masster 0.6.0__tar.gz → 0.6.1__tar.gz

{masster-0.6.0 → masster-0.6.1}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.6.0
+Version: 0.6.1
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster
 Project-URL: documentation, https://github.com/zamboni-lab/masster#readme
 Project-URL: Third-Party Licenses, https://github.com/zamboni-lab/masster/blob/main/THIRD_PARTY_NOTICES.md
-Author: Zamboni Lab
+Author: Zamboni Lab, ETH Zurich
 License:                     GNU AFFERO GENERAL PUBLIC LICENSE
                                Version 3, 19 November 2007
         
@@ -833,6 +833,7 @@ study.save()
 study.plot_samples_pca()
 study.plot_samples_umap()
 study.plot_samples_2d()
+study.plot_heatmap()
 
 # To know more about the available methods...
 dir(study)

{masster-0.6.0 → masster-0.6.1}/README.md

@@ -105,6 +105,7 @@ study.save()
 study.plot_samples_pca()
 study.plot_samples_umap()
 study.plot_samples_2d()
+study.plot_heatmap()
 
 # To know more about the available methods...
 dir(study)

{masster-0.6.0 → masster-0.6.1}/pyproject.toml

@@ -1,10 +1,10 @@
 
 [project]
 name = "masster"
-version = "0.6.0"
+version = "0.6.1"
 description = "Mass spectrometry data analysis package"
 authors = [
-    { name = "Zamboni Lab" }
+    { name = "Zamboni Lab, ETH Zurich" }
 ]
 license = { file = "LICENSE" }
 readme = "README.md"

{masster-0.6.0 → masster-0.6.1}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.5.26"
+__version__ = "0.6.1"
 
 
 def get_version():

{masster-0.6.0 → masster-0.6.1}/src/masster/study/export.py

@@ -524,7 +524,7 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
         # Import here to avoid circular imports
         from masster.study.id import get_id
 
-        # Get full enriched identification data for SOME section
+        # Get full enriched identification data for SME section
         full_id_data = get_id(self)
         if full_id_data is not None and not full_id_data.is_empty():
             # Get top scoring identification for each consensus_uid for SML section
@@ -828,8 +828,8 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
     smf_header = [
         "SFH",
         "SMF_ID",
-        "SOME_ID_REFS",
-        "SOME_ID_REF_ambiguity_code",
+        "SME_ID_REFS",
+        "SME_ID_REF_ambiguity_code",
         "adduct_ion",
         "isotopomer",
         "exp_mass_to_charge",
@@ -847,40 +847,40 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
 
     # 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):
-        # References to SOME entries - each SMF can reference multiple SOME entries for the same consensus_uid
-        some_refs = "null"
-        some_ambiguity = "null"
+        # References to SME entries - each SMF can reference multiple SME entries for the same consensus_uid
+        SME_refs = "null"
+        SME_ambiguity = "null"
         consensus_uid = row["consensus_uid"]
 
