Mercurial > repos > iuc > raceid_main
diff raceid_main.xml @ 0:e01c989c7543 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/raceid commit 39918bfdb08f06862ca395ce58a6f5e4f6dd1a5e
| author | iuc |
|---|---|
| date | Sat, 03 Mar 2018 17:34:16 -0500 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/raceid_main.xml Sat Mar 03 17:34:16 2018 -0500 @@ -0,0 +1,404 @@ +<tool id="raceid_main" name="RaceID" version="@VERSION@.0"> + <description>Race ID pipeline for single-cell RNA analysis</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements" /> + + <command detect_errors="exit_code"><![CDATA[ + ## Filter + echo "Filtering" && + Rscript '@SCRIPT_DIR@/raceID_filter.R' '@SCRIPT_DIR@' '$rconf_source_filter' && + + ## Kmeans + echo "K-means" && + Rscript '@SCRIPT_DIR@/raceID_kmeans_heatmap.R' '@SCRIPT_DIR@' '$rconf_source_kmeans' && + + mkdir '${out_html.files_path}' && + mv plot_*.svg '${out_html.files_path}' && + + echo ' + <html><head></head> + <body> + <h1>RaceID k-means</title></h1><br /> + <h3>Gap statistic</h3> + <img src="plot_gap.svg" ><br /> + <h3>Jaccard Similarity</h3> + <img src="plot_jaccard.svg" ><br /> + <h3>Silhouette Plot</h3> + <img src="plot_silhouette.svg" ><br /> + <h3>Cluster Heatmap</h3> + <img src="plot_clustheatmap.svg" ><br /> + ' > '$out_html' && + + ## Outlier -- relies on kmeans + echo "Outlier" && + Rscript '@SCRIPT_DIR@/raceID_outlierdetect.R' '@SCRIPT_DIR@' '$rconf_source_outlier' && + + mv plot_*.svg '${out_html.files_path}' && + echo ' + <br/> + <h1>RaceID Outlier Detection</h1><br /> + <h3>Background</h3> + <img src="plot_background.svg" ><br /> + <h3>Sensitivity</h3> + <img src="plot_sensitivity.svg" ><br /> + <h3>Outlier Probability</h3> + <img src="plot_outlierprobs.svg" ><br /> + <h3>Final Heatmap</h3> + <img src="plot_finalheat.svg" ><br /> + ' >> '$out_html' && + + ## tSNE -- relies on kmeans and outlier + echo "tSNE" && + Rscript '@SCRIPT_DIR@/raceID_tsne.R' '@SCRIPT_DIR@' '$rconf_source_tsne' && + + ##mkdir '${out_html.files_path}' && + mv plot_*.svg '${out_html.files_path}' && + + echo ' + <br/> + <h1>RaceID tSNE</h1><br /> + <h3>Initial k-means clusters</h3> + <br /><img src="plot_initial.svg" > + <h3>Final clusters</h3> + <br /><img src="plot_final.svg" > + <h3>Labelled</h3> + <br /><img src="plot_labels.svg" > + <h3>Symbols</h3> + <br /><img src="plot_symbols.svg" > + ' >> '$out_html' && + + #if $section_tsne.genexp_select.use_gexpr == "Yes": + #for $gene_set in $section_tsne.genexp_select.geneset: + echo "<h3>Expression for: [${gene_set.genes.value}]</h3>" >> '$out_html' && + echo "<br /><img src=\"plot_${gene_set.genes.value}\" >" >> '$out_html' && + #end for + #end if + echo '</body></html>' >> '$out_html' + + ]]></command> + + <configfiles> + <configfile name="rconf_source_filter"> + count_matrix = '$section_filter.inp_count' + filtering = as.logical( '$section_filter.filtering.do_filter.value' ) + output_table = '$out_table_filter' + output_rdat = '@out_rdat_filter@' + + # Defaults + control_genes_filter=""; + c_mintotal = 3000; c_minexpr = 5; c_maxexpr = 500; c_minnumber = 1; + c_downsample = F; c_dsn = 1; c_rseed = 17000; + + #if $section_filter.filtering.do_filter.value == "T": + control_genes_filter = '$section_filter.filtering.remove_nonendog.value' + #if $section_filter.filtering.default_filtering_select.do_filter_defaults.value == "advanced_options": + c_mintotal = as.integer( '$section_filter.filtering.default_filtering_select.mintotal' ) + c_minexpr = as.integer( '$section_filter.filtering.default_filtering_select.minexpr' ) + c_maxexpr = as.integer( '$section_filter.filtering.default_filtering_select.maxexpr' ) + c_minnumber = as.integer( '$section_filter.filtering.default_filtering_select.minnumber' ) + #if $section_filter.filtering.default_filtering_select.dsn: + c_downsample = T; + c_dsn = as.integer( '$section_filter.filtering.default_filtering_select.dsn' ) + #end if + c_rseed = as.integer( '$section_filter.filtering.default_filtering_select.filter_rseed' ) + #end if + #end if + </configfile> + <configfile name="rconf_source_kmeans"> + sc = readRDS( '@inp_rdat_kmeans@' ) + output_rdat = '@out_rdat_kmeans@' + c_metric = 'pearson'; c_cln = 0; dogap = T; c_clustnr = 20; bgap = 50; + semethod = 'Tibs2001SEmax'; sefactor = .25; c_bootnr = 50; c_rseed = 17000; + + c_metric = '$section_kmeans.metric' + c_cln = as.integer( '$section_kmeans.cln' ) + dogap = as.logical( '$section_kmeans.gapstats.dogap.value' ) + #if $section_kmeans.gapstats.dogap.value == "T": + c_clustnr = as.integer( '$section_kmeans.gapstats.clustnr' ) + bgap = as.integer( '$section_kmeans.gapstats.bgap' ) + semethod = '$section_kmeans.gapstats.semethod.value' + sefactor = as.numeric( '$section_kmeans.gapstats.sefactor' ) + #end if + c_bootnr = as.integer( '$section_kmeans.bootnr' ) + c_rseed = as.integer( '$section_kmeans.kmeans_rseed' ) + + generate_final_rdata = T + </configfile> + <configfile name="rconf_source_outlier"> + sc = readRDS( '@inp_rdat_outlier@' ) + output_rdat = '@out_rdat_outlier@' + output_table= '$out_table_outlier' + # set defaults + c_outminc = 5; c_outlg = 2; c_probthr = 1e-3; c_outdistquant = 0.75; + + c_outminc = as.integer( '$section_outlier.outminc' ) + c_outlg = as.integer( '$section_outlier.outlg' ) + c_probthr = as.numeric( '$section_outlier.probthr' ) + c_outdistquant = as.numeric( '$section_outlier.probthr' ) + + generate_final_rdata = T + </configfile> + <configfile name="rconf_source_tsne" > + sc = readRDS( '@inp_rdat_tsne@' ) + output_rdat = '$out_rdat_tsne' # final output RData + regex_val = "" + c_rseed = '$section_tsne.tsne_rseed' + gene_sets = "" + #if $section_tsne.genexp_select.use_gexpr == 'Yes': + gene_sets = '#for $gns in $section_tsne.genexp_select.geneset# $gns.genes.value _split_ #end for#' + regex_val = '$section_tsne.genexp_select.regex' + #end if + final_rdata = T + </configfile> + </configfiles> + <!-- Filter --> + <inputs> + <section name="section_filter" title="Filtering and Normalisation" expanded="true" > + <param name="inp_count" type="data" format="tsv" label="Count matrix" help="A spreadsheet file with the first row indicating cell IDs, and the first column indicating transcript or gene IDs" /> + <conditional name="filtering" > + <param name="do_filter" type="select" label="Perform filtering?" > + <option value="T" selected="true" >Yes</option> + <option value="F" >No</option> + </param> + <when value="F" /> + <when value="T" > + <param name="remove_nonendog" type="text" label="Control gene name prefixes" help="If ERCC or other non-endogenous spike-in RNAs are within the data, please specify their prefixes (e.g. 'ERCC, HK00') in order to filter them out. (Leave blank if control genes were not used in the experiment.)" /> + <conditional name="default_filtering_select" > + <param name="do_filter_defaults" type="select" label="Parameters" > + <option value="use_defaults" selected="true" >Use Defaults</option> + <option value="advanced_options" >Advanced Options</option > + </param> + <when value="use_defaults" /> + <when value="advanced_options" > + <param name="mintotal" type="integer" value="3000" min="1" label="Minimum total transcripts" help="Discard cells with less than this number of total transcripts before normalisation." /> + <param name="minexpr" type="integer" value="5" min="1" label="Minimum expressed genes" help="Discard genes that do not express a minimum of this number of transcripts after normalisation."