masster 0.3.10__py3-none-any.whl → 0.3.11__py3-none-any.whl

masster/study/defaults/align_def.py

@@ -14,22 +14,74 @@ class align_defaults:
     alignment algorithm settings.
 
     Attributes:
+        algo (str): Alignment algorithm ('pc' for PoseClustering, 'kd' for KD). Default is 'pc'.
         rt_max_diff (float): Maximum retention time difference for alignment. Default is 60.0.
-        mz_max_diff (float): Maximum m/z difference for alignment. Default is 0.01.
+        mz_max_diff (float): Maximum m/z difference for alignment. Default is 0.02.
         rt_pair_distance_frac (float): Fraction of RT difference for pair distance. Default is 0.2.
         mz_pair_max_distance (float): Maximum m/z pair distance. Default is 0.01.
         num_used_points (int): Number of points used for alignment. Default is 1000.
-        save_features (bool): Whether to save features after alignment. Default is True.
-        skip_blanks (bool): Whether to skip blank samples. Default is True.
+        save_features (bool): Whether to save features after alignment. Default is False.
+        skip_blanks (bool): Whether to skip blank samples. Default is False.
+
+        KD algorithm specific parameters:
+        nr_partitions (int): Number of partitions in m/z dimension. Default is 100.
+        warp_enabled (bool): Enable non-linear retention time transformation. Default is True.
+        warp_rt_tol (float): RT tolerance for the LOWESS fit. Default is 5.0.
+        warp_mz_tol (float): m/z tolerance for the LOWESS fit. Default is 0.05.
+        warp_max_pairwise_log_fc (float): Maximum absolute log10 fold change threshold for pairing. Default is 0.5.
+        warp_min_rel_cc_size (float): Minimum relative connected component size. Default is 0.5.
+        warp_max_nr_conflicts (int): Allow up to this many conflicts per connected component for alignment. Default is 0.
+        link_rt_tol (float): Width of RT tolerance window for linking (seconds). Default is 30.0.
+        link_mz_tol (float): m/z tolerance for linking features (ppm or Da). Default is 10.0.
+        link_charge_merging (str): Charge merging strategy for linking. Default is "With_charge_zero".
+        link_adduct_merging (str): Adduct merging strategy for linking. Default is "Any".
+        distance_RT_exponent (float): Exponent for normalized RT differences. Default is 1.0.
+        distance_RT_weight (float): Weight factor for final RT distances. Default is 1.0.
+        distance_MZ_exponent (float): Exponent for normalized m/z differences. Default is 2.0.
+        distance_MZ_weight (float): Weight factor for final m/z distances. Default is 1.0.
+        distance_intensity_exponent (float): Exponent for differences in relative intensity. Default is 1.0.
+        distance_intensity_weight (float): Weight factor for final intensity distances. Default is 1.0.
+        distance_intensity_log_transform (str): Log-transform intensities. Default is "enabled".
+        LOWESS_span (float): Fraction of datapoints for each local regression. Default is 0.666666666666667.
+        LOWESS_num_iterations (int): Number of robustifying iterations for LOWESS fitting. Default is 3.
+        LOWESS_delta (float): Parameter for LOWESS computations (negative auto-computes). Default is -1.0.
+        LOWESS_interpolation_type (str): Method for interpolation between datapoints. Default is "cspline".
+        LOWESS_extrapolation_type (str): Method for extrapolation outside data range. Default is "four-point-linear".
     """
 
     rt_max_diff: float = 60.0
-    mz_max_diff: float = 0.01
+    mz_max_diff: float = 0.02
     rt_pair_distance_frac: float = 0.2
     mz_pair_max_distance: float = 0.01
     num_used_points: int = 1000
-    save_features: bool = True
-    skip_blanks: bool = True
+    save_features: bool = False
+    skip_blanks: bool = False
+    algo: str = "pc"
+
+    # KD algorithm specific parameters
+    nr_partitions: int = 100
+    warp_enabled: bool = True
+    warp_rt_tol: float = 5.0
+    warp_mz_tol: float = 0.05
+    warp_max_pairwise_log_fc: float = 0.5
+    warp_min_rel_cc_size: float = 0.5
+    warp_max_nr_conflicts: int = 0
+    link_rt_tol: float = 30.0
+    link_mz_tol: float = 10.0
+    link_charge_merging: str = "With_charge_zero"
+    link_adduct_merging: str = "Any"
+    distance_RT_exponent: float = 1.0
+    distance_RT_weight: float = 1.0
+    distance_MZ_exponent: float = 2.0
+    distance_MZ_weight: float = 1.0
+    distance_intensity_exponent: float = 1.0
+    distance_intensity_weight: float = 1.0
+    distance_intensity_log_transform: str = "enabled"
+    LOWESS_span: float = 0.666666666666667
+    LOWESS_num_iterations: int = 3
+    LOWESS_delta: float = -1.0
+    LOWESS_interpolation_type: str = "cspline"
+    LOWESS_extrapolation_type: str = "four-point-linear"
 
