Qcxms

tools/qcxms/.shed.yml

@@ -0,0 +1,22 @@
+name: QCxMS
+owner: recetox
+remote_repository_url: "https://github.com/RECETOX/galaxytools/tree/master/tools/qcxms"
+homepage_url: "https://github.com/grimme-lab/QCxMS"
+categories:
+  - Computational chemistry
+  - Molecular Dynamics
+description: "QCxMS is a quantum chemical (QC) based program that enables users to calculate mass spectra (MS) using Born-Oppenheimer Molecular Dynamics (MD)."
+long_description: |
+ "QCxMS is a quantum chemical (QC) based program that enables users to calculate mass spectra (MS) using Born-Oppenheimer Molecular Dynamics (MD).
+  It is the successor of the QCEIMS program, in which the EI part is exchanged to x (x=EI, CID) to account for the greater general applicability of the program.
+  The program was originally developed to calculate Electron Ionization (EI) mass spectra, 
+  in which a (typically 70 eV) electron beam is focused on a molecule in order to create an open-shell radical ion (uneven number of valence electrons).
+  This process not only ionizes the molecule, but simultaneously increases the internal energy of the species, which in turn leads to bond breaking, 
+  fragmentation, rearrangement, etc of the ion."
+auto_tool_repositories:
+  name_template: "{{ tool_id }}"
+  description_template: "{{ tool_name }} tool from the QCxMS package"
+suite:
+  name: suite_qcxms
+  description: tools from QCxMS are used for molecular geometry optimization and in silico calculation of mass spectra using quantum chemistry
+  type: repository_suite_definition

tools/qcxms/macros.xml

@@ -0,0 +1,26 @@
+<macros>
+    <token name="@TOOL_VERSION@">5.2.1</token>
+    <xml name="requirements">
+        <requirements>
+            <container type="docker">recetox/qcxms-docker:@TOOL_VERSION@</container>
+        </requirements>
+    </xml>
+    <xml name="edam">
+        <edam_topics>
+            <edam_topic>topic_3332</edam_topic>
+        </edam_topics>
+        <edam_operations>
+            <edam_operation>operation_0297</edam_operation>
+        </edam_operations>
+    </xml>
+
+    <xml name="creator">
+        <creator>
+            <yield/>
+            <organization
+                url="https://www.recetox.muni.cz/"
+                email="[email protected]"
+                name="RECETOX MUNI" />
+        </creator>
+    </xml>
+</macros>

tools/qcxms/msp_out.sh

@@ -0,0 +1,11 @@
+#!/bin/sh
+
+molname=`sed -n '2{p;q}'  TMPQCXMS/TMP.1/start.xyz`
+kword=$(grep 'NPOINTS' result.jdx)
+num_peaks=$(echo "$kword" | sed 's/^[^=]*=//')
+echo `pwd`
+sed -n '/PEAK/,/END/{/PEAK/!{/END/!p}}' result.jdx > temp.dat
+awk '{print $1, $2}' temp.dat > tempa.dat
+sed "1s/^/NAME: $molname\nNum Peaks: $num_peaks\n/" tempa.dat >> simulated_spectra.msp
+sed -i '$a\ ' simulated_spectra.msp
+rm temp.dat tempa.dat

