Skip to content

From colocalisation

List of features

gentropy.dataset.l2g_features.colocalisation.EQtlColocClppMaximumFeature dataclass

Bases: L2GFeature

Max CLPP for each (study, locus, gene) aggregating over all eQTLs.

Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
class EQtlColocClppMaximumFeature(L2GFeature):
    """Max CLPP for each (study, locus, gene) aggregating over all eQTLs."""

    feature_dependency_type = [Colocalisation, StudyIndex, StudyLocus]
    feature_name = "eQtlColocClppMaximum"

    @classmethod
    def compute(
        cls: type[EQtlColocClppMaximumFeature],
        study_loci_to_annotate: StudyLocus | L2GGoldStandard,
        feature_dependency: dict[str, Any],
    ) -> EQtlColocClppMaximumFeature:
        """Computes the feature.

        Args:
            study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
            feature_dependency (dict[str, Any]): Dictionary with the dependencies required. They are passed as keyword arguments.

        Returns:
            EQtlColocClppMaximumFeature: Feature dataset
        """
        colocalisation_method = "ECaviar"
        colocalisation_metric = "clpp"
        qtl_type = ["eqtl", "sceqtl"]

        return cls(
            _df=convert_from_wide_to_long(
                common_colocalisation_feature_logic(
                    study_loci_to_annotate,
                    colocalisation_method,
                    colocalisation_metric,
                    cls.feature_name,
                    qtl_type,
                    **feature_dependency,
                ),
                id_vars=("studyLocusId", "geneId"),
                var_name="featureName",
                value_name="featureValue",
            ),
            _schema=cls.get_schema(),
        )

compute(study_loci_to_annotate: StudyLocus | L2GGoldStandard, feature_dependency: dict[str, Any]) -> EQtlColocClppMaximumFeature classmethod

Computes the feature.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
feature_dependency dict[str, Any]

Dictionary with the dependencies required. They are passed as keyword arguments.

 required

Returns:

Name Type Description
EQtlColocClppMaximumFeature EQtlColocClppMaximumFeature

Feature dataset
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
@classmethod
def compute(
    cls: type[EQtlColocClppMaximumFeature],
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    feature_dependency: dict[str, Any],
) -> EQtlColocClppMaximumFeature:
    """Computes the feature.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        feature_dependency (dict[str, Any]): Dictionary with the dependencies required. They are passed as keyword arguments.

    Returns:
        EQtlColocClppMaximumFeature: Feature dataset
    """
    colocalisation_method = "ECaviar"
    colocalisation_metric = "clpp"
    qtl_type = ["eqtl", "sceqtl"]

    return cls(
        _df=convert_from_wide_to_long(
            common_colocalisation_feature_logic(
                study_loci_to_annotate,
                colocalisation_method,
                colocalisation_metric,
                cls.feature_name,
                qtl_type,
                **feature_dependency,
            ),
            id_vars=("studyLocusId", "geneId"),
            var_name="featureName",
            value_name="featureValue",
        ),
        _schema=cls.get_schema(),
    )

gentropy.dataset.l2g_features.colocalisation.PQtlColocClppMaximumFeature dataclass

Bases: L2GFeature

Max CLPP for each (study, locus, gene) aggregating over all pQTLs.

Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
class PQtlColocClppMaximumFeature(L2GFeature):
    """Max CLPP for each (study, locus, gene) aggregating over all pQTLs."""

    feature_dependency_type = [Colocalisation, StudyIndex, StudyLocus]
    feature_name = "pQtlColocClppMaximum"

    @classmethod
    def compute(
        cls: type[PQtlColocClppMaximumFeature],
        study_loci_to_annotate: StudyLocus | L2GGoldStandard,
        feature_dependency: dict[str, Any],
    ) -> PQtlColocClppMaximumFeature:
        """Computes the feature.

        Args:
            study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
            feature_dependency (dict[str, Any]): Dataset with the colocalisation results

        Returns:
            PQtlColocClppMaximumFeature: Feature dataset
        """
        colocalisation_method = "ECaviar"
        colocalisation_metric = "clpp"
        qtl_type = "pqtl"
        return cls(
            _df=convert_from_wide_to_long(
                common_colocalisation_feature_logic(
                    study_loci_to_annotate,
                    colocalisation_method,
                    colocalisation_metric,
                    cls.feature_name,
                    qtl_type,
                    **feature_dependency,
                ),
                id_vars=("studyLocusId", "geneId"),
                var_name="featureName",
                value_name="featureValue",
            ),
            _schema=cls.get_schema(),
        )

compute(study_loci_to_annotate: StudyLocus | L2GGoldStandard, feature_dependency: dict[str, Any]) -> PQtlColocClppMaximumFeature classmethod

Computes the feature.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
feature_dependency dict[str, Any]

Dataset with the colocalisation results

 required

Returns:

Name Type Description
PQtlColocClppMaximumFeature PQtlColocClppMaximumFeature

Feature dataset
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
@classmethod
def compute(
    cls: type[PQtlColocClppMaximumFeature],
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    feature_dependency: dict[str, Any],
) -> PQtlColocClppMaximumFeature:
    """Computes the feature.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        feature_dependency (dict[str, Any]): Dataset with the colocalisation results

    Returns:
        PQtlColocClppMaximumFeature: Feature dataset
    """
    colocalisation_method = "ECaviar"
    colocalisation_metric = "clpp"
    qtl_type = "pqtl"
    return cls(
        _df=convert_from_wide_to_long(
            common_colocalisation_feature_logic(
                study_loci_to_annotate,
                colocalisation_method,
                colocalisation_metric,
                cls.feature_name,
                qtl_type,
                **feature_dependency,
            ),
            id_vars=("studyLocusId", "geneId"),
            var_name="featureName",
            value_name="featureValue",
        ),
        _schema=cls.get_schema(),
    )

gentropy.dataset.l2g_features.colocalisation.SQtlColocClppMaximumFeature dataclass

Bases: L2GFeature

Max CLPP for each (study, locus, gene) aggregating over all sQTLs.

Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
class SQtlColocClppMaximumFeature(L2GFeature):
    """Max CLPP for each (study, locus, gene) aggregating over all sQTLs."""

    feature_dependency_type = [Colocalisation, StudyIndex, StudyLocus]
    feature_name = "sQtlColocClppMaximum"

    @classmethod
    def compute(
        cls: type[SQtlColocClppMaximumFeature],
        study_loci_to_annotate: StudyLocus | L2GGoldStandard,
        feature_dependency: dict[str, Any],
    ) -> SQtlColocClppMaximumFeature:
        """Computes the feature.

        Args:
            study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
            feature_dependency (dict[str, Any]): Dataset with the colocalisation results

        Returns:
            SQtlColocClppMaximumFeature: Feature dataset
        """
        colocalisation_method = "ECaviar"
        colocalisation_metric = "clpp"
        qtl_types = ["sqtl", "tuqtl", "scsqtl", "sctuqtl"]
        return cls(
            _df=convert_from_wide_to_long(
                common_colocalisation_feature_logic(
                    study_loci_to_annotate,
                    colocalisation_method,
                    colocalisation_metric,
                    cls.feature_name,
                    qtl_types,
                    **feature_dependency,
                ),
                id_vars=("studyLocusId", "geneId"),
                var_name="featureName",
                value_name="featureValue",
            ),
            _schema=cls.get_schema(),
        )

compute(study_loci_to_annotate: StudyLocus | L2GGoldStandard, feature_dependency: dict[str, Any]) -> SQtlColocClppMaximumFeature classmethod

Computes the feature.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
feature_dependency dict[str, Any]

Dataset with the colocalisation results

 required

Returns:

Name Type Description
SQtlColocClppMaximumFeature SQtlColocClppMaximumFeature

Feature dataset
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
@classmethod
def compute(
    cls: type[SQtlColocClppMaximumFeature],
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    feature_dependency: dict[str, Any],
) -> SQtlColocClppMaximumFeature:
    """Computes the feature.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        feature_dependency (dict[str, Any]): Dataset with the colocalisation results

    Returns:
        SQtlColocClppMaximumFeature: Feature dataset
    """
    colocalisation_method = "ECaviar"
    colocalisation_metric = "clpp"
    qtl_types = ["sqtl", "tuqtl", "scsqtl", "sctuqtl"]
    return cls(
        _df=convert_from_wide_to_long(
            common_colocalisation_feature_logic(
                study_loci_to_annotate,
                colocalisation_method,
                colocalisation_metric,
                cls.feature_name,
                qtl_types,
                **feature_dependency,
            ),
            id_vars=("studyLocusId", "geneId"),
            var_name="featureName",
            value_name="featureValue",
        ),
        _schema=cls.get_schema(),
    )

gentropy.dataset.l2g_features.colocalisation.EQtlColocH4MaximumFeature dataclass

Bases: L2GFeature

Max H4 for each (study, locus, gene) aggregating over all eQTLs.

Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
class EQtlColocH4MaximumFeature(L2GFeature):
    """Max H4 for each (study, locus, gene) aggregating over all eQTLs."""

    feature_dependency_type = [Colocalisation, StudyIndex, StudyLocus]
    feature_name = "eQtlColocH4Maximum"

    @classmethod
    def compute(
        cls: type[EQtlColocH4MaximumFeature],
        study_loci_to_annotate: StudyLocus | L2GGoldStandard,
        feature_dependency: dict[str, Any],
    ) -> EQtlColocH4MaximumFeature:
        """Computes the feature.

        Args:
            study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
            feature_dependency (dict[str, Any]): Dataset with the colocalisation results

        Returns:
            EQtlColocH4MaximumFeature: Feature dataset
        """
        colocalisation_method = "Coloc"
        colocalisation_metric = "h4"
        qtl_type = ["eqtl", "sceqtl"]
        return cls(
            _df=convert_from_wide_to_long(
                common_colocalisation_feature_logic(
                    study_loci_to_annotate,
                    colocalisation_method,
                    colocalisation_metric,
                    cls.feature_name,
                    qtl_type,
                    **feature_dependency,
                ),
                id_vars=("studyLocusId", "geneId"),
                var_name="featureName",
                value_name="featureValue",
            ),
            _schema=cls.get_schema(),
        )

compute(study_loci_to_annotate: StudyLocus | L2GGoldStandard, feature_dependency: dict[str, Any]) -> EQtlColocH4MaximumFeature classmethod

Computes the feature.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
feature_dependency dict[str, Any]

Dataset with the colocalisation results

 required

Returns:

Name Type Description
EQtlColocH4MaximumFeature EQtlColocH4MaximumFeature

Feature dataset
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
@classmethod
def compute(
    cls: type[EQtlColocH4MaximumFeature],
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    feature_dependency: dict[str, Any],
) -> EQtlColocH4MaximumFeature:
    """Computes the feature.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        feature_dependency (dict[str, Any]): Dataset with the colocalisation results

    Returns:
        EQtlColocH4MaximumFeature: Feature dataset
    """
    colocalisation_method = "Coloc"
    colocalisation_metric = "h4"
    qtl_type = ["eqtl", "sceqtl"]
    return cls(
        _df=convert_from_wide_to_long(
            common_colocalisation_feature_logic(
                study_loci_to_annotate,
                colocalisation_method,
                colocalisation_metric,
                cls.feature_name,
                qtl_type,
                **feature_dependency,
            ),
            id_vars=("studyLocusId", "geneId"),
            var_name="featureName",
            value_name="featureValue",
        ),
        _schema=cls.get_schema(),
    )

gentropy.dataset.l2g_features.colocalisation.PQtlColocH4MaximumFeature dataclass

Bases: L2GFeature

Max H4 for each (study, locus, gene) aggregating over all pQTLs.

Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
class PQtlColocH4MaximumFeature(L2GFeature):
    """Max H4 for each (study, locus, gene) aggregating over all pQTLs."""

    feature_dependency_type = [Colocalisation, StudyIndex, StudyLocus]
    feature_name = "pQtlColocH4Maximum"

    @classmethod
    def compute(
        cls: type[PQtlColocH4MaximumFeature],
        study_loci_to_annotate: StudyLocus | L2GGoldStandard,
        feature_dependency: dict[str, Any],
    ) -> PQtlColocH4MaximumFeature:
        """Computes the feature.

        Args:
            study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
            feature_dependency (dict[str, Any]): Dataset with the colocalisation results

        Returns:
            PQtlColocH4MaximumFeature: Feature dataset
        """
        colocalisation_method = "Coloc"
        colocalisation_metric = "h4"
        qtl_type = "pqtl"
        return cls(
            _df=convert_from_wide_to_long(
                common_colocalisation_feature_logic(
                    study_loci_to_annotate,
                    colocalisation_method,
                    colocalisation_metric,
                    cls.feature_name,
                    qtl_type,
                    **feature_dependency,
                ),
                id_vars=("studyLocusId", "geneId"),
                var_name="featureName",
                value_name="featureValue",
            ),
            _schema=cls.get_schema(),
        )

compute(study_loci_to_annotate: StudyLocus | L2GGoldStandard, feature_dependency: dict[str, Any]) -> PQtlColocH4MaximumFeature classmethod

Computes the feature.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
feature_dependency dict[str, Any]

Dataset with the colocalisation results

 required

Returns:

Name Type Description
PQtlColocH4MaximumFeature PQtlColocH4MaximumFeature

Feature dataset
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
@classmethod
def compute(
    cls: type[PQtlColocH4MaximumFeature],
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    feature_dependency: dict[str, Any],
) -> PQtlColocH4MaximumFeature:
    """Computes the feature.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        feature_dependency (dict[str, Any]): Dataset with the colocalisation results

    Returns:
        PQtlColocH4MaximumFeature: Feature dataset
    """
    colocalisation_method = "Coloc"
    colocalisation_metric = "h4"
    qtl_type = "pqtl"
    return cls(
        _df=convert_from_wide_to_long(
            common_colocalisation_feature_logic(
                study_loci_to_annotate,
                colocalisation_method,
                colocalisation_metric,
                cls.feature_name,
                qtl_type,
                **feature_dependency,
            ),
            id_vars=("studyLocusId", "geneId"),
            var_name="featureName",
            value_name="featureValue",
        ),
        _schema=cls.get_schema(),
    )

gentropy.dataset.l2g_features.colocalisation.SQtlColocH4MaximumFeature dataclass

Bases: L2GFeature

Max H4 for each (study, locus, gene) aggregating over all sQTLs.

Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
class SQtlColocH4MaximumFeature(L2GFeature):
    """Max H4 for each (study, locus, gene) aggregating over all sQTLs."""

    feature_dependency_type = [Colocalisation, StudyIndex, StudyLocus]
    feature_name = "sQtlColocH4Maximum"

    @classmethod
    def compute(
        cls: type[SQtlColocH4MaximumFeature],
        study_loci_to_annotate: StudyLocus | L2GGoldStandard,
        feature_dependency: dict[str, Any],
    ) -> SQtlColocH4MaximumFeature:
        """Computes the feature.

        Args:
            study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
            feature_dependency (dict[str, Any]): Dataset with the colocalisation results

        Returns:
            SQtlColocH4MaximumFeature: Feature dataset
        """
        colocalisation_method = "Coloc"
        colocalisation_metric = "h4"
        qtl_types = ["sqtl", "tuqtl", "scsqtl", "sctuqtl"]
        return cls(
            _df=convert_from_wide_to_long(
                common_colocalisation_feature_logic(
                    study_loci_to_annotate,
                    colocalisation_method,
                    colocalisation_metric,
                    cls.feature_name,
                    qtl_types,
                    **feature_dependency,
                ),
                id_vars=("studyLocusId", "geneId"),
                var_name="featureName",
                value_name="featureValue",
            ),
            _schema=cls.get_schema(),
        )

compute(study_loci_to_annotate: StudyLocus | L2GGoldStandard, feature_dependency: dict[str, Any]) -> SQtlColocH4MaximumFeature classmethod

Computes the feature.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
feature_dependency dict[str, Any]

Dataset with the colocalisation results

 required

Returns:

Name Type Description
SQtlColocH4MaximumFeature SQtlColocH4MaximumFeature

Feature dataset
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
@classmethod
def compute(
    cls: type[SQtlColocH4MaximumFeature],
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    feature_dependency: dict[str, Any],
) -> SQtlColocH4MaximumFeature:
    """Computes the feature.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        feature_dependency (dict[str, Any]): Dataset with the colocalisation results

    Returns:
        SQtlColocH4MaximumFeature: Feature dataset
    """
    colocalisation_method = "Coloc"
    colocalisation_metric = "h4"
    qtl_types = ["sqtl", "tuqtl", "scsqtl", "sctuqtl"]
    return cls(
        _df=convert_from_wide_to_long(
            common_colocalisation_feature_logic(
                study_loci_to_annotate,
                colocalisation_method,
                colocalisation_metric,
                cls.feature_name,
                qtl_types,
                **feature_dependency,
            ),
            id_vars=("studyLocusId", "geneId"),
            var_name="featureName",
            value_name="featureValue",
        ),
        _schema=cls.get_schema(),
    )

gentropy.dataset.l2g_features.colocalisation.EQtlColocClppMaximumNeighbourhoodFeature dataclass

Bases: L2GFeature

Max CLPP for each (study, locus) aggregating over all eQTLs.

Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
class EQtlColocClppMaximumNeighbourhoodFeature(L2GFeature):
    """Max CLPP for each (study, locus) aggregating over all eQTLs."""

    feature_dependency_type = [
        Colocalisation,
        StudyIndex,
        GeneIndex,
        StudyLocus,
        VariantIndex,
    ]
    feature_name = "eQtlColocClppMaximumNeighbourhood"

    @classmethod
    def compute(
        cls: type[EQtlColocClppMaximumNeighbourhoodFeature],
        study_loci_to_annotate: StudyLocus | L2GGoldStandard,
        feature_dependency: dict[str, Any],
    ) -> EQtlColocClppMaximumNeighbourhoodFeature:
        """Computes the feature.

        Args:
            study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
            feature_dependency (dict[str, Any]): Dictionary with the dependencies required. They are passed as keyword arguments.

        Returns:
            EQtlColocClppMaximumNeighbourhoodFeature: Feature dataset
        """
        colocalisation_method = "ECaviar"
        colocalisation_metric = "clpp"
        qtl_type = ["eqtl", "sceqtl"]

        return cls(
            _df=convert_from_wide_to_long(
                common_neighbourhood_colocalisation_feature_logic(
                    study_loci_to_annotate,
                    colocalisation_method,
                    colocalisation_metric,
                    cls.feature_name,
                    qtl_type,
                    **feature_dependency,
                ),
                id_vars=("studyLocusId", "geneId"),
                var_name="featureName",
                value_name="featureValue",
            ),
            _schema=cls.get_schema(),
        )

compute(study_loci_to_annotate: StudyLocus | L2GGoldStandard, feature_dependency: dict[str, Any]) -> EQtlColocClppMaximumNeighbourhoodFeature classmethod

Computes the feature.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
feature_dependency dict[str, Any]

Dictionary with the dependencies required. They are passed as keyword arguments.

 required

Returns:

Name Type Description
EQtlColocClppMaximumNeighbourhoodFeature EQtlColocClppMaximumNeighbourhoodFeature

Feature dataset
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
@classmethod
def compute(
    cls: type[EQtlColocClppMaximumNeighbourhoodFeature],
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    feature_dependency: dict[str, Any],
) -> EQtlColocClppMaximumNeighbourhoodFeature:
    """Computes the feature.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        feature_dependency (dict[str, Any]): Dictionary with the dependencies required. They are passed as keyword arguments.

    Returns:
        EQtlColocClppMaximumNeighbourhoodFeature: Feature dataset
    """
    colocalisation_method = "ECaviar"
    colocalisation_metric = "clpp"
    qtl_type = ["eqtl", "sceqtl"]

    return cls(
        _df=convert_from_wide_to_long(
            common_neighbourhood_colocalisation_feature_logic(
                study_loci_to_annotate,
                colocalisation_method,
                colocalisation_metric,
                cls.feature_name,
                qtl_type,
                **feature_dependency,
            ),
            id_vars=("studyLocusId", "geneId"),
            var_name="featureName",
            value_name="featureValue",
        ),
        _schema=cls.get_schema(),
    )

gentropy.dataset.l2g_features.colocalisation.PQtlColocClppMaximumNeighbourhoodFeature dataclass

Bases: L2GFeature

Max CLPP for each (study, locus, gene) aggregating over all pQTLs.

Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
class PQtlColocClppMaximumNeighbourhoodFeature(L2GFeature):
    """Max CLPP for each (study, locus, gene) aggregating over all pQTLs."""

    feature_dependency_type = [
        Colocalisation,
        StudyIndex,
        GeneIndex,
        StudyLocus,
        VariantIndex,
    ]
    feature_name = "pQtlColocClppMaximumNeighbourhood"

    @classmethod
    def compute(
        cls: type[PQtlColocClppMaximumNeighbourhoodFeature],
        study_loci_to_annotate: StudyLocus | L2GGoldStandard,
        feature_dependency: dict[str, Any],
    ) -> PQtlColocClppMaximumNeighbourhoodFeature:
        """Computes the feature.

        Args:
            study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
            feature_dependency (dict[str, Any]): Dataset with the colocalisation results

        Returns:
            PQtlColocClppMaximumNeighbourhoodFeature: Feature dataset
        """
        colocalisation_method = "ECaviar"
        colocalisation_metric = "clpp"
        qtl_type = "pqtl"
        return cls(
            _df=convert_from_wide_to_long(
                common_neighbourhood_colocalisation_feature_logic(
                    study_loci_to_annotate,
                    colocalisation_method,
                    colocalisation_metric,
                    cls.feature_name,
                    qtl_type,
                    **feature_dependency,
                ),
                id_vars=("studyLocusId", "geneId"),
                var_name="featureName",
                value_name="featureValue",
            ),
            _schema=cls.get_schema(),
        )

compute(study_loci_to_annotate: StudyLocus | L2GGoldStandard, feature_dependency: dict[str, Any]) -> PQtlColocClppMaximumNeighbourhoodFeature classmethod

Computes the feature.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
feature_dependency dict[str, Any]

Dataset with the colocalisation results

 required

Returns:

Name Type Description
PQtlColocClppMaximumNeighbourhoodFeature PQtlColocClppMaximumNeighbourhoodFeature

Feature dataset
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
@classmethod
def compute(
    cls: type[PQtlColocClppMaximumNeighbourhoodFeature],
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    feature_dependency: dict[str, Any],
) -> PQtlColocClppMaximumNeighbourhoodFeature:
    """Computes the feature.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        feature_dependency (dict[str, Any]): Dataset with the colocalisation results

    Returns:
        PQtlColocClppMaximumNeighbourhoodFeature: Feature dataset
    """
    colocalisation_method = "ECaviar"
    colocalisation_metric = "clpp"
    qtl_type = "pqtl"
    return cls(
        _df=convert_from_wide_to_long(
            common_neighbourhood_colocalisation_feature_logic(
                study_loci_to_annotate,
                colocalisation_method,
                colocalisation_metric,
                cls.feature_name,
                qtl_type,
                **feature_dependency,
            ),
            id_vars=("studyLocusId", "geneId"),
            var_name="featureName",
            value_name="featureValue",
        ),
        _schema=cls.get_schema(),
    )

gentropy.dataset.l2g_features.colocalisation.SQtlColocClppMaximumNeighbourhoodFeature dataclass

Bases: L2GFeature

Max CLPP for each (study, locus, gene) aggregating over all sQTLs.

Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
class SQtlColocClppMaximumNeighbourhoodFeature(L2GFeature):
    """Max CLPP for each (study, locus, gene) aggregating over all sQTLs."""

    feature_dependency_type = [
        Colocalisation,
        StudyIndex,
        GeneIndex,
        StudyLocus,
        VariantIndex,
    ]
    feature_name = "sQtlColocClppMaximumNeighbourhood"

    @classmethod
    def compute(
        cls: type[SQtlColocClppMaximumNeighbourhoodFeature],
        study_loci_to_annotate: StudyLocus | L2GGoldStandard,
        feature_dependency: dict[str, Any],
    ) -> SQtlColocClppMaximumNeighbourhoodFeature:
        """Computes the feature.

        Args:
            study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
            feature_dependency (dict[str, Any]): Dataset with the colocalisation results

        Returns:
            SQtlColocClppMaximumNeighbourhoodFeature: Feature dataset
        """
        colocalisation_method = "ECaviar"
        colocalisation_metric = "clpp"
        qtl_types = ["sqtl", "tuqtl", "scsqtl", "sctuqtl"]
        return cls(
            _df=convert_from_wide_to_long(
                common_neighbourhood_colocalisation_feature_logic(
                    study_loci_to_annotate,
                    colocalisation_method,
                    colocalisation_metric,
                    cls.feature_name,
                    qtl_types,
                    **feature_dependency,
                ),
                id_vars=("studyLocusId", "geneId"),
                var_name="featureName",
                value_name="featureValue",
            ),
            _schema=cls.get_schema(),
        )

compute(study_loci_to_annotate: StudyLocus | L2GGoldStandard, feature_dependency: dict[str, Any]) -> SQtlColocClppMaximumNeighbourhoodFeature classmethod

Computes the feature.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
feature_dependency dict[str, Any]

Dataset with the colocalisation results

 required

Returns:

Name Type Description
SQtlColocClppMaximumNeighbourhoodFeature SQtlColocClppMaximumNeighbourhoodFeature

Feature dataset
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
@classmethod
def compute(
    cls: type[SQtlColocClppMaximumNeighbourhoodFeature],
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    feature_dependency: dict[str, Any],
) -> SQtlColocClppMaximumNeighbourhoodFeature:
    """Computes the feature.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        feature_dependency (dict[str, Any]): Dataset with the colocalisation results

    Returns:
        SQtlColocClppMaximumNeighbourhoodFeature: Feature dataset
    """
    colocalisation_method = "ECaviar"
    colocalisation_metric = "clpp"
    qtl_types = ["sqtl", "tuqtl", "scsqtl", "sctuqtl"]
    return cls(
        _df=convert_from_wide_to_long(
            common_neighbourhood_colocalisation_feature_logic(
                study_loci_to_annotate,
                colocalisation_method,
                colocalisation_metric,
                cls.feature_name,
                qtl_types,
                **feature_dependency,
            ),
            id_vars=("studyLocusId", "geneId"),
            var_name="featureName",
            value_name="featureValue",
        ),
        _schema=cls.get_schema(),
    )

gentropy.dataset.l2g_features.colocalisation.EQtlColocH4MaximumNeighbourhoodFeature dataclass

Bases: L2GFeature

Max H4 for each (study, locus) aggregating over all eQTLs.

Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
class EQtlColocH4MaximumNeighbourhoodFeature(L2GFeature):
    """Max H4 for each (study, locus) aggregating over all eQTLs."""

    feature_dependency_type = [
        Colocalisation,
        StudyIndex,
        GeneIndex,
        StudyLocus,
        VariantIndex,
    ]
    feature_name = "eQtlColocH4MaximumNeighbourhood"

    @classmethod
    def compute(
        cls: type[EQtlColocH4MaximumNeighbourhoodFeature],
        study_loci_to_annotate: StudyLocus | L2GGoldStandard,
        feature_dependency: dict[str, Any],
    ) -> EQtlColocH4MaximumNeighbourhoodFeature:
        """Computes the feature.

        Args:
            study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
            feature_dependency (dict[str, Any]): Dataset with the colocalisation results

        Returns:
            EQtlColocH4MaximumNeighbourhoodFeature: Feature dataset
        """
        colocalisation_method = "Coloc"
        colocalisation_metric = "h4"
        qtl_type = ["eqtl", "sceqtl"]
        return cls(
            _df=convert_from_wide_to_long(
                common_neighbourhood_colocalisation_feature_logic(
                    study_loci_to_annotate,
                    colocalisation_method,
                    colocalisation_metric,
                    cls.feature_name,
                    qtl_type,
                    **feature_dependency,
                ),
                id_vars=("studyLocusId", "geneId"),
                var_name="featureName",
                value_name="featureValue",
            ),
            _schema=cls.get_schema(),
        )

compute(study_loci_to_annotate: StudyLocus | L2GGoldStandard, feature_dependency: dict[str, Any]) -> EQtlColocH4MaximumNeighbourhoodFeature classmethod

