masster 0.4.4__py3-none-any.whl → 0.4.6__py3-none-any.whl

masster/sample/processing.py

@@ -16,6 +16,7 @@ from .defaults.get_spectrum_def import get_spectrum_defaults
 
 from masster.chromatogram import Chromatogram
 
+
 def get_spectrum(self, scan, **kwargs):
     """Retrieve a single spectrum and optionally post-process it.
 
@@ -252,7 +253,8 @@ def get_spectrum(self, scan, **kwargs):
                 spec=spect,
                 scan_uid=scan_uid,
                 feature_uid=scan_info["feature_uid"][0]
-                if "feature_uid" in scan_info and scan_info["feature_uid"][0] is not None
+                if "feature_uid" in scan_info
+                and scan_info["feature_uid"][0] is not None
                 else feature_uid,
                 q1_step=2,
                 deisotope=deisotope,
@@ -445,7 +447,9 @@ def _spec_to_mat(
             closest_index = np.argmin(np.abs(ar2 - val1))
             closest_indices.append((i, closest_index))
         # filter out pairs that are not within the specified tolerance
-        closest_indices = [(i, j) for i, j in closest_indices if np.abs(ar1[i] - ar2[j]) <= tol]
+        closest_indices = [
+            (i, j) for i, j in closest_indices if np.abs(ar1[i] - ar2[j]) <= tol
+        ]
         # remove duplicates from the list of indices
         closest_indices = list(set(closest_indices))
         # sort the list of indices by the first element (i) in ascending order
@@ -564,9 +568,13 @@ def find_features(self, **kwargs):
             import os
 
             os.environ["OMP_NUM_THREADS"] = str(params.threads)
-            self.logger.debug(f"Set thread count to {params.threads} via OMP_NUM_THREADS")
+            self.logger.debug(
+                f"Set thread count to {params.threads} via OMP_NUM_THREADS",
+            )
         except Exception:
-            self.logger.warning(f"Could not set thread count to {params.threads} - using default")
+            self.logger.warning(
+                f"Could not set thread count to {params.threads} - using default",
+            )
 
     # Set debug mode if enabled
     if hasattr(params, "debug") and params.debug:
@@ -607,7 +615,8 @@ def find_features(self, **kwargs):
     mtd_par.setValue("noise_threshold_int", float(params.get("noise")))
     mtd_par.setValue(
         "min_trace_length",
-        float(params.get("min_trace_length_multiplier")) * float(params.get("chrom_fwhm_min")),
+        float(params.get("min_trace_length_multiplier"))
+        * float(params.get("chrom_fwhm_min")),
     )
     mtd_par.setValue(
         "trace_termination_outliers",
@@ -618,8 +627,14 @@ def find_features(self, **kwargs):
     # Additional MTD parameters
     mtd_par.setValue("min_sample_rate", float(params.get("min_sample_rate")))
     mtd_par.setValue("min_trace_length", float(params.get("min_trace_length")))
-    mtd_par.setValue("trace_termination_criterion", params.get("trace_termination_criterion"))
-    mtd_par.setValue("reestimate_mt_sd", "true" if params.get("reestimate_mt_sd") else "false")
+    mtd_par.setValue(
+        "trace_termination_criterion",
+        params.get("trace_termination_criterion"),
+    )
+    mtd_par.setValue(
+        "reestimate_mt_sd",
+        "true" if params.get("reestimate_mt_sd") else "false",
+    )
     mtd_par.setValue("quant_method", params.get("quant_method"))
 
     mtd.setParameters(mtd_par)  # set the new parameters
@@ -688,7 +703,7 @@ def find_features(self, **kwargs):
     df = feature_map.get_df(export_peptide_identifications=False)  # type: ignore[attr-defined]
     # Sets the file path to the primary MS run (usually the mzML file)
     feature_map.setPrimaryMSRunPath([self.file_path.encode()])
-    
+
     # Store feature map in both attributes for compatibility
     self.features = feature_map
     self._oms_features_map = feature_map
@@ -769,13 +784,15 @@ def find_features(self, **kwargs):
             height_scaleds.append(None)
 
