geney 1.3.33__py2.py3-none-any.whl → 1.3.35__py2.py3-none-any.whl

geney/Transcript.py

@@ -374,6 +374,6 @@ class Transcript:
         protein = str(Seq(self.orf.seq).translate()).replace('*', '')
 
         # Use existing cons_vector or default to an array of ones
-        self.cons_vector = self.cons_vector if hasattr(self, 'cons_vector') else np.ones(len(protein))
+        self.cons_vector = self.cons_vector if hasattr(self, 'cons_vector') and len(self.cons_vector) == len(protein) else np.ones(len(protein))
         self.protein = protein
         return self

geney/oncosplice.py

@@ -305,7 +305,7 @@ def OncospliceAnnotator(reference_transcript, variant_transcript, mut, ref_attri
 
 
 def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_required=False, primary_transcript=False,
-               window_length=13, organism='hg38', splicing_engine=None):
+               window_length=13, organism='hg38', splicing_engine=None, splicing_db=None, verbose=False):
     gene = Gene.from_file(mut_id.split(':')[0], organism=organism)
     reference_gene_proteins = {
         transcript.generate_pre_mrna().generate_mature_mrna().generate_protein().protein: transcript.transcript_id for
@@ -313,7 +313,7 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_require
 
     mutations = [MutSeqMat.from_mutid(m) for m in mut_id.split('|')]
     results = []
-    for reference_transcript in tqdm(gene):
+    for reference_transcript in tqdm(gene, desc=f'Processing {mut_id}...'):
         if (cons_required and not reference_transcript.cons_available) or (
                 protein_coding and not reference_transcript.transcript_biotype == 'protein_coding'):
             continue
@@ -338,12 +338,20 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_require
         if splicing_engine is None:
             missplicing = Missplicing()
         else:
-            missplicing = find_transcript_missplicing_seqs(
-                reference_transcript.pre_mrna.get_context(center, context=7500, padding='N'),
-                mutated_transcript.pre_mrna.get_context(center, context=7500, padding='N'), reference_transcript.donors,
-                reference_transcript.acceptors, threshold=splicing_threshold, engine=splicing_engine)
-        alternative_splicing_paths = develop_aberrant_splicing(reference_transcript, missplicing.aberrant_splicing)
+            missplicing, no_splicing_record = None, True
+            if splicing_db is not None:
+                missplicing = splicing_db.get_mutation_data(engine=splicing_engine, mut_id=mut_id, gene=gene, transcript_id=reference_transcript.transcript_id)
+                no_splicing_record = missplicing is None
+
+            if missplicing is None:
+                missplicing = find_transcript_missplicing_seqs(
+                    reference_transcript.pre_mrna.get_context(center, context=7500, padding='N'),
+                    mutated_transcript.pre_mrna.get_context(center, context=7500, padding='N'), reference_transcript.donors,
+                    reference_transcript.acceptors, threshold=splicing_threshold, engine=splicing_engine)
+                if no_splicing_record and splicing_db is not None:
+                    splicing_db.get_mutation_data(engine=splicing_engine, mut_id=mut_id, gene=gene, transcript_id=reference_transcript.transcript_id, data=missplicing.missplicing)
 
+        alternative_splicing_paths = develop_aberrant_splicing(reference_transcript, missplicing.aberrant_splicing)
         for i, new_boundaries in enumerate(alternative_splicing_paths):
             mutated_transcript.acceptors = new_boundaries['acceptors']
             mutated_transcript.donors = new_boundaries['donors']
@@ -368,7 +376,7 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_require
             report['isoform_id'] = short_hash_of_list(mutated_transcript.exons)
             report['isoform_prevalence'] = new_boundaries['path_weight']
             report['full_missplicing'] = missplicing.aberrant_splicing
-            report['missplicing'] = missplicing.max_delta()
+            report['missplicing'] = missplicing.max_delta
             report['reference_resemblance'] = reference_gene_proteins.get(mutated_transcript.protein, None)
             results.append(report)
 
@@ -378,7 +386,7 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_require
     return pd.DataFrame(results)[
         ['mut_id', 'transcript_id', 'isoform_id', 'primary_transcript', 'missplicing', 'full_missplicing',
          'exon_changes', 'splicing_codes', 'affected_exon', 'affected_intron', 'mutation_distance_from_5',
-         'mutation_distance_from_3', 'engine', 'reference_resemblance', 'oncosplice_score', 'percentile',
+         'mutation_distance_from_3', 'reference_resemblance', 'oncosplice_score', 'percentile',
          'isoform_prevalence', 'reference_protein', 'variant_protein', 'splicing_engine']]
 
 #

{geney-1.3.33.dist-info → geney-1.3.35.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.3.33
+Version: 1.3.35
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.3.33.dist-info → geney-1.3.35.dist-info}/RECORD

@@ -1,7 +1,7 @@
 geney/Fasta_segment.py,sha256=99HxNGNh_MfdVW6hhtlb1vOn7eSmT7oFoEfHDFMxG8w,11275
 geney/Gene.py,sha256=1pqKI3hGZndi7VY4j66ObhJjnz8YiNtBLGJTIHWVujA,6670
 geney/SeqMats.py,sha256=aLpqd7RJSEU07jdPXpbtZPeb2D9BxrZuW6BTkcXpNE4,18819
-geney/Transcript.py,sha256=eRZXVVxDVBbv0l385bnAOBFRBSzBwppXcbBq8KXkwlo,14443
+geney/Transcript.py,sha256=s2QtC5IGAJNZ1Uf3S-eTCzTXy6lrDzXbxb9pcLMwbQg,14485
 geney/__init__.py,sha256=eBdDl42N6UhcYeZDjOnv199Z88fI5_8Y6xW8447OKXM,755
 geney/_mutation_utils.py,sha256=dHssUsnii_mf-wuRoMmF13UlD7k3ml_VwQMItTYnXpU,1132
 geney/allele_linkage.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -11,7 +11,7 @@ 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=_nHLzzFRzxSWm-lYA9cQHTpiA1d8DMQIlch2CI4qZZg,22554
+geney/oncosplice.py,sha256=3_XAUbzpCTYBI9W1uag75ed93lsNw8UuvnM6LjwTXZY,23221
 geney/pangolin_utils.py,sha256=i5j5vEMCWOTIa1mRP2377BAhlUFZjHBzTQBips4lA_4,2934
 geney/power_utils.py,sha256=MehZFUdkJ2EFUot709yPEDxSkXmH5XevMebX2HD768A,7330
 geney/seqmat_utils.py,sha256=wzb3PX5it5bpIFQvcxyzlxfhoJTbHHbsjg0rzh05iVs,19753
@@ -25,7 +25,7 @@ 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-1.3.33.dist-info/METADATA,sha256=d_U3GL4uOMgpg2QxKJPteTcWlg-VEPnSe03RByF0JZY,990
-geney-1.3.33.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
-geney-1.3.33.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.3.33.dist-info/RECORD,,
+geney-1.3.35.dist-info/METADATA,sha256=yhGQQBVx7g7hjOBXPgMZMb5-R9gfnnpjFVNWnRJuPwQ,990
+geney-1.3.35.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
+geney-1.3.35.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.3.35.dist-info/RECORD,,