Computes the feature.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
feature_dependency dict[str, Any]

Dataset with the colocalisation results

 required

Returns:

Name Type Description
EQtlColocH4MaximumNeighbourhoodFeature EQtlColocH4MaximumNeighbourhoodFeature

Feature dataset
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
@classmethod
def compute(
    cls: type[EQtlColocH4MaximumNeighbourhoodFeature],
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    feature_dependency: dict[str, Any],
) -> EQtlColocH4MaximumNeighbourhoodFeature:
    """Computes the feature.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        feature_dependency (dict[str, Any]): Dataset with the colocalisation results

    Returns:
        EQtlColocH4MaximumNeighbourhoodFeature: Feature dataset
    """
    colocalisation_method = "Coloc"
    colocalisation_metric = "h4"
    qtl_type = ["eqtl", "sceqtl"]
    return cls(
        _df=convert_from_wide_to_long(
            common_neighbourhood_colocalisation_feature_logic(
                study_loci_to_annotate,
                colocalisation_method,
                colocalisation_metric,
                cls.feature_name,
                qtl_type,
                **feature_dependency,
            ),
            id_vars=("studyLocusId", "geneId"),
            var_name="featureName",
            value_name="featureValue",
        ),
        _schema=cls.get_schema(),
    )

gentropy.dataset.l2g_features.colocalisation.PQtlColocH4MaximumNeighbourhoodFeature dataclass

Bases: L2GFeature

Max H4 for each (study, locus) aggregating over all pQTLs.

Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
class PQtlColocH4MaximumNeighbourhoodFeature(L2GFeature):
    """Max H4 for each (study, locus) aggregating over all pQTLs."""

    feature_dependency_type = [
        Colocalisation,
        StudyIndex,
        GeneIndex,
        StudyLocus,
        VariantIndex,
    ]
    feature_name = "pQtlColocH4MaximumNeighbourhood"

    @classmethod
    def compute(
        cls: type[PQtlColocH4MaximumNeighbourhoodFeature],
        study_loci_to_annotate: StudyLocus | L2GGoldStandard,
        feature_dependency: dict[str, Any],
    ) -> PQtlColocH4MaximumNeighbourhoodFeature:
        """Computes the feature.

        Args:
            study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
            feature_dependency (dict[str, Any]): Dataset with the colocalisation results

        Returns:
            PQtlColocH4MaximumNeighbourhoodFeature: Feature dataset
        """
        colocalisation_method = "Coloc"
        colocalisation_metric = "h4"
        qtl_type = "pqtl"
        return cls(
            _df=convert_from_wide_to_long(
                common_neighbourhood_colocalisation_feature_logic(
                    study_loci_to_annotate,
                    colocalisation_method,
                    colocalisation_metric,
                    cls.feature_name,
                    qtl_type,
                    **feature_dependency,
                ),
                id_vars=("studyLocusId", "geneId"),
                var_name="featureName",
                value_name="featureValue",
            ),
            _schema=cls.get_schema(),
        )

compute(study_loci_to_annotate: StudyLocus | L2GGoldStandard, feature_dependency: dict[str, Any]) -> PQtlColocH4MaximumNeighbourhoodFeature classmethod

Computes the feature.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
feature_dependency dict[str, Any]

Dataset with the colocalisation results

 required

Returns:

Name Type Description
PQtlColocH4MaximumNeighbourhoodFeature PQtlColocH4MaximumNeighbourhoodFeature

Feature dataset
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
@classmethod
def compute(
    cls: type[PQtlColocH4MaximumNeighbourhoodFeature],
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    feature_dependency: dict[str, Any],
) -> PQtlColocH4MaximumNeighbourhoodFeature:
    """Computes the feature.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        feature_dependency (dict[str, Any]): Dataset with the colocalisation results

    Returns:
        PQtlColocH4MaximumNeighbourhoodFeature: Feature dataset
    """
    colocalisation_method = "Coloc"
    colocalisation_metric = "h4"
    qtl_type = "pqtl"
    return cls(
        _df=convert_from_wide_to_long(
            common_neighbourhood_colocalisation_feature_logic(
                study_loci_to_annotate,
                colocalisation_method,
                colocalisation_metric,
                cls.feature_name,
                qtl_type,
                **feature_dependency,
            ),
            id_vars=("studyLocusId", "geneId"),
            var_name="featureName",
            value_name="featureValue",
        ),
        _schema=cls.get_schema(),
    )

gentropy.dataset.l2g_features.colocalisation.SQtlColocH4MaximumNeighbourhoodFeature dataclass

Bases: L2GFeature

Max H4 for each (study, locus) aggregating over all sQTLs.

Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
class SQtlColocH4MaximumNeighbourhoodFeature(L2GFeature):
    """Max H4 for each (study, locus) aggregating over all sQTLs."""

    feature_dependency_type = [
        Colocalisation,
        StudyIndex,
        GeneIndex,
        StudyLocus,
        VariantIndex,
    ]
    feature_name = "sQtlColocH4MaximumNeighbourhood"

    @classmethod
    def compute(
        cls: type[SQtlColocH4MaximumNeighbourhoodFeature],
        study_loci_to_annotate: StudyLocus | L2GGoldStandard,
        feature_dependency: dict[str, Any],
    ) -> SQtlColocH4MaximumNeighbourhoodFeature:
        """Computes the feature.

