masster 0.4.11__tar.gz → 0.4.13__tar.gz

{masster-0.4.11 → masster-0.4.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.4.11
+Version: 0.4.13
 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-0.4.11 → masster-0.4.13}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.4.11"
+version = "0.4.13"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }

{masster-0.4.11 → masster-0.4.13}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.4.11"
+__version__ = "0.4.13"
 
 
 def get_version():

{masster-0.4.11 → masster-0.4.13}/src/masster/lib/lib.py

@@ -142,11 +142,41 @@ class Lib:
         Returns:
             Accurate mass as float, or None if calculation fails
         """
+        # Skip obviously invalid formulas
+        if not formula or not isinstance(formula, str):
+            return None
+        
+        # Clean up whitespace
+        formula = formula.strip()
+        
+        # Skip formulas that are obviously invalid
+        invalid_patterns = [
+            # Contains parentheses with multipliers like (C12H19NO19S3)nH2O
+            lambda f: '(' in f and ')' in f and any(c.isalpha() and not c.isupper() for c in f.split(')')[1:]),
+            # Contains words instead of chemical symbols
+            lambda f: any(word in f.lower() for word in ['and', 'or', 'not', 'with', 'without']),
+            # Contains lowercase letters at the start (element symbols should be uppercase)
+            lambda f: f and f[0].islower(),
+            # Contains unusual characters that shouldn't be in formulas
+            lambda f: any(char in f for char in ['@', '#', '$', '%', '^', '&', '*', '=', '+', '?', '/', '\\', '|']),
+            # Empty or very short non-standard formulas
+            lambda f: len(f) < 2 and not f.isupper(),
+        ]
+        
+        for pattern_check in invalid_patterns:
+            try:
+                if pattern_check(formula):
+                    warnings.warn(f"Skipping obviously invalid formula: '{formula}'")
+                    return None
+            except Exception:
+                # If pattern checking fails, continue to PyOpenMS parsing
+                pass
+        
         try:
             empirical_formula = oms.EmpiricalFormula(formula)
             return empirical_formula.getMonoWeight()
         except Exception as e:
-            warnings.warn(f"Error calculating accurate mass for formula {formula}: {e}")
+            warnings.warn(f"Error calculating accurate mass for formula '{formula}': {e}")
             return None
     
     def _generate_adduct_variants(self, 
@@ -272,8 +302,12 @@ class Lib:
         all_variants = []
         cmpd_id_counter = 1
         lib_id_counter = 1
+        total_compounds = 0
+        skipped_compounds = 0
         
         for row in df.iter_rows(named=True):
+            total_compounds += 1
+            
             # Extract compound data
             # assign a compound-level uid so all adducts share the same cmpd_uid
             compound_level_uid = cmpd_id_counter
@@ -297,8 +331,12 @@ class Lib:
             )
             all_variants.extend(variants)
             
+            # Track if compound was skipped due to invalid formula
+            if len(variants) == 0:
+                skipped_compounds += 1
+            
             # Handle RT2 column if present
-            if "rt2" in column_mapping:
+            if "rt2" in column_mapping and len(variants) > 0:  # Only if main variants were created
                 rt2_value = self._safe_float_conversion(row.get(column_mapping["rt2"], None))
                 if rt2_value is not None:
                     # Create additional variants with RT2
@@ -321,9 +359,13 @@ class Lib:
             else:
                 self.lib_df = new_lib_df
                 
-            print(f"Successfully imported {len(all_variants)} library entries from {csvfile}")
+            #successful_compounds = total_compounds - skipped_compounds
+            print(f"Imported {len(all_variants)} library entries from {csvfile}")
+            #print(f"Processed {total_compounds} compounds: {successful_compounds} successful, {skipped_compounds} skipped due to invalid formulas")
         else:
             print(f"No valid compounds found in {csvfile}")
+            if skipped_compounds > 0:
+                print(f"All {total_compounds} compounds were skipped due to invalid formulas")
     
     def _map_csv_columns(self, columns: List[str]) -> Dict[str, str]:
         """