Merge branch 'centroid_adduct_fix' into 'master'

Centroid handling and adduct reporting fix Closes #123 and #125 See merge request mass-spectrometry/corems!82
EMSL-Computing · Mar 20, 2024 · e02f8b3 · e02f8b3
2 parents 6136b42 + c107426
commit e02f8b3
Show file tree

Hide file tree

Showing 26 changed files with 11,442 additions and 10,196 deletions.
diff --git a/NEG_ESI_SRFA_CoreMS_prob_score.csv b/NEG_ESI_SRFA_CoreMS_prob_score.csv
@@ -0,0 +1,21 @@
+Index,m/z,Calibrated m/z,Calculated m/z,Peak Height,Peak Area,Resolving Power,S/N,Ion Charge,m/z Error (ppm),m/z Error Score,Isotopologue Similarity,Confidence Score,DBE,H/C,O/C,Heteroatom Class,Ion Type,Adduct,Is Isotopologue,Mono Isotopic Index,Molecular Formula,C,H,O,N
+0,576.0751562737335,576.0751562737335,576.0756831376291,2019730.8188135864,nan,159720.69595125286,8.604138304064543,-1,-0.9145740933897943,0.8591841639497192,0.0,0.5155104983698315,16.0,0.8,0.64,O16 -R,radical,,0,,C25 H20 O16,25,20,16,
+1,585.0773168347159,585.0773168347159,584.069022064519,1746260.2046435073,nan,275209.4679144153,7.43914197658413,-1,1726.3281086760753,0.0,0.0,0.0,35.5,0.3170731707317073,0.12195121951219512,O5,de-protonated,,0,,C41 H13 O5,41,13,5,
+2,593.0820452356501,593.0820452356501,592.074107444949,6469034.8640819015,nan,180997.3119366648,27.55836082011744,-1,1702.3845123893364,0.0,0.0,0.0,37.5,0.3023255813953488,0.09302325581395349,O4,de-protonated,,0,,C43 H13 O4,43,13,4,
+3,597.0754291924612,597.0754291924612,597.076017490259,2068238.426915153,nan,134839.10894778575,8.810782756393296,-1,-0.9852979864257353,0.8384900332430503,0.0,0.5030940199458301,19.0,0.7037037037037037,0.5555555555555556,N1 O15 -R,radical,,0,,C27 H19 O15 N1,27,19,15,1
+4,605.0809297183079,605.0809297183079,605.081102870689,4934544.835880899,nan,152063.12451789412,21.02136870915638,-1,-0.2861639214521796,0.9852510523460122,0.0,0.5911506314076073,21.0,0.6551724137931034,0.4827586206896552,N1 O14 -R,radical,,0,,C29 H19 O14 N1,29,19,14,1
+5,567.0647395512881,567.0647395512881,,3868906.6064003,nan,162257.55310330895,16.481704995981246,-1,,,,,,,,unassigned,,,,,,,,,
+6,567.0663087811229,567.0663087811229,,5463881.346367143,nan,162258.1245318804,23.276364525029468,-1,,,,,,,,unassigned,,,,,,,,,
+7,575.0713087215903,575.0713087215903,,9739433.203502472,nan,186665.9786183644,41.49039540593753,-1,,,,,,,,unassigned,,,,,,,,,
+8,580.0696581879541,580.0696581879541,,1759661.6215911638,nan,185057.4786056693,7.496232576882939,-1,,,,,,,,unassigned,,,,,,,,,
+9,583.0745286807011,583.0745286807011,,3341444.3943076613,nan,157802.2673899728,14.234693770159195,-1,,,,,,,,unassigned,,,,,,,,,
+10,583.0764232748777,583.0764232748777,,4624182.129382659,nan,157802.6959610134,19.69921051547032,-1,,,,,,,,unassigned,,,,,,,,,
+11,587.0717089529447,587.0717089529447,,9364333.081322271,nan,156728.69594017448,39.89245309647384,-1,,,,,,,,unassigned,,,,,,,,,
+12,588.0748249834461,588.0748249834461,,2102297.732396686,nan,273806.7179139468,8.955876831392676,-1,,,,,,,,unassigned,,,,,,,,,
+13,595.0748319653359,595.0748319653359,,2248638.4360681637,nan,135292.60896146248,9.57929438890816,-1,,,,,,,,unassigned,,,,,,,,,
+14,595.0769607848,595.0769607848,,2614726.533038756,nan,135293.10896192447,11.138845091638458,-1,,,,,,,,unassigned,,,,,,,,,
+15,597.0775112334587,597.0775112334587,,2624788.5554853342,nan,154102.55308819498,11.18170973079855,-1,,,,,,,,unassigned,,,,,,,,,
+16,601.0851016849045,601.0851016849045,,3264511.328060631,nan,133939.60894898468,13.906955669626551,-1,,,,,,,,unassigned,,,,,,,,,
+17,605.0824960183015,605.0824960183015,,5173077.227051935,nan,152063.55308892002,22.03752673601681,-1,,,,,,,,unassigned,,,,,,,,,
+18,613.0848231619533,613.0848231619533,,2643269.346562413,nan,116727.207961776,11.26043867869326,-1,,,,,,,,unassigned,,,,,,,,,
+19,613.0872526006148,613.0872526006148,,4497043.9691487,nan,350181.62381927815,19.157596601285515,-1,,,,,,,,unassigned,,,,,,,,,
diff --git a/NEG_ESI_SRFA_CoreMS_prob_score.json b/NEG_ESI_SRFA_CoreMS_prob_score.json
@@ -0,0 +1,201 @@
+{
+    "MassSpecAttrs": {
+        "Aterm": null,
+        "Bterm": null,
+        "Cterm": null,
+        "baseline_noise": 1746260.2046435073,
+        "baseline_noise_std": 0.0,
+        "mobility_rt": 0,
+        "mobility_scan": 0,
+        "polarity": -1,
+        "rt": 0,
+        "tic": 80568004.66102132
+    },
+    "MassSpecPeak": {
+        "implemented_kendrick_rounding_methods": [
+            "floor",
+            "ceil",
+            "round"
+        ],
+        "kendrick_base": {
+            "C": 1,
+            "H": 2
+        },
+        "kendrick_rounding_method": "floor",
+        "legacy_resolving_power": true,
+        "min_peak_datapoints": 5.0,
+        "peak_derivative_threshold": 0.0,
+        "peak_height_max_percent": 10.0,
+        "peak_max_prominence_percent": 0.1,
+        "peak_min_prominence_percent": 0.1
+    },
+    "MassSpectrum": {
