Mercurial > repos > recetox > matchms_filtering
changeset 0:3d275fbdf741 draft
"planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit 4d2ac914c951166e386a94d8ebb8cb1becfac122"
| author | recetox |
|---|---|
| date | Tue, 22 Mar 2022 16:08:03 +0000 |
| parents | |
| children | b8e9a7c7add2 |
| files | macros.xml matchms_filtering.xml matchms_filtering_wrapper.py test-data/filtering/clean_metadata.msp test-data/filtering/default_filters.msp test-data/filtering/input.msp test-data/filtering/mz_range.msp test-data/filtering/normalise_intensities.msp test-data/filtering/relative_intensity.msp |
| diffstat | 9 files changed, 1264 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Tue Mar 22 16:08:03 2022 +0000 @@ -0,0 +1,70 @@ +<macros> + <token name="@TOOL_VERSION@">0.14.0</token> + + <xml name="creator"> + <creator> + <person + givenName="Helge" + familyName="Hecht" + url="https://github.com/hechth" + identifier="0000-0001-6744-996X" /> + <organization + url="https://www.recetox.muni.cz/" + email="GalaxyToolsDevelopmentandDeployment@space.muni.cz" + name="RECETOX MUNI" /> + </creator> + </xml> + + <token name="@HELP_matchms@"> + <![CDATA[ + Documentation + For documentation on the tool see https://github.com/matchms/matchms/blob/master/README.rst + and https://matchms.readthedocs.io/en/latest/. + + Upstream Tools + +-----------+---------------+--------+-----------+ + | Name | Output File | Format | Parameter | + +===========+===============+========+===========+ + | RAMClustR | Mass spectra | msp | references| + +-----------+---------------+--------+-----------+ + | RAMClustR | Mass spectra | msp | queries | + +-----------+---------------+--------+-----------+ + + Downstream Tools + The outputs are two tsv datasets. One containing the similarity scores and the other number of matched peaks. + ]]> + </token> + + <token name="@HELP_formatter@"> + <![CDATA[ + Usage + This tool creates user friendly tables from the data matrices produces by matchms. + The tool can be operated on two modes based on (i) thresholds or (ii) top k matches. + + Input Table Format + The tool expects two data matrices with the format as depicted below. + The tool assumes the reference compound labels as row labels and the query labels as column labels (as naturally outputted by matchms). + + +----------+------+------+-----+ + | | C001 | C002 | ... | + +==========+======+======+=====+ + | Perylene | 0.1 | 0.0 | ... | + +----------+------+------+-----+ + | Glycine | 0.5 | 0.34 | ... | + +----------+------+------+-----+ + | ... | ... | ... | ... | + +----------+------+------+-----+ + + Output Table Format + +----------+-----------+---------+--------+ + | query | reference | matches | scores | + +==========+===========+=========+========+ + | C001 | Glycine | 6 | 0.5 | + +----------+-----------+---------+--------+ + | C002 | Glycine | 3 | 0.34 | + +----------+-----------+---------+--------+ + | ... | ... | ... | ... | + +----------+-----------+---------+--------+ + ]]> + </token> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/matchms_filtering.xml Tue Mar 22 16:08:03 2022 +0000 @@ -0,0 +1,154 @@ +<tool id="matchms_filtering" name="matchMS filtering" version="@TOOL_VERSION@+galaxy1"> + <description>filter and normalize mass spectrometry data</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="creator"/> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">matchms</requirement> + <requirement type="package" version="1.1.4">pandas</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> + + <configfiles> + <configfile name="matchms_python_cli"> + python3 ${__tool_directory__}/matchms_filtering_wrapper.py \ + --spectra "$spectra" \ + --spectra_format "$spectra.ext" \ + #if $normalise_intensities.is_true + -normalise_intensities \ + #end if + #if $default_filters.is_true + -default_filters \ + #end if + #if $clean_metadata.is_true + -clean_metadata \ + #end if + #if $relative_intensity.is_true + -relative_intensity \ + --from_intensity "$relative_intensity.from_intensity" \ + --to_intensity "$relative_intensity.to_intensity" \ + #end if + #if $mz_range.is_true + -mz_range \ + --from_mz "$mz_range.from_mz" \ + --to_mz "$mz_range.to_mz" \ + #end if + --output "$output" + </configfile> + </configfiles> + + <inputs> + <param label="Spectra file" name="spectra" type="data" format="msp,mgf" help="Mass spectra file to be filtered." /> + + <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."