geney 1.2.30__py2.py3-none-any.whl → 1.2.32__py2.py3-none-any.whl

geney/oncosplice.py

@@ -415,20 +415,29 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, primary_tran
     return report
 
 
+import asyncio
+async def oncosplice_prototype(mut_id, splicing_threshold=0.5, protein_coding=True, primary_transcript=False, window_length=13, organism='hg38', engine='spliceai'):
+    import sys, os
+    from pathlib import Path
+    needed_path = Path('/tamir2/yoramzar/Projects/Cancer_mut/Utils')
+    needed_file1 = needed_path / 'rest_api_utils.py'
+    needed_file2 = needed_path / 'uniprot_utils.py'
+
+    if sys.platform == 'linux' and (needed_file1.is_file() and os.access(needed_file1, os.X_OK)) and (needed_file2.is_file() and os.access(needed_file2, os.X_OK)):
+        sys.path.append(str(needed_path))
+        import uniprot_utils as uput
 
+    else:
+        raise SystemError("Oncosplice Prototype can only be run on Power with access to the /tamir2/yoramzar/Projects/Cancer_mut/Utils folder.")
 
-def oncosplice_prototype(mut_id, splicing_threshold=0.5, protein_coding=True, primary_transcript=False, window_length=13, organism='hg38', engine='spliceai', domains=None):
-    import requests
-    import threading
+    # Define async functions
+    async def background_request(ensb_id, Uniprot_features=["Topological domain", "Transmembrane", "Domain"]):
+        return uput.retrieve_protein_data_features_subset(uput.ensembl_id2uniprot_id(ensb_id), Uniprot_features)
 
-    def background_request(url, result):
-        return {'data': 'success'}
 
     gene = Gene(mut_id.split(':')[0], organism=organism)
-
-    domains = {}
-    request_thread = threading.Thread(target=background_request, args=(gene.transcript_ids, domains))
-    request_thread.start()
+    # request_thread = threading.Thread(target=background_request, args=(gene.transcript_ids, domains))
+    # request_thread.start()
 
     mutation = get_mutation(mut_id, rev=gene.rev)
 
@@ -441,6 +450,8 @@ def oncosplice_prototype(mut_id, splicing_threshold=0.5, protein_coding=True, pr
             results.append({'transcript_id': transcript.transcript_id})
             continue
 
+        task1 = asyncio.create_task(background_request(transcript.transcript_id))
+
         transcript.generate_pre_mrna()
         transcript.cons_vector = transform_conservation_vector(transcript.cons_vector, window=window_length)
         transcript.generate_mature_mrna().generate_protein(inplace=True, domains=domains)
@@ -451,7 +462,8 @@ def oncosplice_prototype(mut_id, splicing_threshold=0.5, protein_coding=True, pr
 
         missplicing = Missplicing(find_transcript_missplicing(transcript, mutation, engine=engine), threshold=splicing_threshold)
         transcript.pre_mrna += mutation
-
+        result1 = await task1
+        print(result1)
         for i, new_boundaries in enumerate(develop_aberrant_splicing(transcript, missplicing.aberrant_splicing)):
             transcript.acceptors = new_boundaries['acceptors']
             transcript.donors = new_boundaries['donors']

geney/pangolin_utils.py

@@ -73,7 +73,8 @@ def pangolin_predict_probs(true_seq, models):
 
         scores.append(np.mean(score, axis=0))
 
-    splicing_pred = np.array(scores).max(axis=0)
+    # splicing_pred = np.array(scores).max(axis=0)
+    splicing_pred = np.array(scores).mean(axis=0)
     donor_probs = [splicing_pred[i] * donor_dinucleotide[i] for i in range(len(true_seq))]
     acceptor_probs = [splicing_pred[i] * acceptor_dinucleotide[i] for i in range(len(true_seq))]
     # print(acceptor_probs)

geney/seqmat_utils.py

@@ -140,6 +140,29 @@ class SeqMat:
         end_pos = np.where(self.seqmat[self.ROW_INDS] == end)[0][0] + 1
         return self.seqmat[:, start_pos:end_pos]
 
