pheval 0.4.1__py3-none-any.whl → 0.4.3__py3-none-any.whl

pheval/analyse/benchmark_db_manager.py

@@ -75,6 +75,7 @@ class BenchmarkDBManager:
                 `False` otherwise.
         """
         list_pattern = re.compile(r"^\[\s*(?:[^\[\],\s]+(?:\s*,\s*[^\[\],\s]+)*)?\s*]$")
+        entity = entity.replace("nan", "None").replace("NaN", "None")
         if list_pattern.match(str(entity)):
             list_representation = ast.literal_eval(entity)
             if isinstance(list_representation, list):

pheval/analyse/disease_prioritisation_analysis.py

@@ -38,11 +38,16 @@ class AssessDiseasePrioritisation(AssessPrioritisationBase):
         for _i, row in df.iterrows():
             result = (
                 self.conn.execute(
-                    f"SELECT * FROM '{standardised_disease_result_path}' "
-                    f"WHERE contains_entity_function(CAST(COALESCE(disease_identifier, '') AS VARCHAR),"
-                    f" '{row['disease_identifier']}') "
-                    f"OR contains_entity_function(CAST(COALESCE(disease_name, '') AS VARCHAR), "
-                    f"'{row['disease_name']}')"
+                    (
+                        f"SELECT * FROM '{standardised_disease_result_path}' "
+                        f"WHERE contains_entity_function(CAST(COALESCE(disease_identifier, '') AS VARCHAR),"
+                        f" '{row['disease_identifier']}') "
+                        f"OR contains_entity_function(CAST(COALESCE(disease_name, '') AS VARCHAR), "
+                        f"'{row['disease_name']}')"
+                    )
+                    if standardised_disease_result_path.exists()
+                    and standardised_disease_result_path.stat().st_size > 0
+                    else "SELECT NULL WHERE FALSE"
                 )
                 .fetchdf()
                 .to_dict(orient="records")
@@ -56,9 +61,15 @@ class AssessDiseasePrioritisation(AssessPrioritisationBase):
                     f'UPDATE {self.table_name} SET "{self.column}" = ? WHERE identifier = ?',
                     (disease_match, primary_key),
                 )
+            elif len(result) == 0:
+                relevant_ranks.append(0)
         binary_classification_stats.add_classification(
-            self.db_connection.parse_table_into_dataclass(
-                str(standardised_disease_result_path), RankedPhEvalDiseaseResult
+            (
+                self.db_connection.parse_table_into_dataclass(
+                    str(standardised_disease_result_path), RankedPhEvalDiseaseResult
+                )
+                if standardised_disease_result_path.exists()
+                else []
             ),
             relevant_ranks,
         )

pheval/analyse/gene_prioritisation_analysis.py

@@ -36,11 +36,16 @@ class AssessGenePrioritisation(AssessPrioritisationBase):
         for _i, row in df.iterrows():
             result = (
                 self.conn.execute(
-                    f"SELECT * FROM '{standardised_gene_result_path}' "
-                    f"WHERE contains_entity_function(CAST(COALESCE(gene_identifier, '') AS VARCHAR),"
-                    f" '{row['gene_identifier']}') "
-                    f"OR contains_entity_function(CAST(COALESCE(gene_symbol, '') AS VARCHAR), "
-                    f"'{row['gene_symbol']}')"
+                    (
+                        f"SELECT * FROM '{standardised_gene_result_path}' "
+                        f"WHERE contains_entity_function(CAST(COALESCE(gene_identifier, '') AS VARCHAR), "
+                        f"'{row['gene_identifier']}') "
+                        f"OR contains_entity_function(CAST(COALESCE(gene_symbol, '') AS VARCHAR), "
+                        f"'{row['gene_symbol']}')"
+                    )
+                    if standardised_gene_result_path.exists()
+                    and standardised_gene_result_path.stat().st_size > 0
+                    else "SELECT NULL WHERE FALSE"
                 )
                 .fetchdf()
                 .to_dict(orient="records")
@@ -53,9 +58,15 @@ class AssessGenePrioritisation(AssessPrioritisationBase):
                     f'UPDATE {self.table_name} SET "{self.column}" = ? WHERE identifier = ?',
                     (gene_match, primary_key),
                 )
+            if not result:
+                relevant_ranks.append(0)
         binary_classification_stats.add_classification(
-            self.db_connection.parse_table_into_dataclass(
-                str(standardised_gene_result_path), RankedPhEvalGeneResult
+            (
+                self.db_connection.parse_table_into_dataclass(
+                    str(standardised_gene_result_path), RankedPhEvalGeneResult
+                )
+                if standardised_gene_result_path.exists()
+                else []
             ),
             relevant_ranks,
         )