         if full_id_data is not None:
-            # Find all SOME entries for this consensus_uid
-            some_matches = full_id_data.filter(pl.col("consensus_uid") == consensus_uid)
-            if some_matches.height > 0:
-                # Generate SOME IDs - we'll create a mapping in the SOME section
+            # Find all SME entries for this consensus_uid
+            SME_matches = full_id_data.filter(pl.col("consensus_uid") == consensus_uid)
+            if SME_matches.height > 0:
+                # Generate SME IDs - we'll create a mapping in the SME section
                 # For now, use a simple approach based on consensus_uid and lib_uid
-                some_ids = []
-                for i, some_row in enumerate(some_matches.iter_rows(named=True)):
-                    # Create a unique SOME ID based on consensus_uid and position
-                    some_id_base = consensus_uid * 1000  # Ensure uniqueness across consensus features
-                    some_id = some_id_base + i + 1
-                    some_ids.append(str(some_id))
-
-                if some_ids:
-                    some_refs = "|".join(some_ids)
+                SME_ids = []
+                for i, SME_row in enumerate(SME_matches.iter_rows(named=True)):
+                    # Create a unique SME ID based on consensus_uid and position
+                    SME_id_base = consensus_uid * 1000  # Ensure uniqueness across consensus features
+                    SME_id = SME_id_base + i + 1
+                    SME_ids.append(str(SME_id))
+
+                if SME_ids:
+                    SME_refs = "|".join(SME_ids)
                     # Set ambiguity code: 1=ambiguous identification, 2=multiple evidence same molecule, 3=both
-                    if len(some_ids) > 1:
+                    if len(SME_ids) > 1:
                         # Check if all identifications point to the same compound
                         unique_cmpds = {
                             match["cmpd_uid"]
-                            for match in some_matches.iter_rows(named=True)
+                            for match in SME_matches.iter_rows(named=True)
                             if match.get("cmpd_uid") is not None
                         }
                         if len(unique_cmpds) > 1:
-                            some_ambiguity = "1"  # Ambiguous identification
+                            SME_ambiguity = "1"  # Ambiguous identification
                         else:
-                            some_ambiguity = "2"  # Multiple evidence for same molecule
+                            SME_ambiguity = "2"  # Multiple evidence for same molecule
                     else:
-                        some_ambiguity = "null"
+                        SME_ambiguity = "null"
 
         # Format isotopomer according to mzTab-M specification
         iso_value = row.get("iso_mean", 0)
@@ -892,8 +892,8 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
         smf_row = [
             "SMF",
             str(idx),
-            some_refs,
-            some_ambiguity,
+            SME_refs,
+            SME_ambiguity,
             adduct_list[idx - 1],  # adduct_ion
             isotopomer,  # isotopomer formatted according to mzTab-M specification
             safe_str(row.get("mz", "null")),  # exp_mass_to_charge
@@ -943,16 +943,16 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
         for line in smf_lines:
             f.write(line + "\n")
 
-    # --- SOME (Small Molecule Evidence) table ---
+    # --- SME (Small Molecule Evidence) table ---
     if full_id_data is not None and not full_id_data.is_empty():
-        some_lines = []
+        SME_lines = []
         # Add comment about spectra_ref being dummy placeholders
-        some_lines.append(
+        SME_lines.append(
             "COM\tThe spectra_ref are dummy placeholders, as the annotation was based on aggregated data",
         )
-        some_header = [
-            "SHE",
-            "SOME_ID",
+        SME_header = [
+            "SEH",
+            "SME_ID",
             "evidence_input_id",
             "database_identifier",
             "chemical_formula",
@@ -971,9 +971,9 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
             "id_confidence_measure[1]",
             "rank",
         ]
-        some_lines.append("\t".join(some_header))
+        SME_lines.append("\t".join(SME_header))
 
-        # Create SOME entries for all identification results using enriched data
+        # Create SME entries for all identification results using enriched data
         for consensus_uid in self.consensus_df.select("consensus_uid").to_series().unique():
             # Get consensus feature data for this consensus_uid
             consensus_feature_data = self.consensus_df.filter(
@@ -984,16 +984,16 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
             consensus_row = consensus_feature_data.row(0, named=True)
 
             # Get all identification results for this consensus feature from enriched data
-            some_matches = full_id_data.filter(pl.col("consensus_uid") == consensus_uid)
+            SME_matches = full_id_data.filter(pl.col("consensus_uid") == consensus_uid)
 
-            if some_matches.height > 0:
+            if SME_matches.height > 0:
                 # Sort by score descending to maintain rank order
-                some_matches = some_matches.sort("score", descending=True)
+                SME_matches = SME_matches.sort("score", descending=True)
 
