masster 0.3.10__py3-none-any.whl → 0.3.11__py3-none-any.whl

masster/study/export.py

@@ -18,13 +18,13 @@ from masster._version import get_version
 def _get_mgf_df(self, **kwargs):
     """
     Generate MGF data as a Polars DataFrame.
-    
+
     This is the core data generation function used by export_mgf().
-    
+
     Parameters:
-        **kwargs: Keyword arguments for export parameters. Same as export_mgf() 
+        **kwargs: Keyword arguments for export parameters. Same as export_mgf()
                  except return_data is not relevant here.
-    
+
     Returns:
         pl.DataFrame: DataFrame with columns:
             - mgf_index: MGF index
@@ -115,37 +115,37 @@ def _get_mgf_df(self, **kwargs):
         """Create a dictionary representing an ion for the DataFrame."""
         if spect is None:
             return None
-        
+
         # Prepare spectrum data
-        spectrum_mz = spect.mz.tolist() if hasattr(spect.mz, 'tolist') else list(spect.mz)
-        spectrum_inty = spect.inty.tolist() if hasattr(spect.inty, 'tolist') else list(spect.inty)
-        
+        spectrum_mz = spect.mz.tolist() if hasattr(spect.mz, "tolist") else list(spect.mz)
+        spectrum_inty = spect.inty.tolist() if hasattr(spect.inty, "tolist") else list(spect.inty)
+
         # Determine MS level
         ms_level = spect.ms_level if spect.ms_level is not None else 1
-        
+
         # Get energy if available
-        energy = getattr(spect, 'energy', None)
-        
+        energy = getattr(spect, "energy", None)
+
         # Determine spectrum type based on MS level
         spec_type = f"MS{ms_level}" if ms_level > 1 else "MS1"
-        
+
         # Calculate spectrum length
         spec_len = len(spectrum_mz)
-        
+
         return {
-            'mgf_index': mgf_id,
-            'title': title,
-            'feature_id': id,
-            'feature_uid': uid,
-            'charge': charge,
-            'pepmass': mz,
-            'rtinseconds': rt,
-            'mslevel': ms_level,
-            'type': spec_type,
-            'energy': energy,
-            'spec_len': spec_len,
-            'spec_mz': spectrum_mz,
-            'spec_int': spectrum_inty,
+            "mgf_index": mgf_id,
+            "title": title,
+            "feature_id": id,
+            "feature_uid": uid,
+            "charge": charge,
+            "pepmass": mz,
+            "rtinseconds": rt,
+            "mslevel": ms_level,
+            "type": spec_type,
+            "energy": energy,
+            "spec_len": spec_len,
+            "spec_mz": spectrum_mz,
+            "spec_int": spectrum_inty,
         }
 
     # Collect all ion data
@@ -153,7 +153,7 @@ def _get_mgf_df(self, **kwargs):
     skip = 0
     mgf_counter = 0
     self.logger.info(f"Generating MGF data for {len(grouped)} consensus features...")
-    
+
     tdqm_disable = self.log_level not in ["TRACE", "DEBUG", "INFO"]
     for _consensus_uid, cons_ms2 in tqdm(
         grouped,
@@ -308,7 +308,7 @@ def _get_mgf_df(self, **kwargs):
     # Convert to Polars DataFrame
     if not ion_data:
         return pl.DataFrame()
-    
+
     return pl.DataFrame(ion_data)
 
 
@@ -336,13 +336,13 @@ def export_mgf(self, **kwargs):
         verbose (bool): Enable verbose logging (default: False).
         precursor_trim (float): Precursor trimming value (default: -10).
         centroid_algo (str): Centroiding algorithm (default: "lmp").
-        
+
     Returns:
         None: Writes MGF file to disk.
     """
     # Get mgf data as DataFrame
     mgf_data = self._get_mgf_df(**kwargs)
-    
+
     if mgf_data is None or len(mgf_data) == 0:
         self.logger.warning("No MGF data generated.")
         return
@@ -355,9 +355,9 @@ def export_mgf(self, **kwargs):
         else:
             if hasattr(params, key):
                 params.set(key, value, validate=True)
-    
+
     filename = params.get("filename")
-    
+
     # Prepare output path
     if not os.path.isabs(filename):
         if self.folder is not None:
@@ -370,7 +370,7 @@ def export_mgf(self, **kwargs):
         for row in mgf_data.iter_rows(named=True):
             # Write BEGIN IONS
             f.write("BEGIN IONS\n")
-            
+
             # Write metadata
             if row["mgf_index"] is not None:
                 f.write(f"INDEX={row['mgf_index']}\n")
@@ -381,19 +381,19 @@ def export_mgf(self, **kwargs):
             f.write(f"PEPMASS={row['pepmass']}\n")
             f.write(f"RTINSECONDS={row['rtinseconds']}\n")
             f.write(f"MSLEVEL={row['mslevel']}\n")
-            
+
             if row["energy"] is not None:
                 f.write(f"ENERGY={row['energy']}\n")
-            
+
             # Write spectrum data
             spectrum_mz = row["spec_mz"]
             spectrum_inty = row["spec_int"]
             for mz_val, inty in zip(spectrum_mz, spectrum_inty, strict=False):
                 f.write(f"{mz_val:.5f} {inty:.0f}\n")
-            
+
             # Write END IONS
             f.write("END IONS\n\n")
-    
+
     self.logger.info(f"Exported {len(mgf_data)} spectra to {filename}")
 