pheval/analyse/generate_plots.py

@@ -2,6 +2,7 @@ from pathlib import Path
 from typing import List
 
 import matplotlib
+import numpy as np
 import pandas as pd
 import seaborn as sns
 from matplotlib import pyplot as plt
@@ -368,9 +369,16 @@ class PlotGenerator:
         """
         plt.clf()
         for i, benchmark_result in enumerate(benchmarking_results):
+            y_score = np.array(benchmark_result.binary_classification_stats.scores)
+            y_score = np.nan_to_num(
+                y_score,
+                nan=0.0,
+                posinf=max(y_score[np.isfinite(y_score)]),
+                neginf=min(y_score[np.isfinite(y_score)]),
+            )
             fpr, tpr, thresh = roc_curve(
                 benchmark_result.binary_classification_stats.labels,
-                benchmark_result.binary_classification_stats.scores,
+                y_score,
                 pos_label=1,
             )
             roc_auc = auc(fpr, tpr)
@@ -411,9 +419,16 @@ class PlotGenerator:
         plt.clf()
         plt.figure()
         for i, benchmark_result in enumerate(benchmarking_results):
+            y_score = np.array(benchmark_result.binary_classification_stats.scores)
+            y_score = np.nan_to_num(
+                y_score,
+                nan=0.0,
+                posinf=max(y_score[np.isfinite(y_score)]),
+                neginf=min(y_score[np.isfinite(y_score)]),
+            )
             precision, recall, thresh = precision_recall_curve(
                 benchmark_result.binary_classification_stats.labels,
-                benchmark_result.binary_classification_stats.scores,
+                y_score,
             )
             precision_recall_auc = auc(recall, precision)
             plt.plot(

pheval/analyse/variant_prioritisation_analysis.py

@@ -44,12 +44,16 @@ class AssessVariantPrioritisation(AssessPrioritisationBase):
             )
             result = (
                 self.conn.execute(
-                    f"SELECT * FROM '{standardised_variant_result_path}' "
-                    f"WHERE "
-                    f"chromosome == '{causative_variant.chrom}' AND "
-                    f"start == {causative_variant.pos} AND "
-                    f"ref == '{causative_variant.ref}' AND "
-                    f"alt == '{causative_variant.alt}'"
+                    (
+                        f"SELECT * FROM '{standardised_variant_result_path}' "
+                        f"WHERE "
+                        f"chromosome == '{causative_variant.chrom}' AND "
+                        f"start == {causative_variant.pos} AND "
+                        f"ref == '{causative_variant.ref}' AND "
+                        f"alt == '{causative_variant.alt}'"
+                    )
+                    if standardised_variant_result_path.exists()
+                    else "SELECT NULL WHERE FALSE"
                 )
                 .fetchdf()
                 .to_dict(orient="records")
@@ -66,10 +70,15 @@ class AssessVariantPrioritisation(AssessPrioritisationBase):
                     f'UPDATE {self.table_name} SET "{self.column}" = ? WHERE identifier = ?',
                     (variant_match, primary_key),
                 )
-
+            elif len(result) == 0:
+                relevant_ranks.append(0)
         binary_classification_stats.add_classification(
-            self.db_connection.parse_table_into_dataclass(
-                str(standardised_variant_result_path), RankedPhEvalVariantResult
+            (
+                self.db_connection.parse_table_into_dataclass(
+                    str(standardised_variant_result_path), RankedPhEvalVariantResult
+                )
+                if standardised_variant_result_path.exists()
+                else []
             ),
             relevant_ranks,
         )

pheval/prepare/prepare_corpus.py

@@ -57,6 +57,11 @@ def prepare_corpus(
                     f"Removed {phenopacket_path.name} from the corpus due to missing variant fields."
                 )
                 continue
+            elif phenopacket_util.check_variant_alleles():
+                info_log.warning(
+                    f"Removed {phenopacket_path.name} from the corpus due to identical "
+                    "reference and alternate allele fields."
+                )
         if gene_analysis:
             if phenopacket_util.check_incomplete_gene_record():
                 info_log.warning(

pheval/utils/phenopacket_utils.py

@@ -503,6 +503,19 @@ class PhenopacketUtil:
                 return True
         return False
 
+    def check_variant_alleles(self) -> bool:
+        """
+        Check if any variant record in the phenopacket has identical reference and alternate alleles.
+
+        Returns:
+            bool: True if the reference and alternate alleles are identical, False otherwise.
+        """
+        variants = self.diagnosed_variants()
+        for variant in variants:
+            if variant.ref == variant.alt:
+                return True
+        return False
+
     def check_incomplete_gene_record(self) -> bool:
         """
         Check if any gene record in the phenopacket has incomplete information.

