Mercurial > repos > ebi-gxa > garnett_train_classifier

comparison garnett_train_classifier.xml @ 0:24a22971dd44 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/ commit 4c3dfa7bbd82d702e7e8187c7556f3289804cb49"
author ebi-gxa
date Wed, 08 Apr 2020 06:28:28 -0400
parents
children 2067ebe66b55
comparison
equal deleted inserted replaced
-1:000000000000 0:24a22971dd44
1 <tool id="garnett_train_classifier" name="Garnett - train classifier" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@">
2 <description>Train classifier based on marker gene list</description>
3 <macros>
4 <import>garnett_macros.xml</import>
5 </macros>
6 <expand macro="requirements" />
7 <command detect_errors="exit_code"><![CDATA[
8 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}'
9 ]]></command>
10 <inputs>
11 <param type="data" name="cds_object" label="CDS object" format="rdata" help="CDS object with expression data for training" />
12 <param type="data" name="marker_file_path" format="txt" label="Marker file path" help="File with marker genes specifying cell types.
13 See https://cole-trapnell-lab.github.io/garnett/docs/#constructing-a-marker-file for specification of the file format" />
14 <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" />
15 <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" />
16 <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" />
17 <param type="integer" name="num_unknown" value='500' label="number of outputs" help="Number of outgroups to compare against" />
18 <param type="integer" name="min_observations" value='8' label="Min num of observations" help="The minimum number of representative cells per
19 cell type required to include the cell type in the predictive model" />
20 <param type="integer" name="max_training_samples" value='500' label="Max num of training samples" help="The maximum number of representative cells per cell
21 type to be included in the model training. Decreasing this number
22 increases speed, but may hurt performance of the model." />
23 <param type="boolean" name="propogate_markers" checked="true" label="propogate markers" help="Should markers from child nodes of a cell type be used
24 in finding representatives of the parent type?" />
25 <param type="integer" name="cores" label="cores" value="1" help="The number of cores to use for computation" />
26 <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." />
27 </inputs>
28 <outputs>
29 <data name="output_classifier_path" format="rdata" />
30 </outputs>
31 <tests>
32 <test>
33 <param name="cds_object" value="garnett_cds.rds" />
34 <param name="marker_file_path" value="markers_upd.txt" />
35 <output name="output_classifier_path" value="trained_classifier.rds" />
36 </test>
37 </tests>
38 <help><![CDATA[
39 @HELP@
40
41 @VERSION_HISTORY@
42 ]]></help>
43 <expand macro="citations" />
44 </tool>
45
46