     _param_metadata: dict[str, dict[str, Any]] = field(
         default_factory=lambda: {
@@ -78,6 +130,167 @@ class align_defaults:
                 "description": "Whether to skip blank samples during alignment",
                 "default": True,
             },
+            "algo": {
+                "dtype": str,
+                "description": "Alignment algorithm to use",
+                "default": "pc",
+                "allowed_values": ["pc", "kd"],
+            },
+            # KD algorithm specific parameters
+            "nr_partitions": {
+                "dtype": int,
+                "description": "Number of partitions in m/z dimension for KD algorithm",
+                "default": 100,
+                "min_value": 1,
+                "max_value": 1000,
+            },
+            "warp_enabled": {
+                "dtype": bool,
+                "description": "Enable non-linear retention time transformation for KD algorithm",
+                "default": True,
+            },
+            "warp_rt_tol": {
+                "dtype": float,
+                "description": "RT tolerance for the LOWESS fit in KD algorithm (seconds)",
+                "default": 5.0,
+                "min_value": 0.1,
+                "max_value": 60.0,
+            },
+            "warp_mz_tol": {
+                "dtype": float,
+                "description": "m/z tolerance for the LOWESS fit in KD algorithm (Da)",
+                "default": 0.05,
+                "min_value": 0.001,
+                "max_value": 1.0,
+            },
+            "warp_max_pairwise_log_fc": {
+                "dtype": float,
+                "description": "Maximum absolute log10 fold change between two compatible signals during compatibility graph construction in KD algorithm",
+                "default": 0.5,
+                "min_value": -1.0,
+                "max_value": 10.0,
+            },
+            "warp_min_rel_cc_size": {
+                "dtype": float,
+                "description": "Minimum relative connected component size for KD algorithm",
+                "default": 0.5,
+                "min_value": 0.0,
+                "max_value": 1.0,
+            },
+            "warp_max_nr_conflicts": {
+                "dtype": int,
+                "description": "Allow up to this many conflicts (features from the same map) per connected component to be used for alignment (-1 means allow any number of conflicts)",
+                "default": 0,
+                "min_value": -1,
+                "max_value": 1000,
+            },
+            "link_rt_tol": {
+                "dtype": float,
+                "description": "Width of RT tolerance window for linking in KD algorithm (seconds)",
+                "default": 30.0,
+                "min_value": 0.0,
+                "max_value": 300.0,
+            },
+            "link_mz_tol": {
+                "dtype": float,
+                "description": "m/z tolerance for linking features in KD algorithm (ppm or Da)",
+                "default": 10.0,
+                "min_value": 0.0,
+                "max_value": 100.0,
+            },
+            "link_charge_merging": {
+                "dtype": str,
+                "description": "Charge merging strategy for linking features in KD algorithm",
+                "default": "With_charge_zero",
+                "allowed_values": ["Identical", "With_charge_zero", "Any"],
+            },
+            "link_adduct_merging": {
+                "dtype": str,
+                "description": "Adduct merging strategy for linking features in KD algorithm",
+                "default": "Any",
+                "allowed_values": ["Identical", "With_unknown_adducts", "Any"],
+            },
+            "distance_RT_exponent": {
+                "dtype": float,
+                "description": "Normalized RT differences are raised to this power in KD algorithm",
+                "default": 1.0,
+                "min_value": 0.0,
+                "max_value": 10.0,
+            },
+            "distance_RT_weight": {
+                "dtype": float,
+                "description": "Final RT distances are weighted by this factor in KD algorithm",
+                "default": 1.0,
+                "min_value": 0.0,
+                "max_value": 100.0,
+            },
+            "distance_MZ_exponent": {
+                "dtype": float,
+                "description": "Normalized m/z differences are raised to this power in KD algorithm",
+                "default": 2.0,
+                "min_value": 0.0,
+                "max_value": 10.0,
+            },
+            "distance_MZ_weight": {
+                "dtype": float,
+                "description": "Final m/z distances are weighted by this factor in KD algorithm",
+                "default": 1.0,
+                "min_value": 0.0,
+                "max_value": 100.0,
+            },
+            "distance_intensity_exponent": {
+                "dtype": float,
+                "description": "Differences in relative intensity are raised to this power in KD algorithm",
+                "default": 1.0,
+                "min_value": 0.0,
+                "max_value": 10.0,
+            },
+            "distance_intensity_weight": {
+                "dtype": float,
+                "description": "Final intensity distances are weighted by this factor in KD algorithm",
+                "default": 1.0,
+                "min_value": 0.0,
+                "max_value": 100.0,
+            },
+            "distance_intensity_log_transform": {
+                "dtype": str,
+                "description": "Log-transform intensities in KD algorithm distance calculation",
+                "default": "enabled",
+                "allowed_values": ["enabled", "disabled"],
+            },
+            "LOWESS_span": {
+                "dtype": float,
+                "description": "Fraction of datapoints to use for each local regression in LOWESS fitting",
+                "default": 0.666666666666667,
+                "min_value": 0.0,
+                "max_value": 1.0,
+            },
+            "LOWESS_num_iterations": {
+                "dtype": int,
+                "description": "Number of robustifying iterations for LOWESS fitting",
+                "default": 3,
+                "min_value": 0,
+                "max_value": 10,
+            },
+            "LOWESS_delta": {
+                "dtype": float,
+                "description": "Nonnegative parameter for LOWESS computations (negative value auto-computes)",
+                "default": -1.0,
+                "min_value": -1.0,
+                "max_value": 1000.0,
+            },
+            "LOWESS_interpolation_type": {
+                "dtype": str,
+                "description": "Method to use for interpolation between datapoints computed by LOWESS",
+                "default": "cspline",
+                "allowed_values": ["linear", "cspline", "akima"],
+            },
+            "LOWESS_extrapolation_type": {
+                "dtype": str,
+                "description": "Method to use for extrapolation outside the data range in LOWESS",
+                "default": "four-point-linear",
+                "allowed_values": ["two-point-linear", "four-point-linear", "global-linear"],
+            },
         },
         repr=False,
     )
@@ -152,6 +365,11 @@ class align_defaults:
             if "max_value" in metadata and value > metadata["max_value"]:
                 return False
 
