geney 1.3.64__py2.py3-none-any.whl → 1.3.66__py2.py3-none-any.whl

geney/SeqMats.py

@@ -8,6 +8,7 @@ class SeqMat:
     ROW_INDS = 1
     ROW_SUPERINDS = 2
     ROW_MUTATED = 3
+    ROW_ANNOTATION = 4
 
     def __init__(self, seqmat, alphabet=None):
         self.seqmat = seqmat

geney/spliceai_utils.py

@@ -73,4 +73,4 @@ def run_spliceai_seq(seq, indices, threshold=0):
     ref_seq_acceptor_probs, ref_seq_donor_probs = ref_seq_probs_temp[0, :], ref_seq_probs_temp[1, :]
     acceptor_indices = {a: b for a, b in list(zip(indices, ref_seq_acceptor_probs)) if b >= threshold}
     donor_indices = {a: b for a, b in list(zip(indices, ref_seq_donor_probs)) if b >= threshold}
-    return acceptor_indices, donor_indices
+    return donor_indices, acceptor_indices

geney/splicing_utils.py

@@ -166,7 +166,7 @@ def run_splicing_engine(seq, engine='spliceai'):
     match engine:
         case 'spliceai':
             from .spliceai_utils import sai_predict_probs, sai_models
-            donor_probs, acceptor_probs = sai_predict_probs(seq, models=sai_models)
+            acceptor_probs, donor_probs = sai_predict_probs(seq, models=sai_models)
 
         case 'pangolin':
             from .pangolin_utils import pangolin_predict_probs, pang_models
@@ -199,7 +199,7 @@ def find_transcript_splicing(transcript, engine: str = 'spliceai') -> Tuple[Dict
     # Prepare reference sequence with padding
     ref_indices = transcript.indices
     ref_seq = 'N' * 5000 + transcript.seq + 'N' * 5000
-    ref_seq_acceptor_probs, ref_seq_donor_probs = run_splicing_engine(ref_seq, engine)
+    ref_seq_donor_probs, ref_seq_acceptor_probs = run_splicing_engine(ref_seq, engine)
 
     # Verify lengths
     assert len(ref_seq_donor_probs) == len(ref_indices), (
@@ -212,10 +212,11 @@ def find_transcript_splicing(transcript, engine: str = 'spliceai') -> Tuple[Dict
     )
 
     # Create dictionaries and sort them by probability in descending order
-    donor_probs = dict(sorted((i, p) for i, p in zip(ref_indices, ref_seq_donor_probs)),
-                       key=lambda item: item[1], reverse=True)
-    acceptor_probs = dict(sorted((i, p) for i, p in zip(ref_indices, ref_seq_acceptor_probs)),
-                          key=lambda item: item[1], reverse=True)
+    donor_probs = dict(sorted(((i, p) for i, p in zip(ref_indices, ref_seq_donor_probs)),
+                       key=lambda item: item[1], reverse=True))
+
+    acceptor_probs = dict(sorted(((i, p) for i, p in zip(ref_indices, ref_seq_acceptor_probs)),
+                          key=lambda item: item[1], reverse=True))
 
     return donor_probs, acceptor_probs
 
@@ -332,8 +333,8 @@ def find_transcript_missplicing_seqs(ref_seq, var_seq, donors, acceptors, thresh
     if ref_seq.seq == var_seq.seq:
         return Missplicing({'missed_acceptors': {}, 'missed_donors': {}, 'discovered_acceptors': {}, 'discovered_donors': {}})
 
-    ref_seq_acceptor_probs, ref_seq_donor_probs = run_splicing_engine(ref_seq.seq, engine)
-    mut_seq_acceptor_probs, mut_seq_donor_probs = run_splicing_engine(var_seq.seq, engine)
+    ref_seq_donor_probs, ref_seq_acceptor_probs = run_splicing_engine(ref_seq.seq, engine)
+    mut_seq_donor_probs, mut_seq_acceptor_probs = run_splicing_engine(var_seq.seq, engine)
     ref_indices = ref_seq.indices[5000:-5000]
     mut_indices = var_seq.indices[5000:-5000]
     visible_donors = np.intersect1d(donors, ref_indices)
@@ -462,6 +463,50 @@ def process_pairwise_epistasis(mids, engine='pangolin', fprint=False, db=None):
     return pd.concat(results)
 
