Merge pull request #32 from mmzdouc/dev_mmz

v0.3.1

CHANGELOG.md

@@ -10,6 +10,19 @@ This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 
 N/A
 
+## [0.3.1] 05-06-2024
+
+### Changed
+
+- Loosened typing restrictions for Feature and Sample object attributes: area and height (intensity) now accept float values.
+
+### Removed
+- [Breaking change] Removed toggle 'nonbiological' from 'FragmentAnnotator' and from parameters file; 'nonbiological' fragment annotation is now performed automatically
+
+### Security
+
+- Instead of full file paths, only filenames are now written to the 'out.fermo.session.json' file
+
 ## [0.3.0] 03-06-2024
 
 ### Changed

example_data/case_study_parameters.json

@@ -38,8 +38,7 @@
         },
         "neutral_loss_annotation": {
             "activate_module": true,
-            "mass_dev_ppm": 10.0,
-            "nonbiological": true
+            "mass_dev_ppm": 10.0
         },
         "fragment_annotation": {
             "activate_module": true,

fermo_core/config/schema.json

@@ -224,10 +224,6 @@
                             "type": "number",
                             "minimum": 0.0,
                             "maximum": 100.0
-                        },
-                        "nonbiological": {
-                            "title": "(Optional): Specifies whether neutral losses should be compared to losses originating from synthetic molecules.",
-                            "type": "boolean"
                         }
                     }
                 },

fermo_core/data_analysis/annotation_manager/class_annotation_manager.py

@@ -1,6 +1,6 @@
 """Organize the calling of annotation modules.
 
-Copyright (c) 2022-2024 Mitja Maximilian Zdouc, PhD
+Copyright (c) 2022 to present Mitja Maximilian Zdouc, PhD
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
@@ -122,7 +122,7 @@ def _eval_as_results_file() -> bool:
                 self.run_as_kcb_cosine_annotation,
             ),
             (
-                _eval_as_results_file,
+                _eval_as_results_file(),
                 self.run_as_kcb_deepscore_annotation,
             ),
         )

fermo_core/data_analysis/annotation_manager/class_neutral_loss_annotator.py

@@ -145,8 +145,7 @@ def annotate_feature_pos(self: Self, f_id: int):
         feature = self.validate_nonribosomal_losses(feature)
         feature = self.validate_glycoside_losses(feature)
         feature = self.validate_gen_bio_pos_losses(feature)
-        if self.params.NeutralLossParameters.nonbiological is True:
-            feature = self.validate_gen_other_pos_losses(feature)
+        feature = self.validate_gen_other_pos_losses(feature)
 
         self.features.modify(f_id, feature)
 

fermo_core/data_processing/builder_feature/class_feature_builder.py

@@ -23,6 +23,7 @@
 
 import logging
 
+import numpy as np
 import pandas as pd
 from pydantic import BaseModel
 
@@ -102,16 +103,25 @@ def set_rt_range(self):
         )
         return self
 
-    def set_fwhm(self, fwhm: float):
+    def set_fwhm(self, fwhm: float, s_id: str):
         """Set attribute
 
         Arguments:
             fwhm: the feature with at half maximum intensity of the peak
+            s_id: a sample ID
         """
-        self.feature.fwhm = fwhm
+        if np.isnan(np.sum(fwhm)):
+            logger.warning(
+                f"'FeatureBuilder': feature '{self.feature.f_id}' has no valid FWHM "
+                f"in sample '{s_id}'. Set value to '0.0'."
+            )
+            self.feature.fwhm = 0.0
+        else:
+            self.feature.fwhm = float(fwhm)
+
         return self
 
-    def set_intensity(self, intensity: int):
+    def set_intensity(self, intensity: float):
         """Set attribute
 
         Arguments:
@@ -120,7 +130,7 @@ def set_intensity(self, intensity: int):
         self.feature.intensity = intensity
         return self
 
