matchms: added filters and test and fixed linter warnings

tools/export_to_path/export_to_path.xml

@@ -1,9 +1,9 @@
 <tool id="export_to_path" name="export to path" version="0.0.2">
+    <description>on a filesystem accessible to compute node</description>
     <macros>
         <import>macros.xml</import>
     </macros>
     <expand macro="creator"/>
-    <description>on a filesystem accessible to compute node</description>
     <requirements>
         <requirement type="package" version="3.6">python</requirement>
     </requirements>

tools/filter_compounds/filter_compounds.xml

@@ -44,5 +44,8 @@
             @HELP@
         ]]>
     </help>
+    <citations>
+        <citation type="doi">https://doi.org/10.5281/zenodo.6035335</citation>
+    </citations>
 </tool>
 

tools/matchms/matchms_filtering.xml

@@ -1,4 +1,4 @@
-<tool id="matchms_filtering" name="matchms filtering" version="@TOOL_VERSION@+galaxy0" profile="21.09">
+<tool id="matchms_filtering" name="matchms filtering" version="@TOOL_VERSION@+galaxy1" profile="21.09">
     <description>filter and normalize mass spectrometry data</description>
 
     <macros>
@@ -49,6 +49,16 @@
                 --from_mz "$mz_range.from_mz" \
                 --to_mz "$mz_range.to_mz" \
             #end if
+            #if $require_smiles.is_true
+                -require_smiles \
+            #end if
+            #if $require_inchi.is_true
+                -require_inchi \
+            #end if
+            #if $reduce_to_top_n_peaks.is_true
+                -reduce_to_top_n_peaks \
+                --n_max "$reduce_to_top_n_peaks.n_max" \
+            #end if
             --output "$output"
         </configfile>
     </configfiles>
@@ -59,16 +69,22 @@
         <conditional name="normalise_intensities">
             <param name="is_true" label="Normalize intensities" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false"
                    help="Normalize intensities of peaks (and losses) to unit height."/>
+            <when value="TRUE"></when>
+            <when value="FALSE"></when>
         </conditional>
 
         <conditional name="default_filters">
             <param name="is_true" label="Apply default filters" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false"
                    help="Collection of filters that are considered default and that do no require any (factory) arguments."/>
+            <when value="TRUE"></when>
+            <when value="FALSE"></when>
         </conditional>
 
         <conditional name="clean_metadata">
             <param name="is_true" label="Clean metadata" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false"
                    help="Apply all adding and cleaning filters if possible, so that the spectra have canonical metadata." />
+            <when value="TRUE"></when>
+            <when value="FALSE"></when>
         </conditional>
 
         <conditional name="relative_intensity">
@@ -78,6 +94,7 @@
                 <param label="Minimum intensity" name="from_intensity" value="0" type="float" help="Lower bound for intensity filter." />
                 <param label="Maximum intensity" name="to_intensity" value="1" type="float" help="Upper bound for intensity filter." />
             </when>
+            <when value="FALSE"></when>
         </conditional>
 
         <conditional name="mz_range">
@@ -87,6 +104,30 @@
                 <param label="Minimum m/z" name="from_mz" optional="true" type="float" help="Lower bound for m/z filter." />
                 <param label="Maximum m/z" name="to_mz" optional="true" type="float" help="Upper bound for m/z filter." />
             </when>
+            <when value="FALSE"></when>
+        </conditional>
+
+        <conditional name="require_smiles">
+            <param name="is_true" label="Require SMILES" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false"
+                   help="Remove spectra that does not contain SMILES." />
+            <when value="TRUE"></when>
+            <when value="FALSE"></when>
+        </conditional>
+
+        <conditional name="require_inchi">
+            <param name="is_true" label="Require INCHI" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false"
+                   help="Remove spectra that does not contain INCHI." />
+            <when value="TRUE"></when>
+            <when value="FALSE"></when>
+        </conditional>
+
+        <conditional name="reduce_to_top_n_peaks">
+            <param name="is_true" label="Reduce to top n peaks" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false"
+                   help="Lowest intensity peaks will be removed when it has more peaks than desired." />
+            <when value="TRUE">
+                <param label="Maximum number of peaks" name="n_max" value="5" type="integer" help="Maximum number of peaks. Remove peaks if more peaks are found." />
+            </when>
+            <when value="FALSE"></when>
         </conditional>
 