tools/qcxms/qcxms_neutral_run.xml

@@ -0,0 +1,140 @@
+<tool id="qcxms_neutral_run" name="QCxMS neutral run" version="@TOOL_VERSION@+galaxy0" profile="21.05">
+    <description>required as first step to prepare for the production runs</description>
+
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+
+    <expand macro="edam"/>
+    <expand macro="creator"/>
+    <expand macro="requirements"/>
+
+    <command detect_errors="exit_code"><![CDATA[
+        ln -s '$mol' molecule.xyz &&
+        cat qcxms.in &&
+        /qcxms_bin/qcxms -i molecule.xyz >> '$log' &&
+        /qcxms_bin/qcxms -i molecule.xyz >> '$log' &&
+        python3 rename.py
+
+    ]]></command>
+
+    <environment_variables>
+        <environment_variable name="OMP_NUM_THREADS">1,2,1</environment_variable>
+    </environment_variables>
+
+    <configfiles>
+        <configfile filename="qcxms.in"><![CDATA[
+            ${QC_Level}
+            #if $keywords.ntraj
+            ntraj  ${keywords.ntraj}
+            #end if
+            tmax  ${keywords.tmax} 
+            tinit  ${keywords.tinit} 
+            ieeatm  ${keywords.ieeatm}]]>
+        </configfile>
+        <configfile filename="rename.py">
+import os
+
+def rename_files_with_folder_name(folder_path):
+    if not os.path.exists(folder_path):
+        print(f"The folder '{folder_path}' does not exist.")
+        return
+
+    for root, _, files in os.walk(folder_path):
+        for filename in files:
+            folder_name = os.path.basename(root)
+            new_filename = f"{folder_name}_{filename}"
+
+            old_path = os.path.join(root, filename)
+            new_path = os.path.join(root, new_filename)
+
+            os.rename(old_path, new_path)
+
+path = os.getcwd() + "/TMPQCXMS"
+rename_files_with_folder_name(path) 
+        </configfile>
+    </configfiles>
+
+    <inputs>
+        <param type="data" name="mol" label="Molecule 3D structure [.xzy]" format="xyz,txt" />
+        <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>
+        </param>
+        <section name="keywords" title="Advanced method parameters" expanded="false" 
+            help="List of advanced keywords to specify the method - for more information see [1].">
+            <param name="tmax" type="float" value="20.0" label="Maximum MD time (sampling) [ps]"
+            help="MD time for the mean-free-path (mfp) simulation in the EI mode. In the CID mode, this sets the number of time steps for the simulation 
+            after fragmentation during internal energy scaling (implicit run type). For the explicit run type, the time for the collision MDs is fixed at 50 fs * number_of_atoms."/>
+            <param name="tinit" type="float" value="500.0" label="Initial Temperature [K]"/>
+            <param name="ieeatm" type="float" value="0.6" label="Impact excess energy (IEE) per atom [eV/atom]" />
+            <param name="ntraj" type="integer" optional="true" min="2" label="Number of trajectories[#]" help="Default is 25 * no. of atoms if unspecified."/>
+        </section>
+        <param name="store_extended_output" type="boolean" value="false" label="Store additional outputs?" help="Output the logfile and generated trajectory."/>
+    </inputs>
+
+    <outputs>
+        <data name="qcxms_out" format="txt" from_work_dir="qcxms.gs" label="qcxms.gs generated by ${tool.name} on ${on_string}">
+            <filter>store_extended_output</filter>
+        </data>
+        <data name="trajectory" from_work_dir="trjM" format="txt" label="trajectories generated by ${tool.name} on ${on_string}">
+            <filter>store_extended_output</filter>
+        </data>
+        <data name="log" format="txt" label="logfile of ${tool.name} on ${on_string}">
+            <filter>store_extended_output</filter>
+        </data>
+
+        <collection name="coords1" format="txt" type="list" label="coords 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}" >
+            <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}" >
+            <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"/>
+            <section name="keywords">
+                <param name="ntraj" value="2"/>
+            </section>
+            <param name="store_extended_output" value="true"/>
+            <output_collection name="coords1" type="list" count="2"/>
+            <output_collection name="coords2" type="list" count="2"/>
+            <output_collection name="coords3" type="list" count="2"/>
+            <output name="qcxms_out">
+                <assert_contents>
+                    <has_size value="174613" delta="300"/>
+                </assert_contents>
+            </output>
+            <output name="trajectory">
+                <assert_contents>
+                    <has_size value="22150" delta="300"/>
+                </assert_contents>
+            </output>
+            <output name="log">
+                <assert_contents>
+                    <has_size value="10518" delta="300"/>
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+
+    <help><![CDATA[
+        The QCxMS Neutral Run tool serves as the first step in preparing for production runs. The tool execute neutral runs for mass 
+        spectrometry simulations using the GFN2-xTB and GFN-xTB quantum chemistry methods. For detail information visit the documentation 
+        at https://xtb-docs.readthedocs.io/en/latest/qcxms_doc/qcxms_run.html#excecuting-the-production-runs
+        ]]>
+    </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>

tools/qcxms/qcxms_prod_run.xml

@@ -0,0 +1,86 @@
+<tool id="qcxms_production_run" name="QCxMS production run" version="@TOOL_VERSION@+galaxy0" profile="21.05">
+    <description>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 '${create_folder_structure}' &&
+        find TMPQCXMS/*/ -type d | xargs -I {} -P 4 sh -c 'cd {} && /qcxms_bin/qcxms --prod >> $log' &&
+        /qcxms_bin/getres &&
+        /plotms_bin/PlotMS.v.6.2.0/plotms &&
+        sh ${__tool_directory__}/msp_out.sh
+    ]]></command>
+
+    <environment_variables>
+        <environment_variable name="OMP_NUM_THREADS">1,2,1</environment_variable>
+    </environment_variables>
+
+    <configfiles>
+        <configfile name="create_folder_structure">
+import os
+import shutil
+
+#set in_collection = str("', '").join([str($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 $xyz_files])
+
+#set names = str("', '").join([str($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)
+
+    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'))
+
+        </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 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}">
+            <filter>store_extended_output</filter>
+        </data>
+    </outputs>
+
+    <tests>
+    </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.
+        For detail information visit the documentation at https://xtb-docs.readthedocs.io/en/latest/qcxms_doc/qcxms_run.html#excecuting-the-production-runs
+        ]]>
+    </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>

tools/qcxms/test-data/mol.xyz

@@ -0,0 +1,20 @@
+18
+Lindane
+CL     -2.3574740887    0.2795224786    1.4453580379
+C      -1.5060254335   -0.0564753152   -0.1808833480
+C      -0.7409992814    1.1908990145   -0.6060928106
+C      -0.6154388189   -1.2913844585   -0.1359211653
+CL     -0.4997346103    1.0723730326   -2.4801609516
+C       0.6426193118    1.3751488924    0.0051864041
+CL     -1.5938731432   -2.7512128353    0.4462303221
+C       0.6645445824   -1.0841370821    0.6675278544
+CL      0.4618762434    2.1580321789    1.6895099878
+C       1.4344482422    0.0744384378    0.0415960811
+CL      1.6999230385   -2.6236054897    0.5561774969
+CL      3.0750505924    0.3596521318    0.8505522013
+H      -2.3252866268   -0.2277424186   -0.8540474772
+H      -1.3395941257    2.0737268925   -0.4863004684
+H      -0.3587814867   -1.5482350588   -1.1510624886
+H       1.1898183823    2.1143426895   -0.5496439934
+H       0.4745289683   -0.9351251125    1.7152343988
+H       1.6943985224   -0.1802178770   -0.9732601047