Merge pull request #497 from zargham-ahmad/qcxms_changes

QCxMS New Version
RECETOX · Mar 8, 2024 · 4018b84 · 4018b84
2 parents b33d814 + 9260390
commit 4018b84
Show file tree

Hide file tree

Showing 12 changed files with 198 additions and 36 deletions.
diff --git a/tools/qcxms/msp_out.sh b/tools/qcxms/msp_out.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-molname=`sed -n '2{p;q}'  TMPQCXMS/TMP.1/start.xyz`
+molname=`sed -n '1{p;q}'  molname.txt`
 kword=$(grep 'NPOINTS' result.jdx)
 num_peaks=$(echo "$kword" | sed 's/^[^=]*=//')
 echo `pwd`

diff --git a/tools/qcxms/qcxms_getres.xml b/tools/qcxms/qcxms_getres.xml
@@ -0,0 +1,75 @@
+<tool id="qcxms_getres" name="QCxMS get results" version="@TOOL_VERSION@+galaxy0" profile="22.09">
+    <description>Get result of the Production run to obtain a QCxMS simulated mass spectrum</description>
+
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="edam"/>
+    <expand macro="creator"/>
+    <expand macro="requirements"/>
+
+    <command detect_errors="exit_code"><![CDATA[
+        python3 '${get_res}' &&
+        /plotms_bin/PlotMS.v.6.2.0/plotms &&
+        sh ${__tool_directory__}/msp_out.sh
+    ]]></command>
+
+    <configfiles>
+        <configfile name="get_res">
+#set res_collection = str("', '").join([str($f) for $f in $res_files])
+
+with open('$mol', 'r') as file:
+    lines = file.readlines()
+    molname = lines[1]
+
+with open('molname.txt', 'w') as file:
+    file.write(molname)
+
+input_files = '$res_collection'
+output_file = 'tmpqcxms.res'
+
+with open(output_file, 'w') as output:
+    for file_path in input_files:
+        with open(file_path, 'r') as input_file:
+            output.write(input_file.read())
+
+        </configfile>
+    </configfiles>
+
+    <inputs>
+        <param type="data" name="mol" label="Molecule 3D structure [.xzy]" format="xyz" />
+        <param type="data_collection" collection_type="list" name="res_files" label="res files [.res]" format="txt,text"/>
+    </inputs>
+
+    <outputs>
+        <data name="msp_output" format="msp" from_work_dir="simulated_spectra.msp" label="simulated_spectra.msp generated by ${tool.name} on ${on_string}"/>
+    </outputs>
+
+    <tests>
+        <test>
+            <param name="mol" value="mol.xyz" ftype="xyz"/>
+            <param name="res_files">
+                <collection type="list">
+                  <element name="res_files_1" value="res_files/TMP.1_qcxms.txt" />
+                  <element name="res_files_2" value="res_files/TMP.2_qcxms.txt" />
+                  <element name="res_files_3" value="res_files/TMP.3_qcxms.txt" />
+                </collection>
+            </param>
+            <output name="msp_output" file="output.msp" ftype="msp"/>
+        </test>
+    </tests>
+
+    <help><![CDATA[
+        The QCxMS getres tool is used to simulate mass spectra for a given molecule. 
+        This tool take res and molecules files and generates simulated mass spectra.
+        ]]>
+    </help>
+
+    <citations>
+        <citation type="doi">10.1002/anie.201300158</citation>
+        <citation type="doi">10.1039/C4OB01668H</citation>
+        <citation type="doi">10.1021/jp5096618</citation>
+        <citation type="doi">10.1255/ejms.1313</citation>
+        <citation type="doi">10.1021/acs.jpca.6b02907</citation>
+    </citations>
+</tool>
diff --git a/tools/qcxms/qcxms_neutral_run.xml b/tools/qcxms/qcxms_neutral_run.xml
@@ -1,4 +1,4 @@
-<tool id="qcxms_neutral_run" name="QCxMS neutral run" version="@TOOL_VERSION@+galaxy0" profile="21.05">
+<tool id="qcxms_neutral_run" name="QCxMS neutral run" version="@TOOL_VERSION@+galaxy1" profile="22.09">
     <description>required as first step to prepare for the production runs</description>
 
     <macros>
@@ -56,10 +56,10 @@ rename_files_with_folder_name(path)
     </configfiles>
 