     # Add the computed columns to the dataframe
-    df = df.with_columns([
-        pl.Series("chrom", chroms, dtype=pl.Object),
-        pl.Series("chrom_coherence", coherences, dtype=pl.Float64),
-        pl.Series("chrom_prominence", prominences, dtype=pl.Float64),
-        pl.Series("chrom_prominence_scaled", prominence_scaleds, dtype=pl.Float64),
-        pl.Series("chrom_height_scaled", height_scaleds, dtype=pl.Float64),
-    ])
+    df = df.with_columns(
+        [
+            pl.Series("chrom", chroms, dtype=pl.Object),
+            pl.Series("chrom_coherence", coherences, dtype=pl.Float64),
+            pl.Series("chrom_prominence", prominences, dtype=pl.Float64),
+            pl.Series("chrom_prominence_scaled", prominence_scaleds, dtype=pl.Float64),
+            pl.Series("chrom_height_scaled", height_scaleds, dtype=pl.Float64),
+        ],
+    )
 
     self.features_df = df
     self._features_sync()
@@ -796,10 +813,10 @@ def find_features(self, **kwargs):
 def _clean_features_df(self, df):
     """Clean and standardize features DataFrame."""
     # Convert pandas DataFrame to polars if needed
-    if hasattr(df, 'index'):  # pandas DataFrame
+    if hasattr(df, "index"):  # pandas DataFrame
         df = df.copy()
         df["feature_id"] = df.index
-    
+
     if hasattr(df, "columns") and not isinstance(df, pl.DataFrame):
         df_pl = pl.from_pandas(df)
     else:
@@ -809,35 +826,37 @@ def _clean_features_df(self, df):
     df2 = df_pl.filter(pl.col("quality") != 0)
 
