Mercurial > repos > bcclaywell > microbiome_pplacer_suite
changeset 8:35f9b833e12b draft default tip
planemo upload commit 2774930eebe258ecd56c8f1c5ddabf5092282ab9
author | bcclaywell |
---|---|
date | Mon, 12 Oct 2015 16:09:02 -0400 |
parents | b6ece07bec6a |
children | |
files | usearch-wrapper.sh usearch.xml |
diffstat | 2 files changed, 0 insertions(+), 74 deletions(-) [+] |
line wrap: on
line diff
--- a/usearch-wrapper.sh Mon Oct 12 15:59:59 2015 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,28 +0,0 @@ -#!/bin/bash - -source $(dirname $0)/util.sh -source $1 - -RDP_SEQS="/shared/silo_researcher/Matsen_F/MatsenGrp/micro_refset/rdp/10_31/tax_filter/filtered/rdp_10_31.filter.fasta" -RDP_SEQINFO="/shared/silo_researcher/Matsen_F/MatsenGrp/micro_refset/rdp/10_31/tax_filter/filtered/rdp_10_31.filter.seq_info.csv" - -sqlite3 -csv -header ${CLASS_DB} <<EOF > usearch_meta.csv -SELECT pn.name, CAST(pn.mass AS INT) count, tax_id, tax_name, taxa.rank - FROM multiclass_concat - JOIN taxa USING (tax_id) - JOIN placement_names pn USING (placement_id, name) - WHERE want_rank = 'species'; -EOF - -romp -v usearch_clusters \ - --usearch-quietly \ - --query-group tax_id \ - --query-duplication count \ - --database-name seqname \ - --database-group tax_id \ - ${INPUT_SEQS} \ - usearch_meta.csv \ - ${RDP_SEQS} \ - ${RDP_SEQINFO} \ - ${USEARCH_HITS} \ - ${USEARCH_GROUPS}
--- a/usearch.xml Mon Oct 12 15:59:59 2015 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,46 +0,0 @@ -<tool id="PHYLO_usearch" name="Analyze sequences" version="1.1.0"> - <description>with USEARCH</description> - <macros> - <import>macros.xml</import> - </macros> - <stdio> - <expand macro="basic_errors"/> - </stdio> - <version_command>/home/matsengrp/local/bin/usearch6_64 --version</version_command> - <command interpreter="bash"> - usearch-wrapper.sh $config - </command> - <inputs> - <param name="input_seqs" type="data" format="fasta" label="Input sequences"/> - <param name="class_db" type="data" format="sqlite3" label="Placement database"/> - </inputs> - <outputs> - <data format="csv" name="usearch_hits" label="USEARCH hits"/> - <data format="csv" name="usearch_groups" label="USEARCH groups"/> - </outputs> - <configfiles> - <configfile name="config"> -INPUT_SEQS="${input_seqs}" -CLASS_DB="${class_db}" - -USEARCH_HITS="${usearch_hits}" -USEARCH_GROUPS="${usearch_groups}" - </configfile> - </configfiles> - <!-- The contents of the help tag is parsed as reStructuredText. Please see - help-template.rst for examples of commonly-used sections in other Galaxy - tools. --> - <help> - -.. class:: infomark - -**What it does** - -This tool queries large sequence databases for target sequences and assigns -those sequences to clusters. - - </help> - <citations> - <expand macro="cite_usearch"/> - </citations> -</tool>