MASST XIC

search_single_spectrum/test/test.py

@@ -0,0 +1,9 @@
+import sys
+
+sys.path.insert(0, "../tools/search_single_spectrum")
+
+def test():
+    import xic_masst
+    new_record_df = xic_masst.process_masst_xic("test_data/SEARCH_SINGLE_SPECTRUM-7e961554-view_all_spectra_datasets_matched-main.tsv")
+
+    print(new_record_df)

search_single_spectrum/test/test_data/SEARCH_SINGLE_SPECTRUM-7e961554-view_all_spectra_datasets_matched-main.tsv

@@ -0,0 +1,51 @@
+cluster_scan	dataset_id	filename	filescan	metadata
+295334	MSV000084900	f.MSV000084900/ccms_peak/Global_Foodomics_composite_data_2020/MSV000083010_core/G74022_5x_BG11_01_18395.mzML	574	 
+295334	MSV000084900	f.MSV000084900/ccms_peak/Global_Foodomics_composite_data_2020/MSV000083010_core/G74022_5x_BG11_01_18395.mzML	570	 
+300	MSV000084237	f.MSV000084237/ccms_peak/Raw/std_mix3_Fe_conc46_1_long.mzML	840	 
+300	MSV000084237	f.MSV000084237/ccms_peak/Raw/std_mix2_4.mzML	947	 
+300	MSV000084237	f.MSV000084237/ccms_peak/Raw/std_mix2_4.mzML	941	 
+300	MSV000084237	f.MSV000084237/ccms_peak/Raw/std_mix2_4.mzML	938	 
+131379	MSV000083010	f.MSV000083010/ccms_peak/Samples/G74022_5x_BG11_01_18395.mzML	574	GNPS - GFOP - Food - Beverage - Data set 1|not applicable|not applicable|reverse phase (C18)|not applicable|United States of America|not applicable|not applicable|not specified|not applicable|not applicable|sulfamethazine;sulfadimethoxine|electrospray ionization (positive)|not specified|not applicable|impact HD|MS:1002667|not specified|not specified|solid material, frozen|ethanol-water (19:1)|food|food_source_animal|G74022|not applicable|not applicable|not applicable|MSV000083010_G74022|2018
+131379	MSV000083010	f.MSV000083010/ccms_peak/Samples/G74022_5x_BG11_01_18395.mzML	570	GNPS - GFOP - Food - Beverage - Data set 1|not applicable|not applicable|reverse phase (C18)|not applicable|United States of America|not applicable|not applicable|not specified|not applicable|not applicable|sulfamethazine;sulfadimethoxine|electrospray ionization (positive)|not specified|not applicable|impact HD|MS:1002667|not specified|not specified|solid material, frozen|ethanol-water (19:1)|food|food_source_animal|G74022|not applicable|not applicable|not applicable|MSV000083010_G74022|2018
+132950	MSV000082074	f.MSV000082074/ccms_peak/Samples/G74022_5x_BG11_01_18395.mzML	574	 
+132950	MSV000082074	f.MSV000082074/ccms_peak/Samples/G74022_5x_BG11_01_18395.mzML	570	 
+18313	MSV000081936	f.MSV000081936/ccms_peak/animal/G74022_5x_BG11_01_18395.mzML	574	 
+18313	MSV000081936	f.MSV000081936/ccms_peak/animal/G74022_5x_BG11_01_18395.mzML	570	 
+5636	MSV000081657	f.MSV000081657/ccms_peak/data_mzxml/Samples/G74022_5x_BG11_01_18395.mzML	574	 
+5636	MSV000081657	f.MSV000081657/ccms_peak/data_mzxml/Samples/G74022_5x_BG11_01_18395.mzML	570	 
+3558643	MSV000080673	f.MSV000080673/ccms_peak/2017.AmericanGut3K.mzXMLfiles/Samples/000036206_RC2_01_5354.mzML	763	GNPS_AmericanGut3K_dataset|14|female|reverse phase (C18)|no disease reported|United States of America|disease NOS|disease NOS|5.8|unhealthy (NOS)|Urban|sulfamethizole;sulfachloropyridazine|electrospray ionization (positive)|40.7|-74|Adolescence (8 yrs < x <= 18 yrs)|impact HD|MS:1002667|9606|Homo sapiens|10/10/2015 13:15|swabs, dry|ethanol-water (9:1)|animal|biofluid|36206|not applicable|feces|UBERON:0001988|MSV000080673_36206|2017
+3558643	MSV000080673	f.MSV000080673/ccms_peak/2017.AmericanGut3K.mzXMLfiles/Samples/000036206_RC2_01_5354.mzML	760	GNPS_AmericanGut3K_dataset|14|female|reverse phase (C18)|no disease reported|United States of America|disease NOS|disease NOS|5.8|unhealthy (NOS)|Urban|sulfamethizole;sulfachloropyridazine|electrospray ionization (positive)|40.7|-74|Adolescence (8 yrs < x <= 18 yrs)|impact HD|MS:1002667|9606|Homo sapiens|10/10/2015 13:15|swabs, dry|ethanol-water (9:1)|animal|biofluid|36206|not applicable|feces|UBERON:0001988|MSV000080673_36206|2017
