Mercurial > repos > ebi-gxa > garnett_train_classifier
changeset 1:2067ebe66b55 draft
"planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/ commit 241c850301f8094f6aa0016e2335a8b550c29aed"
author | ebi-gxa |
---|---|
date | Fri, 24 Apr 2020 11:22:40 -0400 |
parents | 24a22971dd44 |
children | e7bb0bf34f26 |
files | garnett_macros.xml garnett_train_classifier.xml |
diffstat | 2 files changed, 30 insertions(+), 8 deletions(-) [+] |
line wrap: on
line diff
--- a/garnett_macros.xml Wed Apr 08 06:28:28 2020 -0400 +++ b/garnett_macros.xml Fri Apr 24 11:22:40 2020 -0400 @@ -4,7 +4,7 @@ <token name="@PROFILE@">18.01</token> <xml name="requirements"> <requirements> - <requirement type="package" version="0.0.3">garnett-cli</requirement> + <requirement type="package" version="0.0.5">garnett-cli</requirement> <yield/> </requirements> </xml> @@ -21,7 +21,7 @@ <citations> <citation type="bibtex"> @article{, - url = {https://doi.org/10.1038/s41592-019-0535-3}, + url = {https://doi.org/10.1038/s41592-019-0535-3}, author = {Hannah A. Pliner and Jay Shendure and Cole Trapnell}, title = {Supervised classification enables rapid annotation of cell atlases}, journal = {Nature Methods} @@ -38,7 +38,7 @@ } </citation> <yield /> + <citation type="doi">10.1101/2020.04.08.032698</citation> </citations> </xml> </macros> -
--- a/garnett_train_classifier.xml Wed Apr 08 06:28:28 2020 -0400 +++ b/garnett_train_classifier.xml Fri Apr 24 11:22:40 2020 -0400 @@ -5,12 +5,37 @@ </macros> <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ - garnett_train_classifier.R --cds-object '${cds_object}' --marker-file-path '${marker_file_path}' --database '${database}' --cds-gene-id-type '${cds_gene_id_type}' --marker-file-gene-id-type '${marker_file_gene_id_type}' --num-unknown '${num_unknown}' --min-observations '${min_observations}' --max-training-samples '${max_training_samples}' --propogate-markers '${propogate_markers}' --cores '${cores}' --classifier-gene-id-type '${classifier_gene_id_type}' --output-path '${output_classifier_path}' + garnett_train_classifier.R --cds-object '${cds_object}' --marker-file-path '${marker_file_path}' --database '${database}' --cores \${GALAXY_SLOTS:-1} --output-path '${output_classifier_path}' + #if $train_id + --train-id '${train_id}' + #end if + #if $cds_gene_id_type + --cds-gene-id-type '${cds_gene_id_type}' + #end if + #if $marker_file_gene_id_type + --marker-file-gene-id-type '${marker_file_gene_id_type}' + #end if + #if $num_unknown + --num-unknown '${num_unknown}' + #end if + #if $min_observations + --min-observations '${min_observations}' + #end if + #if $max_training_samples + --max-training-samples '${max_training_samples}' + #end if + #if $propogate_markers + --propogate-markers '${propogate_markers}' + #end if + #if $classifier_gene_id_type + --classifier-gene-id-type '${classifier_gene_id_type}' + #end if ]]></command> <inputs> <param type="data" name="cds_object" label="CDS object" format="rdata" help="CDS object with expression data for training" /> <param type="data" name="marker_file_path" format="txt" label="Marker file path" help="File with marker genes specifying cell types. See https://cole-trapnell-lab.github.io/garnett/docs/#constructing-a-marker-file for specification of the file format" /> + <param type="text" name="train_id" label="Dataset ID" help="ID of the training dataset" /> <param type="text" name="database" label="gene database" value="org.Hs.eg.db" help="argument for Bioconductor AnnotationDb-class package used for converting gene IDs" /> <param type="text" name="cds_gene_id_type" label="CDS gene id type" value="ENSEMBL" help="Format of the gene IDs in your CDS object" /> <param type="text" name="marker_file_gene_id_type" label="Marker gene id type" value="ENSEMBL" help="Format of the gene IDs in your marker file" /> @@ -22,7 +47,6 @@ increases speed, but may hurt performance of the model." /> <param type="boolean" name="propogate_markers" checked="true" label="propogate markers" help="Should markers from child nodes of a cell type be used in finding representatives of the parent type?" /> - <param type="integer" name="cores" label="cores" value="1" help="The number of cores to use for computation" /> <param type="text" name="classifier_gene_id_type" label="Classifier gene ID type" value="ENSEMBL" help="The type of gene ID that will be used in the classifier. If possible for your organism, this should be 'ENSEMBL', which is the default." /> </inputs> <outputs> @@ -41,6 +65,4 @@ @VERSION_HISTORY@ ]]></help> <expand macro="citations" /> -</tool> - - +</tool> \ No newline at end of file