+        # Allowed values validation for string types
+        if expected_dtype is str and "allowed_values" in metadata:
+            if value not in metadata["allowed_values"]:
+                return False
+
         return True
 
     def set(self, param_name: str, value: Any, validate: bool = True) -> bool:

masster/study/defaults/fill_chrom_def.py

@@ -168,11 +168,7 @@ class fill_chrom_defaults:
             expected_dtype = self._param_metadata[param_name]["dtype"]
 
             # Handle optional types
-            if (
-                isinstance(expected_dtype, str)
-                and expected_dtype.startswith("Optional")
-                and value is not None
-            ):
+            if isinstance(expected_dtype, str) and expected_dtype.startswith("Optional") and value is not None:
                 if "int" in expected_dtype and not isinstance(value, int):
                     try:
                         value = int(value)

masster/study/defaults/integrate_chrom_def.py

@@ -135,11 +135,7 @@ class integrate_chrom_defaults:
             expected_dtype = self._param_metadata[param_name]["dtype"]
 
             # Handle optional types
-            if (
-                isinstance(expected_dtype, str)
-                and expected_dtype.startswith("Optional")
-                and value is not None
-            ):
+            if isinstance(expected_dtype, str) and expected_dtype.startswith("Optional") and value is not None:
                 if "float" in expected_dtype and not isinstance(value, float):
                     try:
                         value = float(value)

masster/study/defaults/study_def.py

@@ -53,13 +53,13 @@ class study_defaults:
             "log_sink": {
                 "dtype": str,
                 "description": "Output sink for logging. Use 'sys.stdout' for console output, or a file path",
-                "default": "sys.stdout",                
+                "default": "sys.stdout",
             },
             "polarity": {
                 "dtype": str,
                 "description": "Polarity of the study (positive/negative)",
                 "default": "positive",
-                "allowed_values": ["positive", "negative","pos","neg"],
+                "allowed_values": ["positive", "negative", "pos", "neg"],
             },
         },
         repr=False,