--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/ct_check_labels.xml	Fri Nov 27 13:37:20 2020 +0000
@@ -0,0 +1,45 @@
+<tool id="ct_check_labels" name="Cell types - check labels" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@">
+     <description>filters non-alphanumeric characters from labels</description>
+    <macros>
+        <import>ct_macros.xml</import>
+    </macros>
+    <expand macro="requirements" />
+    <command detect_errors="exit_code"><![CDATA[
+
+        check_labels.R --input-file "${input_file}"  --condensed "${condensed}" --attribute-type-col-num "${attribute_type_col_num}" --variable-col-num "${variable_col_num}" --avoid-lowercase "${avoid_lowercase}" --output-path "${output_path}"
+
+        #if $label_field
+        --label-field "${label_field}"
+        #end if
+
+        ]]></command>
+        <inputs>
+            
+            <param type="data" name="input_file" label="Input File" multiple="true" format="txt" help="Input metadta file" />
+            <param type="text" name="label_field" label="Label Field" optional="true" help="Name of label field in metadata file">
+                <expand macro="sanitize_strings" />
+            </param>
+            <param type="boolean" name="condensed" checked="false" label="Condensed Metadata File" help="Are the supplied metadata files of condensed format?" /> 
+            <param type="integer" name="attribute_type_col_num" value='5' label="Number of Attribute Type Column" help="Number of the attribute type field in condensed metadata file. Default: 5" />
+            <param type="integer" name="variable_col_num" value='6' label="Number of Label Column" help="Number of the label field in condensed metadata file. Default: 6" />
+            <param type="boolean" name="avoid_lowercase" checked="false" label="Avoid Lowercaase" help="Should setting the labels to lowercase be skipped? Default: False" /> 
+
+        </inputs>
+        <outputs>
+            <data name="output_path" format="txt" />
+        </outputs>
+        <tests>
+        <test>
+            <param name="input_file" value="SDRFs/E-ENAD-27.condensed-sdrf.tsv" />
+            <param name="label_field" value="inferred cell type" />
+            <param name="condensed" value="TRUE" />
+            <output name="output_path" file="checked_SDRF.tsv" compare="sim_size" />
+        </test>
+    </tests>
+        <help><![CDATA[
+    @HELP@
+    
+    @VERSION_HISTORY@
+    ]]></help>
+    <expand macro="citations" />
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/ct_macros.xml	Fri Nov 27 13:37:20 2020 +0000
@@ -0,0 +1,65 @@
+<macros>
+    <token name="@TOOL_VERSION@">1.1.1</token>
+    <token name="@HELP@">More information can be found at https://github.com/ebi-gene-expression-group/cell-types-analysis</token>
+    <token name="@PROFILE@">18.01</token>
+    <xml name="requirements">
+      <requirements>
+        <requirement type="package" version="0.1.9">cell-types-analysis</requirement>
+            <yield/>
+      </requirements>
+    </xml>
+    <xml name="version">
+      <version_command><![CDATA[
+        conda list | grep cell-types-analysis | egrep -o [0-9]\.[0-9]\.[0-9]
+    ]]></version_command>
+    </xml>
+    <token name="@VERSION_HISTORY@"><![CDATA[
+**Version history**
+0.1.6+galaxy0: Add removing non-alphanumeric characters from labels in metadata files
+0.0.5+galaxy0: Initial contribution. Andrey Solovyev, Expression Atlas team https://www.ebi.ac.uk/gxa/home at EMBL-EBI https://www.ebi.ac.uk/.
+0.0.5+galaxy1: Standardise input/output format into .txt. 
+    ]]></token>
+    <xml name="sem_siml_options">
+      <param type="select" name="sem_siml_metric" label="Semantic similarity metric"  help="What semantic similarity metric should be used? NB: if include-sem-siml is set to True, make sure to use a metric that is in the [0;1] interval. See https://www.bioconductor.org/packages/release/bioc/html/Onassis.html for more detail.">
+            <option value="lin" selected="true">lin</option>
+            <option value="jaccard">jaccard</option>
+            <option value="jc_norm">jc_norm</option>
+            <option value="schlicker">schlicker</option>
+            <option value="edge_resnik">edge_resnik</option>
+            <option value="sim">sim</option>
+            <option value="edge_leachod">edge_leachod</option>
+            <option value="edge_slimani">edge_slimani</option>
+            <option value="edge_wupalmer">edge_wupalmer</option>
+            <option value="edge_rada_lca">edge_rada_lca</option>
+            <option value="edge_li">edge_li</option>
+            <option value="resnik">resnik</option>
+        </param>
+    </xml>
+    <xml name="sanitize_strings">
+        <sanitizer invalid_char="">
+        <valid initial="string.ascii_letters,string.digits">
+            <add value="_" />
+            <add value="-" />
+            <add value="[" />
+            <add value="]" />
+            <add value=" " />
+            </valid>
+    </sanitizer>
+    </xml>
+    <xml name="citations">
+      <citations>
+        <citation type="bibtex">
+          @misc{github-cell-types-analysis.git,
+            author = {Andrey Solovyev, EBI Gene Expression Team},
+            year = {2020},
+            title = {Suite of scripts for analysis of scRNA-seq cell type classification tool outputs},
+            publisher = {GitHub},
+            journal = {GitHub repository},
+            url = {https://github.com/ebi-gene-expression-group/cell-types-analysis.git},
+          }
+        </citation>
+        <citation type="doi">10.1101/2020.04.08.032698</citation>
+        <yield />
+      </citations>
+    </xml>
+</macros>