geney 1.2.28__py2.py3-none-any.whl → 1.2.30__py2.py3-none-any.whl

geney/mutation_utils.py

@@ -33,6 +33,7 @@ class DEL(Allele):
         pass
 
 def get_mutation(mut_id, rev=False):
+
     _, _, i, r, a = mut_id.split(':')
     i = int(i)
 

geney/oncosplice.py

@@ -363,14 +363,14 @@ def OncospliceAnnotator(reference_transcript, variant_transcript, mut):
 
 def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, primary_transcript=False, window_length=13, organism='hg38', engine='spliceai', domains=None):
     gene = Gene(mut_id.split(':')[0], organism=organism)
-    mutation = get_mutation(mut_id, rev=gene.rev)
+    mutations = [get_mutation(m, rev=gene.rev) for m in mut_id.split('|')]
 
     results = []
     for tid, transcript in gene.run_transcripts(protein_coding=protein_coding, primary_transcript=primary_transcript):
         if not transcript.cons_available:
             continue
 
-        if mutation not in transcript:
+        if all(mutation not in transcript for mutation in mutations):
             results.append({'transcript_id': transcript.transcript_id})
             continue
 
@@ -382,8 +382,9 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, primary_tran
 
         assert len(ref_protein) == len(cons_vector), f"Protein ({len(ref_protein)}) and conservation vector ({len(cons_vector)}) must be same length. {ref_protein}, \n>{cons_vector}\n>{transcript.cons_seq}"
 
-        missplicing = Missplicing(find_transcript_missplicing(transcript, mutation, engine=engine), threshold=splicing_threshold)
-        transcript.pre_mrna += mutation
+        missplicing = Missplicing(find_transcript_missplicing(transcript, mutations, engine=engine), threshold=splicing_threshold)
+        for mutation in mutations:
+            transcript.pre_mrna += mutation
 
         for i, new_boundaries in enumerate(develop_aberrant_splicing(transcript, missplicing.aberrant_splicing)):
             transcript.acceptors = new_boundaries['acceptors']

geney/pangolin_utils.py

@@ -61,7 +61,7 @@ def pangolin_predict_probs(true_seq, models):
     seq = torch.from_numpy(np.expand_dims(seq, axis=0)).float()
 
     # if torch.cuda.is_available():
-    seq = seq.to(torch.device("cuda"))
+    seq = seq.to(torch.device(device))
 
     scores = []
     for j, model_num in enumerate(model_nums):

geney/splicing_utils.py

@@ -148,15 +148,17 @@ def find_ss_changes(ref_dct, mut_dct, known_splice_sites, threshold=0.5):
     return discovered_pos, deleted_pos
 
 
-def find_transcript_missplicing(transcript, mutation, context=5000, window=2500, threshold=0.5, engine='spliceai'):
+def find_transcript_missplicing(transcript, mutations, context=5000, window=2500, threshold=0.5, engine='spliceai'):
+    from functools import reduce
+
     ref = transcript.pre_mrna
-    var = ref + mutation
+    # for mutation in mutations:
+    #     var = ref + mutation
 
-    # print(len(ref.indices))
-    # print(len(var.indices))
+    var = reduce(lambda acc, mutation: acc + mutation, mutations, ref)
 
+    center = int(np.mean([mutation.position for mutation in mutations]) // 1)
 
-    center = mutation.position
     total_context = context + window
 
     length = ref.seqmat.shape[-1]

{geney-1.2.28.dist-info → geney-1.2.30.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.2.28
+Version: 1.2.30
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.2.28.dist-info → geney-1.2.30.dist-info}/RECORD

@@ -5,13 +5,13 @@ geney/data_setup.py,sha256=2RHmuvcGUQbEglXQEZr0C2QPDTQYRZOEm0EcmyfQJgU,12229
 geney/graphic_utils.py,sha256=tjm6IDQ1BdfSeuPYzjlqAUHFQoDYH9jXTzJjKFS4Hh4,11078
 geney/gtex_utils.py,sha256=asL2lHyU5KsbWpV096vkf1Ka7hSo_RRfZqw7p5nERmE,1919
 geney/immune_utils.py,sha256=ZRni5ttrhpYBnmNr0d0ZatIbNPYs4nmQuoUO00SpsS4,5271
-geney/mutation_utils.py,sha256=C-K8F8wyN5joI3ZuP-d7IMYTI43YPDXUc3IgAJ07o8Q,1546
-geney/oncosplice.py,sha256=3jJc1-CWubH2ElHEjyQtsr9JYVmfPQEpq7EX-IfY-t8,20806
-geney/pangolin_utils.py,sha256=S2uMjQnnxqWSnfuMaEjo-wq52DVKFiXt__L5VPdtzyU,2939
+geney/mutation_utils.py,sha256=C_kv2MB_L8LlhX3W2ooXjJ3uDoJ8zX1WeDtZKoBZJkI,1547
+geney/oncosplice.py,sha256=zOOLdY_9tHpwwMQxTS358MCUlhQ6x-XmwlwlIrqwIwc,20902
+geney/pangolin_utils.py,sha256=MP4wGgiw36NAPfwpaXJ5mD4Q-DTbkL3xHcSlYtuZODw,2939
 geney/power_utils.py,sha256=MehZFUdkJ2EFUot709yPEDxSkXmH5XevMebX2HD768A,7330
 geney/seqmat_utils.py,sha256=fawiPa4PPhmbx6wPynt8SG6eowZKUZ2yN32r6B8Ba-g,16802
 geney/spliceai_utils.py,sha256=gIGPC8u3J15A7EQrk2Elho5PbF9MmUUNopGGH-eEV8s,1873
-geney/splicing_utils.py,sha256=pS3jZEpmnDkbT1jjaJh-O6I--Xm22e5dj-GQu7IAZSQ,15943
+geney/splicing_utils.py,sha256=q47EdcsHrp4aLIPVWvkGBJSzS3l3DKiD9DNDsPpZdHk,16075
 geney/survival_utils.py,sha256=2CAkC2LsspicHIdrqsiPnjgvpr5KHDUfLFFqnRbPJqs,5762
 geney/tcga_utils.py,sha256=vXSMf1OxoF_AdE_rMguy_BoYaart_E1t4FFMx2DS1Ak,15585
 geney/utils.py,sha256=WbV1DBllQyvzoDiYkidRiTX5MBpQGr99M4hTUQ0BKo8,2185
@@ -19,7 +19,7 @@ geney/translation_initiation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NM
 geney/translation_initiation/tis_utils.py,sha256=iXrWVijyPe-f8I9rEVGdxNnXBrOGPoKFjmvaOEnQYNE,4446
 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-1.2.28.dist-info/METADATA,sha256=uTgTWSldfE0pK1rnyAPYmv9nLSKD9B6Ko1_SSEaFWKY,948
-geney-1.2.28.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
-geney-1.2.28.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.2.28.dist-info/RECORD,,
+geney-1.2.30.dist-info/METADATA,sha256=T8wma9mdUQjDbYAvMviVcdGPFJId-piDzxGpIVdcXMo,948
+geney-1.2.30.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
+geney-1.2.30.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.2.30.dist-info/RECORD,,