masster 0.5.6__tar.gz → 0.5.8__tar.gz

{masster-0.5.6 → masster-0.5.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.6
+Version: 0.5.8
 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-0.5.6 → masster-0.5.8}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.5.6"
+version = "0.5.8"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }

{masster-0.5.6 → masster-0.5.8}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.5.6"
+__version__ = "0.5.8"
 
 
 def get_version():

{masster-0.5.6 → masster-0.5.8}/src/masster/sample/plot.py

@@ -86,8 +86,6 @@ def _process_cmap(cmap, fallback="viridis", logger=None):
         cmap = "viridis"
     elif cmap == "grey":
         cmap = "Greys256"
-    elif cmap == "iridescent":
-        cmap = "iridescent_r"
     
     # If cmap package is not available, fall back to process_cmap
     if Colormap is None:
@@ -455,15 +453,15 @@ def plot_2d(
     show_ms2=False,
     show_in_browser=False,
     title=None,
-    cmap=None,
+    cmap='iridescent',
     marker="circle",
-    markersize=10,
+    markersize=5,
     size="static",
     raster_dynamic=True,
     raster_max_px=8,
     raster_threshold=0.8,
     height=600,
-    width=800,
+    width=750,
     mz_range=None,
     rt_range=None
 ):
@@ -529,7 +527,7 @@ def plot_2d(
         return
 
     # Process colormap using the cmap package
-    cmap_palette = _process_cmap(cmap, fallback="iridescent_r", logger=self.logger)
+    cmap_palette = _process_cmap(cmap, fallback="iridescent", logger=self.logger)
 
     # get columns rt, mz, inty from self.ms1_df, It's polars DataFrame
     spectradf = self.ms1_df.select(["rt", "mz", "inty"])

{masster-0.5.6 → masster-0.5.8}/src/masster/study/defaults/merge_def.py

@@ -25,7 +25,7 @@ class merge_defaults:
         link_ms2 (bool): Whether to link MS2 spectra to consensus features. Default is True.
     """
 
-    method: str = "kd"
+    method: str = "qt"
     min_samples: int = 2
     rt_tol: float = 5.0
     mz_tol: float = 0.05

{masster-0.5.6 → masster-0.5.8}/src/masster/study/helpers.py

@@ -2956,6 +2956,17 @@ def consensus_select(
     rt_delta_mean=None,
     id_top_score=None,
     identified=None,
+    # New adduct filter parameters
+    adduct_top=None,
+    adduct_charge_top=None,
+    adduct_mass_neutral_top=None,
+    adduct_mass_shift_top=None,
+    adduct_group=None,
+    adduct_of=None,
+    # New identification filter parameters
+    id_top_name=None,
+    id_top_class=None,
+    id_top_adduct=None,
     sortby=None,
     descending=True,
 ):
@@ -2990,6 +3001,17 @@ def consensus_select(
             - True: select only rows with id_top_name not null
             - False: select only rows with id_top_name null
             - None: no filtering (default)
+        # New adduct filter parameters
+        adduct_top: adduct type filter (list or single string value, e.g. "[M+H]+", "[M+Na]+")
+        adduct_charge_top: adduct charge filter (tuple for range, single value for exact match)
+        adduct_mass_neutral_top: neutral mass filter (tuple for range, single value for minimum)
+        adduct_mass_shift_top: adduct mass shift filter (tuple for range, single value for minimum)
+        adduct_group: adduct group ID filter (list, single value, or tuple for range)
+        adduct_of: adduct representative UID filter (list, single value, or tuple for range)
+        # New identification filter parameters
+        id_top_name: identification name filter (list or single string value for compound names)
+        id_top_class: identification class filter (list or single string value for compound classes)
+        id_top_adduct: identification adduct filter (list or single string value for identified adducts)
         sortby: column name(s) to sort by (string, list of strings, or None for no sorting)
         descending: sort direction (True for descending, False for ascending, default is True)
 
@@ -3004,7 +3026,10 @@ def consensus_select(
     filter_params = [mz, rt, inty_mean, consensus_uid, consensus_id, number_samples, 
                     number_ms2, quality, bl, chrom_coherence_mean, chrom_prominence_mean,
                     chrom_prominence_scaled_mean, chrom_height_scaled_mean, 
-                    rt_delta_mean, id_top_score, identified]
+                    rt_delta_mean, id_top_score, identified,
+                    # New adduct and identification parameters
+                    adduct_top, adduct_charge_top, adduct_mass_neutral_top, adduct_mass_shift_top,
+                    adduct_group, adduct_of, id_top_name, id_top_class, id_top_adduct]
     
     if all(param is None for param in filter_params) and sortby is None:
         return self.consensus_df.clone()
@@ -3132,6 +3157,126 @@ def consensus_select(
         else:
             warnings.append("'id_top_name' column not found in consensus_df")
 