+3558643	MSV000080673	f.MSV000080673/ccms_peak/2017.AmericanGut3K.mzXMLfiles/Samples/000011075_RH2_01_6313.mzML	845	GNPS_AmericanGut3K_dataset|44|female|reverse phase (C18)|no disease reported|United States of America|disease NOS|disease NOS|17.3|unhealthy (NOS)|Urban|sulfamethizole;sulfachloropyridazine|electrospray ionization (positive)|37|-122|Early Adulthood (18 yrs < x <= 45 yrs)|impact HD|MS:1002667|9606|Homo sapiens|1/4/2016 9:00|swabs, dry|ethanol-water (9:1)|animal|biofluid|11075|not applicable|feces|UBERON:0001988|MSV000080673_11075|2017
+3558643	MSV000080673	f.MSV000080673/ccms_peak/2017.AmericanGut3K.mzXMLfiles/Samples/000011075_RH2_01_6313.mzML	840	GNPS_AmericanGut3K_dataset|44|female|reverse phase (C18)|no disease reported|United States of America|disease NOS|disease NOS|17.3|unhealthy (NOS)|Urban|sulfamethizole;sulfachloropyridazine|electrospray ionization (positive)|37|-122|Early Adulthood (18 yrs < x <= 45 yrs)|impact HD|MS:1002667|9606|Homo sapiens|1/4/2016 9:00|swabs, dry|ethanol-water (9:1)|animal|biofluid|11075|not applicable|feces|UBERON:0001988|MSV000080673_11075|2017
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn15_CL21_F11.mzXML	721	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn15_CL21_F07.mzXML	749	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn15_CL21_F07.mzXML	709	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn12_CL21_F03.mzXML	753	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn12_CL21_F03.mzXML	711	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn12_CL21_F03.mzXML	673	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn12_CL21_E11.mzXML	730	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn12_CL21_E11.mzXML	691	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn11_CL21_E07.mzXML	705	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn11_CL21_E03.mzXML	737	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn11_CL21_E03.mzXML	699	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn10_Bsubt_D11.mzXML	753	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn10_Bsubt_D11.mzXML	713	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn10_Bsubt_D11.mzXML	675	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn10_Bsubt_D08.mzXML	726	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn10_Bsubt_D07.mzXML	744	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn10_Bsubt_D07.mzXML	700	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn08_Bsubt_D03.mzXML	728	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn08_Bsubt_D03.mzXML	688	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn08_Bsubt_C11.mzXML	737	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn08_Bsubt_C11.mzXML	698	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn05_control_B11.mzXML	697	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn05_control_B07.mzXML	728	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn05_control_B07.mzXML	683	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn04_control_B03.mzXML	733	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn04_control_B03.mzXML	693	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn04_control_B02.mzXML	699	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn02_control_A07.mzXML	706	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn02_control_A07.mzXML	666	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn02_control_A03.mzXML	733	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn02_control_A03.mzXML	692	 
+22273	MSV000079888	f.MSV000079888/ccms_peak/mzXML/Corn02_control_A03.mzXML	649	 

