diff get_pubchem/get_pubchem_assays.xml @ 5:c2055dd1927b draft default tip

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/get_pubchem/get_pubchem_assays.xml	Thu Apr 24 13:19:33 2014 -0400
@@ -0,0 +1,68 @@
+<tool id="ctb_pubchem_download_assays" name="PubChem Assay Downloader" Version="0.1" >
+    <description>as canonical SMILES</description>
+    <command interpreter="python">
+        get_pubchem_assay.py 
+            -o $pubchem_assay_tsv
+            -p "\${GALAXY_SLOTS:-4}"
+            --white-list $white_list
+    </command>
+    <stdio>
+        <!-- Anything other than zero is an error -->
+        <exit_code range="1:" />
+        <exit_code range=":-1" />
+        <!-- In case the return code has not been set propery check stderr too -->
+        <regex match="Error:" />
+        <regex match="Exception:" />
+    </stdio>
+    <inputs>
+        <param name="white_list" type="select" multiple="true" label="Scoring matrix">
+            <option value="Active" selected="true">Active</option>
+            <option value="Inconclusive" selected="true">Inconclusive</option>
+            <option value="Inactive">Inactive</option>
+            <option value="Unspecified">Unspecified</option>
+            <option value="Probe">Probe</option>
+        </param>
+    </inputs>
+    <outputs>
+        <data format="tabular" name="pubchem_assay_tsv" />
+    </outputs>
+    <tests>
+    </tests>
+    <help>
+
+.. class:: infomark
+
+**What this tool does**
+
+This tool will fetch one PubChem_ Assay file after another and concatenating them.
+It is possible to optionally filter by PUBCHEM_ACTIVITY_OUTCOME.
+
+Columns in the result file:
+
+ - column 1: PubChem AID (assay id)
+ - column 1: PubChem SID (substance id)
+ - column 2: PubChem CID (compound id)
+ - column 3: PubChem Activity Outcome
+            1-Inactive
+            2-Active
+            3-Inconclusive
+            4-Unspecified
+            5-Probe
+ - column 4: PubChem activity score, the higher value, the more active
+ - column 5: Test result specific comment
+ - column 6 and beyond: All remaining columns starting from the 7th column are the TID "names" defined in the associated assay description given by the XML file under the corresponding Description/ directory. These "names" can also be found in the "Result Definitions" section of the assay summary page: e.g. http://pubchem.ncbi.nlm.nih.gov/assay/assay.cgi?aid=2244#aDefinitions
+
+
+
+.. _PubChem: http://pubchem.ncbi.nlm.nih.gov/
+
+-----
+
+.. class:: infomark
+
+**Output**
+
+The output will be one large SMILES file.
+  
+    </help>
+</tool>