Mercurial > repos > devteam > ncbi_blast_plus
changeset 3:e98f6bd363ba draft
planemo upload for repository https://github.com/peterjc/galaxy_blast/tools/ncbi_blast_plus commit a567843bb239ee8faec72eb7e52f3b5aa3191631
line wrap: on
line diff
--- a/tools/ncbi_blast_plus/README.rst Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/README.rst Fri May 15 06:15:59 2015 -0400 @@ -213,6 +213,8 @@ - Replace ``.extra_files_path`` with ``.files_path`` (internal change, thanks to Bjoern Gruening and John Chilton). - Added "NCBI BLAST+ integrated into Galaxy" preprint citation. +v0.1.03 - Reorder XML elements (internal change only). + - Planemo for Tool Shed upload (``.shed.yml``, internal change only). ======= ====================================================================== @@ -233,10 +235,28 @@ As of July 2013, development is continuing on a dedicated GitHub repository: https://github.com/peterjc/galaxy_blast -For making the "Galaxy Tool Shed" http://toolshed.g2.bx.psu.edu/ tarball I use -the following command from the GitHub repository root folder:: +For pushing a release to the test or main "Galaxy Tool Shed", use the following +Planemo commands (which requires you have set your Tool Shed access details in +``~/.planemo.yml`` and that you have access rights on the Tool Shed):: + + $ planemo shed_upload --shed_target testtoolshed --check_diff ~/repositories/galaxy_blast/tools/ncbi_blast_plus/ + ... + +or:: - $ tools/ncbi_blast_plus/make_ncbi_blast_plus.sh + $ planemo shed_upload --shed_target toolshed --check_diff ~/repositories/galaxy_blast/tools/ncbi_blast_plus/ + ... + +To just build and check the tar ball, use:: + + $ planemo shed_upload --tar_only ~/repositories/galaxy_blast/tools/ncbi_blast_plus/ + ... + $ tar -tzf shed_upload.tar.gz + test-data/blastdb.loc + ... + tools/ncbi_blast_plus/tool_dependencies.xml + $ tar -tzf shed_upload.tar.gz | wc -l + 117 This simplifies ensuring a consistent set of files is bundled each time, including all the relevant test files.
--- a/tools/ncbi_blast_plus/blastxml_to_tabular.py Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/blastxml_to_tabular.py Fri May 15 06:15:59 2015 -0400 @@ -1,9 +1,9 @@ #!/usr/bin/env python """Convert a BLAST XML file to tabular output. -Takes three command line options, input BLAST XML filename, output tabular -BLAST filename, output format (std for standard 12 columns, or ext for the -extended 24 columns offered in the BLAST+ wrappers). +Designed to convert BLAST XML files into tabular BLAST output (either +std for standard 12 columns, or ext for the extended 25 columns offered +in the Galaxy BLAST+ wrappers). The 12 columns output are 'qseqid sseqid pident length mismatch gapopen qstart qend sstart send evalue bitscore' or 'std' at the BLAST+ command line, which
--- a/tools/ncbi_blast_plus/blastxml_to_tabular.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/blastxml_to_tabular.xml Fri May 15 06:15:59 2015 -0400 @@ -1,5 +1,10 @@ -<tool id="blastxml_to_tabular" name="BLAST XML to tabular" version="0.1.04"> +<tool id="blastxml_to_tabular" name="BLAST XML to tabular" version="0.1.05"> <description>Convert BLAST XML output to tabular</description> + <stdio> + <!-- Anything other than zero is an error --> + <exit_code range="1:" /> + <exit_code range=":-1" /> + </stdio> <version_command interpreter="python">blastxml_to_tabular.py --version</version_command> <command interpreter="python"> blastxml_to_tabular.py -o "$tabular_file" @@ -11,11 +16,6 @@ #end if #for i in $blastxml_file#"${i}" #end for# </command> - <stdio> - <!-- Anything other than zero is an error --> - <exit_code range="1:" /> - <exit_code range=":-1" /> - </stdio> <inputs> <param name="blastxml_file" type="data" format="blastxml" multiple="true" label="BLAST results as XML"/> <conditional name="output"> @@ -62,8 +62,6 @@ <outputs> <data name="tabular_file" format="tabular" label="$on_string (as tabular)" /> </outputs> - <requirements> - </requirements> <tests> <test> <param name="blastxml_file" value="blastp_four_human_vs_rhodopsin.xml" ftype="blastxml" />