     <inputs>
-        <param type="data" name="mol" label="Molecule 3D structure [.xzy]" format="xyz,txt" />
+        <param type="data" name="mol" label="Molecule 3D structure [.xzy]" format="xyz" />
         <param name="QC_Level" type="select" display="radio" label="QC Method">
             <option value="xtb2" selected="true">GFN2-xTB</option>
-            <option value="xtb">GFN-xTB</option>
+            <option value="xtb1">GFN1-xTB</option>
         </param>
         <section name="keywords" title="Advanced method parameters" expanded="false" 
             help="List of advanced keywords to specify the method - for more information see [1].">
@@ -84,20 +84,20 @@ rename_files_with_folder_name(path)
             <filter>store_extended_output</filter>
         </data>
 
-        <collection name="coords1" format="txt" type="list" label="coords in files generated by ${tool.name} on ${on_string}" >
+        <collection name="coords1" format="txt" type="list" label="input in files generated by ${tool.name} on ${on_string}" >
             <discover_datasets pattern="(?P&lt;designation&gt;.+)\.in" format="txt" directory="TMPQCXMS" recurse="true"/>
         </collection>
-        <collection name="coords2" format="txt" type="list" label="coords start files generated by ${tool.name} on ${on_string}" >
+        <collection name="coords2" format="txt" type="list" label="input start files generated by ${tool.name} on ${on_string}" >
             <discover_datasets pattern="(?P&lt;designation&gt;.+)\.start" format="txt" directory="TMPQCXMS" recurse="true"/>
         </collection>
-        <collection name="coords3" format="txt" type="list" label="coords xyz files generated by ${tool.name} on ${on_string}" >
+        <collection name="coords3" format="txt" type="list" label="input xyz files generated by ${tool.name} on ${on_string}" >
             <discover_datasets pattern="(?P&lt;designation&gt;.+)\.xyz" format="txt" directory="TMPQCXMS" recurse="true"/>
         </collection>
     </outputs>
 
     <tests>
         <test expect_num_outputs="6">
-            <param name="mol" value="mol.xyz" ftype="txt"/>
+            <param name="mol" value="mol.xyz" ftype="xyz"/>
             <section name="keywords">
                 <param name="ntraj" value="2"/>
             </section>

diff --git a/tools/qcxms/qcxms_prod_run.xml b/tools/qcxms/qcxms_prod_run.xml
@@ -1,4 +1,4 @@
-<tool id="qcxms_production_run" name="QCxMS production run" version="@TOOL_VERSION@+galaxy1" profile="21.05">
+<tool id="qcxms_production_run" name="QCxMS production run" version="@TOOL_VERSION@+galaxy2" profile="22.09">
     <description>Production run to obtain a QCxMS simulated mass spectrum</description>
 
     <macros>
@@ -10,10 +10,7 @@
 
     <command detect_errors="exit_code"><![CDATA[
         python3 '${create_folder_structure}' &&
-        find TMPQCXMS/*/ -type d | xargs -I {} -P \${GALAXY_SLOTS:-1} sh -c 'cd {} && /qcxms_bin/qcxms --prod >> $log' &&
-        /qcxms_bin/getres &&
-        /plotms_bin/PlotMS.v.6.2.0/plotms &&
-        sh ${__tool_directory__}/msp_out.sh
+        (cd TMPQCXMS/*/ && /qcxms_bin/qcxms --prod) >> $log
     ]]></command>
 
     <environment_variables>
@@ -25,54 +22,50 @@
 import os
 import shutil
 
-#set in_collection = str("', '").join([str($f) for $f in $in_files])
-#set start_collection = str("', '").join([str($f) for $f in $start_files])
-#set xyz_collection = str("', '").join([str($f) for $f in $xyz_files])
+names = '$xyz_file.name'
+folder_name = names.split("_")[0]
 
-#set names = str("', '").join([str($f.name) for $f in $xyz_files])
-names = '$names'
-folder_names = [x.split("_")[0] for x in names]
-
-in_collection = '$in_collection'
-start_collection = '$start_collection'
-xyz_collection = '$xyz_collection'
 
 # Create a new output folder to store the result
 output_path = 'TMPQCXMS'
 os.makedirs(output_path, exist_ok=True)
 
-for folder_name, in_file, start_file, xyz_file in zip(folder_names, in_collection, start_collection, xyz_collection):
-    new_folder_path = os.path.join(output_path, folder_name)
-    os.makedirs(new_folder_path, exist_ok=True)
+new_folder_path = os.path.join(output_path, folder_name)
+os.makedirs(new_folder_path, exist_ok=True)
 