     # Create new dataframe with required columns and transformations
-    df_result = df2.select([
-        pl.int_range(pl.len()).alias("feature_uid"),
-        pl.col("feature_id").cast(pl.String).alias("feature_id"),
-        pl.col("mz").round(5),
-        pl.col("RT").round(3).alias("rt"),
-        pl.col("RT").round(3).alias("rt_original"),
-        pl.col("RTstart").round(3).alias("rt_start"),
-        pl.col("RTend").round(3).alias("rt_end"),
-        (pl.col("RTend") - pl.col("RTstart")).round(3).alias("rt_delta"),
-        pl.col("MZstart").round(5).alias("mz_start"),
-        pl.col("MZend").round(5).alias("mz_end"),
-        pl.col("intensity").alias("inty"),
-        pl.col("quality"),
-        pl.col("charge"),
-        pl.lit(0).alias("iso"),
-        pl.lit(None, dtype=pl.Int64).alias("iso_of"),
-        pl.lit(None, dtype=pl.Utf8).alias("adduct"),
-        pl.lit(None, dtype=pl.Float64).alias("adduct_charge"),
-        pl.lit(None, dtype=pl.Float64).alias("adduct_mass_shift"),
-        pl.lit(None, dtype=pl.Float64).alias("adduct_mass_neutral"),
-        pl.lit(None, dtype=pl.Int64).alias("adduct_group"),
-        pl.lit(None, dtype=pl.Object).alias("chrom"),
-        pl.lit(None, dtype=pl.Float64).alias("chrom_coherence"),
-        pl.lit(None, dtype=pl.Float64).alias("chrom_prominence"),
-        pl.lit(None, dtype=pl.Float64).alias("chrom_prominence_scaled"),
-        pl.lit(None, dtype=pl.Float64).alias("chrom_height_scaled"),
-        pl.lit(None, dtype=pl.Object).alias("ms2_scans"),
-        pl.lit(None, dtype=pl.Object).alias("ms2_specs"),
-    ])
+    df_result = df2.select(
+        [
+            pl.int_range(pl.len()).alias("feature_uid"),
+            pl.col("feature_id").cast(pl.String).alias("feature_id"),
+            pl.col("mz").round(5),
+            pl.col("RT").round(3).alias("rt"),
+            pl.col("RT").round(3).alias("rt_original"),
+            pl.col("RTstart").round(3).alias("rt_start"),
+            pl.col("RTend").round(3).alias("rt_end"),
+            (pl.col("RTend") - pl.col("RTstart")).round(3).alias("rt_delta"),
+            pl.col("MZstart").round(5).alias("mz_start"),
+            pl.col("MZend").round(5).alias("mz_end"),
+            pl.col("intensity").alias("inty"),
+            pl.col("quality"),
+            pl.col("charge"),
+            pl.lit(0).alias("iso"),
+            pl.lit(None, dtype=pl.Int64).alias("iso_of"),
+            pl.lit(None, dtype=pl.Utf8).alias("adduct"),
+            pl.lit(None, dtype=pl.Float64).alias("adduct_charge"),
+            pl.lit(None, dtype=pl.Float64).alias("adduct_mass_shift"),
+            pl.lit(None, dtype=pl.Float64).alias("adduct_mass_neutral"),
+            pl.lit(None, dtype=pl.Int64).alias("adduct_group"),
+            pl.lit(None, dtype=pl.Object).alias("chrom"),
+            pl.lit(None, dtype=pl.Float64).alias("chrom_coherence"),
+            pl.lit(None, dtype=pl.Float64).alias("chrom_prominence"),
+            pl.lit(None, dtype=pl.Float64).alias("chrom_prominence_scaled"),
+            pl.lit(None, dtype=pl.Float64).alias("chrom_height_scaled"),
+            pl.lit(None, dtype=pl.Object).alias("ms2_scans"),
+            pl.lit(None, dtype=pl.Object).alias("ms2_specs"),
+        ],
+    )
 
     return df_result
 
@@ -859,10 +878,12 @@ def _features_deisotope(
         df = pl.from_pandas(df)
 
     # Initialize new columns
-    df = df.with_columns([
-        pl.lit(0).alias("iso"),
-        pl.col("feature_uid").alias("iso_of"),
-    ])
+    df = df.with_columns(
+        [
+            pl.lit(0).alias("iso"),
+            pl.col("feature_uid").alias("iso_of"),
+        ],
+    )
 
     # Sort by 'mz'
     df = df.sort("mz")
@@ -889,13 +910,13 @@ def _features_deisotope(
         for isotope_offset in [1, 2, 3]:
             offset_mz = isotope_offset * mz_diff
             tolerance_factor = 1.0 if isotope_offset == 1 else 1.5
-            
+
             t_lower = base_mz + offset_mz - tolerance_factor * mz_tol
             t_upper = base_mz + offset_mz + tolerance_factor * mz_tol
-            
+
             li = np.searchsorted(mz_arr, t_lower, side="left")
             ri = np.searchsorted(mz_arr, t_upper, side="right")
-            
+
             if li < ri:
                 cand_idx = np.arange(li, ri)
                 mask = (
@@ -904,22 +925,23 @@ def _features_deisotope(
                     & (intensity_arr[cand_idx] < 2 * base_int)
                 )
                 valid_cand = cand_idx[mask]
-                
+
                 for cand in valid_cand:
                     if cand != i and iso_of_arr[cand] == feature_uid_arr[cand]:
                         iso_arr[cand] = iso_arr[i] + isotope_offset
                         iso_of_arr[cand] = base_feature_uid
 