 
@@ -414,45 +414,47 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
             filename = os.path.join(self.folder, filename)
         else:
             filename = os.path.join(os.getcwd(), filename)
-    
+
     # get mgf data
     mgf_data = self._get_mgf_df(**kwargs)
     # Create mapping from feature_uid to MGF indexes
     mgf_mapping: dict[str, list[int]] = {}
     if mgf_data is not None and len(mgf_data) > 0:
         for row in mgf_data.iter_rows(named=True):
-            feature_uid = row['feature_uid']
-            mgf_index = row['mgf_index']
+            feature_uid = row["feature_uid"]
+            mgf_index = row["mgf_index"]
             if feature_uid not in mgf_mapping:
                 mgf_mapping[feature_uid] = []
             mgf_mapping[feature_uid].append(mgf_index)
-    
+
     # --- Prepare MTD (metadata) section ---
     mtd_lines = []
     mtd_lines.append(f"COM file generated by MASSter on {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
     mtd_lines.append("\nMTD\tmzTab-version\t2.2.0-M")
     id = self.label if self.label else self.folder
     mtd_lines.append(f"MTD\tmzTab-id\t{id}")
-    mtd_lines.append('')
+    mtd_lines.append("")
     mtd_lines.append("MTD\tcv[1]-label\tMS")
     mtd_lines.append("MTD\tcv[1]-full_name\tPSI-MS controlled vocabulary")
     mtd_lines.append("MTD\tcv[1]-version\t4.1.199")
     mtd_lines.append("MTD\tcv[1]-uri\thttps://raw.githubusercontent.com/HUPO-PSI/psi-ms-CV/master/psi-ms.obo")
-    mtd_lines.append('')
+    mtd_lines.append("")
     mtd_lines.append("MTD\tsmall_molecule-quantification_unit\t[MS, MS:1001844, MS1 feature area, ]")
     mtd_lines.append("MTD\tsmall_molecule_feature-quantification_unit\t[MS, MS:1001844, MS1 feature area, ]")
-    mtd_lines.append("MTD\tsmall_molecule-identification_reliability\t[MS, MS:1002955, hr-ms compound identification confidence level, ]")
+    mtd_lines.append(
+        "MTD\tsmall_molecule-identification_reliability\t[MS, MS:1002955, hr-ms compound identification confidence level, ]"
+    )
     mtd_lines.append("MTD\tid_confidence_measure[1]\t[MS, MS:1002888, small molecule confidence measure, ]")
-    mtd_lines.append('')
+    mtd_lines.append("")
     mtd_lines.append("MTD\tsoftware[1]\t[MS, MS:1003430, OpenMS, unknown]")
     mtd_lines.append(f"MTD\tsoftware[2]\t[MS, MS:1002878, MASSter, {get_version()}]")
     mtd_lines.append("MTD\tquantification_method\t[MS, MS:1001834, LC-MS label-free quantitation analysis, ]")
-    mtd_lines.append('')
-    mtd_lines.append("MTD\tdatabase[1]\t[, , \"no database\", null]")
+    mtd_lines.append("")
+    mtd_lines.append('MTD\tdatabase[1]\t[, , "no database", null]')
     mtd_lines.append("MTD\tdatabase[1]-prefix\tnull")
     mtd_lines.append("MTD\tdatabase[1]-version\tUnknown")
     mtd_lines.append("MTD\tdatabase[1]-uri\tnull")
-    #mtd_lines.append('')
+    # mtd_lines.append('')
     for i, row in enumerate(self.samples_df.iter_rows(named=True), 1):
         mtd_lines.append(f"\nMTD\tsample[{i}]\t{row.get('sample_uid', f'sample_{i}')}")
         mtd_lines.append(f"MTD\tsample[{i}]-description\t{row.get('sample_name', 'unknown')}")
@@ -460,15 +462,15 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
         mtd_lines.append(f"MTD\tassay[{i}]\tAssay_{i}")
         mtd_lines.append(f"MTD\tassay[{i}]-sample_ref\tsample[{i}]")
         mtd_lines.append(f"MTD\tassay[{i}]-ms_run_ref\tms_run[{i}]")
-    mtd_lines.append('')
+    mtd_lines.append("")
     mtd_lines.append("MTD\tstudy_variable[1]\tundefined")
     mtd_lines.append("MTD\tstudy_variable[1]_refs\tundefined")
-    #assay_refs = '|'.join([f"assay[{i}]" for i in range(1, len(self.samples_df)+1)])
-    #mtd_lines.append(f"MTD\tstudy_variable[1]-assay_refs\t{assay_refs}")
-    #mtd_lines.append("MTD\tstudy_variable[1]-description\tAll assays grouped (default)")
-    with open(filename, 'w', encoding='utf-8') as f:
+    # assay_refs = '|'.join([f"assay[{i}]" for i in range(1, len(self.samples_df)+1)])
+    # mtd_lines.append(f"MTD\tstudy_variable[1]-assay_refs\t{assay_refs}")
+    # mtd_lines.append("MTD\tstudy_variable[1]-description\tAll assays grouped (default)")
+    with open(filename, "w", encoding="utf-8") as f:
         for line in mtd_lines:
-            f.write(line + '\n')
+            f.write(line + "\n")
 