--- a/tools/ncbi_blast_plus/ncbi_blastdbcmd_info.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_blastdbcmd_info.xml Fri May 15 06:15:59 2015 -0400 @@ -1,14 +1,13 @@ -<tool id="ncbi_blastdbcmd_info" name="NCBI BLAST+ database info" version="0.1.02"> +<tool id="ncbi_blastdbcmd_info" name="NCBI BLAST+ database info" version="0.1.03"> <description>Show BLAST database information from blastdbcmd</description> <macros> <token name="@BINARY@">blastdbcmd</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <command> blastdbcmd -dbtype $db_opts.db_type -db "${db_opts.database.fields.path}" -info -out "$info" </command> - <expand macro="stdio" /> <inputs> <expand macro="input_conditional_choose_db_type" /> </inputs>
--- a/tools/ncbi_blast_plus/ncbi_blastdbcmd_wrapper.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_blastdbcmd_wrapper.xml Fri May 15 06:15:59 2015 -0400 @@ -1,10 +1,10 @@ -<tool id="ncbi_blastdbcmd_wrapper" name="NCBI BLAST+ blastdbcmd entry(s)" version="0.1.02"> +<tool id="ncbi_blastdbcmd_wrapper" name="NCBI BLAST+ blastdbcmd entry(s)" version="0.1.03"> <description>Extract sequence(s) from BLAST database</description> <macros> <token name="@BINARY@">blastdbcmd</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <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 @@ -47,7 +47,6 @@ | sed 's/>\(lcl|\|gnl|BL_ORD_ID|[0-9]* \)/>/1' > "$seq" #end if </command> - <expand macro="stdio" /> <inputs> <expand macro="input_conditional_choose_db_type" /> <conditional name="id_opts">
--- a/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml Fri May 15 06:15:59 2015 -0400 @@ -1,4 +1,4 @@ -<tool id="ncbi_blastn_wrapper" name="NCBI BLAST+ blastn" version="0.1.02"> +<tool id="ncbi_blastn_wrapper" name="NCBI BLAST+ blastn" version="0.1.03"> <description>Search nucleotide database with nucleotide query sequence(s)</description> <!-- If job splitting is enabled, break up the query file into parts --> <parallelism method="multi" split_inputs="query" split_mode="to_size" split_size="1000" merge_outputs="output1"></parallelism> @@ -6,7 +6,7 @@ <token name="@BINARY@">blastn</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <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 @@ -31,14 +31,9 @@ ## End of advanced options: #end if </command> - - <expand macro="stdio" /> - <inputs> <param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> - <expand macro="input_conditional_nucleotide_db" /> - <param name="blast_type" type="select" display="radio" label="Type of BLAST"> <option value="megablast">megablast - Traditional megablast used to find very similar (e.g., intraspecies or closely related species) sequences</option> <option value="blastn">blastn - Traditional BLASTN requiring an exact match of 11, for somewhat similar sequences</option>
--- a/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml Fri May 15 06:15:59 2015 -0400 @@ -1,4 +1,4 @@ -<tool id="ncbi_blastp_wrapper" name="NCBI BLAST+ blastp" version="0.1.02"> +<tool id="ncbi_blastp_wrapper" name="NCBI BLAST+ blastp" version="0.1.03"> <description>Search protein database with protein query sequence(s)</description> <!-- If job splitting is enabled, break up the query file into parts --> <parallelism method="multi" split_inputs="query" split_mode="to_size" split_size="1000" merge_outputs="output1" /> @@ -6,7 +6,7 @@ <token name="@BINARY@">blastp</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <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 @@ -29,9 +29,6 @@ ## End of advanced options: #end if </command> - - <expand macro="stdio" /> - <inputs> <param name="query" type="data" format="fasta" label="Protein query sequence(s)"/>