     # Update the dataframe with isotope assignments
-    df = df.with_columns([
-        pl.Series("iso", iso_arr),
-        pl.Series("iso_of", iso_of_arr),
-    ])
+    df = df.with_columns(
+        [
+            pl.Series("iso", iso_arr),
+            pl.Series("iso_of", iso_of_arr),
+        ],
+    )
 
     return df
 
 
-
 def analyze_dda(self):
     # Preallocate variables
     cycle_records = []
@@ -1106,7 +1128,9 @@ def find_ms2(self, **kwargs):
     feature_rt_start = features_subset.select("rt_start").to_numpy().flatten()
     feature_rt_end = features_subset.select("rt_end").to_numpy().flatten()
     feature_uids = features_subset.select("feature_uid").to_numpy().flatten()
-    feature_indices = features_subset.with_row_index().select("index").to_numpy().flatten()
+    feature_indices = (
+        features_subset.with_row_index().select("index").to_numpy().flatten()
+    )
 
     # Pre-compute RT radius for all features
     rt_radius = np.minimum(feature_rt - feature_rt_start, feature_rt_end - feature_rt)
@@ -1159,15 +1183,17 @@ def find_ms2(self, **kwargs):
 
         scan_uids = ms2_index_arr[final_indices].tolist()
         scan_uid_lists.append(scan_uids)
-        spec_lists.append([
-            self.get_spectrum(
-                scan_uids[0],
-                centroid=centroid,
-                deisotope=deisotope,
-                dia_stats=dia_stats,
-                feature_uid=feature_uid,
-            ),
-        ])
+        spec_lists.append(
+            [
+                self.get_spectrum(
+                    scan_uids[0],
+                    centroid=centroid,
+                    deisotope=deisotope,
+                    dia_stats=dia_stats,
+                    feature_uid=feature_uid,
+                ),
+            ],
+        )
 
         # Collect updates for batch processing
         updated_feature_uids.extend([feature_uid] * len(final_indices))
@@ -1181,11 +1207,13 @@ def find_ms2(self, **kwargs):
         features_df = pl.from_pandas(features_df)
 
     # Update the features_df
-    update_df = pl.DataFrame({
-        "temp_idx": feature_indices,
-        "ms2_scans": pl.Series("ms2_scans", scan_uid_lists, dtype=pl.Object),
-        "ms2_specs": pl.Series("ms2_specs", spec_lists, dtype=pl.Object),
-    })
+    update_df = pl.DataFrame(
+        {
+            "temp_idx": feature_indices,
+            "ms2_scans": pl.Series("ms2_scans", scan_uid_lists, dtype=pl.Object),
+            "ms2_specs": pl.Series("ms2_specs", spec_lists, dtype=pl.Object),
+        },
+    )
 
     # Join and update
     features_df = (
@@ -1196,16 +1224,18 @@ def find_ms2(self, **kwargs):
             how="left",
             suffix="_new",
         )
-        .with_columns([
-            pl.when(pl.col("ms2_scans_new").is_not_null())
-            .then(pl.col("ms2_scans_new"))
-            .otherwise(pl.col("ms2_scans"))
-            .alias("ms2_scans"),
-            pl.when(pl.col("ms2_specs_new").is_not_null())
-            .then(pl.col("ms2_specs_new"))
-            .otherwise(pl.col("ms2_specs"))
-            .alias("ms2_specs"),
-        ])
+        .with_columns(
+            [
+                pl.when(pl.col("ms2_scans_new").is_not_null())
+                .then(pl.col("ms2_scans_new"))
+                .otherwise(pl.col("ms2_scans"))
+                .alias("ms2_scans"),
+                pl.when(pl.col("ms2_specs_new").is_not_null())
+                .then(pl.col("ms2_specs_new"))
+                .otherwise(pl.col("ms2_specs"))
+                .alias("ms2_specs"),
+            ],
+        )
         .drop(["temp_idx", "ms2_scans_new", "ms2_specs_new"])
     )
 
