Mercurial > repos > peterjc > get_orfs_or_cdss
changeset 11:308ec20faefb draft
Uploaded v0.0.5h, depend on Biopython 1.62
| author | peterjc |
|---|---|
| date | Fri, 27 Sep 2013 06:11:59 -0400 |
| parents | e504a2e18cba |
| children | 09b5b1af9b8f |
| files | tools/get_orfs_or_cdss/get_orfs_or_cdss.xml tools/get_orfs_or_cdss/repository_dependencies.xml |
| diffstat | 2 files changed, 108 insertions(+), 110 deletions(-) [+] |
line wrap: on
line diff
--- a/tools/get_orfs_or_cdss/get_orfs_or_cdss.xml Thu Sep 26 10:04:13 2013 -0400 +++ b/tools/get_orfs_or_cdss/get_orfs_or_cdss.xml Fri Sep 27 06:11:59 2013 -0400 @@ -1,113 +1,111 @@ <tool id="get_orfs_or_cdss" name="Get open reading frames (ORFs) or coding sequences (CDSs)" version="0.0.5"> - <description>e.g. to get peptides from ESTs</description> - <version_command interpreter="python">get_orfs_or_cdss.py --version</version_command> - <command interpreter="python"> + <description>e.g. to get peptides from ESTs</description> + <requirements> + <requirement type="package" version="1.62">biopython</requirement> + <requirement type="python-module">Bio</requirement> + </requirements> + <version_command interpreter="python">get_orfs_or_cdss.py --version</version_command> + <command interpreter="python"> get_orfs_or_cdss.py $input_file $input_file.ext $table $ftype $ends $mode $min_len $strand $out_nuc_file $out_prot_file - </command> - <stdio> - <!-- Anything other than zero is an error --> - <exit_code range="1:" /> - <exit_code range=":-1" /> - </stdio> - <inputs> - <param name="input_file" type="data" format="fasta,fastq,sff" label="Sequence file (nucleotides)" help="FASTA, FASTQ, or SFF format." /> - <param name="table" type="select" label="Genetic code" help="Tables from the NCBI, these determine the start and stop codons"> - <option value="1">1. Standard</option> - <option value="2">2. Vertebrate Mitochondrial</option> - <option value="3">3. Yeast Mitochondrial</option> - <option value="4">4. Mold, Protozoan, Coelenterate Mitochondrial and Mycoplasma/Spiroplasma</option> - <option value="5">5. Invertebrate Mitochondrial</option> - <option value="6">6. Ciliate Macronuclear and Dasycladacean</option> - <option value="9">9. Echinoderm Mitochondrial</option> - <option value="10">10. Euplotid Nuclear</option> - <option value="11">11. Bacterial</option> - <option value="12">12. Alternative Yeast Nuclear</option> - <option value="13">13. Ascidian Mitochondrial</option> - <option value="14">14. Flatworm Mitochondrial</option> - <option value="15">15. Blepharisma Macronuclear</option> - <option value="16">16. Chlorophycean Mitochondrial</option> - <option value="21">21. Trematode Mitochondrial</option> - <option value="22">22. Scenedesmus obliquus</option> - <option value="23">23. Thraustochytrium Mitochondrial</option> - </param> - <param name="ftype" type="select" value="True" label="Look for ORFs or CDSs"> - <option value="ORF">Look for ORFs (check for stop codons only, ignore start codons)</option> - <option value="CDS">Look for CDSs (with start and stop codons)</option> - </param> - <param name="ends" type="select" value="open" label="Sequence end treatment"> - <option value="open">Open ended (will allow missing start/stop codons at the ends)</option> - <option value="closed">Complete (will check for start/stop codons at the ends)</option> - <!-- TODO? Circular, for using this on finished bacteria etc --> - </param> - - <param name="mode" type="select" label="Selection criteria" help="Suppose a sequence has ORFs/CDSs of lengths 100, 102 and 102 -- which should be taken? These options would return 3, 2 or 1 ORF."> - <option value="all">All ORFs/CDSs from each sequence</option> - <option value="top">All ORFs/CDSs from each sequence with the maximum length</option> - <option value="one">First ORF/CDS from each sequence with the maximum length</option> - </param> - <param name="min_len" type="integer" size="5" value="30" label="Minimum length ORF/CDS (in amino acids, e.g. 30 aa = 90 bp plus any stop codon)"> - </param> - <param name="strand" type="select" label="Strand to search" help="Use the forward only option if your sequence directionality is known (e.g. from poly-A tails, or strand specific RNA sequencing."