     # --- SML (Small Molecule) table ---
     sml_lines = []
@@ -487,43 +489,54 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
         "reliability",
         "best_id_confidence_measure",
         "best_id_confidence_value",
-        "opt_global_mgf_index",        
+        "opt_global_mgf_index",
     ]
-    
+
     abundance_matrix = self.get_consensus_matrix()
     # Use the matrix as-is since it already has the correct sample columns
     # The matrix columns are sample names, which is what we want for the assay columns
-    
+
     # round to int
     abundance_matrix = abundance_matrix.round(0)
 
     # Use actual number of samples from the abundance matrix
     n_assays = len(abundance_matrix.columns)
-    sml_header += [f"abundance_assay[{i}]" for i in range(1, n_assays+1)]
+    sml_header += [f"abundance_assay[{i}]" for i in range(1, n_assays + 1)]
     sml_header += ["abundance_study_variable[1]", "abundance_variation_study_variable[1]"]
-    sml_lines.append('\t'.join(sml_header))
+    sml_lines.append("\t".join(sml_header))
 
     # get adducts from consensus_df['adducts']. If value is None or [], use 'null'. If there is, take the first element and the first string
     adduct_list = []
-    mapping = {'H1': '[M+H]+', 'H2': '[M+2H]2+', 
-               'Na1': '[M+Na]+', 'Na2': '[M+2Na]2+',
-               'NH4': '[M+NH4]+', 'HCOO': '[M+HCOO]-', 
-               'CH3COO': '[M+CH3COO]-', 'H2O': '[M+H2O]+',
-               'HCO2': '[M+HCO2]-', 'H3PO4': '[M+H3PO4]+',
-               'H3O1': '[M+H3O]+', 'K1': '[M+K]+',
-               'H4N1': '[M+NH4]+', 
-               'H-1': '[M-H]-', 'Cl1': '[M+Cl]-',
-               'Br1': '[M+Br]-', 'I1': '[M+I]-',
-               'H2O2': '[M+H2O2]+', 'H3O2': '[M+H3O2]+',}
+    mapping = {
+        "H1": "[M+H]+",
+        "H2": "[M+2H]2+",
+        "Na1": "[M+Na]+",
+        "Na2": "[M+2Na]2+",
+        "NH4": "[M+NH4]+",
+        "HCOO": "[M+HCOO]-",
+        "CH3COO": "[M+CH3COO]-",
+        "H2O": "[M+H2O]+",
+        "HCO2": "[M+HCO2]-",
+        "H3PO4": "[M+H3PO4]+",
+        "H3O1": "[M+H3O]+",
+        "K1": "[M+K]+",
+        "H4N1": "[M+NH4]+",
+        "H-1": "[M-H]-",
+        "Cl1": "[M+Cl]-",
+        "Br1": "[M+Br]-",
+        "I1": "[M+I]-",
+        "H2O2": "[M+H2O2]+",
+        "H3O2": "[M+H3O2]+",
+    }
     for idx, row in enumerate(self.consensus_df.iter_rows(named=True), 1):
-        adduct = 'null'
-        if 'adducts' in row:
-            row_adducts = row['adducts']
+        adduct = "null"
+        if "adducts" in row:
+            row_adducts = row["adducts"]
             if isinstance(row_adducts, list) and row_adducts:
                 # Each adduct is a dictionary with 'adduct' key
                 first_adduct_dict = row_adducts[0]
-                if isinstance(first_adduct_dict, dict) and 'adduct' in first_adduct_dict:
-                    adduct_str = first_adduct_dict['adduct']
+                if isinstance(first_adduct_dict, dict) and "adduct" in first_adduct_dict:
+                    adduct_str = first_adduct_dict["adduct"]
                     if adduct_str in mapping:
                         adduct = mapping[adduct_str]
                     else:
@@ -533,46 +546,46 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
 