        Args:
            study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
            feature_dependency (dict[str, Any]): Dataset with the colocalisation results

        Returns:
            SQtlColocH4MaximumNeighbourhoodFeature: Feature dataset
        """
        colocalisation_method = "Coloc"
        colocalisation_metric = "h4"
        qtl_types = ["sqtl", "tuqtl", "scsqtl", "sctuqtl"]
        return cls(
            _df=convert_from_wide_to_long(
                common_neighbourhood_colocalisation_feature_logic(
                    study_loci_to_annotate,
                    colocalisation_method,
                    colocalisation_metric,
                    cls.feature_name,
                    qtl_types,
                    **feature_dependency,
                ),
                id_vars=("studyLocusId", "geneId"),
                var_name="featureName",
                value_name="featureValue",
            ),
            _schema=cls.get_schema(),
        )

compute(study_loci_to_annotate: StudyLocus | L2GGoldStandard, feature_dependency: dict[str, Any]) -> SQtlColocH4MaximumNeighbourhoodFeature classmethod

Computes the feature.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
feature_dependency dict[str, Any]

Dataset with the colocalisation results

 required

Returns:

Name Type Description
SQtlColocH4MaximumNeighbourhoodFeature SQtlColocH4MaximumNeighbourhoodFeature

Feature dataset
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
@classmethod
def compute(
    cls: type[SQtlColocH4MaximumNeighbourhoodFeature],
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    feature_dependency: dict[str, Any],
) -> SQtlColocH4MaximumNeighbourhoodFeature:
    """Computes the feature.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        feature_dependency (dict[str, Any]): Dataset with the colocalisation results

    Returns:
        SQtlColocH4MaximumNeighbourhoodFeature: Feature dataset
    """
    colocalisation_method = "Coloc"
    colocalisation_metric = "h4"
    qtl_types = ["sqtl", "tuqtl", "scsqtl", "sctuqtl"]
    return cls(
        _df=convert_from_wide_to_long(
            common_neighbourhood_colocalisation_feature_logic(
                study_loci_to_annotate,
                colocalisation_method,
                colocalisation_metric,
                cls.feature_name,
                qtl_types,
                **feature_dependency,
            ),
            id_vars=("studyLocusId", "geneId"),
            var_name="featureName",
            value_name="featureValue",
        ),
        _schema=cls.get_schema(),
    )

Common logic

gentropy.dataset.l2g_features.colocalisation.common_colocalisation_feature_logic(study_loci_to_annotate: StudyLocus | L2GGoldStandard, colocalisation_method: str, colocalisation_metric: str, feature_name: str, qtl_types: list[str] | str, *, colocalisation: Colocalisation, study_index: StudyIndex, study_locus: StudyLocus) -> DataFrame

Wrapper to call the logic that creates a type of colocalisation features.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
colocalisation_method str

The colocalisation method to filter the data by

 required
colocalisation_metric str

The colocalisation metric to use

 required
feature_name str

The name of the feature to create

 required
qtl_types list[str] | str

The types of QTL to filter the data by

 required
colocalisation Colocalisation

Dataset with the colocalisation results

 required
study_index StudyIndex

Study index to fetch study type and gene

 required
study_locus StudyLocus

Study locus to traverse between colocalisation and study index

 required

Returns:

Name Type Description
DataFrame DataFrame

Feature annotation in long format with the columns: studyLocusId, geneId, featureName, featureValue
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
def common_colocalisation_feature_logic(
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    colocalisation_method: str,
    colocalisation_metric: str,
    feature_name: str,
    qtl_types: list[str] | str,
    *,
    colocalisation: Colocalisation,
    study_index: StudyIndex,
    study_locus: StudyLocus,
) -> DataFrame:
    """Wrapper to call the logic that creates a type of colocalisation features.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        colocalisation_method (str): The colocalisation method to filter the data by
        colocalisation_metric (str): The colocalisation metric to use
        feature_name (str): The name of the feature to create
        qtl_types (list[str] | str): The types of QTL to filter the data by
        colocalisation (Colocalisation): Dataset with the colocalisation results
        study_index (StudyIndex): Study index to fetch study type and gene
        study_locus (StudyLocus): Study locus to traverse between colocalisation and study index

    Returns:
        DataFrame: Feature annotation in long format with the columns: studyLocusId, geneId, featureName, featureValue
    """
    joining_cols = (
        ["studyLocusId", "geneId"]
        if isinstance(study_loci_to_annotate, L2GGoldStandard)
        else ["studyLocusId"]
    )
    return (
        study_loci_to_annotate.df.join(
            colocalisation.extract_maximum_coloc_probability_per_region_and_gene(
                study_locus,
                study_index,
                filter_by_colocalisation_method=colocalisation_method,
                filter_by_qtls=qtl_types,
            ),
            on=joining_cols,
        )
        .selectExpr(
            "studyLocusId",
            "geneId",
            f"{colocalisation_metric} as {feature_name}",
        )
        .distinct()
    )

gentropy.dataset.l2g_features.colocalisation.extend_missing_colocalisation_to_neighbourhood_genes(feature_name: str, local_features: DataFrame, variant_index: VariantIndex, gene_index: GeneIndex, study_locus: StudyLocus) -> DataFrame

This function creates an artificial dataset of features that represents the missing colocalisation to the neighbourhood genes.

Parameters:

Name Type Description Default
feature_name str

The name of the feature to extend

 required
local_features DataFrame

The dataframe of features to extend

 required
variant_index VariantIndex

Variant index containing all variant/gene relationships

 required
gene_index GeneIndex

Gene index to fetch the gene information

 required
study_locus StudyLocus

Study locus to traverse between colocalisation and variant index

 required

Returns:

Name Type Description
DataFrame DataFrame

Dataframe of features that include genes in the neighbourhood not present in the colocalisation results. For these genes, the feature value is set to 0.
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
def extend_missing_colocalisation_to_neighbourhood_genes(
    feature_name: str,
    local_features: DataFrame,
    variant_index: VariantIndex,
    gene_index: GeneIndex,
    study_locus: StudyLocus,
) -> DataFrame:
    """This function creates an artificial dataset of features that represents the missing colocalisation to the neighbourhood genes.