--- a/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml Fri May 15 06:15:59 2015 -0400 @@ -1,4 +1,4 @@ -<tool id="ncbi_blastx_wrapper" name="NCBI BLAST+ blastx" version="0.1.02"> +<tool id="ncbi_blastx_wrapper" name="NCBI BLAST+ blastx" version="0.1.03"> <description>Search protein database with translated nucleotide query sequence(s)</description> <!-- If job splitting is enabled, break up the query file into parts --> <parallelism method="multi" split_inputs="query" split_mode="to_size" split_size="1000" merge_outputs="output1"></parallelism> @@ -6,7 +6,7 @@ <token name="@BINARY@">blastx</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <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 @@ -30,9 +30,6 @@ ## End of advanced options: #end if </command> - - <expand macro="stdio" /> - <inputs> <param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/>
--- a/tools/ncbi_blast_plus/ncbi_convert2blastmask_wrapper.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_convert2blastmask_wrapper.xml Fri May 15 06:15:59 2015 -0400 @@ -1,10 +1,10 @@ -<tool id="ncbi_convert2blastmask_wrapper" name="NCBI BLAST+ convert2blastmask" version="0.1.02"> +<tool id="ncbi_convert2blastmask_wrapper" name="NCBI BLAST+ convert2blastmask" version="0.1.03"> <description>Convert masking information in lower-case masked FASTA input to file formats suitable for makeblastdb</description> <macros> <token name="@BINARY@">convert2blastmask</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <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 @@ -16,7 +16,6 @@ -out "$outfile" -outfmt $outformat </command> - <expand macro="stdio" /> <inputs> <param name="infile" type="data" format="fasta" label="masked FASTA file"/> <param name="masking_algorithm" type="select" label="Used masking algorithm">
--- a/tools/ncbi_blast_plus/ncbi_dustmasker_wrapper.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_dustmasker_wrapper.xml Fri May 15 06:15:59 2015 -0400 @@ -1,11 +1,11 @@ -<tool id="ncbi_dustmasker_wrapper" name="NCBI BLAST+ dustmasker" version="0.1.02"> +<tool id="ncbi_dustmasker_wrapper" name="NCBI BLAST+ dustmasker" version="0.1.03"> <!-- dustmasker wrapper from Edward Kirton and Nicola Soranzo --> <description>masks low complexity regions</description> <macros> <token name="@BINARY@">dustmasker</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <command> ## The command is a Cheetah template which allows some Python based syntax. ## Lines starting hash hash are comments. Galaxy will turn newlines into spaces @@ -20,7 +20,6 @@ -out "$outfile" -window $window -level $level -linker $linker -outfmt $outformat </command> - <expand macro="stdio" /> <inputs> <expand macro="input_conditional_nucleotide_db" /> <param name="window" type="integer" value="64" label="DUST window length" />
--- a/tools/ncbi_blast_plus/ncbi_macros.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_macros.xml Fri May 15 06:15:59 2015 -0400 @@ -1,9 +1,18 @@ <macros> - <xml name="requirements"> + <xml name="preamble"> <requirements> <requirement type="binary">@BINARY@</requirement> <requirement type="package" version="2.2.30">blast+</requirement> </requirements> + <stdio> + <!-- Anything other than zero is an error --> + <exit_code range="1:" /> + <!-- Might see negative return codes for Unix signals via Python subprocess --> + <exit_code range=":-1" /> + <!-- In case the return code has not been set properly check stderr too --> + <regex match="Error:" /> + <regex match="Exception:" /> + </stdio> <version_command>@BINARY@ -version</version_command> </xml> <xml name="output_change_format"> @@ -116,17 +125,6 @@ <option value="PAM30">PAM30</option> </param> </xml> - <xml name="stdio"> - <stdio> - <!