     for idx, row in enumerate(self.consensus_df.iter_rows(named=True), 1):
         # Get MGF indexes for this consensus feature
-        mgf_indexes = mgf_mapping.get(row['consensus_uid'], [])
-        
+        mgf_indexes = mgf_mapping.get(row["consensus_uid"], [])
+
         sml_row = [
             "SML",
             str(idx),
             str(idx),
-            str(row.get('database_identifier', 'null')),
-            str(row.get('chemical_formula', 'null')),
-            str(row.get('smiles', 'null')),
-            str(row.get('inchi', 'null')),
-            str(row.get('chemical_name', 'null')),
-            str(row.get('uri', 'null')),
-            str(row.get('theoretical_neutral_mass', 'null')),
-            adduct_list[idx-1],
-            str(row.get('reliability', 'null')),            
-            str(row.get('best_id_confidence_measure', 'null')),
-            str(row.get('best_id_confidence_value', 'null')),
-            ','.join(map(str, mgf_indexes)) if mgf_indexes else 'null',
+            str(row.get("database_identifier", "null")),
+            str(row.get("chemical_formula", "null")),
+            str(row.get("smiles", "null")),
+            str(row.get("inchi", "null")),
+            str(row.get("chemical_name", "null")),
+            str(row.get("uri", "null")),
+            str(row.get("theoretical_neutral_mass", "null")),
+            adduct_list[idx - 1],
+            str(row.get("reliability", "null")),
+            str(row.get("best_id_confidence_measure", "null")),
+            str(row.get("best_id_confidence_value", "null")),
+            ",".join(map(str, mgf_indexes)) if mgf_indexes else "null",
         ]
         # Add abundance values for each assay
-        consensus_uid = row['consensus_uid']
+        consensus_uid = row["consensus_uid"]
         if consensus_uid in abundance_matrix.index:
             abundance_values = abundance_matrix.loc[consensus_uid].tolist()
-            sml_row += [str(val) if pd.notna(val) else 'null' for val in abundance_values]
+            sml_row += [str(val) if pd.notna(val) else "null" for val in abundance_values]
         else:
-            sml_row += ['null'] * n_assays
-        sml_row += ['null', 'null']
-        sml_lines.append('\t'.join(sml_row))
-    with open(filename, 'a', encoding='utf-8') as f:
-        f.write('\n')
+            sml_row += ["null"] * n_assays
+        sml_row += ["null", "null"]
+        sml_lines.append("\t".join(sml_row))
+    with open(filename, "a", encoding="utf-8") as f:
+        f.write("\n")
         for line in sml_lines:
-            f.write(line + '\n')
+            f.write(line + "\n")
 