/> + </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."/> + </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." /> + </conditional> + + <conditional name="relative_intensity"> + <param name="is_true" label="Filter relative intensity" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" + help="Keep only peaks within set relative intensity range (keep if maximum >= intensity >= minimum)." /> + <when value="TRUE"> + <param label="Minimum intensity" name="from_intensity" optional="true" type="float" help="Lower bound for intensity filter." /> + <param label="Maximum intensity" name="to_intensity" optional="true" type="float" help="Upper bound for intensity filter." /> + </when> + </conditional> + + <conditional name="mz_range"> + <param name="is_true" label="Filter m/z range" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" + help="Keep only peaks between set m/z range (keep if maximum >= m/z >= minimum)." /> + <when value="TRUE"> + <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> + </conditional> + + </inputs> + + <outputs> + <data label="${tool.name} on ${on_string}" name="output" format_source="spectra" /> + </outputs> + + <tests> + <test> + <param name="spectra" value="filtering/input.msp" ftype="msp"/> + <section name="normalise_intensities"> + <param name="is_true" value="TRUE"/> + </section> + <output name="output" file="filtering/normalise_intensities.msp" ftype="msp"/> + </test> + <test> + <param name="spectra" value="filtering/input.msp" ftype="msp"/> + <section name="default_filters"> + <param name="is_true" value="TRUE"/> + </section> + <output name="output" file="filtering/default_filters.msp" ftype="msp"/> + </test> + <test> + <param name="spectra" value="filtering/input.msp" ftype="msp"/> + <section name="clean_metadata"> + <param name="is_true" value="TRUE"/> + </section> + <output name="output" file="filtering/clean_metadata.msp" ftype="msp"/> + </test> + <test> + <param name="spectra" value="filtering/input.msp" ftype="msp"/> + <section name="relative_intensity"> + <param name="is_true" value="TRUE"/> + <param name="from_intensity" value="0.3"/> + <param name="to_intensity" value="0.9"/> + </section> + <output name="output" file="filtering/relative_intensity.msp" ftype="msp"/> + </test> + <test> + <param name="spectra" value="filtering/input.msp" ftype="msp"/> + <section name="mz_range"> + <param name="is_true" value="TRUE"/> + <param name="from_mz" value="300"/> + <param name="to_mz" value="800"/> + </section> + <output name="output" file="filtering/mz_range.msp" ftype="msp"/> + </test> + </tests> + + <help><![CDATA[ + Documentation + For documentation on the tool see https://github.com/matchms/matchms/blob/master/README.rst and https://matchms.readthedocs.io/en/latest/. + + Upstream Tools + +-----------+---------------+--------+-----------+ + | Name | Output File | Format | Parameter | + +===========+===============+========+===========+ + | RAMClustR | Mass spectra | msp | references| + +-----------+---------------+--------+-----------+ + | RAMClustR | Mass spectra | msp | queries | + +-----------+---------------+--------+-----------+ + + Downstream Tools + The output is an msp file after applying the specified filters. + ]]></help> + + + <citations> + <citation type="doi">10.5281/zenodo.4589154</citation> + <citation type="doi">10.21105/joss.02411</citation> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/matchms_filtering_wrapper.py Tue Mar 