> - <option value="both">Search both the forward and reverse strand</option> - <option value="forward">Only search the forward strand</option> - <option value="reverse">Only search the reverse strand</option> - </param> - </inputs> - <outputs> - <data name="out_nuc_file" format="fasta" label="${ftype.value}s (nucleotides)" /> - <data name="out_prot_file" format="fasta" label="${ftype.value}s (amino acids)" /> - </outputs> - <tests> - <test> - <param name="input_file" value="get_orf_input.fasta" /> - <param name="table" value="1" /> - <param name="ftype" value="CDS" /> - <param name="ends" value="open" /> - <param name="mode" value="all" /> - <param name="min_len" value="10" /> - <param name="strand" value="forward" /> - <output name="out_nuc_file" file="get_orf_input.t1_nuc_out.fasta" /> - <output name="out_prot_file" file="get_orf_input.t1_prot_out.fasta" /> - </test> - <test> - <param name="input_file" value="get_orf_input.fasta" /> - <param name="table" value="11" /> - <param name="ftype" value="CDS" /> - <param name="ends" value="closed" /> - <param name="mode" value="all" /> - <param name="min_len" value="10" /> - <param name="strand" value="forward" /> - <output name="out_nuc_file" file="get_orf_input.t11_nuc_out.fasta" /> - <output name="out_prot_file" file="get_orf_input.t11_prot_out.fasta" /> - </test> - <test> - <param name="input_file" value="get_orf_input.fasta" /> - <param name="table" value="11" /> - <param name="ftype" value="CDS" /> - <param name="ends" value="open" /> - <param name="mode" value="all" /> - <param name="min_len" value="10" /> - <param name="strand" value="forward" /> - <output name="out_nuc_file" file="get_orf_input.t11_open_nuc_out.fasta" /> - <output name="out_prot_file" file="get_orf_input.t11_open_prot_out.fasta" /> - </test> - <test> - <param name="input_file" value="Ssuis.fasta" /> - <param name="table" value="11" /> - <param name="ftype" value="ORF" /> - <param name="ends" value="open" /> - <param name="mode" value="all" /> - <param name="min_len" value="100" /> - <param name="strand" value="both" /> - <output name="out_nuc_file" file="get_orf_input.Suis_ORF.nuc.fasta" /> - <output name="out_prot_file" file="get_orf_input.Suis_ORF.prot.fasta" /> - </test> - </tests> - <requirements> - <requirement type="python-module">Bio</requirement> - </requirements> - <help> - + </command> + <stdio> + <!-- Anything other than zero is an error --> + <exit_code range="1:" /> + <exit_code range=":-1" /> + </stdio> + <inputs> + <param name="input_file" type="data" format="fasta,fastq,sff" label="Sequence file (nucleotides)" help="FASTA, FASTQ, or SFF format." /> + <param name="table" type="select" label="Genetic code" help="Tables from the NCBI, these determine the start and stop codons"> + <option value="1">1. Standard</option> + <option value="2">2. Vertebrate Mitochondrial</option> + <option value="3">3. Yeast Mitochondrial</option> + <option value="4">4. Mold, Protozoan, Coelenterate Mitochondrial and Mycoplasma/Spiroplasma</option> + <option value="5">5. Invertebrate Mitochondrial</option> + <option value="6">6. Ciliate Macronuclear and Dasycladacean</option> + <option value="9">9. Echinoderm Mitochondrial</option> + <option value="10">10. Euplotid Nuclear</option> + <option value="11">11. Bacterial</option> + <option value="12">12. Alternative Yeast Nuclear</option> + <option value="13">13. Ascidian Mitochondrial</option> + <option value="14">14. Flatworm Mitochondrial</option> + <option value="15">15. Blepharisma Macronuclear</option> + <option value="16">16. Chlorophycean Mitochondrial</option> + <option value="21">21. Trematode Mitochondrial</option> + <option value="22">22. Scenedesmus obliquus</option> + <option value="23">23. Thraustochytrium Mitochondrial</option> + </param> + <param name="ftype" type="select" value="True" label="Look for ORFs or CDSs"> + <option value="ORF">Look for ORFs (check for stop codons only, ignore start codons)</option> + <option value="CDS">Look for CDSs (with start and stop codons)</option> + </param> + <param name="ends" type="select" value="open" label="Sequence end treatment"> + <option value="open">Open ended (will allow missing start/stop codons at the ends)</option> + <option value="closed">Complete (will check for start/stop codons at the ends)</option> + <!