search_single_spectrum/tools/search_single_spectrum/xic_masst.py

@@ -0,0 +1,104 @@
+#!/usr/bin/env python
+
+import os
+import pymzml
+import pandas as pd
+import shutil
+import urllib.request as request
+from contextlib import closing
+
+
+
+def process_masst_xic(input_filename):
+    df = pd.read_csv(input_filename, sep="\t")
+
+    ms2_records = df.to_dict(orient="records")
+    for record in ms2_records:
+        # Making data file available
+        ftp_url = "ftp://massive.ucsd.edu/" + record["filename"][2:]
+        local_filename = os.path.basename(record["filename"])
+        with closing(request.urlopen(ftp_url)) as r:
+            with open(local_filename, 'wb') as f:
+                shutil.copyfileobj(r, f)
+
+        # Finding the scan
+        run = pymzml.run.Reader(local_filename)
+
+        target_scan = record["filescan"]
+        for spectrum in run:
+            if str(spectrum.ID) == str(target_scan):
+                selected_precursors = spectrum.selected_precursors
+                precursor_dict = selected_precursors[0]
+                precursor_mz = precursor_dict["mz"]
+                precursor_i = precursor_dict["i"]
+
+                record["precursor_mz"] = precursor_mz
+                record["precursor_i"] = precursor_i
+                record["rt"] = spectrum.scan_time_in_minutes()        
+
+        # Perform XIC
+        target_mz = record["precursor_mz"]
+        lower_rt = record["rt"] - 0.1
+        upper_rt = record["rt"] + 0.1
+        run = pymzml.run.Reader(local_filename, MS_precisions={1 : 5e-6, 2 : 20e-6})
+        time_dependent_intensities = []
+
+        for spectrum in run:
+            spectrum_rt = float(spectrum.scan_time_in_minutes())
+            if spectrum_rt < lower_rt or spectrum_rt > upper_rt:
+                continue
+
+            if spectrum.ms_level == 1:
+                has_peak_matches = spectrum.has_peak(target_mz)
+                if has_peak_matches != []:
+                    for mz, I in has_peak_matches:
+                        time_dependent_intensities.append(
+                            [spectrum.scan_time_in_minutes(), I, mz]
+                        )
+
+        intensity = sum([peak[2] for peak in time_dependent_intensities])
+        record["xic_sum"] = (intensity)
+
+        print(record)
+
+        os.remove(local_filename)
+
+    return pd.DataFrame(ms2_records)
+
+
+def main():
+    """
+    Demonstration of the extraction of a specific ion chromatogram, i.e. XIC or EIC
+
+    All intensities and m/z values for a target m/z are extracted.
+
+    usage:
+
+        ./extract_ion_chromatogram.py
+
+    """
+
+    example_file = os.path.join(
+        os.path.dirname(__file__), os.pardir, "tests", "data", "example.mzML"
+    )
+    run = pymzml.run.Reader(example_file)
+    time_dependent_intensities = []
+
+    MZ_2_FOLLOW = 70.06575775
+
+    for spectrum in run:
+        if spectrum.ms_level == 1:
+            has_peak_matches = spectrum.has_peak(MZ_2_FOLLOW)
+            if has_peak_matches != []:
+                for mz, I in has_peak_matches:
+                    time_dependent_intensities.append(
+                        [spectrum.scan_time_in_minutes(), I, mz]
+                    )
+    print("RT   \ti   \tmz")
+    for rt, i, mz in time_dependent_intensities:
+        print("{0:5.3f}\t{1:13.4f}\t{2:10}".format(rt, i, mz))
+    return
+
+
+if __name__ == "__main__":
+    main()

workflow-integration-misc-tests/test_tasks.csv

@@ -2,4 +2,5 @@ task_id,description,regressioncountviews
 adc3ec9194de43f7b97a61369bf2d7f6,ms2lda,
 73da384ea02a4e8ca3edd82649e540c3,msms-chooser,
 1df2ea6e406447dfaa7a8b3ea23bf9e1,batchvalidator,new_annotations
-2b7b4e189177498f8f95ea217ff351ff,lc_mzmine2 small test,
+2b7b4e189177498f8f95ea217ff351ff,lc_mzmine2 small test,
+3484239c925b46dda8c1bf5a7e6d592b,sirius,compound_identifications_summary;compound_formula_summary