22 16:08:03 2022 +0000 @@ -0,0 +1,77 @@ +import argparse +import sys + +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.importing import load_from_mgf, load_from_msp + + +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.") + parser.add_argument("--spectra_format", type=str, required=True, help="Format of spectra file.") + parser.add_argument("--output", type=str, required=True, help="Filtered mass spectra file.") + parser.add_argument("-normalise_intensities", action='store_true', + help="Normalize intensities of peaks (and losses) to unit height.") + parser.add_argument("-default_filters", action='store_true', + help="Collection of filters that are considered default and that do no require any (factory) arguments.") + parser.add_argument("-clean_metadata", action='store_true', + help="Apply all adding and cleaning filters if possible, so that the spectra have canonical metadata.") + parser.add_argument("-relative_intensity", action='store_true', + help="Keep only peaks within set relative intensity range (keep if to_intensity >= intensity >= from_intensity).") + parser.add_argument("--from_intensity", type=float, help="Lower bound for intensity filter") + parser.add_argument("--to_intensity", type=float, help="Upper bound for intensity filter") + parser.add_argument("-mz_range", action='store_true', + 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") + 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): + raise ValueError('No filter selected.') + + if args.spectra_format == 'msp': + spectra = list(load_from_msp(args.spectra)) + elif args.queries_format == 'mgf': + spectra = list(load_from_mgf(args.spectra)) + else: + raise ValueError(f'File format {args.spectra_format} not supported for mass spectra file.') + + filtered_spectra = [] + for spectrum in spectra: + if args.normalise_intensities: + spectrum = normalize_intensities(spectrum) + + if args.default_filters: + spectrum = default_filters(spectrum) + + if args.clean_metadata: + filters = [add_compound_name, add_precursor_mz, add_fingerprint, add_losses, add_parent_mass, + add_retention_index, add_retention_time, clean_compound_name] + for metadata_filter in filters: + spectrum = metadata_filter(spectrum) + + if args.relative_intensity: + spectrum = select_by_relative_intensity(spectrum, args.from_intensity, args.to_intensity) + + if args.mz_range: + spectrum = select_by_mz(spectrum, args.from_mz, args.to_mz) + + filtered_spectra.append(spectrum) + + if args.spectra_format == 'msp': + save_as_msp(filtered_spectra, args.output) + else: + save_as_mgf(filtered_spectra, args.output) + + return 0 + + +if __name__ == "__main__": + main(argv=sys.argv[1:])
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/filtering/clean_metadata.msp Tue Mar 22 16:08:03 2022 +0000 @@ -0,0 +1,197 @@ +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C001 +RETENTION_TIME: 38.74 +RETENTION_INDEX: None +NUM PEAKS: 57 +138.9121 10186226.0 +148.9337 1008656.0 +175.0641 26780143.0 +186.1095 2675456.0 +196.8658 21390430.0 +198.8647 21688594.0 +200.8848 7742528.0 +206.9034 26130980.0 +216.9205 32607700.0 +234.0134 2550129.0 +254.8252 23747536.0 +256.8215 31377637.0 +258.8237 15532799.0 +266.8652 9805546.0 +268.8537 3090354.0 +306.9914 3169316.0 +312.7841 10051801.0 +316.7777 10734168.0 +322.8157 6317648.0 +324.9549 8619910.0 +334.849 4178412.0 +342.8093 3285552.0 +349.9455 2050695.0 +350.9875 6150799.0 +351.941 1965882.0 +366.8281 3253770.0 +370.7418 9765463.0 +372.7383 19374863.0 +382.8218 12815572.0 +384.8177 8311500.0 +392.7685 10913351.0 +413.2664 3965867.0 +426.7772 5431633.0 +428.7834 8554675.0 +434.7287 9943329.0 +436.8161 3705247.0 +440.7322 10603010.0 +442.7401 8271752.0 +450.7016 8762673.0 +460.7076 4528973.0 +462.7862 2123666.0 +484.7242 4273989.0 +486.7743 4886062.0 +488.6825 12267966.0 +492.744 7662344.0 +494.8953 7188793.0 +498.8794 6811405.0 +500.8484 6520691.0 +502.7832 3567833.0 +510.763 4989757.0 +518.7415 