+    def asymmetric_subseq(self, center, left_context, right_context, padding='$'):
+        center_idx = np.where(self.seqmat[self.ROW_INDS] == center)[0][0]
+        start_idx = center_idx - left_context
+        end_idx = center_idx + right_context + 1  # +1 because end index in slicing is exclusive
+        left_padding = max(0, -start_idx)
+        right_padding = max(0, end_idx - len(self.seqmat[self.ROW_INDS]))
+        valid_start_idx = max(0, start_idx)
+        valid_end_idx = min(len(self.seqmat[self.ROW_INDS]), end_idx)
+        valid_subseq = self.seq[valid_start_idx:valid_end_idx]
+        padded_subseq = (padding * left_padding) + valid_subseq + (padding * right_padding)
+        return padded_subseq
+
+    def asymmetric_indices(self, center, left_context, right_context):
+        center_idx = np.where(self.seqmat[self.ROW_INDS] == center)[0][0]
+        start_idx = center_idx - left_context
+        end_idx = center_idx + right_context + 1  # +1 because end index in slicing is exclusive
+        left_padding = max(0, -start_idx)
+        right_padding = max(0, end_idx - len(self.seqmat[self.ROW_INDS]))
+        valid_start_idx = max(0, start_idx)
+        valid_end_idx = min(len(self.seqmat[self.ROW_INDS]), end_idx)
+        valid_subseq = self.indices[valid_start_idx:valid_end_idx]
+        return valid_subseq
+
     def subseq_suffix(self, start):
         start_pos = np.where(self.seqmat[self.ROW_INDS] == start)[0][0]
         return self.seqmat[:, start_pos:]
@@ -166,7 +189,7 @@ class SeqMat:
         # if seq_length % 3 != 0:
         #     temp.seqmat = temp.seqmat[:, :-(seq_length % 3)]  # Trim the extra nucleotides
 
-        if temp.seq[:3] == 'ATG':
+        if temp.seq[1:3] == 'TG':
             for i in range(3, len(temp.seq), 3):
                 codon = temp.seq[i:i + 3]
                 if codon in ['TAA', 'TAG', 'TGA']:
@@ -179,6 +202,11 @@ class SeqMat:
         else:
             return SeqMat('ATG')
 
+    def translate(self, tis_index):
+        from Bio import Seq
+        return Seq(self.orf_seqmat(tis_index).seq).translate()
+
+
 class Gene:
     def __init__(self, gene_name='KRAS', variation=None, organism='hg38'):
         gene_files = list((config[organism]['MRNA_PATH'] / 'protein_coding').glob(f'*_{gene_name}.pkl'))
@@ -419,7 +447,11 @@ class Transcript:
 
     def generate_protein(self, inplace=True, domains=None):
         protein = str(Seq(self.orf.seq).translate()).replace('*', '')
-        cons_vector = self.cons_vector
+        if hasattr(self, 'cons_vector'):
+            cons_vector = self.cons_vector
+        else:
+            cons_vector = np.ones(len(protein))
+
         if domains is not None and np.all(np.isin(domains, np.arange(0, len(protein)))):
             all_indices = np.arange(cons_vector.size)
             mask = ~np.isin(all_indices, domains)

geney/utils.py

@@ -16,10 +16,11 @@ def is_monotonic(A):
 
 
 def available_genes(organism='hg38'):
-    from geney import config_setup
-    annotation_path = config_setup[organism]['MRNA_PATH'] / 'protein_coding'
+    from geney import config
+    annotation_path = config[organism]['MRNA_PATH'] / 'protein_coding'
     return sorted(list(set([m.stem.split('_')[-1] for m in annotation_path.glob('*')])))
 
+
 def contains(a, x):
     """returns true if sorted sequence `a` contains `x`"""
     i = bisect_left(a, x)

{geney-1.2.30.dist-info → geney-1.2.32.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.2.30
+Version: 1.2.32
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.2.30.dist-info → geney-1.2.32.dist-info}/RECORD

@@ -6,20 +6,20 @@ 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_kv2MB_L8LlhX3W2ooXjJ3uDoJ8zX1WeDtZKoBZJkI,1547
-geney/oncosplice.py,sha256=zOOLdY_9tHpwwMQxTS358MCUlhQ6x-XmwlwlIrqwIwc,20902
-geney/pangolin_utils.py,sha256=MP4wGgiw36NAPfwpaXJ5mD4Q-DTbkL3xHcSlYtuZODw,2939
+geney/oncosplice.py,sha256=7wf0_-Gkc_G9HhUXjORHk3buZ66JzVzSFVQ4EZOtUAE,21787
+geney/pangolin_utils.py,sha256=ETTGpuaQgdZ1v8H0NP8sbTEfGWu0VXUFUS7wsURsTc4,2991
 geney/power_utils.py,sha256=MehZFUdkJ2EFUot709yPEDxSkXmH5XevMebX2HD768A,7330
-geney/seqmat_utils.py,sha256=fawiPa4PPhmbx6wPynt8SG6eowZKUZ2yN32r6B8Ba-g,16802
+geney/seqmat_utils.py,sha256=TDWhE5oVTGJceaO6YmE7I_BEWRxWLT74_3rkmY1M0Fs,18368
 geney/spliceai_utils.py,sha256=gIGPC8u3J15A7EQrk2Elho5PbF9MmUUNopGGH-eEV8s,1873
 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
+geney/utils.py,sha256=EsKvBM-Nz2a3_4ZAhF4Dxd4PwT7_6YYKpxEN4LLgg10,2174
 geney/translation_initiation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 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-1.2.30.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,,
+geney-1.2.32.dist-info/METADATA,sha256=aHeSBHWq3b1li4G_CI2ClUEHJc5SfWHowqKrkZbQPGk,948
+geney-1.2.32.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
+geney-1.2.32.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.2.32.dist-info/RECORD,,