Mercurial > repos > iuc > trycycler_reconcile_msa
changeset 1:b64696992ee9 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/trycycler commit e88166111fa3b6c57c870ea4cff6e012a1b1a912"
| author | iuc |
|---|---|
| date | Sat, 13 Feb 2021 17:31:16 +0000 |
| parents | 4ac81df20c74 |
| children | 937ea677d437 |
| files | trycycler_reconcile_msa.xml |
| diffstat | 1 files changed, 74 insertions(+), 111 deletions(-) [+] |
line wrap: on
line diff
--- a/trycycler_reconcile_msa.xml Thu Feb 11 19:26:05 2021 +0000 +++ b/trycycler_reconcile_msa.xml Sat Feb 13 17:31:16 2021 +0000 @@ -1,10 +1,10 @@ -<tool id="trycycler_reconcile_msa" name="Trycycler reconcile/msa" version="@TOOL_VERSION@" profile="21.01"> +<tool id="trycycler_reconcile_msa" name="Trycycler reconcile/msa" version="@TOOL_VERSION@" profile="20.01"> <description>reconcile the contigs within each cluster and perform a multiple sequence alignment</description> <macros> <import>macros.xml</import> </macros> - <expand macro="edam_ontology"/> - <expand macro="requirements"/> + <expand macro="edam_ontology" /> + <expand macro="requirements" /> <version_command>trycycler --version</version_command> <command detect_errors="exit_code"><![CDATA[ #import re @@ -35,159 +35,122 @@ --threads \${GALAXY_SLOTS:-2} && mv '${fullpath}/2_all_seqs.fasta' '$reconciled_cluster' && mv '${fullpath}/3_msa.fasta' '$aligned_cluster' - ]]></command> + ]]> </command> <inputs> - <param name="input_cluster" type="data" - format="fasta" label="Cluster multi-FASTA dataset" - help="The input should be an independent cluster generated by the *trycycler cluster* tool" /> - <param name="reads" type="data" - format="fastq,fastq.gz" label="Long-read datasets" - help="Long reads (FASTQ format) used to generate the assemblies" /> - <param argument="--linear" type="boolean" - truevalue="--linear" falsevalue="" - label="Input contigs are not circular" - help="Use this option if your input contigs are not circular. It will disable the circularisation-correction steps in Trycycler reconcile." /> - <section name='initial_ckeck' - title='Reconcile initial check options' - expanded='true'> - <param argument="--max_mash_dist" type="float" min="0" max="0.2" - value="0.02" label="Max Mash distance" - help="If any of the sequences have a pairwise Mash distance of more than this (default = 0.02), then the contigs will fail the initial check." /> - <param argument="--max_length_diff" type="float" min="1" max="2" - value="1.1" label="Max relative length factor" - help="If any of the sequences have a pairwise relative length factor of more than this, then the contigs will fail the initial check. For example, if set to 1.1 (the default), then no contig can be more than 10% longer than any other." /> + <param name="input_cluster" type="data" format="fasta" label="Cluster multi-FASTA dataset" help="The input should be an independent cluster generated by the *trycycler cluster* tool" /> + <param name="reads" type="data" format="fastq,fastq.gz" label="Long-read datasets" help="Long reads (FASTQ format) used to generate the assemblies" /> + <param argument="--linear" type="boolean" truevalue="--linear" falsevalue="" label="Input contigs are not circular" help="Use this option if your input contigs are not circular. It will disable the circularisation-correction steps in Trycycler reconcile." /> + <section name='initial_ckeck' title='Reconcile initial check options' expanded='true'> + <param argument="--max_mash_dist" type="float" min="0" max="0.2" value="0.02" label="Max Mash distance" help="If any of the sequences have a pairwise Mash distance of more than this (default = 0.02), then the contigs will fail the initial check." /> + <param argument="--max_length_diff" type="float" min="1" max="2" value="1.1" label="Max relative length factor" help="If any of the sequences have a pairwise relative length factor of more than this, then the contigs will fail the initial check. For example, if set to 1.1 (the default), then no contig can be more than 10% longer than any other." /> </section> - <section name="circularisation" - title="Reconcile circularization options" - expanded='true'> - <param argument="--max_add_seq" type="integer" min="0" max="4000" - value="1000" label="Max number of pb to add to circularize" - help="If they are set to 1000, then Trycycler will be willing to add up to 1000 bp to circularise it. Any contig which requires more than 1000 bp added to circularise will cause Trycycler reconcile to fail." /> - <param argument="--max_add_seq_percent" type="integer" min="0" max="10" - value="5" label="Max percentage of a contig length to add to circularize" - help="If they are set to 5, then Trycycler will be willing to add up to 5% of a contig's length to circularise it. Any contig which requires more than 5% of its length added to circularise will cause Trycycler reconcile to fail." /> - <param argument="--max_trim_seq" type="integer" min="0" max="100000" - value="50000" label="Max number of pb to trim to circularize" - help="If they are set to 50000, then Trycycler will be willing to remove up to 5000 bp to circularise it. Any contig which requires more than 5000 bp removed to circularise will cause Trycycler reconcile to