-- TODO? Circular, for using this on finished bacteria etc --> + </param> + <param name="mode" type="select" label="Selection criteria" help="Suppose a sequence has ORFs/CDSs of lengths 100, 102 and 102 -- which should be taken? These options would return 3, 2 or 1 ORF."> + <option value="all">All ORFs/CDSs from each sequence</option> + <option value="top">All ORFs/CDSs from each sequence with the maximum length</option> + <option value="one">First ORF/CDS from each sequence with the maximum length</option> + </param> + <param name="min_len" type="integer" size="5" value="30" label="Minimum length ORF/CDS (in amino acids, e.g. 30 aa = 90 bp plus any stop codon)" /> + <param name="strand" type="select" label="Strand to search" help="Use the forward only option if your sequence directionality is known (e.g. from poly-A tails, or strand specific RNA sequencing."> + <option value="both">Search both the forward and reverse strand</option> + <option value="forward">Only search the forward strand</option> + <option value="reverse">Only search the reverse strand</option> + </param> + </inputs> + <outputs> + <data name="out_nuc_file" format="fasta" label="${ftype.value}s (nucleotides)" /> + <data name="out_prot_file" format="fasta" label="${ftype.value}s (amino acids)" /> + </outputs> + <tests> + <test> + <param name="input_file" value="get_orf_input.fasta" /> + <param name="table" value="1" /> + <param name="ftype" value="CDS" /> + <param name="ends" value="open" /> + <param name="mode" value="all" /> + <param name="min_len" value="10" /> + <param name="strand" value="forward" /> + <output name="out_nuc_file" file="get_orf_input.t1_nuc_out.fasta" /> + <output name="out_prot_file" file="get_orf_input.t1_prot_out.fasta" /> + </test> + <test> + <param name="input_file" value="get_orf_input.fasta" /> + <param name="table" value="11" /> + <param name="ftype" value="CDS" /> + <param name="ends" value="closed" /> + <param name="mode" value="all" /> + <param name="min_len" value="10" /> + <param name="strand" value="forward" /> + <output name="out_nuc_file" file="get_orf_input.t11_nuc_out.fasta" /> + <output name="out_prot_file" file="get_orf_input.t11_prot_out.fasta" /> + </test> + <test> + <param name="input_file" value="get_orf_input.fasta" /> + <param name="table" value="11" /> + <param name="ftype" value="CDS" /> + <param name="ends" value="open" /> + <param name="mode" value="all" /> + <param name="min_len" value="10" /> + <param name="strand" value="forward" /> + <output name="out_nuc_file" file="get_orf_input.t11_open_nuc_out.fasta" /> + <output name="out_prot_file" file="get_orf_input.t11_open_prot_out.fasta" /> + </test> + <test> + <param name="input_file" value="Ssuis.fasta" /> + <param name="table" value="11" /> + <param name="ftype" value="ORF" /> + <param name="ends" value="open" /> + <param name="mode" value="all" /> + <param name="min_len" value="100" /> + <param name="strand" value="both" /> + <output name="out_nuc_file" file="get_orf_input.Suis_ORF.nuc.fasta" /> + <output name="out_prot_file" file="get_orf_input.Suis_ORF.prot.fasta" /> + </test> + </tests> + <help> **What it does** Takes an input file of nucleotide sequences (typically FASTA, but also FASTQ @@ -169,5 +167,5 @@ This tool is available to install into other Galaxy Instances via the Galaxy Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/get_orfs_or_cdss - </help> + </help> </tool>
--- a/tools/get_orfs_or_cdss/repository_dependencies.xml Thu Sep 26 10:04:13 2013 -0400 +++ b/tools/get_orfs_or_cdss/repository_dependencies.xml Fri Sep 27 06:11:59 2013 -0400 @@ -2,5 +2,5 @@ <repositories description="This requires Biopython as a dependency."> <!-- Leave out the tool shed and revision to get the current tool shed and latest revision at the time of upload --> -<repository changeset_revision="2f6c871cfa35" name="package_biopython_1_61" owner="biopython" toolshed="http://testtoolshed.g2.bx.psu.edu" /> +<repository changeset_revision="ac9cc2992b69" name="package_biopython_1_62" owner="biopython" toolshed="http://testtoolshed.g2.bx.psu.edu" /> </repositories>