Merge pull request RECETOX#486 from RECETOX/wverastegui/issue482

Read RI from comments and add them to RI column field
zargham-ahmad · Feb 22, 2024 · de7fd09 · de7fd09
2 parents 45ad41f + 26ac471
commit de7fd09
Show file tree

Hide file tree

Showing 9 changed files with 179 additions and 7,413 deletions.
diff --git a/tools/riassigner/.shed.yml b/tools/riassigner/.shed.yml
@@ -13,3 +13,12 @@ repositories:
       - riassigner.xml
       - macros.xml
       - test-data
+  assign_ri_from_comment:
+    description: "Assign RI from Comment Field is a tool for assigning retention indices from the comment field in csv, tsv, parquet, or msp files."
+    long_description: |
+      "Assign RI from Comment Field is a tool for assigning retention indices from the comment field in csv, tsv, parquet, or msp files.
+      The tool will read RI from the comment field and assign them to the RI field."
+    include:
+      - riassigner_from_comment.xml
+      - macros.xml
+      - test-data
diff --git a/tools/riassigner/macros.xml b/tools/riassigner/macros.xml
@@ -1,19 +1,24 @@
 <macros>
-    <token name="@TOOL_VERSION@">0.3.4</token>
+    <token name="@TOOL_VERSION@">0.4.0</token>
     <xml name="creator">
         <creator>
             <person
                 givenName="Helge"
                 familyName="Hecht"
                 url="https://github.com/hechth"
                 identifier="0000-0001-6744-996X" />
+            <person
+                givenName="Wudmir"
+                familyName="Rojas"
+                url="https://github.com/wverastegui"
+                identifier="0000-0001-7036-9987" />
             <organization
                 url="https://www.recetox.muni.cz/"
                 email="[email protected]"
                 name="RECETOX MUNI" />
         </creator>
     </xml>
-
+ 
     <token name="@HELP@">
         <![CDATA[
         RIAssigner can be used to read data from .msp, .csv and .tsv files using matchms and pandas and to compute the