@@ -1242,4 +1272,4 @@ def find_ms2(self, **kwargs):
     self.store_history(["find_ms2"], params.to_dict())
     self.logger.debug(
         "Parameters stored to find_ms2",
-    )
+    )

masster/sample/sample.py

@@ -39,7 +39,7 @@ import sys
 import polars as pl
 
 from masster._version import get_version
-from masster.logger import MassterLogger
+from masster.logger import MasterLogger
 
 from masster.sample.defaults.sample_def import sample_defaults
 from masster.sample.defaults.find_features_def import find_features_defaults
@@ -56,14 +56,15 @@ from masster.sample.helpers import _estimate_memory_usage
 from masster.sample.helpers import _get_scan_uids
 from masster.sample.helpers import _get_feature_uids
 from masster.sample.helpers import _features_sync
-#from masster.sample.helpers import _parse_adduct_specs
-#from masster.sample.helpers import _calculate_adduct_mass_shift
-#from masster.sample.helpers import _parse_formula_expression
-#from masster.sample.helpers import _calculate_molecular_mass
-#from masster.sample.helpers import _parse_legacy_adduct_format
-#from masster.sample.helpers import _extract_adduct_probability
-#from masster.sample.helpers import _detect_adduct_groups_direct
-#from masster.sample.helpers import _check_adduct_relationship
+
+# from masster.sample.helpers import _parse_adduct_specs
+# from masster.sample.helpers import _calculate_adduct_mass_shift
+# from masster.sample.helpers import _parse_formula_expression
+# from masster.sample.helpers import _calculate_molecular_mass
+# from masster.sample.helpers import _parse_legacy_adduct_format
+# from masster.sample.helpers import _extract_adduct_probability
+# from masster.sample.helpers import _detect_adduct_groups_direct
+# from masster.sample.helpers import _check_adduct_relationship
 from masster.sample.adducts import _get_adducts
 from masster.sample.adducts import find_adducts
 from masster.sample.helpers import features_delete
@@ -179,7 +180,7 @@ class Sample:
         self.log_sink = params.log_sink
 
         # Initialize independent logger
-        self.logger = MassterLogger(
+        self.logger = MasterLogger(
             instance_type="sample",
             level=params.log_level.upper(),
             label=params.log_label if params.log_label else "",
@@ -298,7 +299,12 @@ class Sample:
     find_ms2_defaults = find_ms2_defaults
     get_spectrum_defaults = get_spectrum_defaults
 
-    def logger_update(self, level: str | None = None, label: str | None = None, sink: str | None = None):
+    def logger_update(
+        self,
+        level: str | None = None,
+        label: str | None = None,
+        sink: str | None = None,
+    ):
         """Update the logging configuration for this Sample instance.
 
         Args:
@@ -346,7 +352,10 @@ class Sample:
 
         # Get all currently loaded modules that are part of the sample package
         for module_name in sys.modules:
-            if module_name.startswith(sample_module_prefix) and module_name != current_module:
+            if (
+                module_name.startswith(sample_module_prefix)
+                and module_name != current_module
+            ):
                 sample_modules.append(module_name)
 
         # Add core masster modules
@@ -361,7 +370,10 @@ class Sample:
         study_modules = []
         study_module_prefix = f"{base_modname}.study."
         for module_name in sys.modules:
-            if module_name.startswith(study_module_prefix) and module_name != current_module:
+            if (
+                module_name.startswith(study_module_prefix)
+                and module_name != current_module
+            ):
                 study_modules.append(module_name)
 
         """ # Add parameters submodules
@@ -372,7 +384,9 @@ class Sample:
                 parameters_modules.append(module_name)
         """
 
-        all_modules_to_reload = core_modules + sample_modules + study_modules  # + parameters_modules
+        all_modules_to_reload = (
+            core_modules + sample_modules + study_modules
+        )  # + parameters_modules
 
         # Reload all discovered modules
         for full_module_name in all_modules_to_reload:
@@ -401,7 +415,6 @@ class Sample:
     def get_version(self):
         return get_version()
 