-    def set_rel_intensity(self, intensity: int, max_intensity: int):
+    def set_rel_intensity(self, intensity: float, max_intensity: float):
         """Calculate and set attribute for relative intensity
 
         Arguments:
@@ -130,7 +140,7 @@ def set_rel_intensity(self, intensity: int, max_intensity: int):
         self.feature.rel_intensity = round((intensity / max_intensity), 2)
         return self
 
-    def set_area(self, area: int):
+    def set_area(self, area: float):
         """Set attribute
 
         Arguments:
@@ -139,7 +149,7 @@ def set_area(self, area: int):
         self.feature.area = area
         return self
 
-    def set_rel_area(self, area: int, max_area: int):
+    def set_rel_area(self, area: float, max_area: float):
         """Calculate and set attribute for relative area
 
         Arguments:

fermo_core/data_processing/builder_feature/class_general_feature_director.py

@@ -46,7 +46,7 @@ def construct_mzmine3(row: pd.Series) -> Feature:
         return (
             FeatureBuilder()
             .set_f_id(int(row["id"]))
-            .set_area(int(row["area"]))
+            .set_area(float(row["area"]))
             .set_mz(float(row["mz"]))
             .set_rt(float(row["rt"]))
             .set_rt_start(float(row["rt_range:min"]))

fermo_core/data_processing/builder_feature/class_specific_feature_director.py

@@ -55,12 +55,12 @@ def construct_mzmine3(
             FeatureBuilder()
             .set_f_id(int(row["id"]))
             .set_mz(float(row["mz"]))
-            .set_fwhm(float(row[f"datafile:{s_id}:fwhm"]))
-            .set_intensity(int(row[f"datafile:{s_id}:intensity_range:max"]))
+            .set_fwhm(float(row[f"datafile:{s_id}:fwhm"]), s_id)
+            .set_intensity(float(row[f"datafile:{s_id}:intensity_range:max"]))
             .set_rt_start(float(row[f"datafile:{s_id}:rt_range:min"]))
             .set_rt_stop(float(row[f"datafile:{s_id}:rt_range:max"]))
             .set_rt(float(row[f"datafile:{s_id}:rt"]))
-            .set_area(int(row[f"datafile:{s_id}:area"]))
+            .set_area(float(row[f"datafile:{s_id}:area"]))
             .set_rt_range()
             .set_rel_intensity(
                 row[f"datafile:{s_id}:intensity_range:max"], max_intensity

fermo_core/data_processing/builder_feature/dataclass_feature.py

@@ -282,16 +282,16 @@ class SampleInfo(BaseModel):
 
     Attributes:
         s_id: identifier of sample
-        value: an integer indicating the respective value (area or height)
+        value: indicating the respective value (area or height)
     """
 
     s_id: str
-    value: int
+    value: float
 
     def to_json(self: Self) -> dict:
         return {
             "s_id": str(self.s_id),
-            "value": int(self.value),
+            "value": float(self.value),
         }
 
 
@@ -374,9 +374,9 @@ class Feature(BaseModel):
     trace_rt: Optional[tuple] = None
     trace_int: Optional[tuple] = None
     fwhm: Optional[float] = None
-    intensity: Optional[int] = None
+    intensity: Optional[float] = None
     rel_intensity: Optional[float] = None
-    area: Optional[int] = None
+    area: Optional[float] = None
     rel_area: Optional[float] = None
     Spectrum: Optional[Any] = None
     samples: Optional[set] = None
@@ -405,9 +405,9 @@ def to_json(self: Self) -> dict:
             ("trace_rt", self.trace_rt, list),
             ("trace_int", self.trace_int, list),
             ("fwhm", self.fwhm, float),
-            ("intensity", self.intensity, int),
+            ("intensity", self.intensity, float),
             ("rel_intensity", self.rel_intensity, float),
-            ("area", self.area, int),
+            ("area", self.area, float),
             ("rel_area", self.rel_area, float),
             ("samples", self.samples, list),
             ("blank", self.blank, bool),