4243468.0 +546.6093 7177067.0 +550.6949 6104789.0 +566.5977 5171811.0 +612.6927 2005587.0 +676.6436 1982714.0 +800.4451 2792137.0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C002 +RETENTION_TIME: 520.25 +RETENTION_INDEX: 1234.5 +NUM PEAKS: 35 +131.1733 1971789.0 +267.2688 6103973.0 +279.0196 1946255.0 +289.6491 46498377.0 +301.1565 15185412.0 +309.1649 18045974.0 +310.1623 295359836.0 +311.1658 13124727.0 +312.0296 38757284.0 +330.6757 12666597.0 +525.375 1073323842.0 +526.3783 181668883.0 +527.3812 23642795.0 +551.3321 111616808.0 +552.3348 28340614.0 +553.3314 2609936.0 +562.3269 7538206.0 +578.2905 7578406.0 +619.3008 4742103.0 +624.296 11790213.0 +813.5403 25060147.0 +814.5336 5865975.0 +955.1171 2322927.0 +1047.7378 150394804.0 +1048.7399 90978863.0 +1049.7432 29946438.0 +1050.7453 6807767.0 +1069.7158 5074652.0 +1074.1979 3402288.0 +1075.1968 33352763.0 +1076.2004 10417953.0 +1101.6535 2023916.0 +1206.3127 3738816.0 +1216.8041 4439324.0 +1217.807 3565334.0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C003 +RETENTION_TIME: 483.67 +RETENTION_INDEX: None +NUM PEAKS: 26 +265.2529 11366224.0 +266.2564 1420444.0 +279.6362 29849749.0 +280.6546 8848921.0 +288.6414 202172046.0 +378.2093 15309961.0 +379.1966 2902366.0 +522.3565 4089569222.0 +523.354 1201714423.0 +549.3267 63300808.0 +576.2749 7386007.0 +577.3074 2354251.0 +617.2778 2323470.0 +625.4543 4040374.0 +796.9808 13576738.0 +797.9841 6368973.0 +809.9883 12596682.0 +810.9916 6601055.0 +1043.7028 144351468.0 +1044.7068 83271854.0 +1045.706 27998321.0 +1046.7131 6505178.0 +1058.1594 20718345.0 +1059.1626 6608764.0 +1071.1639 15461047.0 +1072.1671 5096642.0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C004 +RETENTION_TIME: 473.48 +RETENTION_INDEX: None +NUM PEAKS: 24 +124.1405 6517662.0 +170.2437 1237313.0 +275.6336 28001849.0 +296.147 190395687.0 +482.3247 145772322.0 +483.3283 36245876.0 +496.34 12577588056.0 +497.3442 3337125302.0 +498.3462 532285213.0 +499.3493 68176083.0 +770.964 49250157.0 +771.9675 22666873.0 +783.9721 9839299.0 +784.9749 3622908.0 +949.6233 8009033.0 +950.6274 3674694.0 +991.6726 1420557258.0 +992.6749 763118028.0 +993.6787 239161906.0 +994.6801 53549573.0 +1017.6897 168186952.0 +1018.6656 120599518.0 +1019.6555 57647644.0 +1020.6591 12469103.0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C005 +RETENTION_TIME: 41.72 +RETENTION_INDEX: None +NUM PEAKS: 20 +218.1386 14009249.0 +337.0623 88672453.0 +338.0654 8770055.0 +353.0361 37061354.0 +359.0443 48435582.0 +360.0459 5025128.0 +375.018 29159485.0 +376.0216 2740193.0 +381.0261 13522755.0 +396.9999 10317665.0 +417.0027 13822994.0 +418.9966 4386311.0 +432.9764 9779399.0 +438.9851 11307111.0 +440.9796 3364168.0 +454.9592 9820452.0 +456.9603 3774845.0 +470.9263 3632486.0 +512.8989 4072570.0 +572.871 3485486.0 +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/filtering/default_filters.msp Tue Mar 22 16:08:03 2022 +0000 @@ -0,0 +1,199 @@ +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C001 +RETENTION_TIME: 38.74 +RETENTION_INDEX: None +CHARGE: -1 +NUM PEAKS: 57 +138.9121 10186226.0 +148.9337 1008656.0 +175.0641 26780143.0 +186.1095 2675456.0 +196.8658 21390430.0 +198.8647 21688594.0 +200.8848 7742528.0 +206.9034 26130980.0 +216.9205 32607700.0 +234.0134 2550129.0 +254.8252 23747536.0 +256.8215 31377637.0 +258.8237 15532799.0 +266.8652 9805546.0 +268.8537 3090354.0 +306.9914 3169316.0 +312.7841 10051801.0 +316.7777 10734168.0 +322.8157 6317648.0 +324.9549 8619910.0 +334.849 4178412.0 +342.8093 3285552.0 +349.9455 2050695.0 +350.9875 6150799.0 +351.941 1965882.0 +366.8281 3253770.0 +370.7418 9765463.0 +372.7383 19374863.0 +382.8218 12815572.0 +384.8177 8311500.0 +392.7685 10913351.0 +413.2664 3965867.0 +426.7772 5431633.0 +428.7834 8554675.0 +434.7287 9943329.0 +436.8161 3705247.0 +440.7322 10603010.0 +442.7401 8271752.0 +450.7016 8762673.0 +460.7076 4528973.0 +462.7862 2123666.0 +484.7242 4273989.0 +486.7743 4886062.0 +488.6825 