    Args:
        feature_name (str): The name of the feature to extend
        local_features (DataFrame): The dataframe of features to extend
        variant_index (VariantIndex): Variant index containing all variant/gene relationships
        gene_index (GeneIndex): Gene index to fetch the gene information
        study_locus (StudyLocus): Study locus to traverse between colocalisation and variant index

    Returns:
        DataFrame: Dataframe of features that include genes in the neighbourhood not present in the colocalisation results. For these genes, the feature value is set to 0.
    """
    coding_variant_gene_lut = (
        variant_index.df.select(
            "variantId", f.explode("transcriptConsequences").alias("tc")
        )
        .select(f.col("tc.targetId").alias("geneId"), "variantId")
        .join(gene_index.df.select("geneId", "biotype"), "geneId", "left")
        .filter(f.col("biotype") == "protein_coding")
        .drop("biotype")
        .distinct()
    )
    local_features_w_variant = local_features.join(
        study_locus.df.select("studyLocusId", "variantId"), "studyLocusId"
    )
    return (
        # Get the genes that are not present in the colocalisation results
        coding_variant_gene_lut.join(
            local_features_w_variant, ["variantId", "geneId"], "left_anti"
        )
        # We now link the missing variant/gene to the study locus from the original dataframe
        .join(
            local_features_w_variant.select("studyLocusId", "variantId").distinct(),
            "variantId",
        )
        .drop("variantId")
        # Fill the information for missing genes with 0
        .withColumn(feature_name, f.lit(0.0))
    )

gentropy.dataset.l2g_features.colocalisation.common_neighbourhood_colocalisation_feature_logic(study_loci_to_annotate: StudyLocus | L2GGoldStandard, colocalisation_method: str, colocalisation_metric: str, feature_name: str, qtl_types: list[str] | str, *, colocalisation: Colocalisation, study_index: StudyIndex, gene_index: GeneIndex, study_locus: StudyLocus, variant_index: VariantIndex) -> DataFrame

Wrapper to call the logic that creates a type of colocalisation features.

Parameters:

Name Type Description Default
study_loci_to_annotate StudyLocus | L2GGoldStandard

The dataset containing study loci that will be used for annotation

 required
colocalisation_method str

The colocalisation method to filter the data by

 required
colocalisation_metric str

The colocalisation metric to use

 required
feature_name str

The name of the feature to create

 required
qtl_types list[str] | str

The types of QTL to filter the data by

 required
colocalisation Colocalisation

Dataset with the colocalisation results

 required
study_index StudyIndex

Study index to fetch study type and gene

 required
gene_index GeneIndex

Gene index to add gene type

 required
study_locus StudyLocus

Study locus to traverse between colocalisation and study index

 required
variant_index VariantIndex

Variant index to annotate all overlapping genes

 required

Returns:

Name Type Description
DataFrame DataFrame

Feature annotation in long format with the columns: studyLocusId, geneId, featureName, featureValue
Source code in src/gentropy/dataset/l2g_features/colocalisation.py 
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
def common_neighbourhood_colocalisation_feature_logic(
    study_loci_to_annotate: StudyLocus | L2GGoldStandard,
    colocalisation_method: str,
    colocalisation_metric: str,
    feature_name: str,
    qtl_types: list[str] | str,
    *,
    colocalisation: Colocalisation,
    study_index: StudyIndex,
    gene_index: GeneIndex,
    study_locus: StudyLocus,
    variant_index: VariantIndex,
) -> DataFrame:
    """Wrapper to call the logic that creates a type of colocalisation features.

    Args:
        study_loci_to_annotate (StudyLocus | L2GGoldStandard): The dataset containing study loci that will be used for annotation
        colocalisation_method (str): The colocalisation method to filter the data by
        colocalisation_metric (str): The colocalisation metric to use
        feature_name (str): The name of the feature to create
        qtl_types (list[str] | str): The types of QTL to filter the data by
        colocalisation (Colocalisation): Dataset with the colocalisation results
        study_index (StudyIndex): Study index to fetch study type and gene
        gene_index (GeneIndex): Gene index to add gene type
        study_locus (StudyLocus): Study locus to traverse between colocalisation and study index
        variant_index (VariantIndex): Variant index to annotate all overlapping genes

    Returns:
        DataFrame: Feature annotation in long format with the columns: studyLocusId, geneId, featureName, featureValue
    """
    # First maximum colocalisation score for each studylocus, gene
    local_feature_name = feature_name.replace("Neighbourhood", "")
    local_max = common_colocalisation_feature_logic(
        study_loci_to_annotate,
        colocalisation_method,
        colocalisation_metric,
        local_feature_name,
        qtl_types,
        colocalisation=colocalisation,
        study_index=study_index,
        study_locus=study_locus,
    )
    extended_local_max = local_max.unionByName(
        extend_missing_colocalisation_to_neighbourhood_genes(
            local_feature_name,
            local_max,
            variant_index,
            gene_index,
            study_locus,
        )
    )
    return (
        extended_local_max.join(
            # Compute average score in the vicinity (feature will be the same for any gene associated with a studyLocus)
            # (non protein coding genes in the vicinity are excluded see #3552)
            gene_index.df.filter(f.col("biotype") == "protein_coding").select("geneId"),
            "geneId",
            "inner",
        )
        .withColumn(
            "regional_max",
            f.max(local_feature_name).over(Window.partitionBy("studyLocusId")),
        )
        .withColumn(
            feature_name,
            f.when(
                (f.col("regional_max").isNotNull()) & (f.col("regional_max") != 0.0),
                f.col(local_feature_name)
                / f.coalesce(f.col("regional_max"), f.lit(0.0)),
            ).otherwise(f.lit(0.0)),
        )
        .drop("regional_max", local_feature_name)
    )
  • 2024-10-01
  • 2024-10-21
  • Contributors
    • ireneisdoomed