{pheval-0.4.1.dist-info → pheval-0.4.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: pheval
-Version: 0.4.1
+Version: 0.4.3
 Summary: 
 Author: Yasemin Bridges
 Author-email: y.bridges@qmul.ac.uk

{pheval-0.4.1.dist-info → pheval-0.4.3.dist-info}/RECORD

@@ -2,20 +2,20 @@ pheval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pheval/analyse/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pheval/analyse/analysis.py,sha256=Yt2xH0WS_2NO13-wYvywzmCRCj8RinQ1MeozJQuGe3o,4009
 pheval/analyse/assess_prioritisation_base.py,sha256=znBscRTqIKxxZMHR-H6KrjFJ6Uv5P5HzwTQUWS6Eoos,3434
-pheval/analyse/benchmark_db_manager.py,sha256=RaAnvq5Tfvsw8161iQUe_P146X98BckMRhMq6BibwNI,5111
+pheval/analyse/benchmark_db_manager.py,sha256=R1GstKKoh4PIPupyAarm7DhZyOdVDVtyY4A1nPNTkDs,5181
 pheval/analyse/benchmark_generator.py,sha256=-LljszuKAT3oJfGQn7JHAILCGg5QXYny4nPPf273g_E,5896
 pheval/analyse/benchmarking_data.py,sha256=aRvDmwqjFGKvWDRGjMwaQxfDZscptRBwI-rcSqY-X5s,913
 pheval/analyse/binary_classification_stats.py,sha256=E35YjvGM-zFnuEt8M3pgN03vBab4MH6ih726QKvuogg,12519
-pheval/analyse/disease_prioritisation_analysis.py,sha256=1Ut4u6p9mDGbGBoXrVxTuUgv_nrqxzBhq5N9jbGWRWs,5725
-pheval/analyse/gene_prioritisation_analysis.py,sha256=_7r16BC0S2H9rOY016mLLUg6PcxaCQOh5FQcNKFTy-4,5582
-pheval/analyse/generate_plots.py,sha256=rMSdgawGYYc7BAAolqz73TAnanKtrxCC48bI6WQq6xc,21455
+pheval/analyse/disease_prioritisation_analysis.py,sha256=mOIAiz_WzWQBP-3g8Twv-ii8ZxbXktAmgi6zl4sJaC8,6182
+pheval/analyse/gene_prioritisation_analysis.py,sha256=wPH-mCW_KY3XxrwAvw-ucxLbWzUKBucO4zSo3XqBsaY,6022
+pheval/analyse/generate_plots.py,sha256=5oxsdnAbbVgQj8ZrWTLs12rSM24EXp-IdLCjy5QB1_g,21992
 pheval/analyse/generate_summary_outputs.py,sha256=nKqwbpA-9bbL5mCySiuyV_AUDIokmCg3vD8_JAsg1ls,4157
 pheval/analyse/parse_benchmark_summary.py,sha256=vyAOIdIWF4rZjGTPFE69ajhEC9AkkN3QBVqSe_uYZsg,2946
 pheval/analyse/parse_corpus.py,sha256=N88enptR4qG6cmqXU_TKg8DMmCeFog37eeK5nFEMQOQ,8678
 pheval/analyse/prioritisation_result_types.py,sha256=qJoB6O-lFYmzAMcTQeDJZQNLJ6hleoKDYATTkhvFF98,1228
 pheval/analyse/rank_stats.py,sha256=53ZickUtQlctYsorAIUwlCX7M6UC-wCxoV1MbL6F9gc,17987
 pheval/analyse/run_data_parser.py,sha256=VQBUoOIRYRWc5uqURUvaWdaW3E3C7Su0JvLavQLHQaY,4105
-pheval/analyse/variant_prioritisation_analysis.py,sha256=LPEZDhFfzx-sQl9g8pM700l4Zzpy6qdOS68vOV2mZA0,6020
+pheval/analyse/variant_prioritisation_analysis.py,sha256=8ntbALzAAfJ4ijviQKvLiwKBeRvTLWI0Tb9dpnCYxhs,6404
 pheval/cli.py,sha256=EBGh6TIxAiWs0eDdQiefq6YuD0mb93siGsNmsVO1j7c,1527
