geney 1.3.29__py2.py3-none-any.whl → 1.3.31__py2.py3-none-any.whl

geney/Gene.py

@@ -138,6 +138,9 @@ class Gene:
         if tid is None:
             tid = self.primary_transcript
 
+        if tid is None:
+            return Transcript()
+
         if tid not in self.transcripts:
             raise AttributeError(f"Transcript '{tid}' not found in gene '{self.gene_name}'.")
 
@@ -170,6 +173,12 @@ class Gene:
             self._primary_transcript = protein_coding[0]
             return self._primary_transcript
 
+        # # Fallback 2: find a proitein coding transcript that is not fully defined
+        # protein_coding = [k for k, v in self.transcripts.items() if v.get('transcript_biotype') == 'protein_coding_CDS_not_defined']
+        # if protein_coding:
+        #     self._primary_transcript = protein_coding[0]
+        #     return self._primary_transcript
+
         # No primary or protein-coding transcript found
         self._primary_transcript = None
         return None

geney/oncosplice.py

@@ -5,7 +5,7 @@ from tqdm import tqdm
 import pandas as pd
 import numpy as np
 from .SeqMats import SeqMat, MutSeqMat
-from .splicing_utils import find_transcript_missplicing_seqs, develop_aberrant_splicing
+from .splicing_utils import find_transcript_missplicing_seqs, develop_aberrant_splicing, Missplicing
 from .Gene import Gene
 import copy
 from . import config
@@ -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', engine='spliceai'):
+               window_length=13, organism='hg38', splicing_engine=None):
     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
@@ -335,10 +335,13 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_require
         assert len(reference_transcript.protein) == len(
             reference_transcript.cons_vector), f"Protein ({len(reference_transcript.protein)}) and conservation vector ({len(reference_transcript.cons_vector)}) must be same length."
 
-        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=engine)
+        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)
 
         for i, new_boundaries in enumerate(alternative_splicing_paths):
@@ -359,7 +362,7 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_require
 
             report = OncospliceAnnotator(reference_transcript, mutated_transcript, current_mutations[0])
             report['mut_id'] = mut_id
-            report['engine'] = engine
+            report['splicing_engine'] = splicing_engine if splicing_engine is not None else 'None'
             report['oncosplice_score'] = affected_cons_scores
             report['percentile'] = percentile
             report['isoform_id'] = short_hash_of_list(mutated_transcript.exons)
@@ -376,7 +379,7 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_require
         ['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',
-         'isoform_prevalence', 'reference_protein', 'variant_protein']]
+         'isoform_prevalence', 'reference_protein', 'variant_protein', 'splicing_engine']]
 
 #
 # import asyncio

geney/splicing_utils.py

@@ -460,7 +460,7 @@ def process_pairwise_epistasis(mids, engine='pangolin', fprint=False, db=None):
 
 
 class Missplicing:
-    def __init__(self, splicing_dict, threshold=0.5):
+    def __init__(self, splicing_dict=None, threshold=0.5):
         """
         Initialize a Missplicing object.
 
@@ -475,6 +475,8 @@ class Missplicing:
                                   }
             threshold (float): The threshold above which a delta is considered significant.
         """
+        if splicing_dict is None:
+            splicing_dict = {'missed_acceptors': {}, 'missed_donors': {}, 'discovered_acceptors': {}, 'discovered_donors': {}}
         self.missplicing = splicing_dict
         self.threshold = threshold
 

{geney-1.3.29.dist-info → geney-1.3.31.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.3.29
+Version: 1.3.31
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.3.29.dist-info → geney-1.3.31.dist-info}/RECORD

@@ -1,5 +1,5 @@
 geney/Fasta_segment.py,sha256=99HxNGNh_MfdVW6hhtlb1vOn7eSmT7oFoEfHDFMxG8w,11275
-geney/Gene.py,sha256=JGWtfA6-d1W3I9YRASwaF8vaZ6CCuY0KEawQNdloIqY,6259
+geney/Gene.py,sha256=1pqKI3hGZndi7VY4j66ObhJjnz8YiNtBLGJTIHWVujA,6670
 geney/SeqMats.py,sha256=aLpqd7RJSEU07jdPXpbtZPeb2D9BxrZuW6BTkcXpNE4,18819
 geney/Transcript.py,sha256=eRZXVVxDVBbv0l385bnAOBFRBSzBwppXcbBq8KXkwlo,14443
 geney/__init__.py,sha256=eBdDl42N6UhcYeZDjOnv199Z88fI5_8Y6xW8447OKXM,755
@@ -11,12 +11,12 @@ 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=LOgpdsTC1JotC2qFnqNMefl0t77vvWCJ5XctZsbrLNA,22343
+geney/oncosplice.py,sha256=_nHLzzFRzxSWm-lYA9cQHTpiA1d8DMQIlch2CI4qZZg,22554
 geney/pangolin_utils.py,sha256=i5j5vEMCWOTIa1mRP2377BAhlUFZjHBzTQBips4lA_4,2934
 geney/power_utils.py,sha256=MehZFUdkJ2EFUot709yPEDxSkXmH5XevMebX2HD768A,7330
 geney/seqmat_utils.py,sha256=wzb3PX5it5bpIFQvcxyzlxfhoJTbHHbsjg0rzh05iVs,19753
 geney/spliceai_utils.py,sha256=PFIhTK8Ihrj-cv5tgRN0UFPYEmC4uxtqXSP9bBLnZRM,3077
-geney/splicing_utils.py,sha256=elu5KtkcNGTWhviimIRt0DRWNcjwZrshDphM5XFPImA,38485
+geney/splicing_utils.py,sha256=Fd-T5KC3swuUzrxg0YKnUYQX-J98yWuvrsyzJHM3Rus,38651
 geney/survival_utils.py,sha256=KnAzEviMuXh6SnVXId9PgsFLSbgkduTvYoIthxN7FPA,6886
 geney/tcga_utils.py,sha256=D_BNHm-D_K408dlcJm3hzH2c6QNFjQsKvUcOPiQRk7g,17612
 geney/tis_utils.py,sha256=2makfGfVlDFVIbxzXE85AY9jmAjcNmxyIAxjvkRA5LY,7396
@@ -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-1.3.29.dist-info/METADATA,sha256=Chxu6iycgZPwhUI1X7-VrCdFoZC3TQqF3MMnX6SS9Ps,990
-geney-1.3.29.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
-geney-1.3.29.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.3.29.dist-info/RECORD,,
+geney-1.3.31.dist-info/METADATA,sha256=4B9E4JtQM_t7CiVr02rbZmZgnFPbJE-REz9441hDGI8,990
+geney-1.3.31.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
+geney-1.3.31.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.3.31.dist-info/RECORD,,