Mercurial > repos > earlhaminst > gstf_preparation
diff gstf_preparation.xml @ 0:28879ca33b5f draft
planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/gstf_preparation commit 651fae48371f845578753052c6fe173e3bb35670
| author | earlhaminst |
|---|---|
| date | Wed, 15 Mar 2017 20:18:57 -0400 |
| parents | |
| children | 19644996bc2a |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gstf_preparation.xml Wed Mar 15 20:18:57 2017 -0400 @@ -0,0 +1,82 @@ +<tool id="gstf_preparation" name="GeneSeqToFamily preparation" version="0.3.0"> + <description>converts data for the workflow</description> + <command detect_errors="exit_code"> +<![CDATA[ +python '$__tool_directory__/gstf_preparation.py' +#for $q in $queries + --gff3 '${q.genome}:${q.gff3_input}' +#end for +#if str($json) != 'None' + #for $v in $json + --json '$v' + #end for +#end if +#for $fasta_input in $fasta_inputs + --fasta '${fasta_input}' +#end for +-o '$output_db' +--of '$output_fasta' +]]> + </command> + + <inputs> + <repeat name="queries" title="GFF3 dataset"> + <param name="gff3_input" type="data" format="gff3" label="GFF3 dataset" /> + <param name="genome" type="text" label="Genome name" help="Genome name without whitespaces or special characters"> + <validator type="empty_field" /> + </param> + </repeat> + <param name="json" type="data" format="json" multiple="true" optional="true" label="Gene features in JSON format generated by 'Get features by Ensembl ID' tool" /> + <param name="fasta_inputs" type="data" format="fasta" multiple="true" label="Corresponding FASTA datasets" help="Each FASTA header line should start with a transcript id" /> + </inputs> + + <outputs> + <data name="output_db" format="sqlite" label="${tool.name} on ${on_string}: SQLite" /> + <data name="output_fasta" format="fasta" label="${tool.name} on ${on_string}: FASTA" /> + </outputs> + + <tests> + <test> + <param name="fasta_inputs" ftype="fasta" value="Caenorhabditis_elegans.WBcel235.cds.all.shortened.fa" /> + <param name="gff3_input" ftype="gff3" value="Caenorhabditis_elegans.WBcel235.87.chromosome.I.shortened.gff3" /> + <param name="genome" value="caenorhabditis_elegans" /> + <output name="output_db" file="test1.sqlite" compare="sim_size" /> + <output name="output_fasta" file="test1.fasta" /> + </test> + <test> + <param name="fasta_inputs" ftype="fasta" value="CDS.fasta" /> + <param name="json" ftype="json" value="gene.json" /> + + <output name="output_db" file="test2.sqlite" compare="sim_size" /> + <output name="output_fasta" file="test2.fasta" /> + </test> + </tests> + <help> +<![CDATA[ +**What it does** + +This tool converts a set of GFF3 and/or JSON gene feature information datasets into SQLite format and modify the header lines of a corresponding CDS FASTA to be used with the GeneSeqToFamily workflow. + +Example GFF3 file:: + + scaffold_0 MYZPE13164_Clone_G006_v1.0 gene 44968 69413 . - . ID=MYZPE13164_G006_v1.0_000000030;Name=MYZPE13164_G006_v1.0_000000030;biotype=protein_coding + scaffold_0 MYZPE13164_Clone_G006_v1.0 mRNA 44968 69413 . - . ID=MYZPE13164_G006_v1.0_000000030.1;Parent=MYZPE13164_G006_v1.0_000000030;Name=MYZPE13164_G006_v1.0_000000030.1;biotype=protein_coding;_AED=0.31 + scaffold_0 MYZPE13164_Clone_G006_v1.0 three_prime_utr 44968 46637 . - . ID=MYZPE13164_G006_v1.0_000000030.1.3utr1;Parent=MYZPE13164_G006_v1.0_000000030.1 + scaffold_0 MYZPE13164_Clone_G006_v1.0 exon 44968 47432 . - . ID=MYZPE13164_G006_v1.0_000000030.1.exon1;Parent=MYZPE13164_G006_v1.0_000000030.1 + scaffold_0 MYZPE13164_Clone_G006_v1.0 CDS 46638 47432 . - 0 ID=MYZPE13164_G006_v1.0_000000030.1.cds1;Parent=MYZPE13164_G006_v1.0_000000030.1 + scaffold_0 MYZPE13164_Clone_G006_v1.0 exon 53325 53539 . - . ID=MYZPE13164_G006_v1.0_000000030.1.exon2;Parent=MYZPE13164_G006_v1.0_000000030.1 + scaffold_0 MYZPE13164_Clone_G006_v1.0 CDS 53325 53539 . - 2 ID=MYZPE13164_G006_v1.0_000000030.1.cds2;Parent=MYZPE13164_G006_v1.0_000000030.1 + scaffold_0 MYZPE13164_Clone_G006_v1.0 exon 54614 54719 . - . ID=MYZPE13164_G006_v1.0_000000030.1.exon3;Parent=MYZPE13164_G006_v1.0_000000030.1 + scaffold_0 MYZPE13164_Clone_G006_v1.0 CDS 54614 54719 . - 0 ID=MYZPE13164_G006_v1.0_000000030.1.cds3;Parent=MYZPE13164_G006_v1.0_000000030.1 + scaffold_0 MYZPE13164_Clone_G006_v1.0 CDS 54852 55106 . - 0 ID=MYZPE13164_G006_v1.0_000000030.1.cds4;Parent=MYZPE13164_G006_v1.0_000000030.1 + scaffold_0 MYZPE13164_Clone_G006_v1.0 exon 54852 55117 . - . ID=MYZPE13164_G006_v1.0_000000030.1.exon4;Parent=MYZPE13164_G006_v1.0_000000030.1 + scaffold_0 MYZPE13164_Clone_G006_v1.0 five_prime_utr 55107 55117 . - . ID=MYZPE13164_G006_v1.0_000000030.1.5utr1;Parent=MYZPE13164_G006_v1.0_000000030.1 + scaffold_0 MYZPE13164_Clone_G006_v1.0 five_prime_utr 68851 69413 . - . ID=MYZPE13164_G006_v1.0_000000030.1.5utr2;Parent=MYZPE13164_G006_v1.0_000000030.1 + scaffold_0 MYZPE13164_Clone_G006_v1.0 exon 68851 69413 . - . ID=MYZPE13164_G006_v1.0_000000030.1.exon5;Parent=MYZPE13164_G006_v1.0_000000030.1 + +The following features are parsed: **gene**, **mRNA**, **transcript**, **exon**, **five_prime_utr**, **three_prime_utr** and **CDS**, all other are ignored. Also, **ID** and **Parent** tags are needed to create relations. +]]> + </help> + <citations> + </citations> +</tool>