     </inputs>
@@ -135,6 +176,28 @@
             </section>
             <output name="output" file="filtering/mz_range.msp" ftype="msp"/>
         </test>
+        <test>
+            <param name="spectra" value="filtering/require_filter.msp" ftype="msp"/>
+            <section name="require_smiles">
+                <param name="is_true" value="TRUE"/>
+            </section>
+            <output name="output" file="filtering/require_smiles_out.msp" ftype="msp"/>
+        </test>
+        <test>
+            <param name="spectra" value="filtering/require_filter.msp" ftype="msp"/>
+            <section name="require_inchi">
+                <param name="is_true" value="TRUE"/>
+            </section>
+            <output name="output" file="filtering/require_inchi_out.msp" ftype="msp"/>
+        </test>
+        <test>
+            <param name="spectra" value="filtering/input.msp" ftype="msp"/>
+            <section name="reduce_to_top_n_peaks">
+                <param name="is_true" value="TRUE"/>
+                <param name="n_max" value="5"/>
+            </section>
+            <output name="output" file="filtering/reduce_to_top_n_peaks.msp" ftype="msp"/>
+        </test>
     </tests>
 
     <help>

tools/matchms/matchms_filtering_wrapper.py

@@ -4,10 +4,18 @@
 from matchms.exporting import save_as_mgf, save_as_msp
 from matchms.filtering import add_compound_name, add_fingerprint, add_losses, add_parent_mass, add_precursor_mz,\
     add_retention_index, add_retention_time, clean_compound_name
-from matchms.filtering import default_filters, normalize_intensities, select_by_mz, select_by_relative_intensity
+from matchms.filtering import default_filters, normalize_intensities, reduce_to_number_of_peaks, select_by_mz, \
+    select_by_relative_intensity
 from matchms.importing import load_from_mgf, load_from_msp
 
 
+def require_key(spectrum, key):
+    if spectrum.get(key):
+        return spectrum
+
+    return None
+
+
 def main(argv):
     parser = argparse.ArgumentParser(description="Compute MSP similarity scores")
     parser.add_argument("--spectra", type=str, required=True, help="Mass spectra file to be filtered.")
@@ -27,13 +35,23 @@ def main(argv):
                         help="Keep only peaks between set m/z range (keep if to_mz >= m/z >= from_mz).")
     parser.add_argument("--from_mz", type=float, help="Lower bound for m/z  filter")
     parser.add_argument("--to_mz", type=float, help="Upper bound for m/z  filter")
+    parser.add_argument("-require_smiles", action='store_true',
+                        help="Remove spectra that does not contain SMILES.")
+    parser.add_argument("-require_inchi", action='store_true',
+                        help="Remove spectra that does not contain INCHI.")
+    parser.add_argument("-reduce_to_top_n_peaks", action='store_true',
+                        help="reduce to top n peaks filter.")
+    parser.add_argument("--n_max", type=int, help="Maximum number of peaks. Remove peaks if more peaks are found.")
     args = parser.parse_args()
 
     if not (args.normalise_intensities
             or args.default_filters
             or args.clean_metadata
             or args.relative_intensity
-            or args.mz_range):
+            or args.mz_range
+            or args.require_smiles
+            or args.require_inchi
+            or args.reduce_to_top_n_peaks):
         raise ValueError('No filter selected.')
 
     if args.spectra_format == 'msp':
@@ -63,7 +81,17 @@ def main(argv):
         if args.mz_range:
             spectrum = select_by_mz(spectrum, args.from_mz, args.to_mz)
 