 pheval/cli_pheval.py,sha256=fWbKUcPTZZSa1EJEtH_lNn1XE6qRApRHihqUZS5owrA,2424
 pheval/cli_pheval_utils.py,sha256=O6tWnE85QQHGNcP08OwJGANMfXJPsZtFEu-D6ATld00,16700
@@ -29,7 +29,7 @@ pheval/prepare/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pheval/prepare/create_noisy_phenopackets.py,sha256=ydhA4mpqKTDc4hBu8YfvNW2nMubHK3dbO-cv0lA4JFQ,11504
 pheval/prepare/create_spiked_vcf.py,sha256=90A-Mi8QKhvN036vtFEVWAHgzHO37itiLYrqYlG4LiA,23953
 pheval/prepare/custom_exceptions.py,sha256=_G3_95dPtHIs1SviYBV1j7cYc-hxlhuw8hhnYdzByYY,1719
-pheval/prepare/prepare_corpus.py,sha256=eRvozzezIgAqHAumtqul0WfXfBO1iOBaSlN8fPSn0Nw,4223
+pheval/prepare/prepare_corpus.py,sha256=mwI3FJJ6GGSbmbvz4enrVP86MBoHSssMIRebkapmu5Y,4484
 pheval/prepare/update_phenopacket.py,sha256=21fzUPbwKN6Ey5TSh9PFzjT2x86U19RAE6WmkjG8u28,4770
 pheval/resources/alternate_ouputs/CADA_results.txt,sha256=Rinn2TtfwFNsx0aEWegKJOkjKnBm-Mf54gdaT3bWP0k,547
 pheval/resources/alternate_ouputs/DeepPVP_results.txt,sha256=MF9MZJYa4r4PEvFzALpi-lNGLxjENOnq_YgrgFMn-oQ,1508
@@ -47,11 +47,11 @@ pheval/utils/docs_gen.py,sha256=6FGtHicBC0rZKi0tdL3Epsg8d4osE44I9f1Ga0j4JLA,3193
 pheval/utils/docs_gen.sh,sha256=LyKLKjaZuf4UJ962CWfM-XqkxtvM8O2N9wHZS5mcb9A,477
 pheval/utils/exomiser.py,sha256=m2u0PH2z9lFPaB3LVkZCmPmH5e55q1NoTzNl46zRRP8,683
 pheval/utils/file_utils.py,sha256=m21cz-qjDYqnI8ClUv3J9fKizex98a-9bSEerQ75i_c,3576
-pheval/utils/phenopacket_utils.py,sha256=W9T_X48EJ-xn5GghzbZlt-lI-DxWoSm7_SHr8DCJg2Q,26856
+pheval/utils/phenopacket_utils.py,sha256=6xQ8WCLdR1VhiU3nCDzaqEVKjGvDWrzvPA50_6ZAHXM,27310
 pheval/utils/semsim_utils.py,sha256=s7ZCR2VfPYnOh7ApX6rv66eGoVSm9QJaVYOWBEhlXpo,6151
 pheval/utils/utils.py,sha256=9V6vCT8l1g4O2-ZATYqsVyd7AYZdWGd-Ksy7_oIC3eE,2343
-pheval-0.4.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-pheval-0.4.1.dist-info/METADATA,sha256=H14Zz0k7MLDs1eEryeaXjCfNUm1FqAyv0M1mXhXq740,6469
-pheval-0.4.1.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-pheval-0.4.1.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
-pheval-0.4.1.dist-info/RECORD,,
+pheval-0.4.3.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+pheval-0.4.3.dist-info/METADATA,sha256=Y6dy74TNnyirSwcpgG9ktJopwoVEZWlixSR4CJOZfDo,6469
+pheval-0.4.3.dist-info/WHEEL,sha256=RaoafKOydTQ7I_I3JTrPCg6kUmTgtm4BornzOqyEfJ8,88
+pheval-0.4.3.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
+pheval-0.4.3.dist-info/RECORD,,

{pheval-0.4.1.dist-info → pheval-0.4.3.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.9.1
+Generator: poetry-core 2.0.0
 Root-Is-Purelib: true
 Tag: py3-none-any