Skip to content

Commit

Permalink
Merge pull request #31 from mmzdouc/dev_mmz
Browse files Browse the repository at this point in the history 
Dev mmz
  • Loading branch information
@mmzdouc
mmzdouc authored Jun 3, 2024
2 parents 82924df + ab75578 commit 00eab95
Show file tree
Hide file tree
Showing 24 changed files with 487 additions and 267 deletions.
15 changes: 12 additions & 3 deletions CHANGELOG.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,16 @@ This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm

N/A

## [0.2.1] 27-05-2024
## [0.3.0] 03-06-2024

### Changed

- [Breaking change] Parameter settings for `additional_modules/feature_filtering` were changed from a list of ranges to a dictionary with explicit values.
- Reworked score assignment for qualitative phenotype data: phenotype-associated features now always receive a score of 1.0, and non-associated ones a score of 0.0.
- For all modules with runtime restriction, the 'maximum_runtime' parameter was set to a default of '0' (unlimited runtime). Therefore, runtime restriction must now be specified explicitly.
- Added a 'module_passed' parameter to all modules. This allows a more accurate description via the SummaryWriter (e.g. module was activated but timed out, and lack of e.g. annotation is due to premature ending and not because there were no hits).

## [0.2.2] 27-05-2024

### Changed

Expand All @@ -30,7 +39,7 @@ N/A
- Replaced global logger with logger specific for `main_cli()`. `main()` now needs an argument `logger`
- Reworked output file naming: all output files now start with `out.fermo.` and a suffix specifying their type
- Removed output directory selection: the output directory is now always `results` located in the directory in which the peaktable resides.
- Features now always have default result values (before, some Features could have an empty dictionary)
- Features now always have default result values (previously, some Features could have an empty dictionary)
- MS2Query assignment now uses temporary directories for data reading/writing

### Fixed
Expand All @@ -45,4 +54,4 @@ N/A

## [0.1.0] 19-05-2024

First public release of `fermo_core`
- First public release of `fermo_core`
14 changes: 5 additions & 9 deletions example_data/case_study_parameters.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -66,14 +66,10 @@
"additional_modules": {
"feature_filtering": {
"activate_module": true,
"filter_rel_int_range": [
0.1,
1.0
],
"filter_rel_area_range": [
0.1,
1.0
]
"filter_rel_int_range_min": 0.1,
"filter_rel_int_range_max": 1.0,
"filter_rel_area_range_min": 0.1,
"filter_rel_area_range_max": 1.0
},
"blank_assignment": {
"activate_module": true,
Expand Down Expand Up @@ -148,4 +144,4 @@
}
}
}
}
}
46 changes: 24 additions & 22 deletions fermo_core/config/schema.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -351,27 +351,29 @@
"title": "Specifies whether this module should be run.",
"type": "boolean"
},
"filter_rel_int_range": {
"title": "(Optional): restrict data analysis to molecular features that have a relative intensity (intensity relative to the highest feature intensity per sample) that is inside the specified range. If a feature is detected in multiple samples, at least one occurrence must be inside the specified range. Else, the feature is not considered.",
"type": "array",
"minItems": 2,
"maxItems": 2,
"items": {
"type": "number",
"minimum": 0.0,
"maximum": 1.0
}
"filter_rel_int_range_min": {
"title": "(Optional): restrict data analysis to molecular features that have a relative intensity (intensity relative to the highest feature intensity per sample) that greater or equal to the specified value. If a feature is detected in multiple samples, at least one occurrence must be inside the specified range. Else, the feature is not considered.",
"type": "number",
"minimum": 0.0,
"maximum": 1.0
},
"filter_rel_area_range": {
"title": "(Optional): restrict data analysis to molecular features that have a relative area (area relative to the highest feature area per sample that is inside the specified range. If a feature is detected in multiple samples, at least one occurrence must be inside the specified range. Else, the feature is not considered.",
"type": "array",
"minItems": 2,
"maxItems": 2,
"items": {
"type": "number",
"minimum": 0.0,
"maximum": 1.0
}
"filter_rel_int_range_max": {
"title": "(Optional): restrict data analysis to molecular features that have a relative intensity (intensity relative to the highest feature intensity per sample) that less or equal to the specified value. If a feature is detected in multiple samples, at least one occurrence must be inside the specified range. Else, the feature is not considered.",
"type": "number",
"minimum": 0.0,
"maximum": 1.0
},
"filter_rel_area_range_min": {
"title": "(Optional): restrict data analysis to molecular features that have a relative area (area relative to the highest feature area per sample) that greater or equal to the specified value. If a feature is detected in multiple samples, at least one occurrence must be inside the specified range. Else, the feature is not considered.",
"type": "number",
"minimum": 0.0,
"maximum": 1.0
},
"filter_rel_area_range_max": {
"title": "(Optional): restrict data analysis to molecular features that have a relative area (area relative to the highest feature area per sample) that less or equal to the specified value. If a feature is detected in multiple samples, at least one occurrence must be inside the specified range. Else, the feature is not considered.",
"type": "number",
"minimum": 0.0,
"maximum": 1.0
}
}
},
Expand Down Expand Up @@ -518,7 +520,7 @@
]
},
"p_val_cutoff": {
"title": "(Optional): Minimum Bonferroni-corrected p-value to consider. A value of zero disables the cutoff filtering (automatically applies to both score and p-value).",
"title": "(Optional): Maximum Bonferroni-corrected p-value to consider. A value of zero disables the cutoff filtering (automatically applies to both score and p-value).",
"type": "number",
"minimum": 0.0,
"maximum": 1.0
Expand Down Expand Up @@ -566,7 +568,7 @@
]
},
"p_val_cutoff": {
"title": "(Optional): Minimum Bonferroni-corrected p-value to consider. A value of zero disables the cutoff filtering (automatically applies to both score and p-value).",
"title": "(Optional): Maximum Bonferroni-corrected p-value to consider. A value of zero disables the cutoff filtering (automatically applies to both score and p-value).",
"type": "number",
"minimum": 0.0,
"maximum": 1.0
Expand Down
19 changes: 14 additions & 5 deletions fermo_core/data_analysis/annotation_manager/class_annotation_manager.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -68,13 +68,15 @@ class AnnotationManager(BaseModel):
features: Repository
samples: Repository