-    shutil.copy2(os.path.join(os.path.dirname(in_collection[0]), in_file), os.path.join(new_folder_path, 'qcxms.in'))
-    shutil.copy2(os.path.join(os.path.dirname(start_collection[0]), start_file), os.path.join(new_folder_path, 'qcxms.start'))
-    shutil.copy2(os.path.join(os.path.dirname(xyz_collection[0]), xyz_file), os.path.join(new_folder_path, 'start.xyz'))
+shutil.copy2(os.path.join(os.path.dirname('$in_file'), '$in_file'), os.path.join(new_folder_path, 'qcxms.in'))
+shutil.copy2(os.path.join(os.path.dirname('$start_file'), '$start_file'), os.path.join(new_folder_path, 'qcxms.start'))
+shutil.copy2(os.path.join(os.path.dirname('$xyz_file'), '$xyz_file'), os.path.join(new_folder_path, 'start.xyz'))
 
         </configfile>
     </configfiles>
 
     <inputs>
-        <param type="data_collection" collection_type="list" name="in_files" label="in files [.in]" format="in,txt,text"/>
-        <param type="data_collection" collection_type="list" name="start_files" label="start files [.start]" format="start,txt,text"/>
-        <param type="data_collection" collection_type="list" name="xyz_files" label="xyz files [.xyz]" format="xyz,txt,text"/>
+        <param type="data" name="in_file" label="in files [.in]" format="txt,text"/>
+        <param type="data" name="start_file" label="start files [.start]" format="txt,text"/>
+        <param type="data" name="xyz_file" label="xyz files [.xyz]" format="xyz,txt,text"/>
         <param name="store_extended_output" type="boolean" value="false" label="Store additional outputs" help="Output the logfile."/>
     </inputs>
 
     <outputs>
-        <data name="msp_output" format="msp" from_work_dir="simulated_spectra.msp" label="simulated_spectra.msp generated by ${tool.name} on ${on_string}"/>
-        <data name="log" format="txt" label="logfile of ${tool.name} on ${on_string}">
+        <data name="log" format="txt" label="logfile_of_${tool.id}_on_${on_string}">
             <filter>store_extended_output</filter>
         </data>
+        <data name="res_files" format="txt" from_work_dir="TMPQCXMS/*/qcxms.res" label="res files generated by ${tool.name} on ${on_string}"/>
     </outputs>
 
     <tests>
-        <test expect_failure="true"/>
+        <test expect_num_outputs="1">
+            <param name="in_file" value="TMP.1_qcxms_in.txt" ftype="txt"/>
+            <param name="start_file" value="TMP.1_qcxms_start.txt" ftype="txt"/>
+            <param name="xyz_file" value="TMP.1_start_xyz.txt" ftype="txt"/>
+            <output name="res_files" file="res_out.txt" ftype="txt"/>
+        </test>
     </tests>
 
     <help><![CDATA[
         The QCxMS production run tool is used to simulate mass spectra for a given molecule using the QCxMS (Quantum Chemistry by Mass Spectrometry) method. 
-        This tool generates simulated mass spectra based on the equilibrium structure of a molecule and allows you to perform QCxMS production runs.
+        This tool allows you to perform QCxMS production runs and generates res files which are further used by QCxMS get results tool to produce the simulated mass spectra.
         For detail information visit the documentation at https://xtb-docs.readthedocs.io/en/latest/qcxms_doc/qcxms_run.html#excecuting-the-production-runs
         ]]>
     </help>