/> + <param name="maxexpr" type="integer" value="500" min="0" label="Maximum expressed genes" help="Discard genes that express more than this number of transcripts after normalisation. Useful if genes have oversaturated counts derived from UMI data. Set to 0 to disable this step." /> + + <param name="minnumber" type="integer" value="1" label="Minimum Cells" help="Discard genes that do not have the minimum expressed transcripts in at least this number of cells" /> + + <param name="dsn" type="integer" value="1" min="1" optional="true" label="Downsample counts" help="Average transcripts across this many samples. If this is set to 1, then sampling noise should be comparable across cells. For higher values, the data approximates median normalisation." /> + <param name="filter_rseed" type="integer" value="17000" min="0" label="Seed value (for reproducibility)" /> + </when> + </conditional> + </when> + </conditional> + <param name="filter_table_output" type="boolean" checked="false" label="Generate output table of filtered matrix?" /> + </section> + + <!-- Kmeans --> + <section name="section_kmeans" title="Clustering (k-means)" expanded="true" > + <param name="metric" type="select" label="Distance metric"> + <option value="pearson" selected="true" /> + <option value="spearman" /> + <option value="kendall" /> + <option value="euclidean" /> + <option value="maximum" /> + <option value="manhattan" /> + <option value="canberra" /> + <option value="binary" /> + <option value="minkowski" /> + </param> + + <param name="cln" type="integer" value="0" min="0" label="Number of clusters for k-means" help="Leave as zero to automatically determine the number based on gap statistics" /> + + <conditional name="gapstats"> + <param name="dogap" type="select" label="Use gap statistics to determine clusters" > + <option value="T" selected="true" >Yes</option> + <option value="F" >No</option> + </param> + + <when value="F" /> + <when value="T" > + <param name="clustnr" type="integer" value="2" min="0" label="Maximum number of clusters for the computation of the gap statistic" help="If more major cell types are expected, a higher number than 2 should bde chosen." /> + <param name="bgap" type="integer" value="50" min="1" label="Number of bootstraps to run the gap statistic calculation" /> + <param name="semethod" type="select" label="Method used for determining first local maximum" > + <option value="Tibs2001SEmax" selected="true" /> + <option value="globalmax" /> + <option value="firstmax" /> + <option value="firstSEmax" /> + <option value="globalSEmax" /> + </param> + + <param name="sefactor" type="float" value="0.25" min="0.0001" max="1" label="Fraction of the standard deviation that the local maximum must differ from neighbouring points." /> + </when> + </conditional> + + <param name="bootnr" type="integer" value="50" min="1" label="Number of bootstraps for clustering" /> + <param name="kmeans_rseed" type="integer" value="17000" min="1" label="Seed value (for reproducibility)" /> + </section> + <!-- Outlier --> + <section name="section_outlier" title="Outlier Detection" expanded="true" > + <param name="outminc" type="integer" value="5" min="1" label="Expression cutoff threshold for outlier genes" /> + <param name="probthr" type="float" value="1e-3" min="1e-8" max="1" label="Probability threshold of observing a given gene expression level in a cell" help="If lower than this cutoff, the cell is considered an outlier for this gene." /> + <param name="outlg" type="integer" value="2" min="1" label="Minimal number of outlier genes required to flag an outlier cells" /> + <param name="outdistquant" type="select" label="Merge cells into outlier clusters if their similarity exceeds this quantile in a similarity distribution for all cell pairs" > + <option value="0.25">first (0.25)</option> + <option value="0.50">second (0.50)</option> + <option value="0.75">third (0.75)</option> + </param> + </section> + <section name="section_tsne" title="tSNE plots" expanded="true" > + <!