def return_attrs(self: Self) -> tuple[Stats, Repository, Repository]:
def return_attrs(
self: Self,
) -> tuple[Stats, Repository, Repository, ParameterManager]:
"""Returns modified attributes from AnnotationManager to the calling function
Returns:
Tuple containing Stats, Feature Repository and Sample Repository objects.
"""
return self.stats, self.features, self.samples
return self.stats, self.features, self.samples, self.params

def run_analysis(self: Self):
"""Organizes calling of data analysis steps."""
Expand Down Expand Up @@ -179,6 +181,7 @@ def run_user_lib_mod_cosine_matching(self: Self):
mod_cosine_annotator.calculate_scores_mod_cosine()
mod_cosine_annotator.extract_userlib_scores()
self.features = mod_cosine_annotator.return_features()
self.params.SpectralLibMatchingCosineParameters.module_passed = True
except Exception as e:
logger.error(str(e))
logger.error(
Expand Down Expand Up @@ -216,6 +219,7 @@ def run_user_lib_ms2deepscore_matching(self: Self):
ms2deepscore_annotator.calculate_scores_ms2deepscore()
ms2deepscore_annotator.extract_userlib_scores()
self.features = ms2deepscore_annotator.return_features()
self.params.SpectralLibMatchingDeepscoreParameters.module_passed = True
except Exception as e:
logger.error(str(e))
logger.error(
Expand All @@ -242,6 +246,7 @@ def run_feature_adduct_annotation(self: Self):
)
adduct_annotator.run_analysis()
self.features = adduct_annotator.return_features()
self.params.AdductAnnotationParameters.module_passed = True
except Exception as e:
logger.error(str(e))
logger.error(
Expand All @@ -264,6 +269,7 @@ def run_neutral_loss_annotation(self: Self):
)
neutralloss_annotator.run_analysis()
self.features = neutralloss_annotator.return_features()
self.params.NeutralLossParameters.module_passed = True
except Exception as e:
logger.error(str(e))
logger.error(
Expand All @@ -287,6 +293,7 @@ def run_fragment_annotation(self: Self):
)
fragment_annotator.run_analysis()
self.features = fragment_annotator.return_features()
self.params.FragmentAnnParameters.module_passed = True
except Exception as e:
logger.error(str(e))
logger.error(
Expand Down Expand Up @@ -323,6 +330,7 @@ def run_ms2query_results_assignment(self: Self):
self.params.MS2QueryResultsParameters.filepath,
)
self.features = ms2query_annotator.return_features()

except Exception as e:
logger.error(str(e))
logger.error(
Expand All @@ -331,8 +339,7 @@ def run_ms2query_results_assignment(self: Self):
return