fermo_core/data_processing/builder_sample/dataclass_sample.py

@@ -71,8 +71,8 @@ class Sample(BaseModel):
     features: Optional[dict] = None
     feature_ids: Optional[set] = None
     networks: Optional[dict] = None
-    max_intensity: Optional[int] = None
-    max_area: Optional[int] = None
+    max_intensity: Optional[float] = None
+    max_area: Optional[float] = None
     Scores: Optional[Scores] = None
 
     def to_json(self: Self) -> dict:
@@ -84,8 +84,8 @@ def to_json(self: Self) -> dict:
         attributes = (
             ("s_id", self.s_id, str),
             ("feature_ids", self.feature_ids, list),
-            ("max_intensity", self.max_intensity, int),
-            ("max_area", self.max_area, int),
+            ("max_intensity", self.max_intensity, float),
+            ("max_area", self.max_area, float),
         )
 
         json_dict = {}

fermo_core/input_output/core_module_parameter_managers.py

@@ -65,13 +65,11 @@ class NeutralLossParameters(BaseModel):
     Attributes:
         activate_module: bool to indicate if module should be executed.
         mass_dev_ppm: The estimated maximum mass deviation in ppm.
-        nonbiological: Switch on comparison against losses in 'generic_other_pos.csv'
         module_passed: indicates that the module ran without errors
     """
 
     activate_module: bool = True
     mass_dev_ppm: PositiveFloat = 10.0
-    nonbiological: bool = False
     module_passed: bool = False
 
     @model_validator(mode="after")
@@ -86,7 +84,6 @@ def to_json(self: Self) -> dict:
             return {
                 "activate_module": self.activate_module,
                 "mass_dev_ppm": float(self.mass_dev_ppm),
-                "nonbiological": self.nonbiological,
                 "module_passed": self.module_passed,
             }
         else:

fermo_core/input_output/input_file_parameter_managers.py

@@ -1,6 +1,6 @@
 """Organizes classes that handle and validate input file parameter.
 
-Copyright (c) 2022-2023 Mitja Maximilian Zdouc, PhD
+Copyright (c) 2022 to present Mitja Maximilian Zdouc, PhD
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
@@ -74,7 +74,7 @@ def validate_polarity_format(self):
     def to_json(self: Self) -> dict:
         """Convert attributes to json-compatible ones."""
         return {
-            "filepath": str(self.filepath.resolve()),
+            "filepath": str(self.filepath.name),
             "format": str(self.format),
             "polarity": str(self.polarity),
         }
@@ -119,7 +119,7 @@ def validate_rel_int_range(self):
     def to_json(self: Self) -> dict:
         """Convert attributes to json-compatible ones."""
         return {
-            "filepath": str(self.filepath.resolve()),
+            "filepath": str(self.filepath.name),
             "format": self.format,
             "rel_int_from": self.rel_int_from,
         }
@@ -170,7 +170,7 @@ def validate_phenotype_format(self):
     def to_json(self: Self) -> dict:
         """Convert attributes to json-compatible ones."""
         return {
-            "filepath": str(self.filepath.resolve()),
+            "filepath": str(self.filepath.name),
             "format": str(self.format),
         }
 
@@ -224,7 +224,7 @@ def validate_group_metadata_format(self):
     def to_json(self: Self) -> dict:
         """Convert attributes to json-compatible ones."""
         return {
-            "filepath": str(self.filepath.resolve()),
+            "filepath": str(self.filepath.name),
             "format": str(self.format),
         }
 
@@ -261,7 +261,7 @@ def validate_spectral_library_format(self):
     def to_json(self: Self) -> dict:
         """Convert attributes to json-compatible ones."""
         return {
-            "filepath": str(self.filepath.resolve()),
+            "filepath": str(self.filepath.name),
             "format": str(self.format),
         }
 