     # --- SMF (Small Molecule Feature) table ---
     smf_lines = []
     smf_header = [
         "SFH",
         "SMF_ID",
-        "SME_ID_REFS",
-        "SME_ID_REF_ambiguity_code",
+        "SOME_ID_REFS",
+        "SOME_ID_REF_ambiguity_code",
         "adduct_ion",
         "isotopomer",
         "exp_mass_to_charge",
@@ -581,9 +594,9 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
         "retention_time_in_seconds_start",
         "retention_time_in_seconds_end",
     ]
-    smf_header += [f"abundance_assay[{i}]" for i in range(1, n_assays+1)]
-    smf_lines.append('\t'.join(smf_header))
-    
+    smf_header += [f"abundance_assay[{i}]" for i in range(1, n_assays + 1)]
+    smf_lines.append("\t".join(smf_header))
+
     # SMF table uses the same consensus features as SML, just different metadata
     for idx, row in enumerate(self.consensus_df.iter_rows(named=True), 1):
         smf_row = [
@@ -591,26 +604,26 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
             str(idx),
             "null",
             "null",
-            adduct_list[idx-1],  # adduct_ion
-            str(row.get('isotopomer', 'null')),
-            str(row.get('mz', 'null')),  # exp_mass_to_charge
-            str(row.get('charge', 'null')),
-            str(row.get('rt', 'null')),  # retention_time_in_seconds
-            str(row.get('retention_time_in_seconds_start', 'null')),
-            str(row.get('retention_time_in_seconds_end', 'null')),
+            adduct_list[idx - 1],  # adduct_ion
+            str(row.get("isotopomer", "null")),
+            str(row.get("mz", "null")),  # exp_mass_to_charge
+            str(row.get("charge", "null")),
+            str(row.get("rt", "null")),  # retention_time_in_seconds
+            str(row.get("retention_time_in_seconds_start", "null")),
+            str(row.get("retention_time_in_seconds_end", "null")),
         ]
         # Add abundance values for each assay - same as SML
-        consensus_uid = row['consensus_uid']
+        consensus_uid = row["consensus_uid"]
         if consensus_uid in abundance_matrix.index:
             abundance_values = abundance_matrix.loc[consensus_uid].tolist()
-            smf_row += [str(val) if pd.notna(val) else 'null' for val in abundance_values]
+            smf_row += [str(val) if pd.notna(val) else "null" for val in abundance_values]
         else:
-            smf_row += ['null'] * n_assays
-        smf_lines.append('\t'.join(smf_row))
-    with open(filename, 'a', encoding='utf-8') as f:
-        f.write('\n')
+            smf_row += ["null"] * n_assays
+        smf_lines.append("\t".join(smf_row))
+    with open(filename, "a", encoding="utf-8") as f:
+        f.write("\n")
         for line in smf_lines:
-            f.write(line + '\n')
+            f.write(line + "\n")
 
     # --- MGF table ---
     if include_mgf and mgf_data is not None and len(mgf_data) > 0:
@@ -618,9 +631,9 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
         # Header
         mgf_header = [
             "COM",
-            "MGH", 
+            "MGH",
             "mgf_id",
-            "prec_id", 
+            "prec_id",
             "prec_rt",
             "prec_mz",
             "prec_int",
@@ -630,10 +643,10 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
             "spec_tic",
             "spec_len",
             "spec_mz",
-            "spec_int"
+            "spec_int",
         ]
-        mgf_lines.append('\t'.join(mgf_header))
-        
+        mgf_lines.append("\t".join(mgf_header))
+
         # Data rows
         for row in mgf_data.iter_rows(named=True):
             # Calculate spectrum TIC (total ion current) from the spectrum data
@@ -641,11 +654,11 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
             spectrum_inty = row["spec_int"]
             spec_tic = sum(spectrum_inty) if spectrum_inty else 0
             spec_len = row["spec_len"] if row["spec_len"] is not None else 0
-            
+
             # Format spectrum data as pipe-separated strings
-            spec_mz_str = '|'.join([f"{mz:.4f}" for mz in spectrum_mz]) if spectrum_mz else ""
-            spec_int_str = '|'.join([f"{int(inty)}" for inty in spectrum_inty]) if spectrum_inty else ""
-            
+            spec_mz_str = "|".join([f"{mz:.4f}" for mz in spectrum_mz]) if spectrum_mz else ""
+            spec_int_str = "|".join([f"{int(inty)}" for inty in spectrum_inty]) if spectrum_inty else ""
+
             mgf_row = [
                 "COM",
                 "MGF",
@@ -660,15 +673,15 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
                 f"{int(spec_tic)}" if spec_tic > 0 else "null",
                 str(spec_len) if spec_len > 0 else "null",
                 spec_mz_str if spec_mz_str else "null",
-                spec_int_str if spec_int_str else "null"
+                spec_int_str if spec_int_str else "null",
             ]
-            mgf_lines.append('\t'.join(mgf_row))
-        
+            mgf_lines.append("\t".join(mgf_row))
+
         # Write MGF table
-        with open(filename, 'a', encoding='utf-8') as f:
-            f.write('\n')
+        with open(filename, "a", encoding="utf-8") as f:
+            f.write("\n")
             for line in mgf_lines:
-                f.write(line + '\n')
+                f.write(line + "\n")
 
-    if include_mgf:    
+    if include_mgf:
         self.logger.info(f"Exported mzTab-M to {filename}")