Mercurial > repos > rnateam > graphclust_align_cluster
diff align_cluster.xml @ 0:c05c83b3ef0f draft
planemo upload for repository https://github.com/bgruening/galaxytools/tools/GraphClust/AlignCluster commit 4406735e44aba20859c252be39f4e99df28c7a92
author | rnateam |
---|---|
date | Sat, 27 Oct 2018 13:21:39 -0400 |
parents | |
children | 953353eacec2 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/align_cluster.xml Sat Oct 27 13:21:39 2018 -0400 @@ -0,0 +1,224 @@ +<tool id="graphclust_align_cluster" name="Align GraphClust cluster " version="0.1" > +<description>structural alignment and conservation analysis of predicted clusters</description> + <requirements> + <requirement type="package" version="0.6.0">graphclust-wrappers</requirement> + <requirement type="package" version='0.5'>perl-array-utils</requirement> + <requirement type="package" version='0.18.1'>scikit-learn</requirement> + <requirement type="package" version='1.8.10'>locarna</requirement> + <requirement type="package" version='2.1'>rnaz</requirement> + <requirement type="package" version="1.1.2">infernal</requirement> + <requirement type="package" version='2.2.10'>viennarna</requirement> + <requirement type="package" version='1.3.30'>graphicsmagick</requirement> + <requirement type="package" version='0.6.1'>rscape</requirement> + <requirement type="package" version='6.0'>unzip</requirement> + <requirement type="package" version='0.1'>evofold2</requirement> + <requirement type="package" version='1.70'>biopython</requirement> + <requirement type="package" version='0.23.0'>pandas</requirement> + </requirements> + <command detect_errors="aggressive"> + <![CDATA[ + #set $alignment_clustal = 'cluster.aln' + mkdir ./RESULTS/ && + 'gc_align_clusters.pl' + '$cluster_all_fa' + ./RESULTS/ C1 + $results_top_num + + " + #if str($advanced_opts.advanced_opts_selector) == "show": + #if str($advanced_opts.param_type.param_type_selector) == "gclust": + $advanced_opts.param_type.p + $advanced_opts.param_type.max_diff_am + $advanced_opts.param_type.max_diff + $advanced_opts.param_type.tau + $advanced_opts.param_type.struct_weight + $advanced_opts.param_type.indel_opening + $advanced_opts.param_type.indel + $advanced_opts.param_type.alifold_consensus_dp + #end if + #end if + " + && + R-scape --outdir ./RESULTS/ result.aln.sth && + RNAz --locarnate '$alignment_clustal' > alignment.rnaz.out && + #if str($genomic_cons_opts.genomic_cons_opts_selector) != "no": + clustal_to_alma.py '$alignment_clustal' $cluster_all && + EvoFoldV2.sh -o alignment.evofold.out '${alignment_clustal}.ama' + #if str($genomic_cons_opts.genomic_cons_opts_selector) == "hg38_100way": + '$__tool_directory__/hg38.100way.nh' + #elif str($genomic_cons_opts.genomic_cons_opts_selector) == "hg38_20way": + '$__tool_directory__/hg38.20way.nh' + #else + '$alignment_clustal'.ama '$genomic_cons_opts.phylo_tree' + #end if + && + #else + touch alignment.evofold.out && + #end if + + extract_conservation_metrics.py + '$alignment_clustal' alignment.rnaz.out RESULTS/result.aln.sum alignment.evofold.out + '$cluster_all' + #if str($bed_opts.bed_opts_selector) == "yes": + '$bed_opts.transcript_loci_fasta' + '$bed_opts.transcript_loci_bed' + '$bed_opts.genome_version' + #else + '' '' '' + #end if + conservation_metrics.tsv + +]]> + </command> + <inputs> + <param type="data" name="cluster_all_fa" label="cluster-sequences-sorted" format="fasta" + help="Cluster sequences from the collect-result step"/> + <param type="data" name="cluster_all" label="cmsearch-results" format="txt" + help="Tabular cmsearch results of the cluster-collection step (CLUSTERS-cmsearch)"/> + <param name="results_top_num" type="integer" value="5" size="5" label="results_top_num" + help="Top number of cmsearch hit sequences are used for structural alignment and metrics"/> + + <conditional name="genomic_cons_opts"> + <param type="select" name="genomic_cons_opts_selector" label="Phylo tree for evofold" + help="For MAF genomic alignments as input data, corresponding phylo tree is required to perform Evofold2 structural conservation predcition. For other genomic alignemnts, please upload the tree file."