-        filtered_spectra.append(spectrum)
+        if args.reduce_to_top_n_peaks:
+            spectrum = reduce_to_number_of_peaks(spectrum_in=spectrum, n_max=args.n_max)
+
+        if args.require_smiles and spectrum is not None:
+            spectrum = require_key(spectrum, "smiles")
+
+        if args.require_inchi and spectrum is not None:
+            spectrum = require_key(spectrum, "inchi")
+
+        if spectrum is not None:
+            filtered_spectra.append(spectrum)
 
     if args.spectra_format == 'msp':
         save_as_msp(filtered_spectra, args.output)

tools/matchms/matchms_formatter.xml

@@ -16,16 +16,16 @@
         <requirement type="package" version="1.1.4">pandas</requirement>
         <requirement type="package" version="8.0.1">click</requirement>
     </requirements>
+
+    <command detect_errors="aggressive"><![CDATA[
+        sh ${matchms_formatter_cli}
+    ]]></command>
 
     <environment_variables>
         <environment_variable name="MPLCONFIGDIR">\$_GALAXY_JOB_TMP_DIR</environment_variable>
         <environment_variable name="XDG_CACHE_HOME">\$_GALAXY_JOB_TMP_DIR</environment_variable>
     </environment_variables>
 
-    <command detect_errors="aggressive"><![CDATA[
-        sh ${matchms_formatter_cli}
-    ]]></command>
-
     <configfiles>
         <configfile name="matchms_formatter_cli">
             python3 ${__tool_directory__}/formatter.py \
@@ -57,4 +57,8 @@
         @HELP_formatter@
         @HELP_matchms@
     </help>
+
+    <citations>
+        <citation type="doi">https://doi.org/10.5281/zenodo.6035335</citation>
+    </citations>
 </tool>

tools/matchms/matchms_metadata_export.xml

@@ -1,4 +1,4 @@
-<tool id="matchms_metadata_export" name="matchms metadata export " version="@TOOL_VERSION@+galaxy0" profile="21.09">
+<tool id="matchms_metadata_export" name="matchms metadata export" version="@TOOL_VERSION@+galaxy0" profile="21.09">
     <description>extract all metadata from mass spectra file to tabular format</description>
     <macros>
         <import>macros.xml</import>

tools/matchms/matchms_metadata_match.xml

@@ -12,14 +12,14 @@
         <requirement type="package" version="@TOOL_VERSION@">matchms</requirement>
     </requirements>
 
-    <environment_variables>
-        <environment_variable name="MPLCONFIGDIR">\$_GALAXY_JOB_TMP_DIR</environment_variable>
-    </environment_variables>
-
     <command detect_errors="exit_code"><![CDATA[
         python3 '${python_wrapper}'
     ]]> </command>
 
+    <environment_variables>
+        <environment_variable name="MPLCONFIGDIR">\$_GALAXY_JOB_TMP_DIR</environment_variable>
+    </environment_variables>
+
 <configfiles>
 <configfile name="python_wrapper">
 @init_logger@

tools/matchms/matchms_networking.xml

@@ -16,15 +16,15 @@
         <requirement type="package" version="@TOOL_VERSION@">matchms</requirement>
     </requirements>
 
+    <command detect_errors="aggressive"><![CDATA[
+        sh ${matchms_networking_cli}
+    ]]></command>
+
     <environment_variables>
         <environment_variable name="MPLCONFIGDIR">\$_GALAXY_JOB_TMP_DIR</environment_variable>
         <environment_variable name="XDG_CACHE_HOME">\$_GALAXY_JOB_TMP_DIR</environment_variable>
     </environment_variables>
 
-    <command detect_errors="aggressive"><![CDATA[
-        sh ${matchms_networking_cli}
-    ]]></command>
-
     <configfiles>
         <configfile name="matchms_networking_cli">
             python3 ${__tool_directory__}/matchms_networking_wrapper.py \
@@ -78,7 +78,7 @@
     </inputs>
 