12267966.0 +492.744 7662344.0 +494.8953 7188793.0 +498.8794 6811405.0 +500.8484 6520691.0 +502.7832 3567833.0 +510.763 4989757.0 +518.7415 4243468.0 +546.6093 7177067.0 +550.6949 6104789.0 +566.5977 5171811.0 +612.6927 2005587.0 +676.6436 1982714.0 +800.4451 2792137.0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C002 +RETENTION_TIME: 520.25 +RETENTION_INDEX: 1234.5 +CHARGE: -1 +NUM PEAKS: 35 +131.1733 1971789.0 +267.2688 6103973.0 +279.0196 1946255.0 +289.6491 46498377.0 +301.1565 15185412.0 +309.1649 18045974.0 +310.1623 295359836.0 +311.1658 13124727.0 +312.0296 38757284.0 +330.6757 12666597.0 +525.375 1073323842.0 +526.3783 181668883.0 +527.3812 23642795.0 +551.3321 111616808.0 +552.3348 28340614.0 +553.3314 2609936.0 +562.3269 7538206.0 +578.2905 7578406.0 +619.3008 4742103.0 +624.296 11790213.0 +813.5403 25060147.0 +814.5336 5865975.0 +955.1171 2322927.0 +1047.7378 150394804.0 +1048.7399 90978863.0 +1049.7432 29946438.0 +1050.7453 6807767.0 +1069.7158 5074652.0 +1074.1979 3402288.0 +1075.1968 33352763.0 +1076.2004 10417953.0 +1101.6535 2023916.0 +1206.3127 3738816.0 +1216.8041 4439324.0 +1217.807 3565334.0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C003 +RETENTION_TIME: 483.67 +CHARGE: -1 +NUM PEAKS: 26 +265.2529 11366224.0 +266.2564 1420444.0 +279.6362 29849749.0 +280.6546 8848921.0 +288.6414 202172046.0 +378.2093 15309961.0 +379.1966 2902366.0 +522.3565 4089569222.0 +523.354 1201714423.0 +549.3267 63300808.0 +576.2749 7386007.0 +577.3074 2354251.0 +617.2778 2323470.0 +625.4543 4040374.0 +796.9808 13576738.0 +797.9841 6368973.0 +809.9883 12596682.0 +810.9916 6601055.0 +1043.7028 144351468.0 +1044.7068 83271854.0 +1045.706 27998321.0 +1046.7131 6505178.0 +1058.1594 20718345.0 +1059.1626 6608764.0 +1071.1639 15461047.0 +1072.1671 5096642.0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C004 +RETENTION_TIME: 473.48 +CHARGE: -1 +NUM PEAKS: 24 +124.1405 6517662.0 +170.2437 1237313.0 +275.6336 28001849.0 +296.147 190395687.0 +482.3247 145772322.0 +483.3283 36245876.0 +496.34 12577588056.0 +497.3442 3337125302.0 +498.3462 532285213.0 +499.3493 68176083.0 +770.964 49250157.0 +771.9675 22666873.0 +783.9721 9839299.0 +784.9749 3622908.0 +949.6233 8009033.0 +950.6274 3674694.0 +991.6726 1420557258.0 +992.6749 763118028.0 +993.6787 239161906.0 +994.6801 53549573.0 +1017.6897 168186952.0 +1018.6656 120599518.0 +1019.6555 57647644.0 +1020.6591 12469103.0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C005 +RETENTION_TIME: 41.72 +CHARGE: -1 +NUM PEAKS: 20 +218.1386 14009249.0 +337.0623 88672453.0 +338.0654 8770055.0 +353.0361 37061354.0 +359.0443 48435582.0 +360.0459 5025128.0 +375.018 29159485.0 +376.0216 2740193.0 +381.0261 13522755.0 +396.9999 10317665.0 +417.0027 13822994.0 +418.9966 4386311.0 +432.9764 9779399.0 +438.9851 11307111.0 +440.9796 3364168.0 +454.9592 9820452.0 +456.9603 3774845.0 +470.9263 3632486.0 +512.8989 4072570.0 +572.871 3485486.0 +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/filtering/input.msp Tue Mar 22 16:08:03 2022 +0000 @@ -0,0 +1,193 @@ +NAME:C001 +IONMODE:Negative +RETENTIONTIME:38.74 +RETENTIONINDEX: -1 +SPECTRUMTYPE:Centroid +Num Peaks:57 +216.9205 32607700 +256.8215 31377637 +175.0641 26780143 +206.9034 26130980 +254.8252 23747536 +198.8647 21688594 +196.8658 21390430 +372.7383 19374863 +258.8237 15532799 +382.8218 12815572 +488.6825 12267966 +392.7685 10913351 +316.7777 10734168 +440.7322 10603010 +138.9121 10186226 +312.7841 10051801 +434.7287 9943329 +266.8652 9805546 +370.7418 9765463 +450.7016 8762673 +324.9549 8619910 +428.7834 8554675 +384.8177 8311500 +442.7401 8271752 +200.8848 7742528 +492.744 7662344 +494.8953 7188793 +546.6093 7177067 +498.8794 6811405 +500.8484 6520691 +322.8157 6317648 +350.9875 6150799 +550.6949 6104789 +426.7772 5431633 +566.5977 5171811 +510.763 4989757 +486.7743 4886062 +460.7076 4528973 +484.7242 4273989 +518.7415 4243468 +334.849 4178412 +413.2664 3965867 +436.8161 3705247 +502.7832 