fail." /> - <param argument="--max_trim_seq_percent" type="integer" min="0" max="20" - value="10" label="Max percentage of a contig length to trim to circularize" - help="If they are set to 10, then Trycycler will be willing to remove up to 10% of a contig's length to circularise it. Any contig which requires more than 10% of its length removed to circularise will cause Trycycler reconcile to fail." /> + <section name="circularisation" title="Reconcile circularization options" expanded='true'> + <param argument="--max_add_seq" type="integer" min="0" max="4000" value="1000" label="Max number of pb to add to circularize" help="If they are set to 1000, then Trycycler will be willing to add up to 1000 bp to circularise it. Any contig which requires more than 1000 bp added to circularise will cause Trycycler reconcile to fail." /> + <param argument="--max_add_seq_percent" type="integer" min="0" max="10" value="5" label="Max percentage of a contig length to add to circularize" help="If they are set to 5, then Trycycler will be willing to add up to 5% of a contig's length to circularise it. Any contig which requires more than 5% of its length added to circularise will cause Trycycler reconcile to fail." /> + <param argument="--max_trim_seq" type="integer" min="0" max="100000" value="50000" label="Max number of pb to trim to circularize" help="If they are set to 50000, then Trycycler will be willing to remove up to 5000 bp to circularise it. Any contig which requires more than 5000 bp removed to circularise will cause Trycycler reconcile to fail." /> + <param argument="--max_trim_seq_percent" type="integer" min="0" max="20" value="10" label="Max percentage of a contig length to trim to circularize" help="If they are set to 10, then Trycycler will be willing to remove up to 10% of a contig's length to circularise it. Any contig which requires more than 10% of its length removed to circularise will cause Trycycler reconcile to fail." /> </section> - <section name="final_check" - title="Reconcile final check" - expanded="true"> - <param argument="--min_identity" type="integer" min="70" max="100" - value="98" label="Min global alignment percentage identity" - help="If any of the sequences have a pairwise global alignment percent identity of less than this (default = 98), then the contigs will fail the final check." /> - <param argument="--max_indel_size" type="integer" min="100" max="400" - value="250" label="Max alignment indel size" - help="If any of the sequences have a pairwise alignment indel size of more than this (default = 250), then the contigs will fail the final check." /> + <section name="final_check" title="Reconcile final check" expanded="true"> + <param argument="--min_identity" type="integer" min="70" max="100" value="98" label="Min global alignment percentage identity" help="If any of the sequences have a pairwise global alignment percent identity of less than this (default = 98), then the contigs will fail the final check." /> + <param argument="--max_indel_size" type="integer" min="100" max="400" value="250" label="Max alignment indel size" help="If any of the sequences have a pairwise alignment indel size of more than this (default = 250), then the contigs will fail the final check." /> </section> - <section name="msa" - title="Multiple sequence alignment (MSA) options" - expanded="true"> - <param argument="--kmer" type="integer" min="20" max="45" - value="32" label="k-mer size" - help="The k-mer size used for sequence partitioning (default = 32)" /> - <param argument="--step" type="integer" min="500" max="1500" - value="1000" label="Step size" - help="The step size used for sequence partitioning (default = 1000)." /> - <param argument="--lookahead" type="integer" min="500" max="1500" - value="1000" label="Look-ahead margin" - help="The look-ahead margin used for sequence partitioning (default = 10000)." /> + <section name="msa" title="Multiple sequence alignment (MSA) options" expanded="true"> + <param argument="--kmer" type="integer" min="20" max="45" value="32" label="k-mer size" help="The k-mer size used for sequence partitioning (default = 32)" /> + <param argument="--step" type="integer" min="500" max="1500" value="1000" label="Step size" help="The step size used for sequence partitioning (default = 1000)." /> + <param argument="--lookahead" type="integer" min="500" max="1500" value="1000" label="Look-ahead margin" help="The look-ahead margin used for sequence partitioning (default = 10000)." /> </section> - + </inputs> <outputs> - <data name="reconciled_cluster" format="fasta" label="Trycycler reconcile on ${input_cluster.element_identifier}" from_work_dir="selected_cluster"/> - <data name="aligned_cluster" format="fasta" label="Trycycler msa on ${input_cluster.element_identifier}" from_work_dir="selected_clusters"/> + <data name="reconciled_cluster" format="fasta" label="Trycycler reconcile on ${input_cluster.element_identifier}" from_work_dir="selected_cluster" /> + <data name="aligned_cluster" format="fasta" label="Trycycler msa on ${input_cluster.element_identifier}" from_work_dir="selected_clusters" /> </outputs> <tests> <test> - <param name='input_cluster' value='cluster_01.fasta'/> - <param