-
     def info(self):
         # show the key attributes of the object
         str = f"File: {os.path.basename(self.file_path)}\n"

masster/sample/sample5_schema.json

@@ -1,47 +1,53 @@
 {
   "features_df": {
     "columns": {
-      "feature_uid": {
-        "dtype": "pl.Int64"
-      },
-      "feature_id": {
+      "adduct": {
         "dtype": "pl.Utf8"
       },
-      "sample_uid": {
-        "dtype": "pl.Int32"
+      "adduct_charge": {
+        "dtype": "pl.Int64"
       },
-      "mz": {
-        "dtype": "pl.Float64"
+      "adduct_group": {
+        "dtype": "pl.Int64"
       },
-      "rt": {
+      "adduct_mass_neutral": {
         "dtype": "pl.Float64"
       },
-      "rt_original": {
+      "adduct_mass_shift": {
         "dtype": "pl.Float64"
       },
-      "rt_start": {
-        "dtype": "pl.Float64"
+      "charge": {
+        "dtype": "pl.Int32"
       },
-      "rt_end": {
-        "dtype": "pl.Float64"
+      "chrom": {
+        "dtype": "pl.Object"
       },
-      "rt_delta": {
+      "chrom_area": {
         "dtype": "pl.Float64"
       },
-      "mz_start": {
+      "chrom_coherence": {
         "dtype": "pl.Float64"
       },
-      "mz_end": {
+      "chrom_height_scaled": {
         "dtype": "pl.Float64"
       },
-      "inty": {
+      "chrom_prominence": {
         "dtype": "pl.Float64"
       },
-      "quality": {
+      "chrom_prominence_scaled": {
         "dtype": "pl.Float64"
       },
-      "charge": {
-        "dtype": "pl.Int32"
+      "feature_id": {
+        "dtype": "pl.Utf8"
+      },
+      "feature_uid": {
+        "dtype": "pl.Int64"
+      },
+      "filled": {
+        "dtype": "pl.Boolean"
+      },
+      "inty": {
+        "dtype": "pl.Float64"
       },
       "iso": {
         "dtype": "pl.Int64"
@@ -49,47 +55,41 @@
       "iso_of": {
         "dtype": "pl.Int64"
       },
-      "adduct": {
-        "dtype": "pl.Utf8"
+      "ms2_scans": {
+        "dtype": "pl.Object"
       },
-      "adduct_charge": {
-        "dtype": "pl.Int64"
+      "ms2_specs": {
+        "dtype": "pl.Object"
       },
-      "adduct_mass_shift": {
+      "mz": {
         "dtype": "pl.Float64"
       },
-      "adduct_mass_neutral": {
+      "mz_end": {
         "dtype": "pl.Float64"
       },
-      "adduct_group": {
-        "dtype": "pl.Int64"
-      },
-      "chrom": {
-        "dtype": "pl.Object"
-      },
-      "filled": {
-        "dtype": "pl.Boolean"
+      "mz_start": {
+        "dtype": "pl.Float64"
       },
-      "chrom_area": {
+      "quality": {
         "dtype": "pl.Float64"
       },
-      "chrom_coherence": {
+      "rt": {
         "dtype": "pl.Float64"
       },
-      "chrom_prominence": {
+      "rt_delta": {
         "dtype": "pl.Float64"
       },
-      "chrom_prominence_scaled": {
+      "rt_end": {
         "dtype": "pl.Float64"
       },
-      "chrom_height_scaled": {
+      "rt_original": {
         "dtype": "pl.Float64"
       },
-      "ms2_scans": {
-        "dtype": "pl.Object"
+      "rt_start": {
+        "dtype": "pl.Float64"
       },
-      "ms2_specs": {
-        "dtype": "pl.Object"
+      "sample_uid": {
+        "dtype": "pl.Int32"
       }
     }
   },