Mercurial > repos > ebi-gxa > garnett_train_classifier

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/garnett_macros.xml	Wed Apr 08 06:28:28 2020 -0400
@@ -0,0 +1,44 @@
+<macros>
+    <token name="@TOOL_VERSION@">0.2.8</token>
+    <token name="@HELP@">More information can be found at https://cole-trapnell-lab.github.io/garnett/docs/</token>
+    <token name="@PROFILE@">18.01</token>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="0.0.3">garnett-cli</requirement>
+            <yield/>
+        </requirements>
+    </xml>
+    <xml name="version">
+        <version_command><![CDATA[
+        echo $(R --version | grep version | grep -v GNU)", garnett version" $(R --vanilla --slave -e "library(garnett); cat(sessionInfo()\$otherPkgs\$garnett\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
+        ]]></version_command>
+    </xml>
+    <token name="@VERSION_HISTORY@"><![CDATA[
+    **Version history**
+    0.2.8+galaxy0: Initial contribution. Andrey Solovyev, Expression Atlas team https://www.ebi.ac.uk/gxa/home at EMBL-EBI https://www.ebi.ac.uk/.
+    ]]></token>
+    <xml name="citations">
+        <citations>
+            <citation type="bibtex">
+                @article{,
+                url = {https://doi.org/10.1038/s41592-019-0535-3},
+                author = {Hannah A. Pliner and Jay Shendure and Cole Trapnell},
+                title = {Supervised classification enables rapid annotation of cell atlases},
+                journal = {Nature Methods}
+            }
+        </citation>
+            <citation type="bibtex">
+                @misc{githubgarnett-cli.git,
+                    author = {Andrey Solovyev, EBI Gene Expression Team},
+                    year = {2019},
+                    title = {garnett-cli: command line interface for Garnett tool},
+                    publisher = {GitHub},
+                    journal = {GitHub repository},
+                    url = {https://github.com/ebi-gene-expression-group/garnett-cli.git},
+                  }
+            </citation>
+            <yield />
+        </citations>
+    </xml>
+</macros>
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/garnett_train_classifier.xml	Wed Apr 08 06:28:28 2020 -0400
@@ -0,0 +1,46 @@
+<tool id="garnett_train_classifier" name="Garnett - train classifier" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@">
+    <description>Train classifier based on marker gene list</description>
+    <macros>
+        <import>garnett_macros.xml</import>
+    </macros>
+    <expand macro="requirements" />
+    <command detect_errors="exit_code"><![CDATA[
+        garnett_train_classifier.R --cds-object '${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}'
+    ]]></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="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" />
+        <param type="integer" name="num_unknown" value='500' label="number of outputs" help="Number of outgroups to compare against" />
+        <param type="integer" name="min_observations" value='8' label="Min num of observations" help="The minimum number of representative cells per
+        cell type required to include the cell type in the predictive model" />
+        <param type="integer" name="max_training_samples" value='500' label="Max num of training samples" help="The maximum number of representative cells per cell
+        type to be included in the model training. Decreasing this number
+        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>
+        <data name="output_classifier_path" format="rdata" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="cds_object" value="garnett_cds.rds" />
+            <param name="marker_file_path" value="markers_upd.txt" />
+            <output name="output_classifier_path" value="trained_classifier.rds" />
+        </test>
+    </tests>
+    <help><![CDATA[
+        @HELP@
+
+        @VERSION_HISTORY@
+    ]]></help>
+    <expand macro="citations" />
+</tool>
+
+