geney 1.2.41__py2.py3-none-any.whl → 1.2.43__py2.py3-none-any.whl

geney/oncosplice.py

@@ -443,6 +443,10 @@ async def oncosplice_prototype(mut_id, splicing_threshold=0.5, protein_coding=Tr
 
     def inspect_domain(row, modified_vector, conservation_vector):
         v1, v2 = modified_vector[row.start:row.end], conservation_vector[row.start:row.end]
+        if sum(v2) == 0:
+            return pd.Series([f'{row.type}|{row.start}|{row.end}|{row.description}', 0],
+                             index=['domain_identifier', 'score'])
+
         return pd.Series([f'{row.type}|{row.start}|{row.end}|{row.description}', sum(v1 * v2) / sum(v2)],
                          index=['domain_identifier', 'score'])
 
@@ -466,6 +470,9 @@ async def oncosplice_prototype(mut_id, splicing_threshold=0.5, protein_coding=Tr
         transcript.cons_vector = transform_conservation_vector(transcript.cons_vector, window=window_length)
         transcript.generate_mature_mrna().generate_protein(inplace=True)
         ref_protein, cons_vector = transcript.protein, transcript.cons_vector
+        if sum(cons_vector) == 0:
+            cons_vector = np.ones(len(ref_protein))/len(ref_protein)
+
         reference_transcript = copy.deepcopy(transcript)
 
         assert len(ref_protein) == len(
@@ -494,17 +501,21 @@ async def oncosplice_prototype(mut_id, splicing_threshold=0.5, protein_coding=Tr
                 cons_vector))
 
             out = domains_df.apply(lambda row: inspect_domain(row, modified_positions, cons_vector), axis=1)
-            domains_affected = '+'.join([f'{a}:{b}' for a, b in list(zip(out.domain_identifier, out.score))])
+            domains_affected = '+'.join([f'{a}:{round(b, 3)}' for a, b in list(zip(out.domain_identifier, out.score))])
 
             report = OncospliceAnnotator(reference_transcript, transcript, mutation)
             report['mut_id'] = mut_id
             report['oncosplice_score'] = affected_cons_scores
+            report['cons_available'] = transcript.cons_available
+            report['transcript_id'] = transcript.transcript_id
             report['percentile'] = percentile
             report['isoform_id'] = i
             report['isoform_prevalence'] = new_boundaries['path_weight']
             report['full_missplicing'] = missplicing.aberrant_splicing
             report['missplicing'] = max(missplicing)
-            report['domains_affected'] = domains_affected
+            report['domains'] = domains_affected
+            report['max_domain_score'] = out.score.max()
+
             report['reference_resemblance'] = reference_gene_proteins.get(transcript.protein, None)
             results.append(pd.Series(report))
 

{geney-1.2.41.dist-info → geney-1.2.43.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.2.41
+Version: 1.2.43
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.2.41.dist-info → geney-1.2.43.dist-info}/RECORD

@@ -6,7 +6,7 @@ geney/graphic_utils.py,sha256=oMsBpB9YeEn96gGpKh4MmtagJffWZbk-xPrIwHvkFhA,11016
 geney/gtex_utils.py,sha256=asL2lHyU5KsbWpV096vkf1Ka7hSo_RRfZqw7p5nERmE,1919
 geney/immune_utils.py,sha256=ZRni5ttrhpYBnmNr0d0ZatIbNPYs4nmQuoUO00SpsS4,5271
 geney/mutation_utils.py,sha256=C_kv2MB_L8LlhX3W2ooXjJ3uDoJ8zX1WeDtZKoBZJkI,1547
-geney/oncosplice.py,sha256=1K8p-sytnMUKTYwO_z_YJLelLosKj8TZpM0i5lHcMFI,22941
+geney/oncosplice.py,sha256=bw9C9zutzvxE4q1bPmBG88ByGnrMgbBlxZuAlp_65xw,23414
 geney/pangolin_utils.py,sha256=lLmnjJdJjqwWS85-1jlPLIjD2z14sWjzU87hS-8xxpQ,2873
 geney/power_utils.py,sha256=MehZFUdkJ2EFUot709yPEDxSkXmH5XevMebX2HD768A,7330
 geney/seqmat_utils.py,sha256=YV5DFLbfjXLIswPGvqK1-eEfwn9TUby0b2kewdGAKws,18372
@@ -20,7 +20,7 @@ geney/translation_initiation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NM
 geney/translation_initiation/tis_utils.py,sha256=AF3siFjuQH-Rs44EV-80zHdbxRMvN4woLFSHroWIETc,4448
 geney/translation_initiation/resources/kozak_pssm.json,sha256=pcd0Olziutq-6H3mFWDCD9cujQ_AlZO-iiOvBl82hqE,1165
 geney/translation_initiation/resources/tis_regressor_model.joblib,sha256=IXb4DUDhJ5rBDKcqMk9zE3ECTZZcdj7Jixz3KpoZ7OA,2592025
-geney-1.2.41.dist-info/METADATA,sha256=e7eHu8HlNdNuNXLWxK17ok3lAetzKTJ7ie-8MRct1T8,948
-geney-1.2.41.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
-geney-1.2.41.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.2.41.dist-info/RECORD,,
+geney-1.2.43.dist-info/METADATA,sha256=zbXK3WDJrB4kLGtcZxDWyfTPFqZdCd2-HzldPGlMmoY,948
+geney-1.2.43.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
+geney-1.2.43.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.2.43.dist-info/RECORD,,