> + <option value="no">No</option> + <option value="hg38_100way">hg38-100way</option> + <option value="hg38_20way">hg38-20way</option> + <option value="user_phylo_tree">from history</option> + </param> + <when value="no" /> + <when value="hg38_100way" /> + <when value="hg38_20way" /> + <when value="user_phylo_tree"> + <param format="newick" name="phylo_tree" type="data" label="Newick phylo-tree" /> + </when> + </conditional> + <conditional name="bed_opts"> + <param type="select" name="bed_opts_selector" label="Extract genomic coordinates of the clusters" > + <option value="no">No</option> + <option value="yes">Yes</option> + </param> + <when value="no" /> + <when value="yes" > + <param format="fasta" name="transcript_loci_fasta" type="data" label="Loci reference sequence" + help="Sequence of reference species (human) for the genomic loci (precursor mRNA/lncRNA) to locate the clusters" /> + <param name='transcript_loci_bed' type="text" value="chr1 0 100000 gene 0 +" + help="bed entry string of the reference transcript loci for bed/ucsc-track output. 'chrom start end name score strand' white-space separated."> + <validator type="regex" message="one-line bed string must have at least 6 entries as BED6 format (chrom start end name 0 strand) + (space and tab allowed)">^\S+\s+[0-9]+\s+[0-9]+\s+\S+\s+\S+\s+[-+]\s*$</validator> + </param> + <param name='genome_version' value="hg38" type="text" label="reference genome assembly" + help="ucsc reference genome assembly version used in the input MAF alignments (e.g. hg38, hg19, mm10). To identify the reference in clusters"> + <validator type="regex" message="ucsc genome assembly version has an alphabet prefix and a number suffix">^[a-zA-Z]+[0-9]+$</validator> + </param> + </when> + </conditional> + <conditional name="advanced_opts"> + <param name="advanced_opts_selector" type="select" label="Locarna alignment options"> + <option value="hide" selected="True">Hide</option> + <option value="show">Show</option> + </param> + <when value="hide"></when> + <when value="show"> + <conditional name="param_type"> + <param name="param_type_selector" type="select" label="Choose the type of parameters"> + <option value="locarna">LocARNA defaults</option> + <option value="gclust" selected="True">GrapClust defaults(changeable)</option> + </param> + <when value="gclust"> + <param name="p" type="float" value="0.001" size="5" label="minimal probability" help="-p"/> + <param name="max_diff_am" type="integer" value="50" size="5" label=" maximal difference for sizes of matched arcs" help="--max-diff-am"/> + <param argument="tau" type="integer" value="50" min="0" max="200" label="Sequence contribution at structure match in percent"/> + <param name="max_diff" type="integer" value="100" size="5" label="maximal difference for alignment traces" help="--max-diff"/> + <param name="struct_weight" argument="struct-weight" + label="Structure weight" type="integer" + value="180" min="0" max="800" /> + <param name="indel_opening" argument="indel-opening" + label="Indel opening score" type="integer" + value="-400" max="0" min="-1500" /> + <param argument="indel" label="Indel score" type="integer" + value="-200" min="-1000" max="0" /> + <param name="alifold_consensus_dp" + type="boolean" checked="True" + truevalue="--alifold-consensus-dp" falsevalue=" " + label="Compute consensus dot plot by alifold" /> + </when> + <when value="locarna"> + </when> + </conditional> + </when> + </conditional> + </inputs> + <outputs> + <data