geney 1.3.72__py2.py3-none-any.whl → 1.3.74__py2.py3-none-any.whl

geney/oncosplice.py

@@ -306,7 +306,7 @@ 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, splicing_db=None, verbose=False,
-               tis_engine=None, tis_db=None):
+               tis_engine=None, tis_db=None, target_transcripts=None):
 
     gene = Gene.from_file(mut_id.split(':')[0], organism=organism)
     reference_gene_proteins = {
@@ -319,6 +319,9 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_require
 
     results = []
     for reference_transcript in tqdm(gene, desc=f'Processing {mut_id}...'):
+        if target_transcripts is not None and reference_transcript.transcript_id not in target_transcripts:
+            continue
+
         # if (cons_required and not reference_transcript.cons_available) or (
         #         protein_coding and not reference_transcript.transcript_biotype == 'protein_coding'):
         if protein_coding and not reference_transcript.transcript_biotype == 'protein_coding':

geney/splicing_utils.py

@@ -223,6 +223,9 @@ def find_transcript_splicing(transcript, engine: str = 'spliceai') -> Tuple[Dict
 
 def find_transcript_missplicing(mut_id, transcript=None, threshold=0.5, engine='spliceai', organism='hg38', db=None, force_recompute=False):
     gene = Gene.from_file(mut_id.split(':')[0], organism=organism)
+    if transcript not in gene.transcripts:
+        return np.nan
+
     reference_transcript = gene.transcript(transcript) if transcript is not None else gene.transcript()
 
     if db is not None:
@@ -230,6 +233,9 @@ def find_transcript_missplicing(mut_id, transcript=None, threshold=0.5, engine='
         if cached_data and not force_recompute:
             return Missplicing(cached_data)
 
+    if reference_transcript is None:
+        return Missplicing({'missed_acceptors': {}, 'missed_donors': {}, 'discovered_acceptors': {}, 'discovered_donors': {}})
+
     variant_transcript = reference_transcript.clone()
     mutations = [MutSeqMat.from_mutid(m) for m in mut_id.split('|')]
     mutations = [m for m in mutations if m in reference_transcript]
@@ -540,7 +546,12 @@ def process_pairwise_epistasis_explicit(mid, engine='spliceai'):
     lower_pos, upper_pos = int(parts[2]), int(parts[6])
 
     # Load gene and its transcript (as pre-mRNA)
-    g = Gene.from_file(parts[0]).transcript().generate_pre_mrna()
+    g = Gene.from_file(parts[0]).transcript()
+
+    if g is not None:
+        g.generate_pre_mrna()
+    else:
+        return pd.DataFrame()
 
     # If gene is on the reverse strand, swap positions and set factor to -1.
     if g.rev:

{geney-1.3.72.dist-info → geney-1.3.74.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.3.72
+Version: 1.3.74
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.3.72.dist-info → geney-1.3.74.dist-info}/RECORD

@@ -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=YZvAnbe8gj9fPvs2DldeQpqhhe_QR9xBLe_0tcm9tdg,24793
+geney/oncosplice.py,sha256=Y32tz6DdDVIGdrM4rl9RMC48il5k15VP_Wnmi2nXQ04,24948
 geney/pangolin_utils.py,sha256=9jdBXlOcRaUdfi-UpUxHA0AkTMZkUF-Lt7HVZ1nEm3s,2973
 geney/power_utils.py,sha256=MehZFUdkJ2EFUot709yPEDxSkXmH5XevMebX2HD768A,7330
 geney/seqmat_utils.py,sha256=wzb3PX5it5bpIFQvcxyzlxfhoJTbHHbsjg0rzh05iVs,19753
 geney/spliceai_utils.py,sha256=tVY0T6F6l3fNoaktpn7Kq0oH5ZM0ThFYt9nPi_lfakw,3077
-geney/splicing_utils.py,sha256=Xeji_AMEyB5Yb21E-qWoAFYHFHgZhVXZ6Xt2t1wuhsg,47240
+geney/splicing_utils.py,sha256=wH_Cfd2Fm52qSbkxB8VmK-zMXfHkkEjVLzD-TN7qZVo,47544
 geney/survival_utils.py,sha256=KnAzEviMuXh6SnVXId9PgsFLSbgkduTvYoIthxN7FPA,6886
 geney/tcga_utils.py,sha256=D_BNHm-D_K408dlcJm3hzH2c6QNFjQsKvUcOPiQRk7g,17612
 geney/tis_utils.py,sha256=la0CZroaKe5RgAyFd4Bf_DqQncklWgAY2823xVst98o,7813
@@ -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-1.3.72.dist-info/METADATA,sha256=NgbWgh5UPWkP2EgvbJ2nASR2pbmb_lvehLtakhv4-eQ,990
-geney-1.3.72.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
-geney-1.3.72.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.3.72.dist-info/RECORD,,
+geney-1.3.74.dist-info/METADATA,sha256=Ay8aCZoysVN3uvYzGFHAWLM5N7evz_WxeR1t3oiM6D4,990
+geney-1.3.74.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
+geney-1.3.74.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.3.74.dist-info/RECORD,,