-- tSNE --> + <conditional name="genexp_select" > + <param name="use_gexpr" type="select" label="Highlight the expression of a set of (related) genes over all clusters?" > + <option value="Yes" /> + <option value="No" selected="true" /> + </param> + <when value="No" /> + <when value="Yes" > + <repeat name="geneset" title="Gene sets" > + <param name="genes" type="text" label="Gene(s) of interest" help="e.g. 'Apoa1__chr9+Apoa1bp__chr6'" > + <sanitizer invalid_char="" > + <valid initial="string.letters,string.digits"> + <add value="+" /><add value="_" /><add value="-" /> + </valid> + </sanitizer> + </param> + </repeat> + <param name="regex" type="text" value="" label="Regular expression to apply over cell labels to identify cell types" help="e.g. for barcodes [ cl_1_ACCAG, cl_1_ACGGA, cl_2_TTAC, ... ] can be grouped into [ cl_1, cl_2, ... ] by the expression: '_[ACTG]+', which removes the last '_' and any following characters belonging to A C T or G." > + <sanitizer invalid_char="" > + <valid initial="string.printable" /> + </sanitizer> + </param> + </when> + </conditional> + <param name="tsne_rseed" type="integer" min="1" value="15555" label="Seed (for reproducibility)" /> + </section> + </inputs> + + <outputs> + <!-- Filter --> + <data name="out_table_filter" format="tabular" label="${tool.name} on ${on_string}: Filter Table" > + <filter>section_filter['filtering']['do_filter'] == "T"</filter> + </data> + <!-- Outlier --> + <data name="out_table_outlier" format="tabular" label="${tool.name} on ${on_string}: Outliers" /> + <!-- TSNE --> + <data name="out_html" format="html" label="${tool.name} on ${on_string}: Web Report" /> + <data name="out_rdat_tsne" format="rdata" label="${tool.name} on ${on_string}: tSNE RData" /> + </outputs> + + <tests> + <!-- vanilla run on all but filter --> + <test> + <!-- Filter --> + <param name="inp_count" value="transcript_counts_intestine_sub.tsv" /> + <!-- These test params are MANDATORY due to the reduced size of the + input set (due to file size constraints) --> + <param name="do_filter" value="T" /> + <param name="do_filter_defaults" value="advanced_options" /> + <param name="mintotal" value="10" /> + <param name="minexpr" value="1" /> + <param name="maxexpr" value="2000" /> + <!-- Outlier --> + <!-- ... With reduced minc --> + <param name="inp_rdat_outlier" value="trans_outlier_in.rds" /> + <param name="outminc" value="1" /> + <output name="out_table_outlier" value="out_outlier1.table" /> + <!-- tSNE --> + <output name="out_html" value="out_1.html" /> + <output name="out_rdat_tsne" value="out_tsne1.rdat" /> + </test> + <!-- manual gap statistics --> + <test> + <!-- Filter --> + <param name="inp_count" value="transcript_counts_intestine_sub.tsv" /> + <param name="filter_table_output" value="T" /> + <!-- See message from previous test .. --> + <param name="do_filter" value="T" /> + <param name="do_filter_defaults" value="advanced_options" /> + <param name="mintotal" value="10" /> + <param name="minexpr" value="1" /> + <param name="maxexpr" value="2000" /> + <output name="out_table_filter" value="out_filter2.table" /> + <!-- Kmeans --> + <!