param name="database" type="select" display="radio" label="Nucleotide BLAST database"> + <param name="database" type="select" label="Nucleotide BLAST database"><options from_file="blastdb.loc"><column name="name" index="0"/><column name="value" index="1"/> --- a/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml @@ -23,7 +23,7 @@ <option value="file">FASTA file</option></param><when value="db"> - <param name="database" type="select" display="radio" label="Protein BLAST database"> + <param name="database" type="select" label="Protein BLAST database"><options from_file="blastdb_p.loc"><column name="name" index="0"/><column name="value" index="1"/> --- a/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml @@ -23,7 +23,7 @@ <option value="file">FASTA file</option></param><when value="db"> - <param name="database" type="select" display="radio" label="Nucleotide BLAST database"> + <param name="database" type="select" label="Nucleotide BLAST database"><options from_file="blastdb.loc"><column name="name" index="0"/><column name="value" index="1"/> --- a/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @@ -23,7 +23,7 @@ <option value="file">FASTA file</option></param><when value="db"> - <param name="database" type="select" display="radio" label="Protein BLAST database"> + <param name="database" type="select" label="Protein BLAST database"><options from_file="blastdb_p.loc"><column name="name" index="0"/><column name="value" index="1"/> --- a/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml @@ -22,7 +22,7 @@ <option value="file">FASTA file</option></param><when value="db"> - <param name="database" type="select" display="radio" label="Nucleotide BLAST database"> + <param name="database" type="select" label="Nucleotide BLAST database"><options from_file="blastdb.loc"><column name="name" index="0"/><column name="value" index="1"/>

1 0

galaxy-dist commit c4c2b6eea3e1: Added support for BLAST+ -max_target_seqs option
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 1286381268 -3600 # Node ID c4c2b6eea3e11ee8a024b32f58419f7b1d36f114 # Parent 9bf65ebafa8fc89115a5b42ebb9865ed99c1cf84 Added support for BLAST+ -max_target_seqs option --- a/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml @@ -3,7 +3,8 @@ <command> ## The command is a Cheetah template which allows some Python based syntax. ## Lines starting hash hash are comments. Galaxy will turn newlines into spaces -blastn -query "$query" +blastn +-query "$query" #if $db_opts.db_opts_selector == "db": -db "$db_opts.database" #else: @@ -16,6 +17,11 @@ blastn -query "$query" -out $output1 -outfmt $out_format -num_threads 8 +## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string +## Note -max_target_seqs overrides -num_descriptions and -num_alignments +#if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0): +-max_target_seqs $adv_opts.max_hits +#end if </command><inputs><param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> @@ -62,6 +68,7 @@ blastn -query "$query" <when value="basic"><param name="filter_query" type="hidden" value="" /><param name="strand" type="hidden" value="" /> + <param name="max_hits" type="hidden" value="" /></when><when value="advanced"> @@ -71,6 +78,10 @@ blastn -query "$query" <option value="-strand plus">Plus (forward)</option><option value="-strand minus">Minus (reverse complement)</option></param> +  + <param name="max_hits" type="integer" value="0" lable="Maximum hits to show" help="Use zero for default limits"> + <validator type="in_range" min="0" /> + </param></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml @@ -17,6 +17,11 @@ blastp -out $output1 -outfmt $out_format -num_threads 8 +## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string +## Note -max_target_seqs overrides -num_descriptions and -num_alignments +#if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0): +-max_target_seqs $adv_opts.max_hits +#end if </command><inputs><param name="query" type="data" format="fasta" label="Protein query sequence(s)"/> @@ -60,6 +65,7 @@ blastp <when value="basic"><param name="filter_query" type="hidden" value="" /><param name="matrix" type="hidden" value="" /> + <param name="max_hits" type="hidden" value="" /></when><when value="advanced"> @@ -74,6 +80,10 @@ blastp <option value="-matrix PAM70">PAM70</option><option value="-matrix PAM30">PAM30</option></param> +  + <param name="max_hits" type="integer" value="0" lable="Maximum hits to show" help="Use zero for default limits"> + <validator type="in_range" min="0" /> + </param></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml @@ -17,6 +17,11 @@ tblastx -out $output1 -outfmt $out_format -num_threads 8 +## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string +## Note -max_target_seqs overrides -num_descriptions and -num_alignments +#if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0): +-max_target_seqs $adv_opts.max_hits +#end if </command><inputs><param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> @@ -57,6 +62,7 @@ tblastx <param name="filter_query" type="hidden" value="" /><param name="strand" type="hidden" value="" /><param name="matrix" type="hidden" value="" /> + <param name="max_hits" type="hidden" value="" /></when><when value="advanced"> @@ -76,6 +82,10 @@ tblastx <option value="-matrix PAM70">PAM70</option><option value="-matrix PAM30">PAM30</option></param> +  + <param name="max_hits" type="integer" value="0" lable="Maximum hits to show (in plain text output)" help="Use zero for default limits"> + <validator type="in_range" min="0" /> + </param></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @@ -17,6 +17,11 @@ blastx -out $output1 -outfmt $out_format -num_threads 8 +## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string +## Note -max_target_seqs overrides -num_descriptions and -num_alignments +#if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0): +-max_target_seqs $adv_opts.max_hits +#end if </command><inputs><param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> @@ -57,6 +62,7 @@ blastx <param name="filter_query" type="hidden" value="" /><param name="strand" type="hidden" value="" /><param name="matrix" type="hidden" value="" /> + <param name="max_hits" type="hidden" value="" /></when><when value="advanced"> @@ -76,7 +82,10 @@ blastx <option value="-matrix PAM70">PAM70</option><option value="-matrix PAM30">PAM30</option></param> - +  + <param name="max_hits" type="integer" value="0" lable="Maximum hits to show" help="Use zero for default limits"> + <validator type="in_range" min="0" /> + </param></when></conditional></inputs> --- a/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml +++ b/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml @@ -16,6 +16,11 @@ tblastn -out $output1 -outfmt $out_format -num_threads 8 +## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string +## Note -max_target_seqs overrides -num_descriptions and -num_alignments +#if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0): +-max_target_seqs $adv_opts.max_hits +#end if </command><inputs><param name="query" type="data" format="fasta" label="Protein query sequence(s)"/> @@ -55,6 +60,7 @@ tblastn <when value="basic"><param name="filter_query" type="hidden" value="" /><param name="matrix" type="hidden" value="" /> + <param name="max_hits" type="hidden" value="" /></when><when value="advanced"> @@ -69,6 +75,10 @@ tblastn <option value="-matrix PAM70">PAM70</option><option value="-matrix PAM30">PAM30</option></param> +  + <param name="max_hits" type="integer" value="0" lable="Maximum hits to show" help="Use zero for default limits"> + <validator type="in_range" min="0" /> + </param></when></conditional></inputs>

1 0

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