3567833 +342.8093 3285552 +366.8281 3253770 +306.9914 3169316 +268.8537 3090354 +800.4451 2792137 +186.1095 2675456 +234.0134 2550129 +462.7862 2123666 +349.9455 2050695 +612.6927 2005587 +676.6436 1982714 +351.941 1965882 +148.9337 1008656 + +NAME:C002 +IONMODE:Negative +RETENTIONTIME:520.25 +RETENTIONINDEX: 1234.5 +SPECTRUMTYPE:Centroid +Num Peaks:35 +525.375 1073323842 +310.1623 295359836 +526.3783 181668883 +1047.7378 150394804 +551.3321 111616808 +1048.7399 90978863 +289.6491 46498377 +312.0296 38757284 +1075.1968 33352763 +1049.7432 29946438 +552.3348 28340614 +813.5403 25060147 +527.3812 23642795 +309.1649 18045974 +301.1565 15185412 +311.1658 13124727 +330.6757 12666597 +624.296 11790213 +1076.2004 10417953 +578.2905 7578406 +562.3269 7538206 +1050.7453 6807767 +267.2688 6103973 +814.5336 5865975 +1069.7158 5074652 +619.3008 4742103 +1216.8041 4439324 +1206.3127 3738816 +1217.807 3565334 +1074.1979 3402288 +553.3314 2609936 +955.1171 2322927 +1101.6535 2023916 +131.1733 1971789 +279.0196 1946255 + +NAME:C003 +IONMODE:Negative +RETENTIONTIME:483.67 +SPECTRUMTYPE:Centroid +Num Peaks:26 +522.3565 4089569222 +523.354 1201714423 +288.6414 202172046 +1043.7028 144351468 +1044.7068 83271854 +549.3267 63300808 +279.6362 29849749 +1045.706 27998321 +1058.1594 20718345 +1071.1639 15461047 +378.2093 15309961 +796.9808 13576738 +809.9883 12596682 +265.2529 11366224 +280.6546 8848921 +576.2749 7386007 +1059.1626 6608764 +810.9916 6601055 +1046.7131 6505178 +797.9841 6368973 +1072.1671 5096642 +625.4543 4040374 +379.1966 2902366 +577.3074 2354251 +617.2778 2323470 +266.2564 1420444 + +NAME:C004 +IONMODE:Negative +RETENTIONTIME:473.48 +SPECTRUMTYPE:Centroid +Num Peaks:24 +496.34 12577588056 +497.3442 3337125302 +991.6726 1420557258 +992.6749 763118028 +498.3462 532285213 +993.6787 239161906 +296.147 190395687 +1017.6897 168186952 +482.3247 145772322 +1018.6656 120599518 +499.3493 68176083 +1019.6555 57647644 +994.6801 53549573 +770.964 49250157 +483.3283 36245876 +275.6336 28001849 +771.9675 22666873 +1020.6591 12469103 +783.9721 9839299 +949.6233 8009033 +124.1405 6517662 +950.6274 3674694 +784.9749 3622908 +170.2437 1237313 + +NAME:C005 +IONMODE:Negative +RETENTIONTIME:41.72 +SPECTRUMTYPE:Centroid +Num Peaks:20 +337.0623 88672453 +359.0443 48435582 +353.0361 37061354 +375.018 29159485 +218.1386 14009249 +417.0027 13822994 +381.0261 13522755 +438.9851 11307111 +396.9999 10317665 +454.9592 9820452 +432.9764 9779399 +338.0654 8770055 +360.0459 5025128 +418.9966 4386311 +512.8989 4072570 +456.9603 3774845 +470.9263 3632486 +572.871 3485486 +440.9796 3364168 +376.0216 2740193
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/filtering/mz_range.msp Tue Mar 22 16:08:03 2022 +0000 @@ -0,0 +1,129 @@ +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C001 +RETENTION_TIME: 38.74 +RETENTION_INDEX: None +NUM PEAKS: 41 +306.9914 3169316.0 +312.7841 10051801.0 +316.7777 10734168.0 +322.8157 6317648.0 +324.9549 8619910.0 +334.849 4178412.0 +342.8093 3285552.0 +349.9455 2050695.0 +350.9875 6150799.0 +351.941 1965882.0 +366.8281 3253770.0 +370.7418 9765463.0 +372.7383 19374863.0 +382.8218 12815572.0 +384.8177 8311500.0 +392.7685 10913351.0 +413.2664 3965867.0 +426.7772 5431633.0 +428.7834 8554675.0 +434.7287 9943329.0 +436.8161 3705247.0 +440.7322 10603010.0 +442.7401 8271752.0 +450.7016 8762673.0 +460.7076 4528973.0 +462.7862 2123666.0 +484.7242 4273989.0 +486.7743 4886062.0 +488.6825 12267966.0 +492.744 7662344.0 +494.8953 7188793.0 +498.8794 6811405.0 +500.8484 6520691.0 +502.7832 3567833.0 +510.763 4989757.0 +518.7415 4243468.0 +546.6093 7177067.0 +550.6949 6104789.0 +566.5977 5171811.0 +612.6927 2005587.0 +676.6436 1982714.0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C002 +RETENTION_TIME: 520.25 +RETENTION_INDEX: 1234.5 +NUM PEAKS: 16 +301.1565 15185412.0 +309.1649 18045974.0 +310.1623 295359836.0 +311.1658 13124727.0 +312.0296 38757284.0 +330.6757 12666597.0 +525.375 1073323842.0 +526.3783 181668883.0 +527.3812 23642795.0 +551.3321 111616808.0 +552.3348 28340614.0 +553.3314 2609936.0 +562.3269 7538206.0 +578.2905 7578406.0 +619.3008 4742103.0 +624.296 11790213.0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C003 +RETENTION_TIME: 483.67 +NUM PEAKS: 11 +378.2093 15309961.0 +379.1966 2902366.0 +522.3565 4089569222.0 +523.354 1201714423.0 +549.3267 63300808.0 +576.2749 7386007.0 +577.3074 2354251.0 +617.2778 2323470.0 +625.4543 4040374.0 +796.9808 13576738.0 +797.9841 6368973.0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C004 +RETENTION_TIME: 473.48 +NUM PEAKS: 10 +482.3247 145772322.0 +483.3283 36245876.0 +496.34 12577588056.0 +497.3442 3337125302.0 +498.3462 532285213.0 +499.3493 68176083.0 +770.964 49250157.0 +771.9675 22666873.0 +783.9721 9839299.0 +784.9749 3622908.0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C005 +RETENTION_TIME: 41.72 +NUM PEAKS: 19 +337.0623 88672453.0 +338.0654 8770055.0 +353.0361 37061354.0 +359.0443 48435582.0 +360.0459 5025128.0 +375.018 29159485.0 +376.0216 2740193.0 +381.0261 13522755.0 +396.9999 10317665.0 +417.0027 13822994.0 +418.9966 4386311.0 +432.9764 9779399.0 +438.9851 11307111.0 +440.9796 3364168.0 +454.9592 9820452.0 +456.9603 3774845.0 +470.9263 3632486.0 +512.8989 4072570.0 +572.871 3485486.0 +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/filtering/normalise_intensities.msp Tue Mar 22 16:08:03 2022 +0000 @@ -0,0 +1,194 @@ +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C001 +RETENTION_TIME: 38.74 +RETENTION_INDEX: None +NUM PEAKS: 57 +138.9121 0.31238713555387226 +148.9337 0.03093306182282099 +175.0641 0.8212827951680125 +186.1095 0.08204982258791635 +196.8658 0.6559932163262051 +198.8647 0.6651371915222478 +200.8848 0.23744477531380626 +206.9034 0.8013745219687375 +216.9205 1.0 +234.0134 0.0782063439003671 +254.8252 0.7282800074828951 +256.8215 0.9622769161885076 +258.8237 0.4763537140000675 +266.8652 0.30071259242448867 +268.8537 0.09477374975849262 +306.9914 0.09719532503059093 +312.7841 0.30826464301376666 +316.7777 0.3291912033047409 +322.8157 0.1937471210787636 +324.9549 0.2643519782137348 +334.849 0.12814188059875428 +342.8093 0.10076000453880525 +349.9455 0.06288990023828728 +350.9875 0.18863026217733847 +351.941 0.06028888882073866 +366.8281 0.09978532677864431 +370.7418 0.29948334289140294 +372.7383 0.5941806076478868 +382.8218 0.3930228749651156 +384.8177 0.2548937827568335 +392.7685 0.33468631642219476 +413.2664 0.1216236349083192 +426.7772 0.1665751647616974 +428.7834 0.262351377128715 +434.7287 0.3049380667756389 +436.8161 0.11363104420121628 +440.7322 0.32516890182380237 +442.7401 0.25367480687076976 +450.7016 0.268730177228078 +460.7076 0.13889274619185038 +462.7862 0.06512774590050817 +484.7242 0.13107299809554185 +486.7743 0.14984380989766222 +488.6825 0.376229111528872 +492.744 0.23498572423077985 +494.8953 0.22046305013846423 +498.8794 0.20888946475832396 +500.8484 0.19997396320500985 +502.7832 0.10941688619559184 +510.763 0.15302388699601627 +518.7415 0.13013699218282798 +546.6093 0.2201034418250904 +550.6949 0.18721924576097057 +566.5977 0.15860704680182902 +612.6927 0.061506545999871196 +676.6436 0.06080508591528995 +800.4451 0.08562814917948829 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C002 +RETENTION_TIME: 520.25 +RETENTION_INDEX: 1234.5 +NUM PEAKS: 35 +131.1733 0.0018370867419900284 +267.2688 0.005686981655625982 +279.0196 0.0018132970906277511 +289.6491 0.04332185234360982 +301.1565 0.014148024487841387 +309.1649 0.01681316793110052 +310.1623 0.2751824048272655 +311.1658 0.012228114653210135 +312.0296 0.03610959011940033 +330.6757 0.011801281686240601 +525.375 1.0 +526.3783 0.16925822001818533 +527.3812 0.022027643545069038 +551.3321 0.10399173449088443 +552.3348 0.026404532249270578 +553.3314 0.00243163889393971 +562.3269 0.0070232353973927655 +578.2905 0.007060689144739971 +619.3008 0.004418147454139941 +624.296 0.010984767633625341 +813.5403 0.023348169508005768 +814.5336 0.005465242427736922 +955.1171 0.0021642368399005527 +1047.7378 0.1401206216753359 +1048.7399 0.08476366539149328 +1049.7432 0.027900654796038715 +1050.7453 0.006342696149667753 +1069.7158 0.004727978454800783 +1074.1979 0.0031698615710057058 +1075.1968 0.03107427758042852 +1076.2004 0.009706253222314986 +1101.6535 0.0018856526994021623 +1206.3127 0.003483399747305716 +1216.8041 0.004136052723591693 +1217.807 0.0033217691254826334 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C003 +RETENTION_TIME: 483.67 +NUM PEAKS: 26 +265.2529 0.0027793206039538215 +266.2564 0.00034733340430054716 +279.6362 0.0072989959038771346 +280.6546 0.002163778266032735 +288.6414 0.049436024927126176 +378.2093 0.0037436610481220017 +379.1966 0.0007096996877780199 +522.3565 1.0 +523.354 0.29384865685493955 +549.3267 0.015478600450010918 +576.2749 0.0018060599048590942 +577.3074 0.0005756721239330571 +617.2778 0.0005681454143142512 +625.4543 0.0009879705613649104 +796.9808 0.0033198455052339984 +797.9841 0.0015573701420036753 +809.9883 0.0030801977705220513 +810.9916 0.0016141198844341264 +1043.7028 0.035297475152995465 +1044.7068 0.020362011126266247 +1045.706 0.0068462763386867055 +1046.7131 0.0015906756058816994 +1058.1594 0.00506614361447774 +1059.1626 0.0016160049240511426 +1071.1639 0.0037806052815603864 +1072.1671 0.0012462539997079428 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C004 +RETENTION_TIME: 473.48 +NUM PEAKS: 24 +124.1405 0.0005181964913289414 +170.2437 9.837442556482469e-05 +275.6336 0.002226328996889195 +296.147 0.015137694616192635 +482.3247 0.011589847063758851 +483.3283 0.00288178272643532 +496.34 1.0 +497.3442 0.2653231515567137 +498.3462 0.04232013408533278 +499.3493 0.005420441717160338 +770.964 0.003915707588825487 +771.9675 0.0018021637295703144 +783.9721 0.0007822882222085712 +784.9749 0.0002880447335267696 +949.6233 0.0006367701791743273 +950.6274 0.00029216205711611197 +991.6726 0.11294353509394345 +992.6749 0.06067284320350776 +993.6787 0.01901492598860482 +994.6801 0.004257539105397458 +1017.6897 0.013371955835345416 +1018.6656 0.00958844553208827 +1019.6555 0.004583362385803359 +1020.6591 0.0009913747329363162 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C005 +RETENTION_TIME: 41.72 +NUM PEAKS: 20 +218.1386 0.15798873862212878 +337.0623 1.0 +338.0654 0.09890394032518758 +353.0361 0.4179579198062785 +359.0443 0.5462303157441691 +360.0459 0.0566706776455141 +375.018 0.3288449119592981 +376.0216 0.03090241565776916 +381.0261 0.15250232222627247 +396.9999 0.1163570494660839 +417.0027 0.1558882553976487 +418.9966 0.049466444781898614 +432.9764 0.11028677643551825 +438.9851 0.12751548668671656 +440.9796 0.037939268467062706 +454.9592 0.11074974998154162 +456.9603 0.042570661713847026 +470.9263 0.04096521385282981 +512.8989 0.04592824335196862 +572.871 0.03930742730214083 +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/filtering/relative_intensity.msp Tue Mar 22 16:08:03 2022 +0000 @@ -0,0 +1,51 @@ +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C001 +RETENTION_TIME: 38.74 +RETENTION_INDEX: None +NUM PEAKS: 16 +138.9121 10186226.0 +175.0641 26780143.0 +196.8658 21390430.0 +198.8647 21688594.0 +206.9034 26130980.0 +254.8252 23747536.0 +258.8237 15532799.0 +266.8652 9805546.0 +312.7841 10051801.0 +316.7777 10734168.0 +372.7383 19374863.0 +382.8218 12815572.0 +392.7685 10913351.0 +434.7287 9943329.0 +440.7322 10603010.0 +488.6825 12267966.0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C002 +RETENTION_TIME: 520.25 +RETENTION_INDEX: 1234.5 +NUM PEAKS: 0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C003 +RETENTION_TIME: 483.67 +NUM PEAKS: 0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C004 +RETENTION_TIME: 473.48 +NUM PEAKS: 0 + +IONMODE: negative +SPECTRUMTYPE: Centroid +COMPOUND_NAME: C005 +RETENTION_TIME: 41.72 +NUM PEAKS: 3 +353.0361 37061354.0 +359.0443 48435582.0 +375.018 29159485.0 +