name="alignment_ps" format="data" from_work_dir="cluster.aln.ps" label="alignment.ps" /> + <data name="alignment_png" format="png" from_work_dir="cluster.aln.png" label="alignment.png" /> + <data name="structure_ps" format="data" from_work_dir="cluster.alirna.ps" label="structure.ps" /> + <data name="structure_png" format="png" from_work_dir="cluster.alirna.png" label="structure.png" /> + <data name="alignment_sth" format="stockholm" from_work_dir="result.aln.sth" label="alignment.sth" /> + <data name="alignment_clustal_out" format="clustal" from_work_dir="cluster.aln" label="alignment.clustal" /> + <data name="Rscape_R2R" format="pdf" from_work_dir="RESULTS/result.aln_1.R2R.sto.pdf" label="Rscape-R2R" /> + <data name="rnaz_out" format="txt" from_work_dir="alignment.rnaz.out" label="rnaz.out" /> + <data name="rscape_out" format="txt" from_work_dir="alignment.sum" label="Rscape.summary" /> + <data name="evofold_out" format="txt" from_work_dir="alignment.evofold.out" label="evofold.out" /> + <data name="cons_tsv" format="tabular" from_work_dir="conservation_metrics.tsv" label="conservation_metrics.tsv" /> + </outputs> + <tests> + <test> + <param name="cluster_all_fa" value="cluster1.all.fa"/> + <param name="cluster_all" value="cluster1.all"/> + <output name="alignment_ps" file="alignment1.ps" compare="sim_size" /> + <output name="alignment_png" file="alignment1.png" compare="sim_size" /> + <output name="structure_ps" file="structure1.ps" compare="sim_size" /> + <output name="structure_png" file="structure1.png" compare="sim_size" /> + <output name="alignment_sth" file="alignment1.sth" compare="sim_size" delta="100" /> + <output name="alignment_clustal_out" file="alignment1.clustal" /> + <output name="Rscape_R2R" file="alignment1_R2R.sto.pdf" compare="sim_size" /> + <output name="rnaz_out" file="alignment1.rnaz.out" compare="sim_size" delta="10"/> + <output name="evofold_out" file="alignment1.evofold.out" /> + <output name="cons_tsv" file="alignment1.cons.tsv" compare="sim_size" delta="0"/> + <conditional name="genomic_cons_opts"> + <param name="genomic_cons_opts_selector" value="no"/> + </conditional> + <param name="results_top_num" value="5"/> + + </test> + + <test> + <param name="cluster_all_fa" value="cluster2.all.fa"/> + <param name="cluster_all" value="cluster2.all"/> + <output name="alignment_png" file="alignment2.png" compare="sim_size" /> + <output name="structure_png" file="structure2.png" compare="sim_size" /> + <output name="alignment_sth" file="alignment2.sth" compare="sim_size" delta="100" /> + <output name="alignment_clustal_out" file="alignment2.clustal" /> + <output name="rnaz_out" file="alignment2.rnaz.out" /> + <output name="evofold_out" file="alignment2.evofold.out" /> + <output name="cons_tsv" file="alignment2.cons.tsv" /> + <conditional name="genomic_cons_opts"> + <param name="genomic_cons_opts_selector" value="hg38_20way"/> + </conditional> + </test> + + <test> + <param name="cluster_all_fa" value="cluster2.all.fa"/> + <param name="cluster_all" value="cluster2.all"/> + <output name="cons_tsv" file="alignment2b.cons.tsv" /> + <conditional name="genomic_cons_opts"> + <param name="genomic_cons_opts_selector" value="hg38_20way"/> + </conditional> + <conditional name="bed_opts"> + <param name="bed_opts_selector" value="yes"/> + <param name="transcript_loci_fasta" value="alignment2b-transcript.fa"/> + <param name="transcript_loci_bed" value="chr7 27162434 27166719 Hoxa9-Xtend5UTR 2 -"/> + </conditional> + </test> + </tests> + <help> + <![CDATA[ + Align predicted clusters of glob_report_no_align step with locarna and conservation analysis and visualizations. + + ]]> + </help> + <citations> + <citation type="doi">10.5281/zenodo.597695</citation> + </citations> +</tool>