     <outputs>
-        <data label="Similarity network of ${scores.name}" name="similarity_network_file">
+        <data label="Similarity network of ${scores.name}" name="similarity_network_file" format="graphml">
             <change_format>
                 <when input="graph_format" value="graphml" format="graphml"/>
                 <when input="graph_format" value="cyjs" format="cyjs"/>

tools/matchms/matchms_similarity.xml

@@ -13,14 +13,14 @@
         <requirement type="package" version="@TOOL_VERSION@">matchms</requirement>
     </requirements>
 
-    <environment_variables>
-        <environment_variable name="MPLCONFIGDIR">\$_GALAXY_JOB_TMP_DIR</environment_variable>
-    </environment_variables>
-
     <command detect_errors="exit_code"><![CDATA[
         sh ${matchms_python_cli}
     ]]> </command>
 
+    <environment_variables>
+        <environment_variable name="MPLCONFIGDIR">\$_GALAXY_JOB_TMP_DIR</environment_variable>
+    </environment_variables>
+
     <configfiles>
         <configfile name="matchms_python_cli">
             python3 ${__tool_directory__}/matchms_similarity_wrapper.py \
@@ -64,6 +64,7 @@
                 <param label="Reference spectra" name="references" type="data" format="msp,mgf"
                        help="Reference mass spectra to match against as library."/>
             </when>
+            <when value="TRUE"></when>
         </conditional>
         <param label="Scores array type" name="array_type" type="select" display="radio"
                help="Matrix type for storing scores objects. Sparse type more memory-efficient and better for large arrays.
@@ -113,6 +114,7 @@
                 <param label="tolerance" name="tolerance" type="float" value="60"
                        help="Peaks will be considered a match when less than tolerance apart."/>
             </when>
+            <when value="FALSE"></when>
         </conditional>
     </inputs>
 

tools/matchms/matchms_spectral_similarity.xml

@@ -12,14 +12,14 @@
         <requirement type="package" version="@TOOL_VERSION@">matchms</requirement>
     </requirements>
 
-    <environment_variables>
-        <environment_variable name="MPLCONFIGDIR">\$_GALAXY_JOB_TMP_DIR</environment_variable>
-    </environment_variables>
-
     <command detect_errors="exit_code"><![CDATA[
         python3 ${python_wrapper}
     ]]> </command>
 
+    <environment_variables>
+        <environment_variable name="MPLCONFIGDIR">\$_GALAXY_JOB_TMP_DIR</environment_variable>
+    </environment_variables>
+
 <configfiles>
 <configfile name="python_wrapper">
 @init_logger@

tools/matchms/test-data/filtering/reduce_to_top_n_peaks.msp

@@ -0,0 +1,57 @@
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C001
+RETENTION_TIME: 38.74
+RETENTION_INDEX: None
+NUM PEAKS: 5
+175.0641    26780143.0
+206.9034    26130980.0
+216.9205    32607700.0
+254.8252    23747536.0
+256.8215    31377637.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C002
+RETENTION_TIME: 520.25
+RETENTION_INDEX: 1234.5
+NUM PEAKS: 5
+310.1623    295359836.0
+525.375     1073323842.0
+526.3783    181668883.0
+551.3321    111616808.0
+1047.7378   150394804.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C003
+RETENTION_TIME: 483.67
+NUM PEAKS: 5
+288.6414    202172046.0
+522.3565    4089569222.0
+523.354     1201714423.0
+1043.7028   144351468.0
+1044.7068   83271854.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C004
+RETENTION_TIME: 473.48
+NUM PEAKS: 5
+496.34      12577588056.0
+497.3442    3337125302.0
+498.3462    532285213.0
+991.6726    1420557258.0
+992.6749    763118028.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C005
+RETENTION_TIME: 41.72
+NUM PEAKS: 5
+218.1386    14009249.0
+337.0623    88672453.0
+353.0361    37061354.0
+359.0443    48435582.0
+375.018     29159485.0
+