diff --git a/tools/riassigner/riassigner_from_comment.xml b/tools/riassigner/riassigner_from_comment.xml
@@ -0,0 +1,73 @@
+<tool id="riassigner_from_comment" name="RIAssigner init from comment" version="@TOOL_VERSION@+galaxy4" profile="21.09">
+    <description>Assign different retention indices from unstructured comment metadata</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="creator"/>
+
+    <xrefs>
+        <xref type="bio.tools">riassigner</xref>
+    </xrefs>
+
+    <requirements>
+        <requirement type="package" version="@TOOL_VERSION@">riassigner</requirement>
+    </requirements>
+
+    <command detect_errors="exit_code"><![CDATA[
+        python ${script} &&
+        mv results.${input.ext} ${output}
+        ]]>
+    </command>
+
+    <configfiles>
+        <configfile name="script">
+from RIAssigner.data import PandasData, MatchMSData
+#if $input.ext in ["csv", "tsv", "parquet"]
+query = PandasData('${input}', '${input.ext}', rt_unit="seconds")
+#else
+query = MatchMSData('${input}', '${input.ext}', rt_unit="seconds")
+#end if
+query.init_ri_from_comment('${format}')
+query.write('results.${input.ext}')
+        </configfile>
+    </configfiles>
+
+    <inputs>
+        <param name="input" type="data" format="csv,tsv,parquet,msp,mgf" label="Input File">
+            <help>
+                File with 'comment' metadata in which to assign the selected retention index type from 'comment' to 'retention_index'.
+            </help>
+        </param>
+        <param name="format" type="select" label="GC column type" help="Type of gas chromatographic column for which to set the retention index value">
+            <option value="SemiStdNP">Semi Standard Non-Polar</option>
+            <option value="StdNP">Standard Non-Polar</option>
+            <option value="StdPolar">Standard Polar</option>
+        </param>
+    </inputs>
+
+    <outputs>
+        <data format_source="input" name="output" label="${on_string} with ${format} RI"/>
+    </outputs>
+
+    <tests>
+        <test>
+            <param name="input" value="nist_to_ri_2mols_input.csv" ftype="csv"/>
+            <output name="output" file="nist_to_ri_2mols_output.csv" ftype="csv"/>
+        </test>
+        <test>
+            <param name="input" value="nist_ei_ms_2mols_input.msp" ftype="msp"/>
+            <output name="output" file="nist_ei_ms_2mols_output.msp" ftype="msp"/>
+        </test>
+    </tests>
+
+    <help><![CDATA[
+        This tool can be used to assign retention indices (RI) from the comment field in csv, tsv, parquet, or msp files.
+        The tool will read RI from the comment field and assign them to the RI field. The type of gas chromatographic column
+        for which to set the retention index value can be selected.
+    ]]></help>
+
+    <citations>
+        <citation type="doi">10.21105/joss.04337</citation>
+    </citations>
+</tool>
+
diff --git a/tools/riassigner/test-data/aplcms_aligned_peaks.csv b/tools/riassigner/test-data/aplcms_aligned_peaks.csv
diff --git a/tools/riassigner/test-data/nist_ei_ms_2mols_input.msp b/tools/riassigner/test-data/nist_ei_ms_2mols_input.msp
@@ -0,0 +1,40 @@
+NAME: Water
+FORMULA: H2O
+MW: 18
+CASNO: 7732185
+ID: 9
+COMMENT: SemiStdNP=317 StdNP=323/4/2 StdPolar=1053/14/2 ; NIST MS# 7, Seq# M67
+NUM PEAKS: 5
+STDINCHI: InChI=1S/H2O/h1H2
+SMILES: O
+16.0	8.99
+17.0	211.81
+18.0	999.0
+19.0	5.0
+20.0	3.0
+
+NAME: Methyl Alcohol
+FORMULA: CH4O
+MW: 32
+CASNO: 67561
+ID: 32
+COMMENT: SemiStdNP=354/16/10 StdNP=379/7/34 StdPolar=903/8/35 ; NIST MS# 229809, Seq# M1806
+NUM PEAKS: 16
+STDINCHI: InChI=1S/CH4O/c1-2/h2H,1H3
+SMILES: CO
+2.0	3.0
+12.0	2.0
+13.0	5.99
+14.0	15.99
+15.0	122.89
+16.0	1.0
+17.0	3.0
+18.0	6.99
+19.0	1.0
+28.0	44.96
+29.0	444.6
+30.0	63.94
+31.0	999.0
+32.0	742.33
+33.0	10.99
+34.0	1.0
diff --git a/tools/riassigner/test-data/nist_ei_ms_2mols_output.msp b/tools/riassigner/test-data/nist_ei_ms_2mols_output.msp
@@ -0,0 +1,43 @@
+FORMULA: H2O
+CASNO: 7732185
+ID: 9
+COMMENT: SemiStdNP=317 StdNP=323/4/2 StdPolar=1053/14/2 ; NIST MS# 7, Seq# M67
+SMILES: O
+COMPOUND_NAME: Water
+NOMINAL_MASS: 18
+INCHI: InChI=1S/H2O/h1H2
+RETENTION_INDEX: 317
+NUM PEAKS: 5
+16.0        8.99
+17.0        211.81
+18.0        999.0
+19.0        5.0
+20.0        3.0
+
+FORMULA: CH4O
+CASNO: 67561
+ID: 32
+COMMENT: SemiStdNP=354/16/10 StdNP=379/7/34 StdPolar=903/8/35 ; NIST MS# 229809, Seq# M1806
+SMILES: CO
+COMPOUND_NAME: Methyl Alcohol
+NOMINAL_MASS: 32
+INCHI: InChI=1S/CH4O/c1-2/h2H,1H3
+RETENTION_INDEX: 354
+NUM PEAKS: 16
+2.0         3.0
+12.0        2.0
+13.0        5.99
+14.0        15.99
+15.0        122.89
+16.0        1.0
+17.0        3.0
+18.0        6.99
+19.0        1.0
+28.0        44.96
+29.0        444.6
+30.0        63.94
+31.0        999.0
+32.0        742.33
+33.0        10.99
+34.0        1.0
+
diff --git a/tools/riassigner/test-data/nist_to_ri_2mols_input.csv b/tools/riassigner/test-data/nist_to_ri_2mols_input.csv
@@ -0,0 +1,3 @@
+casno,num_peaks,compound_name,retention_index,formula,id,comment,inchi,smiles,nominal_mass,
+7732185,5,Water,,H2O,9,"SemiStdNP=317 StdNP=323/4/2 StdPolar=1053/14/2 ; NIST MS# 7, Seq# M67",InChI=1S/H2O/h1H2,O,18
+67561,16,Methyl Alcohol,,CH4O,32,"SemiStdNP=354/16/10 StdNP=379/7/34 StdPolar=903/8/35 ; NIST MS# 229809, Seq# M1806","InChI=1S/CH4O/c1-2/h2H,1H3",CO,32
diff --git a/tools/riassigner/test-data/nist_to_ri_2mols_output.csv b/tools/riassigner/test-data/nist_to_ri_2mols_output.csv
@@ -0,0 +1,3 @@
+casno,num_peaks,compound_name,retention_index,formula,id,comment,inchi,smiles,nominal_mass,unnamed: 10
+7732185,5,Water,317.0,H2O,9,"SemiStdNP=317 StdNP=323/4/2 StdPolar=1053/14/2 ; NIST MS# 7, Seq# M67",InChI=1S/H2O/h1H2,O,18,
+67561,16,Methyl Alcohol,354.0,CH4O,32,"SemiStdNP=354/16/10 StdNP=379/7/34 StdPolar=903/8/35 ; NIST MS# 229809, Seq# M1806","InChI=1S/CH4O/c1-2/h2H,1H3",CO,32,