+        "calib_minimize_method": "Powell",
+        "calib_pol_order": 2,
+        "calib_sn_threshold": 2.0,
+        "do_calibration": true,
+        "max_calib_ppm_error": 1.0,
+        "max_picking_mz": 1200.0,
+        "min_calib_ppm_error": -1.0,
+        "min_picking_mz": 50.0,
+        "noise_max_mz": 1200.0,
+        "noise_min_mz": 50.0,
+        "noise_threshold_absolute_abundance": 1000000.0,
+        "noise_threshold_log_nsigma": 6,
+        "noise_threshold_log_nsigma_bins": 500,
+        "noise_threshold_log_nsigma_corr_factor": 0.463,
+        "noise_threshold_method": "relative_abundance",
+        "noise_threshold_methods_implemented": [
+            "minima",
+            "signal_noise",
+            "relative_abundance",
+            "absolute_abundance",
+            "log"
+        ],
+        "noise_threshold_min_relative_abundance": 1,
+        "noise_threshold_min_s2n": 4.0,
+        "noise_threshold_min_std": 6,
+        "picking_point_extrapolate": 3
+    },
+    "MolecularFormulaSearch": {
+        "adduct_atoms_neg": [
+            "Cl",
+            "Br"
+        ],
+        "adduct_atoms_pos": [
+            "Na",
+            "K"
+        ],
+        "db_chunk_size": 300,
+        "db_jobs": 3,
+        "error_method": "None",
+        "ion_charge": -1,
+        "ionization_type": "ESI",
+        "isAdduct": false,
+        "isProtonated": true,
+        "isRadical": false,
+        "isotopologue_filter_atoms": [
+            "Cl",
+            "Br"
+        ],
+        "isotopologue_filter_threshold": 33.0,
+        "isotopologue_score_weight": 0.4,
+        "max_abun_error": 100.0,
+        "max_dbe": 40.0,
+        "max_hc_filter": 3.0,
+        "max_oc_filter": 1.2,
+        "max_ppm_error": 10.0,
+        "min_abun_error": -100.0,
+        "min_dbe": 0.0,
+        "min_hc_filter": 0.3,
+        "min_oc_filter": 0.0,
+        "min_op_filter": 2.0,
+        "min_peaks_per_class": 15,
+        "min_ppm_error": -10.0,
+        "mz_error_average": 0.0,
+        "mz_error_range": 1.5,
+        "mz_error_score_weight": 0.6,
+        "output_min_score": 0.1,
+        "output_score_method": "prob_score",
+        "score_method": "prob_score",
+        "score_methods": [
+            "S_P_lowest_error",
+            "N_S_P_lowest_error",
+            "lowest_error",
+            "prob_score",
+            "air_filter_error",
+            "water_filter_error",
+            "earth_filter_error"
+        ],
+        "url_database": "postgresql+psycopg2://coremsappdb:coremsapppnnl@molformdb:5432/coremsapp",
+        "use_isotopologue_filter": false,
+        "use_min_peaks_filter": true,
+        "use_pah_line_rule": false,
+        "use_runtime_kendrick_filter": false,
+        "usedAtoms": {
+            "C": [
+                1,
+                100
+            ],
+            "H": [
+                1,
+                200
+            ]
+        },
+        "used_atom_valences": {
+            "13C": 4,
+            "Ac": 3,
+            "Ag": 0,
+            "Al": 3,
+            "As": 5,
+            "At": 1,
+            "Au": 3,
+            "B": 4,
+            "Ba": 2,
+            "Be": 2,
+            "Bi": 3,
+            "Br": 1,
+            "C": 4,
+            "Ca": 2,
+            "Cd": 2,
+            "Cl": 1,
+            "Co": 1,
+            "Cr": 1,
+            "Cs": 1,
+            "Cu": 2,
+            "F": 1,
+            "Fe": 3,
+            "Fr": 1,
+            "Ga": 3,
+            "Ge": 4,
+            "H": 1,
+            "Hf": 4,
+            "Hg": 1,
+            "I": 1,
+            "In": 3,
+            "Ir": 4,
+            "K": 1,
+            "La": 3,
+            "Li": 1,
+            "Mg": 2,
+            "Mn": 1,
+            "Mo": 6,
+            "N": 3,
+            "Na": 1,
+            "Nb": 5,
+            "Ni": 1,
+            "O": 2,
+            "Os": 4,
+            "P": 3,
+            "Pb": 4,
+            "Pd": 4,
+            "Po": 2,
+            "Pt": 4,
+            "Ra": 2,
+            "Rb": 1,
+            "Re": 4,
+            "Rh": 6,
+            "Ru": 8,
+            "S": 2,
+            "Sb": 5,
+            "Sc": 3,
+            "Se": 6,
+            "Si": 4,
+            "Sn": 4,
+            "Sr": 2,
+            "Ta": 5,
+            "Tc": 7,
+            "Te": 6,
+            "Ti": 4,
+            "Tl": 3,
+            "V": 5,
+            "W": 6,
+            "Y": 3,
+            "Zn": 2,
+            "Zr": 4
+        }
+    },
+    "analyzer": "Unknown",
+    "instrument_label": "Unknown",
+    "sample_name": "ESI_NEG_SRFA_COREMS"
+}
diff --git a/README.md b/README.md
@@ -1,4 +1,4 @@
-![CoreMS Logo](https://github.com/EMSL-Computing/CoreMS/blob/v2.0.1/docs/CoreMS.COLOR_small.png?raw=true)  
+![CoreMS Logo](https://github.com/EMSL-Computing/CoreMS/tree/master/docs/CoreMS.COLOR_small.png?raw=true)  
 