-- Anything other than zero is an error --> - <exit_code range="1:" /> - <!-- Might see negative return codes for Unix signals via Python subprocess --> - <exit_code range=":-1" /> - <!-- In case the return code has not been set properly check stderr too --> - <regex match="Error:" /> - <regex match="Exception:" /> - </stdio> - </xml> <xml name="input_query_gencode"> <param name="query_gencode" type="select" label="Query genetic code"> <!-- See http://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi for details -->
--- a/tools/ncbi_blast_plus/ncbi_makeblastdb.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_makeblastdb.xml Fri May 15 06:15:59 2015 -0400 @@ -1,10 +1,10 @@ -<tool id="ncbi_makeblastdb" name="NCBI BLAST+ makeblastdb" version="0.1.02"> +<tool id="ncbi_makeblastdb" name="NCBI BLAST+ makeblastdb" version="0.1.03"> <description>Make BLAST database</description> <macros> <token name="@BINARY@">makeblastdb</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <command interpreter="python">check_no_duplicates.py ##First check for duplicates (since BLAST+ 2.2.28 fails to do so) ##and abort (via the ampersand ampersand trick) if any are found. @@ -47,7 +47,6 @@ ## Capture the stdout log information to the primary file (plain text): > "$outfile" </command> - <expand macro="stdio" /> <inputs> <param name="dbtype" type="select" display="radio" label="Molecule type of input"> <option value="prot">protein</option>
--- a/tools/ncbi_blast_plus/ncbi_makeprofiledb.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_makeprofiledb.xml Fri May 15 06:15:59 2015 -0400 @@ -1,10 +1,10 @@ -<tool id="ncbi_makeprofiledb" name="NCBI BLAST+ makeprofiledb" version="0.1.02"> +<tool id="ncbi_makeprofiledb" name="NCBI BLAST+ makeprofiledb" version="0.1.03"> <description>Make profile database</description> <macros> <token name="@BINARY@">makeprofiledb</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <command> ##Unlike makeblastdb, makeprofiledb needs directory to exist already: mkdir -p $outfile.files_path && @@ -34,7 +34,13 @@ -logfile "$outfile" </command> - <expand macro="stdio" /> + <configfiles> + <configfile name="infiles"> +#for $infile in $input_file +${infile} +#end for + </configfile> + </configfiles> <inputs> <param name="input_file" type="data" multiple="true" optional="false" format="pssm-asn1" label="Input PSSM files(s)" @@ -75,13 +81,6 @@ label="Observation threshold" help="Exclude domains with with maximum number of independent observations below this threshold" /> </inputs> - <configfiles> - <configfile name="infiles"> -#for $infile in $input_file -${infile} -#end for - </configfile> - </configfiles> <outputs> <data name="outfile" format="blastdbd" label="RPS database from ${on_string}" /> </outputs>
--- a/tools/ncbi_blast_plus/ncbi_rpsblast_wrapper.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_rpsblast_wrapper.xml Fri May 15 06:15:59 2015 -0400 @@ -1,4 +1,4 @@ -<tool id="ncbi_rpsblast_wrapper" name="NCBI BLAST+ rpsblast" version="0.1.02"> +<tool id="ncbi_rpsblast_wrapper" name="NCBI BLAST+ rpsblast" version="0.1.03"> <description>Search protein domain database (PSSMs) with protein query sequence(s)</description> <!-- If job splitting is enabled, break up the query file into parts --> <parallelism method="multi" split_inputs="query" split_mode="to_size" split_size="1000" merge_outputs="output1" /> @@ -6,7 +6,7 @@ <token name="@BINARY@">deltablast</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <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 @@ -27,9 +27,6 @@ ## End of advanced options: #end if </command> - - <expand macro="stdio" /> - <inputs> <param name="query" type="data" format="fasta" label="Protein query sequence(s)"/>
