geney 1.4.34__py2.py3-none-any.whl → 1.4.36__py2.py3-none-any.whl

geney/pipelines.py

@@ -9,6 +9,16 @@ from .Oncosplice import Oncosplice
 from .utils.TranscriptLibrary import TranscriptLibrary
 
 
+def splicing_analysis(mut_id, transcript_id=None, splicing_engine='spliceai'):
+    m = MutationalEvent(mut_id)
+    assert m.compatible(), 'Mutations in event are incompatible'
+    reference_transcript = Gene.from_file(
+        m.gene).transcript(transcript_id).generate_pre_mrna().generate_mature_mrna().generate_protein()
+    tl = TranscriptLibrary(reference_transcript, m)
+    splicing_results = tl.predict_splicing(m.position, engine=splicing_engine, inplace=True).get_event_columns('event')
+    ss = SpliceSimulator(splicing_results, tl.event, feature='event', max_distance=100_000_000)
+    return ss
+
 def max_splicing_delta(mut_id, transcript_id=None, splicing_engine='spliceai'):
     m = MutationalEvent(mut_id)
     assert m.compatible(), 'Mutations in event are incompatible'

geney/utils/spliceai_pytorch_utils.py

@@ -65,12 +65,14 @@ def sai_predict_probs(seq: str, model) -> list:
     is the donor probability. These probabilities corresponds to the
     middel <L NTs> NTs of the input seq.
     '''
-    x = one_hot_encode(seq)[None, :, :].transpose(1, 2)  # shape: [1, 4, L]
+    x = one_hot_encode(seq)[None, :, :].transpose(1, 2).to(device)  # shape: [1, 4, L]
+    # print(x.shape)
     y = model(x)
+    # print(y.shape)
     probs = torch.softmax(y, dim=1)  # shape: [1, 3, L]
     acceptor_probs = probs[0, :, 1]       # [L]
     donor_probs    = probs[0, :, 2]       # [L]
-    return acceptor_probs.tolist(), donor_probs.tolist()
+    return acceptor_probs.tolist() + [0], donor_probs.tolist() + [0]
 
 
 def run_spliceai_seq(seq, indices, threshold=0):

geney/utils/spliceai_utils.py

@@ -26,7 +26,7 @@ if sys.platform == 'darwin':
     model_filenames = [f"models/spliceai{i}.h5" for i in range(1, 6)]
     model_paths = [resources.files('spliceai').joinpath(f) for f in model_filenames]
 else:
-    model_paths = [f"/tamir2/nicolaslynn/home/miniconda3/lib/python3.10/site-packages/spliceai/models/spliceai{i}.h5"
+    model_paths = [f"/tamir2/nicolaslynn/tools/SpliceAI/spliceai/models/spliceai{i}.h5"
                    for i in range(1, 6)]
 
 # Load models onto correct device

geney/utils/splicing_utils.py

@@ -20,7 +20,7 @@ def run_splicing_engine(seq: Optional[str] = None, engine: str = 'spliceai') ->
 
     if seq is None:
         from geney.utils.utils import generate_random_sequence
-        seq = generate_random_sequence(15_000)
+        seq = generate_random_sequence(15_001)
 
     match engine:
         case 'spliceai':
@@ -30,12 +30,12 @@ def run_splicing_engine(seq: Optional[str] = None, engine: str = 'spliceai') ->
         case 'spliceai-pytorch':
             from geney.utils.spliceai_pytorch_utils import sai_predict_probs, model
             acceptor_probs, donor_probs = sai_predict_probs(seq, model=model)
-            print(len(acceptor_probs), len(donor_probs), donor_probs)
 
         case 'pangolin':
             from geney.utils.pangolin_utils import pangolin_predict_probs, pang_models
             # print(seq)
             donor_probs, acceptor_probs = pangolin_predict_probs(seq, models=pang_models)
+
         case _:
             raise ValueError(f"Engine '{engine}' not implemented")
 

{geney-1.4.34.dist-info → geney-1.4.36.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.4.34
+Version: 1.4.36
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn
@@ -31,4 +31,5 @@ Requires-Dist: pyfastx
 Requires-Dist: tensorflow
 Requires-Dist: keras
 Requires-Dist: redis
+Requires-Dist: seaborn
 

