masster 0.5.14__tar.gz → 0.5.16__tar.gz

{masster-0.5.14 → masster-0.5.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.14
+Version: 0.5.16
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster

{masster-0.5.14 → masster-0.5.16}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.5.14"
+version = "0.5.16"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }

{masster-0.5.14 → masster-0.5.16}/src/masster/__init__.py

@@ -22,7 +22,7 @@ from masster.lib import Lib
 from masster.sample.sample import Sample
 from masster.spectrum import Spectrum
 from masster.study.study import Study
-from masster.wizard import Wizard, wizard_def
+from masster.wizard import Wizard
 
 
 __all__ = [

{masster-0.5.14 → masster-0.5.16}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.5.14"
+__version__ = "0.5.16"
 
 
 def get_version():

{masster-0.5.14 → masster-0.5.16}/src/masster/sample/adducts.py

@@ -107,7 +107,9 @@ def _get_adducts(self, adducts_list: list = None, **kwargs):
 
     # 1. Single adducts
     for spec in base_specs:
-        if charge_min <= spec["charge"] <= charge_max:
+        # For neutral adducts (charge=0), always allow them
+        # For charged adducts, check if absolute value is within range
+        if spec["charge"] == 0 or (charge_min <= abs(spec["charge"]) <= charge_max):
             formatted_name = _format_adduct_name([spec])
             combinations_list.append(
                 {
@@ -125,7 +127,7 @@ def _get_adducts(self, adducts_list: list = None, **kwargs):
         base_charge = spec["charge"]
         for multiplier in range(2, min(max_combinations + 1, 5)):
             total_charge = base_charge * multiplier
-            if charge_min <= total_charge <= charge_max:
+            if charge_min <= abs(total_charge) <= charge_max:
                 components = [spec] * multiplier
                 formatted_name = _format_adduct_name(components)
 
@@ -146,7 +148,8 @@ def _get_adducts(self, adducts_list: list = None, **kwargs):
         for pos_spec in positive_specs:
             for neut_spec in neutral_specs:
                 total_charge = pos_spec["charge"] + neut_spec["charge"]
-                if charge_min <= total_charge <= charge_max:
+                # For combinations with neutrals, the total charge should follow abs() rule only if non-zero
+                if total_charge == 0 or (charge_min <= abs(total_charge) <= charge_max):
                     components = [pos_spec, neut_spec]
                     formatted_name = _format_adduct_name(components)
                     combinations_list.append(
@@ -166,7 +169,7 @@ def _get_adducts(self, adducts_list: list = None, **kwargs):
         for combo in combinations(positive_specs, 2):
             if combo[0]["formula"] != combo[1]["formula"]:
                 total_charge = combo[0]["charge"] + combo[1]["charge"]
-                if charge_min <= total_charge <= charge_max:
+                if total_charge == 0 or (charge_min <= abs(total_charge) <= charge_max):
                     components = list(combo)
                     formatted_name = _format_adduct_name(components)
                     combinations_list.append(
@@ -189,7 +192,7 @@ def _get_adducts(self, adducts_list: list = None, **kwargs):
                 components = [pos_spec] + list(neut_combo)
                 total_charge = sum(spec["charge"] for spec in components)
 
-                if charge_min <= total_charge <= charge_max:
+                if total_charge == 0 or (charge_min <= abs(total_charge) <= charge_max):
                     formatted_name = _format_adduct_name(components)
                     total_mass_shift = sum(spec["mass_shift"] for spec in components)
                     combined_prob = np.prod(

{masster-0.5.14 → masster-0.5.16}/src/masster/sample/processing.py

@@ -586,6 +586,12 @@ def find_features(self, **kwargs):
     self.logger.debug(
         f"Parameters: chrom_fwhm={params.get('chrom_fwhm')}, noise={params.get('noise')}, tol_ppm={params.get('tol_ppm')}, isotope_filtering_model={params.get('isotope_filtering_model')}",
     )
+    # check that noise is not lower than 1% quantile of ms1_df inty
+    noise_threshold = self.ms1_df.select(pl.col("inty")).quantile(0.01)[0, 0]
+    if params.get("noise") < noise_threshold / 10:
+        self.logger.warning(
+            f"Warning: noise threshold {params.get('noise')} is lower than 1% quantile of MS1 intensities ({noise_threshold:.1f}). This may lead to many false positives.",
+        )
 
     exp = oms.MSExperiment()
     # find max number of cycles in self.ms1_df

{masster-0.5.14 → masster-0.5.16}/src/masster/study/id.py

@@ -1503,7 +1503,8 @@ def _get_adducts(study, adducts_list: list | None = None, **kwargs):
 
     # 1. Single adducts (filter out neutral adducts with charge == 0)
     for spec in base_specs:
-        if charge_min <= spec["charge"] <= charge_max and spec["charge"] != 0:
+        # Study-level filtering: exclude neutral adducts (charge=0) but use abs() for charged adducts
+        if spec["charge"] != 0 and charge_min <= abs(spec["charge"]) <= charge_max:
             formatted_name = _format_adduct_name([spec])
             combinations_list.append(
                 {
@@ -1521,7 +1522,7 @@ def _get_adducts(study, adducts_list: list | None = None, **kwargs):
         base_charge = spec["charge"]
         for multiplier in range(2, min(max_combinations + 1, 4)):  # Up to 3x multiplier
             total_charge = base_charge * multiplier
-            if charge_min <= total_charge <= charge_max and total_charge != 0:
+            if charge_min <= abs(total_charge) <= charge_max and total_charge != 0:
                 components = [spec] * multiplier
                 formatted_name = _format_adduct_name(components)
                 probability_multiplied = float(spec["probability"]) ** multiplier
@@ -1543,7 +1544,7 @@ def _get_adducts(study, adducts_list: list | None = None, **kwargs):
         for pos_spec in positive_specs[:2]:  # Limit to first 2 positive specs
             for neut_spec in neutral_specs[:1]:  # Only 1 neutral loss
                 total_charge = pos_spec["charge"] + neut_spec["charge"]
-                if charge_min <= total_charge <= charge_max and total_charge != 0:
+                if charge_min <= abs(total_charge) <= charge_max and total_charge != 0:
                     components = [pos_spec, neut_spec]
                     formatted_name = _format_adduct_name(components)
                     combinations_list.append(

{masster-0.5.14 → masster-0.5.16}/src/masster/study/plot.py

@@ -449,6 +449,9 @@ def plot_alignment(
             rt_current = row_dict["rt"]
             mz = row_dict["mz"]
             inty = row_dict["inty"]
+            # Skip if inty is None
+            if inty is None:
+                continue
             alpha = inty / max_inty
             size = markersize + 2 if sample_idx == 0 else markersize
 

{masster-0.5.14 → masster-0.5.16}/src/masster/wizard/__init__.py

@@ -12,6 +12,6 @@ The analyze() function combines create_analysis() with immediate execution of th
 generated script for fully automated processing.
 """
 
-from .wizard import Wizard, wizard_def, create_analysis, create_notebook, analyze
+from .wizard import Wizard, wizard_def, create_scripts
 
-__all__ = ["Wizard", "wizard_def", "create_analysis", "create_notebook", "analyze"]
+__all__ = ["Wizard", "wizard_def", "create_scripts"]