+    # Handle adduct_top filter (string or list)
+    if adduct_top is not None:
+        if "adduct_top" in available_columns:
+            if isinstance(adduct_top, list):
+                filter_conditions.append(pl.col("adduct_top").is_in(adduct_top))
+            else:
+                filter_conditions.append(pl.col("adduct_top") == adduct_top)
+        else:
+            warnings.append("'adduct_top' column not found in consensus_df")
+
+    # Handle adduct_charge_top filter (single value, range tuple, or list)
+    if adduct_charge_top is not None:
+        if "adduct_charge_top" in available_columns:
+            if isinstance(adduct_charge_top, tuple) and len(adduct_charge_top) == 2:
+                filter_conditions.append(
+                    (pl.col("adduct_charge_top") >= adduct_charge_top[0]) &
+                    (pl.col("adduct_charge_top") <= adduct_charge_top[1])
+                )
+            elif isinstance(adduct_charge_top, list):
+                filter_conditions.append(pl.col("adduct_charge_top").is_in(adduct_charge_top))
+            else:
+                filter_conditions.append(pl.col("adduct_charge_top") == adduct_charge_top)
+        else:
+            warnings.append("'adduct_charge_top' column not found in consensus_df")
+
+    # Handle adduct_mass_neutral_top filter (single value, range tuple, or list)
+    if adduct_mass_neutral_top is not None:
+        if "adduct_mass_neutral_top" in available_columns:
+            if isinstance(adduct_mass_neutral_top, tuple) and len(adduct_mass_neutral_top) == 2:
+                filter_conditions.append(
+                    (pl.col("adduct_mass_neutral_top") >= adduct_mass_neutral_top[0]) &
+                    (pl.col("adduct_mass_neutral_top") <= adduct_mass_neutral_top[1])
+                )
+            elif isinstance(adduct_mass_neutral_top, list):
+                filter_conditions.append(pl.col("adduct_mass_neutral_top").is_in(adduct_mass_neutral_top))
+            else:
+                filter_conditions.append(pl.col("adduct_mass_neutral_top") == adduct_mass_neutral_top)
+        else:
+            warnings.append("'adduct_mass_neutral_top' column not found in consensus_df")
+
+    # Handle adduct_mass_shift_top filter (single value, range tuple, or list)
+    if adduct_mass_shift_top is not None:
+        if "adduct_mass_shift_top" in available_columns:
+            if isinstance(adduct_mass_shift_top, tuple) and len(adduct_mass_shift_top) == 2:
+                filter_conditions.append(
+                    (pl.col("adduct_mass_shift_top") >= adduct_mass_shift_top[0]) &
+                    (pl.col("adduct_mass_shift_top") <= adduct_mass_shift_top[1])
+                )
+            elif isinstance(adduct_mass_shift_top, list):
+                filter_conditions.append(pl.col("adduct_mass_shift_top").is_in(adduct_mass_shift_top))
+            else:
+                filter_conditions.append(pl.col("adduct_mass_shift_top") == adduct_mass_shift_top)
+        else:
+            warnings.append("'adduct_mass_shift_top' column not found in consensus_df")
+
+    # Handle adduct_group filter (single value or list)
+    if adduct_group is not None:
+        if "adduct_group" in available_columns:
+            if isinstance(adduct_group, list):
+                filter_conditions.append(pl.col("adduct_group").is_in(adduct_group))
+            else:
+                filter_conditions.append(pl.col("adduct_group") == adduct_group)
+        else:
+            warnings.append("'adduct_group' column not found in consensus_df")
+
+    # Handle adduct_of filter (single value or list)
+    if adduct_of is not None:
+        if "adduct_of" in available_columns:
+            if isinstance(adduct_of, list):
+                filter_conditions.append(pl.col("adduct_of").is_in(adduct_of))
+            else:
+                filter_conditions.append(pl.col("adduct_of") == adduct_of)
+        else:
+            warnings.append("'adduct_of' column not found in consensus_df")
+
+    # Handle id_top_name filter (string or list)
+    if id_top_name is not None:
+        if "id_top_name" in available_columns:
+            if isinstance(id_top_name, list):
+                filter_conditions.append(pl.col("id_top_name").is_in(id_top_name))
+            else:
+                filter_conditions.append(pl.col("id_top_name") == id_top_name)
+        else:
+            warnings.append("'id_top_name' column not found in consensus_df")
+
+    # Handle id_top_class filter (string or list)
+    if id_top_class is not None:
+        if "id_top_class" in available_columns:
+            if isinstance(id_top_class, list):
+                filter_conditions.append(pl.col("id_top_class").is_in(id_top_class))
+            else:
+                filter_conditions.append(pl.col("id_top_class") == id_top_class)
+        else:
+            warnings.append("'id_top_class' column not found in consensus_df")
+
+    # Handle id_top_adduct filter (string or list)
+    if id_top_adduct is not None:
+        if "id_top_adduct" in available_columns:
+            if isinstance(id_top_adduct, list):
+                filter_conditions.append(pl.col("id_top_adduct").is_in(id_top_adduct))
+            else:
+                filter_conditions.append(pl.col("id_top_adduct") == id_top_adduct)
+        else:
+            warnings.append("'id_top_adduct' column not found in consensus_df")
+
+    # Handle id_top_score filter (single value, range tuple, or list)
+    if id_top_score is not None:
+        if "id_top_score" in available_columns:
+            if isinstance(id_top_score, tuple) and len(id_top_score) == 2:
+                filter_conditions.append(
+                    (pl.col("id_top_score") >= id_top_score[0]) &
+                    (pl.col("id_top_score") <= id_top_score[1])
+                )
+            elif isinstance(id_top_score, list):
+                filter_conditions.append(pl.col("id_top_score").is_in(id_top_score))
+            else:
+                filter_conditions.append(pl.col("id_top_score") == id_top_score)
+        else:
+            warnings.append("'id_top_score' column not found in consensus_df")
+
     # Log warnings once
     for warning in warnings:
         self.logger.warning(warning)

{masster-0.5.6 → masster-0.5.8}/src/masster/study/id.py

@@ -1201,7 +1201,7 @@ def lib_reset(study):
         logger.info("Library and identification data reset completed")
 
 
-def _get_adducts(study, adducts_list: list = None, **kwargs):
+def _get_adducts(study, adducts_list: list | None = None, **kwargs):
     """
     Generate comprehensive adduct specifications for study-level adduct filtering.