{geney-1.4.34.dist-info → geney-1.4.36.dist-info}/RECORD

@@ -23,7 +23,7 @@ geney/gtex_utils.py,sha256=asL2lHyU5KsbWpV096vkf1Ka7hSo_RRfZqw7p5nERmE,1919
 geney/immune_utils.py,sha256=b-8dRcCti7xsU7RG3op18lkSnAD8dp_BymGaR-hbNcI,5272
 geney/mutation_utils.py,sha256=C_kv2MB_L8LlhX3W2ooXjJ3uDoJ8zX1WeDtZKoBZJkI,1547
 geney/pangolin_utils.py,sha256=9jdBXlOcRaUdfi-UpUxHA0AkTMZkUF-Lt7HVZ1nEm3s,2973
-geney/pipelines.py,sha256=p_zZjQRkcQ_MwOZWv247QVG5iNSrrV4g8BT3vJNwpZM,3103
+geney/pipelines.py,sha256=uYauL2Oy7aPYiwkjpWSMSNDIdNLUPoMgoKh78JD1sBk,3709
 geney/power_utils.py,sha256=orOhsr9vkQ-Y4nD1zHj_MmR2J3uYiUsiklqVy-5T-2M,7331
 geney/seqmat_utils.py,sha256=wzb3PX5it5bpIFQvcxyzlxfhoJTbHHbsjg0rzh05iVs,19753
 geney/spliceai_utils.py,sha256=nyBnLdYs1rB-duA9lfJYM9Q2xNlvZA3I_sCJ1z5WjFw,3294
@@ -43,11 +43,11 @@ geney/utils/TranscriptLibrary.py,sha256=W1hv4Y8wRlmwTs3iFdn4_IqS-2suVDzZe4fwti2K
 geney/utils/__init__.py,sha256=-nJ-DMx1JzP-ZCe_QuQCeM0ZYIT_16jxoXDhUaO_4Oc,714
 geney/utils/mutation_utils.py,sha256=r-pHr56gEa5kh_DPX8MjFY3ZfYaOtyo4CUfJ5ZHlXPw,3243
 geney/utils/pangolin_utils.py,sha256=JQSPbWxdzqGFYfWQktkfLMaMSGR28eGQhNzO7MLMe5M,6162
-geney/utils/spliceai_pytorch_utils.py,sha256=wwBoT2utKZjjaWAUo11mSoympVK1vkNxAxcJvXAh8SM,2792
-geney/utils/spliceai_utils.py,sha256=VtrIbjyQxk_3lw86eWjftRYyal9OzxArJ0GV5u_ymTg,2721
-geney/utils/splicing_utils.py,sha256=LKfozj7GYLYbGKwhZmh3A8Vc830TH2bDNGZX0kz6Fqs,21035
+geney/utils/spliceai_pytorch_utils.py,sha256=oFKX00mUiaHNJ2qyivQfgzbouz57N3p1Q7uNrMmjtdk,2857
+geney/utils/spliceai_utils.py,sha256=8CBMCo13vRaj-E3h0eZkjiRmRpYI9po4_42O43vKaME,2691
+geney/utils/splicing_utils.py,sha256=JpUmuuzlzVZUI_zzaIwa03Xv-NGXzR6jlOmDAbNTYzc,20966
 geney/utils/utils.py,sha256=GXqlatNhix1akt3fburNzIwhiW9ZdCQSt2vmU80neyA,2370
-geney-1.4.34.dist-info/METADATA,sha256=xDiZZ7s1Yn16NtaOxv1X3B-3Y63ALpvclp5Sn51t97I,990
-geney-1.4.34.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
-geney-1.4.34.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.4.34.dist-info/RECORD,,
+geney-1.4.36.dist-info/METADATA,sha256=5UEnYWM74boaWda13s82U6Xpk_h0lzDbKqA86zNPTOI,1013
+geney-1.4.36.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
+geney-1.4.36.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.4.36.dist-info/RECORD,,