name="reads" value="reads.fastq.gz"/> - <output name='reconciled_cluster' file='reconciled_cluster_01.fasta'/> - <output name='aligned_cluster' file='aligned_cluster_01.fasta'/> + <param name='input_cluster' value='cluster_01.fasta' /> + <param name="reads" value="reads.fastq.gz" /> + <output name='reconciled_cluster' file='reconciled_cluster_01.fasta' /> + <output name='aligned_cluster' file='aligned_cluster_01.fasta' /> </test> <test> - <param name='input_cluster' value='cluster_01.fasta'/> - <param name="reads" value="reads.fastq.gz"/> + <param name='input_cluster' value='cluster_01.fasta' /> + <param name="reads" value="reads.fastq.gz" /> <section name="initial_check"> - <param name="max_mash_dist" value="0.3"/> + <param name="max_mash_dist" value="0.3" /> </section> <section name="circularisation"> - <param name="max_add_seq_percent" value="7"/> - <param name="max_trim_seq" value="47000"/> + <param name="max_add_seq_percent" value="7" /> + <param name="max_trim_seq" value="47000" /> </section> <section name="final_check"> - <param name="max_indel_size" value="230"/> + <param name="max_indel_size" value="230" /> </section> <section name="msa"> - <param name="kmer" value="30"/> - </section> - <output name='reconciled_cluster' file='reconciled_cluster_02.fasta'/> - <output name='aligned_cluster' file='aligned_cluster_02.fasta'/> + <param name="kmer" value="30" /> + </section> + <output name='reconciled_cluster' file='reconciled_cluster_02.fasta' /> + <output name='aligned_cluster' file='aligned_cluster_02.fasta' /> </test> <test> - <param name='input_cluster' value='cluster_01.fasta'/> - <param name="reads" value="reads.fastq.gz"/> + <param name='input_cluster' value='cluster_01.fasta' /> + <param name="reads" value="reads.fastq.gz" /> <section name="initial_check"> - <param name="max_mash_dist" value="0.3"/> + <param name="max_mash_dist" value="0.3" /> </section> <section name="circularisation"> - <param name="max_add_seq" value="900"/> - <param name="max_trim_seq" value="45000"/> + <param name="max_add_seq" value="900" /> + <param name="max_trim_seq" value="45000" /> </section> <section name="final_check"> - <param name="min_identity" value="97"/> + <param name="min_identity" value="97" /> </section> <section name="msa"> - <param name="step" value="1100"/> - </section> - <output name='reconciled_cluster' file='reconciled_cluster_03.fasta'/> - <output name='aligned_cluster' file='aligned_cluster_03.fasta'/> + <param name="step" value="1100" /> + </section> + <output name='reconciled_cluster' file='reconciled_cluster_03.fasta' /> + <output name='aligned_cluster' file='aligned_cluster_03.fasta' /> </test> <test> - <param name='input_cluster' value='cluster_01.fasta'/> - <param name="reads" value="reads.fastq.gz"/> + <param name='input_cluster' value='cluster_01.fasta' /> + <param name="reads" value="reads.fastq.gz" /> <section name="initial_check"> - <param name="max_length_diff" value="1.2"/> + <param name="max_length_diff" value="1.2" /> </section> <section name="circularisation"> - <param name="max_add_seq" value="920"/> - <param name="max_trim_seq_percent" value="12"/> + <param name="max_add_seq" value="920" /> + <param name="max_trim_seq_percent" value="12" /> </section> <section name="final_check"> - <param name="min_identity" value="95"/> - <param name="max_indel_size" value="230"/> + <param name="min_identity" value="95" /> + <param name="max_indel_size" value="230" /> </section> <section name="msa"> - <param name="kmer" value="33"/> - </section> - <output name='reconciled_cluster' file='reconciled_cluster_04.fasta'/> - <output name='aligned_cluster' file='aligned_cluster_04.fasta'/> + <param name="kmer" value="33" /> + </section> + <output name='reconciled_cluster' file='reconciled_cluster_04.fasta' /> + <output name='aligned_cluster' file='aligned_cluster_04.fasta' /> </test> <test> - <param name='input_cluster' value='cluster_01.fasta'/> - <param name="reads" value="reads.fastq.gz"/> + <param name='input_cluster' value='cluster_01.fasta' /> + <param name="reads" value="reads.fastq.gz" /> <section name="initial_check"> - <param name="max_mash_dist" value="0.3"/> + <param name="max_mash_dist" value="0.3" /> </section> <section name="circularisation"> - <param name="max_add_seq_percentage" value="8"/> - <param name="max_trim_seq" value="45300"/> + <param name="max_add_seq_percentage" value="8" /> + <param name="max_trim_seq" value="45300" /> </section> <section name="final_check"> - <param name="min_identity" value="97"/> + <param name="min_identity" value="97" /> </section> <section name="msa"> - <param name="step" value="1100"/> - <param name="lookahead" value="980"/> - </section> - <output name='reconciled_cluster' file='reconciled_cluster_05.fasta'/> - <output name='aligned_cluster' file='aligned_cluster_05.fasta'/> + <param name="step" value="1100" /> + <param name="lookahead" value="980" /> + </section> + <output name='reconciled_cluster' file='reconciled_cluster_05.fasta' /> + <output name='aligned_cluster' file='aligned_cluster_05.fasta' /> </test> - + </tests> <help><![CDATA[ @@ -250,6 +213,6 @@ .. class:: infomark @PIPELINE@ - ]]></help> - <expand macro='citations'/> + ]]> </help> + <expand macro='citations' /> </tool>