diff --git a/tools/qcxms/test-data/TMP.1_qcxms_in.txt b/tools/qcxms/test-data/TMP.1_qcxms_in.txt
@@ -0,0 +1,7 @@
+
+            xtb2
+            ntraj  2
+            tmax  20.0 
+            tinit  500.0 
+            ieeatm  0.6
+
diff --git a/tools/qcxms/test-data/TMP.1_qcxms_start.txt b/tools/qcxms/test-data/TMP.1_qcxms_start.txt
@@ -0,0 +1,9 @@
+   1
+  0.23866896224151D+00
+  0.89173254224222D+04
+ -0.18091580000000D-03  0.53537546000000D-04  0.34508200000000D-04  0.50383142501519D+00
+  0.10322794000000D-03 -0.29410216000000D-03 -0.13830620000000D-03  0.50383142501512D+00
+ -0.12351298000000D-02  0.10941877000000D-02 -0.68662608000000D-03  0.10000000000000D+01
+  0.39194769000000D-04 -0.86113874000000D-03 -0.14824698000000D-03  0.99998640424089D+00
+  0.73344203000000D-03  0.11470574000000D-02 -0.89203254000000D-04  0.99998640424076D+00
+  0.13882303000000D-02 -0.37015395000000D-03  0.30430224000000D-03  0.99999999999989D+00
diff --git a/tools/qcxms/test-data/TMP.1_start_xyz.txt b/tools/qcxms/test-data/TMP.1_start_xyz.txt
@@ -0,0 +1,8 @@
+6
+6325
+C           -0.59857822001968       -0.02215985716365        0.13568410610374
+C            0.61205863904343       -0.05505705225983       -0.22393772541246
+H           -1.05122375889205        0.99067995917981        0.32453382107060
+H           -1.32624440512690       -0.87343794346470        0.13238115658175
+H            1.30113828028591        0.80217555351015       -0.27588079204055
+H            1.17175212384004       -1.04560876534258       -0.26477384393492
diff --git a/tools/qcxms/test-data/output.msp b/tools/qcxms/test-data/output.msp
@@ -0,0 +1,52 @@
+NAME: Lindane
+Num Peaks: 49
+95.953354 29.195388847147174971
+96.956708 0.668804095247536257
+96.959630 0.006270038392945652
+97.950404 18.872816291174281389
+97.960062 0.002090012797648551
+98.953758 0.408597509163542982
+98.956680 0.006270038392945652
+99.947454 3.027383551460257394
+99.957112 0.001045006398824275
+100.950808 0.060610371892150218
+100.953730 0.001045006398824275
+112.007977 100.000000000000000000
+113.011331 6.469344248109893947
+113.014253 0.062015503068284489
+114.005027 31.968992563911168503
+114.014685 0.191684279973595856
+114.017607 0.002818886409876120
+115.008381 2.170542578675819456
+115.011303 0.016913318459256720
+116.011735 0.056377728197522396
+116.014657 0.002818886409876120
+117.015089 0.002818886409876120
+121.969004 48.616737474503565863
+122.972358 2.314913873279450307
+122.975280 0.028382084687048212
+123.966054 31.214972837163390551
+123.975712 0.030155965625322630
+123.978634 0.003547760585881026
+124.969408 1.333958011267293520
+124.972330 0.010643281757643079
+125.963104 4.931387222118633673
+125.972762 0.017738802929405131
+126.966458 0.184483555628484647
+126.969380 0.005321640878821540
+127.969812 0.001773880292940513
+147.984654 75.667375851606607284
+148.988008 4.978153862789445938
+148.990930 0.042283303452986920
+149.981704 48.524317372305198148
+149.991362 0.157857662942868432
+149.994284 0.002818886691764789
+150.985058 3.038759966527995626
+150.987980 0.036645528018447289
+151.978754 7.912614881227955976
+151.988412 0.087385490521223547
+151.991334 0.005637773383529577
+152.982108 0.467935188781944900
+152.985030 0.002818886691764789
+153.985462 0.019732207867858554
+
diff --git a/tools/qcxms/test-data/res_files/TMP.1_qcxms.txt b/tools/qcxms/test-data/res_files/TMP.1_qcxms.txt
@@ -0,0 +1,5 @@
+ 0.0000000  1    1    1 1 1   17     1
+ 0.0000000  1    1    1 3 1   17     1
+ 0.0000000  1    1    2 2 1   17     1
+ 0.0000000  1    1    3 2 1   17     1
+ 1.0000000  1    1    4 1 3    1     6  6   6 17   2
diff --git a/tools/qcxms/test-data/res_files/TMP.2_qcxms.txt b/tools/qcxms/test-data/res_files/TMP.2_qcxms.txt
@@ -0,0 +1,6 @@
+ 0.0000000  1    2    1 2 1   17     1
+ 0.0000000  1    2    1 3 1   17     1
+ 0.0000000  1    2    1 4 1   17     1
+ 0.0000001  1    2    2 1 2    1     1 17   1
+ 0.0000000  1    2    2 3 1   17     1
+ 0.9999999  1    2    3 1 3    1     5  6   6 17   1
diff --git a/tools/qcxms/test-data/res_files/TMP.3_qcxms.txt b/tools/qcxms/test-data/res_files/TMP.3_qcxms.txt
@@ -0,0 +1,4 @@
+ 0.3707160  1    3    1 1 3    1     2  6   2 17   2
+ 0.0000000  1    3    1 3 1   17     1
+ 0.0000000  1    3    2 2 1   17     1
+ 0.6292840  1    3    3 1 3    1     4  6   4 17   2
diff --git a/tools/qcxms/test-data/res_out.txt b/tools/qcxms/test-data/res_out.txt
@@ -0,0 +1,3 @@
+ 0.2874820  1    1    1 2 1    1     1
+ 0.2874820  1    1    1 3 1    1     1
+ 0.4250359  1    1    2 1 2    1     2  6   2