--- a/tools/ncbi_blast_plus/ncbi_rpstblastn_wrapper.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_rpstblastn_wrapper.xml Fri May 15 06:15:59 2015 -0400 @@ -1,4 +1,4 @@ -<tool id="ncbi_rpstblastn_wrapper" name="NCBI BLAST+ rpstblastn" version="0.1.02"> +<tool id="ncbi_rpstblastn_wrapper" name="NCBI BLAST+ rpstblastn" version="0.1.03"> <description>Search protein domain database (PSSMs) with translated nucleotide query sequence(s)</description> <!-- If job splitting is enabled, break up the query file into parts --> <parallelism method="multi" split_inputs="query" split_mode="to_size" split_size="1000" merge_outputs="output1"></parallelism> @@ -6,7 +6,7 @@ <token name="@BINARY@">rpstblastn</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <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 @@ -28,7 +28,6 @@ ## End of advanced options: #end if </command> - <expand macro="stdio" /> <inputs> <param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/>
--- a/tools/ncbi_blast_plus/ncbi_segmasker_wrapper.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_segmasker_wrapper.xml Fri May 15 06:15:59 2015 -0400 @@ -1,10 +1,10 @@ -<tool id="ncbi_segmasker_wrapper" name="NCBI BLAST+ segmasker" version="0.1.02"> +<tool id="ncbi_segmasker_wrapper" name="NCBI BLAST+ segmasker" version="0.1.03"> <description>low-complexity regions in protein sequences</description> <macros> <token name="@BINARY@">segmasker</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <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 @@ -22,7 +22,6 @@ -hicut $hicut -outfmt $outformat </command> - <expand macro="stdio" /> <inputs> <expand macro="input_conditional_protein_db" /> <param name="window" type="integer" value="12" label="SEG window length" help="(-window)" />
--- a/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml Fri May 15 06:15:59 2015 -0400 @@ -1,4 +1,4 @@ -<tool id="ncbi_tblastn_wrapper" name="NCBI BLAST+ tblastn" version="0.1.02"> +<tool id="ncbi_tblastn_wrapper" name="NCBI BLAST+ tblastn" version="0.1.03"> <description>Search translated nucleotide database with protein query sequence(s)</description> <!-- If job splitting is enabled, break up the query file into parts --> <parallelism method="multi" split_inputs="query" split_mode="to_size" split_size="1000" merge_outputs="output1"></parallelism> @@ -6,7 +6,7 @@ <token name="@BINARY@">tblastn</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <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 @@ -30,9 +30,6 @@ ## End of advanced options: #end if </command> - - <expand macro="stdio" /> - <inputs> <param name="query" type="data" format="fasta" label="Protein query sequence(s)"/>
--- a/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml Thu Apr 02 04:48:24 2015 -0400 +++ b/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml Fri May 15 06:15:59 2015 -0400 @@ -1,4 +1,4 @@ -<tool id="ncbi_tblastx_wrapper" name="NCBI BLAST+ tblastx" version="0.1.02"> +<tool id="ncbi_tblastx_wrapper" name="NCBI BLAST+ tblastx" version="0.1.03"> <description>Search translated nucleotide database with translated nucleotide query sequence(s)</description> <!-- If job splitting is enabled, break up the query file into parts --> <parallelism method="multi" split_inputs="query" split_mode="to_size" split_size="1000" merge_outputs="output1"></parallelism> @@ -6,7 +6,7 @@ <token name="@BINARY@">tblastx</token> <import>ncbi_macros.xml</import> </macros> - <expand macro="requirements" /> + <expand macro="preamble" /> <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 @@ -29,9 +29,6 @@ ## End of advanced options: #end if </command> - - <expand macro="stdio" /> - <inputs> <param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/>