logger.info(
"'AnnotationManager': completed annotation from existing MS2Query "
"results"
"'AnnotationManager': completed annotation from existing MS2Query results."
)

def run_ms2query_annotation(self: Self):
Expand All @@ -359,6 +366,7 @@ def run_ms2query_annotation(self: Self):
)
ms2query_annotator.run_ms2query()
self.features = ms2query_annotator.return_features()
self.params.Ms2QueryAnnotationParameters.module_passed = True
except Exception as e:
logger.error(str(e))
logger.error(
Expand Down Expand Up @@ -401,7 +409,6 @@ def run_as_kcb_cosine_annotation(self: Self):
)
mibig_bgcs = {key for key, value in kcb_results.items()}
spec_library = UtilityMethodManager().create_mibig_spec_lib(mibig_bgcs)

kcb_annotator = ModCosAnnotator(
features=self.features,
active_features=self.stats.active_features,
Expand All @@ -417,6 +424,7 @@ def run_as_kcb_cosine_annotation(self: Self):
kcb_annotator.calculate_scores_mod_cosine()
kcb_annotator.extract_mibig_scores(kcb_results)
self.features = kcb_annotator.return_features()
self.params.AsKcbCosineMatchingParams.module_passed = True
except Exception as e:
logger.error(str(e))
logger.error(
Expand Down Expand Up @@ -478,6 +486,7 @@ def run_as_kcb_deepscore_annotation(self: Self):
kcb_annotator.calculate_scores_ms2deepscore()
kcb_annotator.extract_mibig_scores(kcb_results)
self.features = kcb_annotator.return_features()
self.params.AsKcbDeepscoreMatchingParams.module_passed = True
except Exception as e:
logger.error(str(e))
logger.error(
Expand Down
23 changes: 14 additions & 9 deletions fermo_core/data_analysis/class_analysis_manager.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -67,13 +67,15 @@ class AnalysisManager(BaseModel):
features: Repository
samples: Repository

def return_attributes(self: Self) -> tuple[Stats, Repository, Repository]:
def return_attributes(
self: Self,
) -> tuple[Stats, Repository, Repository, ParameterManager]:
"""Returns modified attributes to the calling function
Returns:
Tuple containing Stats, Feature Repository and Sample Repository objects.
"""
return self.stats, self.features, self.samples
return self.stats, self.features, self.samples, self.params

def analyze(self: Self):
"""Organizes calling of data analysis steps."""
Expand Down Expand Up @@ -108,6 +110,7 @@ def run_feature_filter(self: Self):
)
feature_filter.filter()
self.stats, self.features, self.samples = feature_filter.return_values()
self.params.FeatureFilteringParameters.module_passed = True
except Exception as e:
logger.warning(str(e))
return
Expand Down Expand Up @@ -138,6 +141,7 @@ def run_blank_assignment(self: Self):
)
blank_assigner.run_analysis()
self.stats, self.features = blank_assigner.return_attrs()
self.params.BlankAssignmentParameters.module_passed = True
except Exception as e:
logger.warning(str(e))
return
Expand Down Expand Up @@ -181,6 +185,7 @@ def run_group_factor_assignment(self: Self):
)
group_fact_ass.run_analysis()
self.features = group_fact_ass.return_features()
self.params.GroupFactAssignmentParameters.module_passed = True
except Exception as e:
logger.warning(str(e))
return
Expand Down Expand Up @@ -211,7 +216,7 @@ def run_phenotype_manager(self: Self):
samples=self.samples,
)
phenotype_manager.run_analysis()
self.stats, self.features = phenotype_manager.return_attrs()
self.stats, self.features, self.params = phenotype_manager.return_attrs()
except Exception as e:
logger.warning(str(e))
return
Expand Down Expand Up @@ -241,11 +246,9 @@ def run_sim_networks_manager(self: Self):
samples=self.samples,
)
sim_networks_manager.run_analysis()
(
self.stats,
self.features,
self.samples,
) = sim_networks_manager.return_attrs()
(self.stats, self.features, self.samples, self.params) = (
sim_networks_manager.return_attrs()
)
except Exception as e:
logger.warning(str(e))
return
Expand All @@ -261,7 +264,9 @@ def run_annotation_manager(self: Self):
samples=self.samples,
)
annotation_manager.run_analysis()
self.stats, self.features, self.samples = annotation_manager.return_attrs()
self.stats, self.features, self.samples, self.params = (
annotation_manager.return_attrs()
)
except Exception as e:
logger.warning(str(e))
return
Expand Down
Loading

0 comments on commit 00eab95

Please sign in to comment.