-                for i, some_row in enumerate(some_matches.iter_rows(named=True)):
-                    # Generate unique SOME_ID
-                    some_id_base = consensus_uid * 1000
-                    some_id = some_id_base + i + 1
+                for i, SME_row in enumerate(SME_matches.iter_rows(named=True)):
+                    # Generate unique SME_ID
+                    SME_id_base = consensus_uid * 1000
+                    SME_id = SME_id_base + i + 1
 
                     # Create evidence input ID using consensus_uid:mz:rt format
                     consensus_mz = consensus_row.get("mz", 0)
@@ -1002,15 +1002,15 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
 
                     # Database identifier - use db_id if available, otherwise fallback to cmpd_uid
                     db_id = "null"
-                    if some_row.get("db_id") is not None and some_row["db_id"] != "":
-                        db_id = safe_str(some_row["db_id"])
-                    elif some_row.get("cmpd_uid") is not None:
-                        db_id = f"cmpd:{some_row['cmpd_uid']}"
+                    if SME_row.get("db_id") is not None and SME_row["db_id"] != "":
+                        db_id = safe_str(SME_row["db_id"])
+                    elif SME_row.get("cmpd_uid") is not None:
+                        db_id = f"cmpd:{SME_row['cmpd_uid']}"
 
                     # Get adduct information
                     adduct_ion = "null"
-                    if some_row.get("adduct") is not None and some_row["adduct"] != "":
-                        adduct_ion = safe_str(some_row["adduct"])
+                    if SME_row.get("adduct") is not None and SME_row["adduct"] != "":
+                        adduct_ion = safe_str(SME_row["adduct"])
                         # Replace ? with H for better mzTab compatibility
                         adduct_ion = adduct_ion.replace("?", "H")
 
@@ -1019,8 +1019,8 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
 
                     # Identification method
                     id_method = "[MS, MS:1002888, small molecule confidence measure, ]"
-                    if some_row.get("matcher") is not None:
-                        id_method = f"[MS, MS:1002888, {some_row['matcher']}, ]"
+                    if SME_row.get("matcher") is not None:
+                        id_method = f"[MS, MS:1002888, {SME_row['matcher']}, ]"
 
                     # MS level - assume MS1 for now
                     ms_level = "[MS, MS:1000511, ms level, 1]"
@@ -1030,18 +1030,18 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
 
                     # Theoretical mass-to-charge from lib_df
                     theoretical_mz = "null"
-                    if some_row.get("mz") is not None:  # This comes from lib_df via get_id() join
-                        theoretical_mz = safe_str(some_row["mz"])
+                    if SME_row.get("mz") is not None:  # This comes from lib_df via get_id() join
+                        theoretical_mz = safe_str(SME_row["mz"])
 
-                    some_line = [
-                        "SOME",
-                        str(some_id),
+                    SME_line = [
+                        "SME",
+                        str(SME_id),
                         evidence_id,
                         db_id,
-                        safe_str(some_row.get("formula", "null")),
-                        safe_str(some_row.get("smiles", "null")),
-                        safe_str(some_row.get("inchi", "null")),
-                        safe_str(some_row.get("name", "null")),
+                        safe_str(SME_row.get("formula", "null")),
+                        safe_str(SME_row.get("smiles", "null")),
+                        safe_str(SME_row.get("inchi", "null")),
+                        safe_str(SME_row.get("name", "null")),
                         "null",  # uri - not available in current data
                         "null",  # derivatized_form
                         adduct_ion,
@@ -1053,15 +1053,15 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
                         spectra_ref,
                         id_method,
                         ms_level,
-                        safe_str(some_row.get("score", "null")),
+                        safe_str(SME_row.get("score", "null")),
                         str(i + 1),  # rank within this consensus feature
                     ]
-                    some_lines.append("\t".join(some_line))
+                    SME_lines.append("\t".join(SME_line))
 
-        # Write SOME table
+        # Write SME table
         with open(filename, "a", encoding="utf-8") as f:
             f.write("\n")
-            for line in some_lines:
+            for line in SME_lines:
                 f.write(line + "\n")
 
     # --- MGF table ---