geney 1.2.59__py2.py3-none-any.whl → 1.2.61__py2.py3-none-any.whl

geney/pangolin_utils.py

@@ -5,7 +5,7 @@ from pangolin.model import *
 import numpy as np
 import sys
 
-pang_model_nums = [0, 1, 2, 3, 4, 5, 6]
+pang_model_nums = [0, 1, 2, 3, 4, 5, 6, 7]
 pang_models = []
 
 device = torch.device('cpu')
@@ -52,6 +52,7 @@ def pangolin_predict_probs(true_seq, models, just_ss=False):
         model_nums = [0, 2, 4, 6]
     else:
         model_nums = [0, 1, 2, 3, 4, 5, 6, 7]
+
     INDEX_MAP = {0: 1, 1: 2, 2: 4, 3: 5, 4: 7, 5: 8, 6: 10, 7: 11}
 
     seq = true_seq

geney/seqmat_utils.py

@@ -3,7 +3,7 @@ import numpy as np
 import copy
 from Bio.Seq import Seq
 
-NT_ALPHABET = ['A', 'T', 'G', 'C']
+NT_ALPHABET = ['A', 'T', 'G', 'C', 'N']
 
 
 '''
@@ -119,7 +119,6 @@ class SeqMat:
 
     @property
     def seq(self):
-
         return ''.join(self.vectorized_map_v2c(self.seqmat[self.ROW_SEQ, :])).replace('-', '')
 
     @property
@@ -242,6 +241,14 @@ class Gene:
         key = list(self.transcripts.keys())[index]
         return Transcript(self.transcripts[key])
 
+    def splice_sites(self):
+        from collections import Counter
+        acceptors, donors = [], []
+        for transcript in self.transcripts.values():
+            acceptors.extend(transcript['acceptors'])
+            donors.extend(transcript['donors'])
+        return Counter(acceptors), Counter(donors)
+
     def transcript(self, tid=None):
         if tid is None:
             tid = self.primary_transcript

geney/splicing_utils.py

@@ -173,7 +173,7 @@ def find_transcript_missplicing(transcript, mutations, context=5000, window=2500
     ref_seq = 'N'*ref_start_pad + ref.seq + 'N'*ref_end_pad
     var_seq = 'N'*var_start_pad + var.seq + 'N'*var_end_pad
 
-    # print(ref_seq)
+    print(len(ref_seq))
 
     if engine == 'spliceai':
         from .spliceai_utils import sai_predict_probs, sai_models
@@ -358,3 +358,40 @@ def missplicing(mut_id, splicing_threshold=0.5, primary_transcript=True, organis
 
     return results
 
+
+import sqlite3
+import json
+
+def get_or_compute_splicing(tool, gene, mutation_id, transcript_id, force_recompute=False):
+    conn = sqlite3.connect(os.path.join(tool_parameters['splicing_db'], 'mutation_data.db'))
+    cursor = conn.cursor()
+    # Create table if it doesn't exist
+    cursor.execute('''CREATE TABLE IF NOT EXISTS mutations (
+                         tool TEXT,
+                         gene TEXT,
+                         mutation_id TEXT, 
+                         transcript_id TEXT, 
+                         data TEXT,
+                         PRIMARY KEY (tool, gene, mutation_id, transcript_id)
+                      )''')
+
+    # Look up entry
+    cursor.execute('SELECT data FROM mutations WHERE tool=? AND gene=? AND mutation_id=? AND transcript_id=?',
+                   (tool, gene, mutation_id, transcript_id))
+    row = cursor.fetchone()
+
+    # If entry is found and force_recompute is False, return data
+    if row and not force_recompute:
+        return json.loads(row[0])
+
+    # Otherwise, compute the dictionary
+    computed_data = find_transcript_missplicing(tool, mutation_id, transcript_id)  # Replace with actual function
+
+    # Store in the database
+    data_json = json.dumps(computed_data)
+    cursor.execute('REPLACE INTO mutations (tool, mutation_id, transcript_id, data) VALUES (?, ?, ?, ?)',
+                   (tool, mutation_id, transcript_id, data_json))
+    conn.commit()
+    conn.close()
+
+    return computed_data

{geney-1.2.59.dist-info → geney-1.2.61.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.2.59
+Version: 1.2.61
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.2.59.dist-info → geney-1.2.61.dist-info}/RECORD

@@ -7,11 +7,11 @@ 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=eWgY2Lcj894UBFnIVhbxiVz5oqASHg-Ot1wFbjlJbI8,21857
-geney/pangolin_utils.py,sha256=HvXfdLhHWTDXNmYtc8K3p64iTvDtsBq6-Jml5tpg7JI,2930
+geney/pangolin_utils.py,sha256=i5j5vEMCWOTIa1mRP2377BAhlUFZjHBzTQBips4lA_4,2934
 geney/power_utils.py,sha256=MehZFUdkJ2EFUot709yPEDxSkXmH5XevMebX2HD768A,7330
-geney/seqmat_utils.py,sha256=2cRXT_Ox4IdzCM8x3H2HexxFZzjo5WHs0HZiUQv8fBM,18347
+geney/seqmat_utils.py,sha256=f-4dtufdKHc52jf_xZqbwBu-DXCa2Tl0Wsigguus6-E,18661
 geney/spliceai_utils.py,sha256=PFIhTK8Ihrj-cv5tgRN0UFPYEmC4uxtqXSP9bBLnZRM,3077
-geney/splicing_utils.py,sha256=34xdarFpTHsHZkhi7VrHby9DaIBZ2xCLqPMrTmasEgE,16860
+geney/splicing_utils.py,sha256=H4X_J8tlZwJkidL5QVvSXFoQL3DsyY6QhOyHhczSLuQ,18324
 geney/survival_utils.py,sha256=KnAzEviMuXh6SnVXId9PgsFLSbgkduTvYoIthxN7FPA,6886
 geney/tcga_utils.py,sha256=D_BNHm-D_K408dlcJm3hzH2c6QNFjQsKvUcOPiQRk7g,17612
 geney/tis_utils.py,sha256=2makfGfVlDFVIbxzXE85AY9jmAjcNmxyIAxjvkRA5LY,7396
@@ -20,7 +20,7 @@ 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-1.2.59.dist-info/METADATA,sha256=fiwDiB2jrpokLcoAhC6YQ2OQyY6RBdJSjhQx_T99lXo,948
-geney-1.2.59.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
-geney-1.2.59.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.2.59.dist-info/RECORD,,
+geney-1.2.61.dist-info/METADATA,sha256=QaodEhA1cBBwdnPunohDs6niKp2PEHToPX-Cdudd6oY,948
+geney-1.2.61.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
+geney-1.2.61.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.2.61.dist-info/RECORD,,