-- ... Auto gap with gap params --> + <param name="inp_rdat_kmeans" value="trans_filter_ds.rds" /> + <param name="clustnr" value="5" /> + <param name="bgap" value="10" /> + <param name="semethod" value="globalSEmax" /> + <param name="sefactor" value="0.6" /> + <!-- Outlier --> + <!-- ... With reduced minc --> + <param name="inp_rdat_outlier" value="trans_outlier_in.rds" /> + <param name="outminc" value="1" /> + <output name="out_table_outlier" value="out_outlier2.table" /> + <!-- tSNE --> + <output name="out_html" value="out_2.html" /> + <output name="out_rdat_tsne" value="out_tsne2.rdat" /> + </test> + <!-- complex run --> + <test> + <!-- Filter --> + <param name="inp_count" value="transcript_counts_intestine_sub.tsv" /> + <param name="do_filter" value="T" /> + <param name="do_filter_defaults" value="advanced_options" /> + <param name="mintotal" value="10" /> + <param name="minexpr" value="1" /> + <param name="maxexpr" value="2000" /> + <param name="dsn" value="3" /> + <output name="out_table_filter" value="out_filter3.table" /> + <!-- Kmeans --> + <!-- ... Set k-value, no gap, no R obj, metrics and bootrepl. --> + <param name="inp_rdat_kmeans" value="trans_filter_ds.rds" /> + <param name="metric" value="manhattan" /> + <param name="cln" value="6" /> + <param name="dogap" value="T" /> + <param name="bootnr" value="10" /> + <!-- Outlier --> + <!-- ... No R out, other opts--> + <param name="inp_rdat_outlier" value="trans_outlier_in.rds" /> + <param name="outminc" value="1" /> + <param name="probthr" value="1e-5" /> + <param name="outlg" value="10" /> + <param name="outdistquant" value="0.50" /> + <output name="out_table_outlier" value="out_outlier3.table" /> + <!-- tSNE --> + <param name="use_gexpr" value="Yes" /> + <repeat name="geneset"> + <param name="genes" value="1110007C09Rik__chr13+1110037F02Rik__chr4+1300002K09Rik__chr4" /> + </repeat> + <repeat name="geneset"> + <param name="genes" value="0610010K14Rik__chr11+1500009L16Rik__chr10" /> + </repeat> + <param name="regex" value="[^_]+__" /> + <output name="out_html" value="out_3.html" /> + <output name="out_rdat_tsne" value="out_tsne3.rdat" /> + </test> + </tests> + + <help><![CDATA[ + +****** +RaceID +****** + +RaceID(v2) pipeline for scRNA, performs: + * filtering + * normalisation + * k-means clustering + * outlier detection + +Generates heatmaps, tSNE plots, and an R object which can be passed into the RaceID DiffGenes tool for expression analysis between different sets of clusters. + +**Filtering** + +This takes a count matrix/spreadsheet with cellIDs as columns and geneIDs/transcriptIDs as rows, and filters based on standard single-cell RNA pre-processing methods (minimum/maximum transcript expression in a minimum of X number of cells). A filtered matrix is produced as output + +**K-means Clustering** + +This performs k-means clustering and plots gap statistics, jaccard similarity, silhoutte plots, and preliminary heatmap. + +**Outlier Detection** + +This performs outlier detection by calibrating against a background noise model within each cluster, and searching for cells that fall outside of the transcript count distribution for that gene (modelled as a negative binomial). Cells that are outliers for more than a user-set amount of genes are suspected as being outlier cells. + +**tSNE plots** + +Generates multiple tSNE plots with custom expression highlighting for gene subsets of interest. A tSNE map can be drawn for original clusters (derived via k-means) and final clustering (derived from outliers). Any number of genes subsets of interest can be specified to measure expression within clusters for related marker genes or genes characterising a cell type. + + ]]></help> + <expand macro="citations" /> +</tool>