 <div align="left">
 

diff --git a/corems/mass_spectrum/factory/MassSpectrumClasses.py b/corems/mass_spectrum/factory/MassSpectrumClasses.py
@@ -1376,6 +1376,8 @@ def __init__(self, data_dict, d_params, auto_process=True):
 
         self.is_centroid = True
         self.data_dict = data_dict
+        self._mz_exp = data_dict[Labels.mz]
+        self._abundance = data_dict[Labels.abundance]
 
         if auto_process:
             self.process_mass_spec()

diff --git a/corems/mass_spectrum/input/massList.py b/corems/mass_spectrum/input/massList.py
@@ -83,6 +83,10 @@ def add_molecular_formula(self, mass_spec_obj, dataframe):
             ion_type_df = dataframe["Ion Type"]
             ion_charge_df = dataframe["Ion Charge"]
             is_isotopologue_df = dataframe['Is Isotopologue']
+            if 'Adduct' in dataframe:
+                adduct_df = dataframe['Adduct']
+            else:
+                adduct_df = None
 
         mass_spec_mz_exp_list = mass_spec_obj.mz_exp
 
@@ -102,7 +106,11 @@ def add_molecular_formula(self, mass_spec_obj, dataframe):
             if sum(counts) > 0:
 
                 ion_type = str(Labels.ion_type_translate.get(ion_type_df[df_index]))
-                mfobj = MolecularFormula(formula_list, int(ion_charge_df[df_index]), mspeak_parent=mass_spec_obj[ms_peak_index] , ion_type=ion_type)
+                if adduct_df is not None:
+                    adduct_atom = str(adduct_df[df_index])
+                else:
+                    adduct_atom = None
+                mfobj = MolecularFormula(formula_list, int(ion_charge_df[df_index]), mspeak_parent=mass_spec_obj[ms_peak_index] , ion_type=ion_type, adduct_atom=adduct_atom)
                 mfobj.is_isotopologue = bool(is_isotopologue_df[df_index])
                 mass_spec_obj[ms_peak_index].add_molecular_formula(mfobj)
 