@@ -290,7 +290,7 @@ def validate_ms2query_result_format(self):
     def to_json(self: Self) -> dict:
         """Convert attributes to json-compatible ones."""
         return {
-            "filepath": str(self.filepath.resolve()),
+            "filepath": str(self.filepath.name),
             "score_cutoff": self.score_cutoff,
         }
 
@@ -312,6 +312,6 @@ class AsResultsParameters(BaseModel):
     def to_json(self: Self) -> dict:
         """Convert attributes to json-compatible ones."""
         return {
-            "directory_path": str(self.directory_path.resolve()),
+            "directory_path": str(self.directory_path.name),
             "similarity_cutoff": self.similarity_cutoff,
         }

fermo_core/input_output/output_file_parameter_managers.py

@@ -74,6 +74,8 @@ def _create_output_dir():
     def to_json(self: Self) -> dict:
         """Convert attributes to json-compatible ones."""
         try:
-            return {"directory_path": str(self.directory_path.resolve())}
+            return {
+                "directory_path": f"{self.directory_path.parent.name}/{self.directory_path.name}"
+            }
         except AttributeError:
             return {"directory_path": "not specified"}

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "fermo_core"
-version = "0.3.0"
+version = "0.3.1"
 description = "Data processing/analysis functionality of metabolomics dashboard FERMO"
 readme = "README.md"
 requires-python = ">=3.11,<3.12"

tests/test_data/test.parameters.json

@@ -38,8 +38,7 @@
         },
         "neutral_loss_annotation": {
             "activate_module": true,
-            "mass_dev_ppm": 10.0,
-            "nonbiological": true
+            "mass_dev_ppm": 10.0
         },
         "fragment_annotation": {
             "activate_module": true,

tests/test_data_analysis/test_annotation_manager/test_class_neutral_loss_annotator.py

@@ -1,20 +1,23 @@
-import numpy as np
 from pathlib import Path
+
+import numpy as np
 import pytest
 
 from fermo_core.data_analysis.annotation_manager.class_neutral_loss_annotator import (
     NeutralLossAnnotator,
 )
-from fermo_core.data_processing.class_repository import Repository
 from fermo_core.data_processing.builder_feature.dataclass_feature import (
     Feature,
     NeutralLoss,
 )
+from fermo_core.data_processing.class_repository import Repository
 from fermo_core.data_processing.class_stats import Stats
 from fermo_core.input_output.class_parameter_manager import ParameterManager
-from fermo_core.input_output.input_file_parameter_managers import MsmsParameters
 from fermo_core.input_output.core_module_parameter_managers import NeutralLossParameters
-from fermo_core.input_output.input_file_parameter_managers import PeaktableParameters
+from fermo_core.input_output.input_file_parameter_managers import (
+    MsmsParameters,
+    PeaktableParameters,
+)
 from fermo_core.utils.utility_method_manager import UtilityMethodManager as Utils
 
 
@@ -49,7 +52,6 @@ def annotator_pos():
         format="mzmine3",
         polarity="positive",
     )
-    params.NeutralLossParameters = NeutralLossParameters(nonbiological=True)
     return NeutralLossAnnotator(
         features=features, samples=Repository(), params=params, stats=stats
     )
@@ -86,7 +88,6 @@ def annotator_neg():
         format="mzmine3",
         polarity="negative",
     )
-    params.NeutralLossParameters = NeutralLossParameters(nonbiological=True)
     return NeutralLossAnnotator(
         features=features, samples=Repository(), params=params, stats=stats
     )

tests/test_data_processing/test_builder_feature/test_class_feature_builder.py

@@ -69,7 +69,7 @@ def test_set_rt_range_invalid():
 
 
 def test_set_fwhm_valid():
-    feature1 = FeatureBuilder().set_fwhm(12.34).get_result()
+    feature1 = FeatureBuilder().set_fwhm(12.34, "sample1").get_result()
     assert feature1.fwhm == 12.34