 
+def process_pairwise_epistasis_explicit(mid, engine='spliceai'):
+    donor_probs, acceptor_probs = {}, {}
+    lower_pos, upper_pos = int(mid.split(':')[2]), int(mid.split(':')[6])
+    g = Gene.from_file(mid.split(':')[0]).transcript().generate_pre_mrna()
+    print(g.rev)
+    if g.rev:
+        lower_pos, upper_pos, factor = upper_pos, lower_pos, -1
+    else:
+        factor = 1
+
+    lb, ub = lower_pos - (factor * 7500), upper_pos + (factor * 7500)
+
+    for m in ['wild_type'] + mid.split('|') + [mid]:
+        transcript = g.clone().pre_mrna
+        if m != 'wild_type':
+            mutations = [MutSeqMat.from_mutid(cm) for cm in m.split('|')]
+            if g.rev:
+                mutations = [m.reverse_complement() for m in mutations]
+            for mutation in mutations:
+                if mutation in transcript:
+                    transcript.mutate(mutation, inplace=True)
+
+        donors, acceptors = find_transcript_splicing(transcript[lb:ub], engine=engine)
+        donor_probs[m] = donors
+        acceptor_probs[m] = acceptors
+
+    acceptors = pd.DataFrame.from_dict(acceptor_probs).T
+    donors = pd.DataFrame.from_dict(donor_probs).T
+
+    acceptors = acceptors.map(lambda x: 0 if x < 0.01 else round(x, 2) if isinstance(x, (int, float)) else x).round(2)
+    acceptors = acceptors.loc[:, acceptors.nunique() > 1]
+    donors = donors.map(lambda x: 0 if abs(x) < 0.01 else round(x, 2) if isinstance(x, (int, float)) else x).round(2)
+    donors = donors.loc[:, donors.nunique() > 1]
+
+    donors.loc['residual'] = (donors.iloc[3] - donors.iloc[0]) - (
+                (donors.iloc[1] - donors.iloc[0]) + (donors.iloc[2] - donors.iloc[0]))
+    acceptors.loc['residual'] = (acceptors.iloc[3] - acceptors.iloc[0]) - (
+                (acceptors.iloc[1] - acceptors.iloc[0]) + (acceptors.iloc[2] - acceptors.iloc[0]))
+
+    donors = donors.loc[:, donors.loc['residual'].abs() > 0.1]
+    acceptors = acceptors.loc[:, acceptors.loc['residual'].abs() > 0.1]
+
+    return acceptors, donors
+
 
 class Missplicing:
     def __init__(self, splicing_dict=None, threshold=0.5):

{geney-1.3.64.dist-info → geney-1.3.66.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.3.64
+Version: 1.3.66
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.3.64.dist-info → geney-1.3.66.dist-info}/RECORD

@@ -1,6 +1,6 @@
 geney/Fasta_segment.py,sha256=99HxNGNh_MfdVW6hhtlb1vOn7eSmT7oFoEfHDFMxG8w,11275
 geney/Gene.py,sha256=nMWJjoQaiVFm2iRjoiq7ghZqnXtW0tJDcq2S0AyOIvY,6883
-geney/SeqMats.py,sha256=ksS1JW3vDj-CRBpcy-K28UFZSfJaMuc-JNNM26T09us,19259
+geney/SeqMats.py,sha256=9-eJnfU2w3LGc0XvVvFEO_QrBneTkC6xkZKDfTcEw5o,19282
 geney/Transcript.py,sha256=CpfxYkuCwFILozrtLuiWnlr1mRnMKn4o84HVJislgYs,14499
 geney/__init__.py,sha256=eBdDl42N6UhcYeZDjOnv199Z88fI5_8Y6xW8447OKXM,755
 geney/_mutation_utils.py,sha256=dHssUsnii_mf-wuRoMmF13UlD7k3ml_VwQMItTYnXpU,1132
@@ -15,8 +15,8 @@ geney/oncosplice.py,sha256=YZvAnbe8gj9fPvs2DldeQpqhhe_QR9xBLe_0tcm9tdg,24793
 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=PFIhTK8Ihrj-cv5tgRN0UFPYEmC4uxtqXSP9bBLnZRM,3077
-geney/splicing_utils.py,sha256=cVLXArVWJIxGaaWttm_dxJQbo6OBBkry4OFozaw-M2U,38768
+geney/spliceai_utils.py,sha256=tVY0T6F6l3fNoaktpn7Kq0oH5ZM0ThFYt9nPi_lfakw,3077
+geney/splicing_utils.py,sha256=_nXLCK41GhcrkXHXAqkhNV2IcwFltSxrR-rm8fUIrfE,40767
 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-1.3.64.dist-info/METADATA,sha256=UBUHpebp0LZs-uSCEwFF0snqM-FoUX8mC2-1HaBx3cY,990
-geney-1.3.64.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
-geney-1.3.64.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.3.64.dist-info/RECORD,,
+geney-1.3.66.dist-info/METADATA,sha256=bl8lWCBcJsbfBPJmkoY8xG0n6G7z7X1C-6jA1bSevCk,990
+geney-1.3.66.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
+geney-1.3.66.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.3.66.dist-info/RECORD,,