diff --git a/corems/mass_spectrum/input/numpyArray.py b/corems/mass_spectrum/input/numpyArray.py
@@ -7,19 +7,27 @@
 from corems.encapsulation.constant import Labels
 
 def ms_from_array_profile(mz, abundance, dataname:str, polarity:int = -1, auto_process:bool = True, data_type:str = Labels.simulated_profile):
-    """
-    Create a MassSpecProfile object from an array of m/z values and abundance values.
+    """Create a MassSpecProfile object from an array of m/z values and abundance values.
 
-    Parameters:
-        mz (numpy.ndarray): Array of m/z values.
-        abundance (numpy.ndarray): Array of abundance values.
-        dataname (str): Name of the data.
-        polarity (int, optional): Polarity of the data. Defaults to -1.
-        auto_process (bool, optional): Flag to automatically process the data. Defaults to True.
-        data_type (str, optional): Type of the data. Defaults to Labels.simulated_profile.
+    Parameters
+    ----------
+    mz : numpy.ndarray
+        Array of m/z values.
+    abundance : numpy.ndarray
+        Array of abundance values.
+    dataname : str
+        Name of the data.
+    polarity : int, optional
+        Polarity of the data. The default is -1.
+    auto_process : bool, optional
+        Flag to automatically process the data. The default is True.
+    data_type : str, optional
+        Type of the data. The default is Labels.simulated_profile.
 
-    Returns:
-        MassSpecProfile: The created MassSpecProfile object.
+    Returns
+    -------
+    MassSpecProfile
+        The created MassSpecProfile object.
     """
     data_dict = {Labels.mz: mz, Labels.abundance: abundance}
 
@@ -32,37 +40,50 @@ def ms_from_array_profile(mz, abundance, dataname:str, polarity:int = -1, auto_p
     return ms
 
 def ms_from_array_centroid(mz, abundance, rp:list[float], s2n:list[float], dataname:str, polarity:int=-1, auto_process:bool=True):
-    """
-    Create a MassSpecCentroid object from an array of m/z values, abundance values, resolution power, and signal-to-noise ratio.
+    """Create a MassSpecCentroid object from an array of m/z values, abundance values, resolution power, and signal-to-noise ratio.
 
-    Parameters:
-        mz (numpy.ndarray): Array of m/z values.
-        abundance (numpy.ndarray): Array of abundance values.
-        rp list(float): Resolution power.
-        s2n list(float): Signal-to-noise ratio.
-        dataname (str): Name of the data.
-        polarity (int, optional): Polarity of the data. Defaults to -1.
-        auto_process (bool, optional): Flag to automatically process the data. Defaults to True.
+    Parameters
+    ----------
+    mz : numpy.ndarray
+        Array of m/z values.
+    abundance : numpy.ndarray
+        Array of abundance values.
+    rp : list(float)
+        List of resolving power values.
+    s2n : list(float)
+        List of signal-to-noise ratio values.
+    dataname : str
+        Name of the data.
+    polarity : int, optional
+        Polarity of the data. The default is -1.
+    auto_process : bool, optional
 
-    Returns:
-        MassSpecCentroid: The created MassSpecCentroid object.
+    Returns
+    -------
+    MassSpecCentroid
+        The created MassSpecCentroid object.
     """
     data_dict = {Labels.mz: mz, Labels.abundance: abundance, Labels.s2n : s2n, Labels.rp: rp}
 
     output_parameters = get_output_parameters(polarity, dataname)
-
-    return MassSpecCentroid(data_dict, output_parameters)
+    output_parameters[Labels.label] = Labels.corems_centroid
+
+    return MassSpecCentroid(data_dict, output_parameters, auto_process)
 
 def get_output_parameters(polarity:int, file_location:str):
-    """
-    Get the output parameters for creating a MassSpecProfile or MassSpecCentroid object.
+    """Generate the output parameters for creating a MassSpecProfile or MassSpecCentroid object.
 
-    Parameters:
-        polarity (int): Polarity of the data.
-        file_location (str): File location.
+    Parameters
+    ----------
+    polarity : int
+        Polarity of the data.
+    file_location : str
+        File location.
 
-    Returns:
-        dict: Output parameters.
+    Returns
+    -------
+    dict
+        Output parameters.
     """
     d_params = default_parameters(file_location)