geney 1.3.10__py2.py3-none-any.whl → 1.3.12__py2.py3-none-any.whl

geney/splicing_utils.py

@@ -356,9 +356,13 @@ def process_pairwise_epistasis(mids, engine='pangolin', fprint=False):
     results = []
     for mid in mids:
         m1, m2 = mid.split('|')
-        missplicing1 = find_transcript_missplicing(m1, threshold=0.25, engine=engine)
-        missplicing2 = find_transcript_missplicing(m2, threshold=0.25, engine=engine)
-        missplicing_both = find_transcript_missplicing(mid, threshold=0.25, engine=engine)
+        # missplicing1 = find_transcript_missplicing(m1, threshold=0.25, engine=engine)
+        # missplicing2 = find_transcript_missplicing(m2, threshold=0.25, engine=engine)
+        # missplicing_both = find_transcript_missplicing(mid, threshold=0.25, engine=engine)
+
+        missplicing1 = Missplicing(get_or_compute_splicing(m1, engine=engine), threshold=0.25)
+        missplicing2 = Missplicing(get_or_compute_splicing(m2, engine=engine), threshold=0.25)
+        missplicing_both = Missplicing(get_or_compute_splicing(mid, engine=engine), threshold=0.25)
 
         if fprint:
             print(missplicing1)
@@ -457,8 +461,9 @@ class Missplicing:
         self.threshold = threshold
 
     def __str__(self):
+        import pprint
         """String representation displays the filtered splicing events passing the threshold."""
-        return str(self.significant_events)
+        return pprint.pprint(self.aberrant_splicing)
 
     def __bool__(self):
         """
@@ -528,6 +533,7 @@ class Missplicing:
             return splicing_dict
         return None
 
+    @property
     def max_delta(self):
         """
         Returns the maximum absolute delta found in all events.
@@ -591,69 +597,72 @@ cursor = conn.cursor()
 # Create table once at startup, not in the function
 cursor.execute('''
 CREATE TABLE IF NOT EXISTS mutations (
-    tool TEXT,
+    engine TEXT,
     gene TEXT,
-    mutation_id TEXT,
+    mut_id TEXT,
     transcript_id TEXT,
     data TEXT,
-    PRIMARY KEY (tool, gene, mutation_id, transcript_id)
+    PRIMARY KEY (engine, gene, mut_id, transcript_id)
 )''')
 
 
-def get_splicing(tool, gene, mutation_id, transcript_id, force_recompute=False):
+def get_splicing(engine, gene, mut_id, transcript_id, force_recompute=False):
     """
     Retrieve computed splicing data for a given mutation from a database,
     Args:
-        tool (str): Name of the tool used for computation.
+        engine (str): Name of the tool used for computation.
         gene (str): Gene name or identifier.
-        mutation_id (str): A unique identifier for the mutation.
+        mut_id (str): A unique identifier for the mutation.
         transcript_id (str): ID for the transcript.
         force_recompute (bool): If True, ignore cached value and recompute.
     Returns:
         dict: The splicing data.
     """
     # Lookup in the database
-    cursor.execute('SELECT data FROM mutations WHERE tool=? AND gene=? AND mutation_id=? AND transcript_id=?',
-                   (tool, gene, mutation_id, transcript_id))
+    cursor.execute('SELECT data FROM mutations WHERE engine=? AND gene=? AND mut_id=? AND transcript_id=?',
+                   (engine, gene, mut_id, transcript_id))
     row = cursor.fetchone()
     # If found and no force recompute, return cached data
     if row:
         return json.loads(row[0])
     return None
 
-def save_splicing(tool, gene, mutation_id, transcript_id, splicing):
+def save_splicing(engine, gene, mut_id, transcript_id, splicing):
     data_json = json.dumps(convert_numpy_to_native(splicing))
-    cursor.execute('REPLACE INTO mutations (tool, gene, mutation_id, transcript_id, data) VALUES (?, ?, ?, ?, ?)',
-                   (tool, gene, mutation_id, transcript_id, data_json))
+    cursor.execute('REPLACE INTO mutations (engine, gene, mut_id, transcript_id, data) VALUES (?, ?, ?, ?, ?)',
+                   (engine, gene, mut_id, transcript_id, data_json))
     return None
 
-def get_or_compute_splicing(tool, gene, mutation_id, transcript_id, force_recompute=False):
+def get_or_compute_splicing(mut_id, transcript_id=None, engine='spliceai', force_recompute=False):
     """
     Retrieve computed splicing data for a given mutation from a database,
     or compute and store it if not found or if force_recompute is True.
     Args:
-        tool (str): Name of the tool used for computation.
-        gene (str): Gene name or identifier.
-        mutation_id (str): A unique identifier for the mutation.
+        engine (str): Name of the tool used for computation.
+        mut_id (str): A unique identifier for the mutation.
         transcript_id (str): ID for the transcript.
         force_recompute (bool): If True, ignore cached value and recompute.
     Returns:
         dict: The computed splicing data.
     """
+    gene = mut_id.split(':')[0]
+    if transcript_id is None:
+        transcript_id = Gene.from_file(gene).transcript().transcript_id
+
     # Lookup in the database
-    cursor.execute('SELECT data FROM mutations WHERE tool=? AND gene=? AND mutation_id=? AND transcript_id=?',
-                   (tool, gene, mutation_id, transcript_id))
+    cursor.execute('SELECT data FROM mutations WHERE engine=? AND gene=? AND mut_id=? AND transcript_id=?',
+                   (engine, gene, mut_id, transcript_id))
     row = cursor.fetchone()
     # If found and no force recompute, return cached data
     if row and not force_recompute:
         return json.loads(row[0])
     # Otherwise, compute the data
-    computed_data = convert_numpy_to_native(find_transcript_missplicing(mutation_id, transcript=transcript_id, engine=tool).missplicing) # Replace with your actual function
+    computed_data = convert_numpy_to_native(find_transcript_missplicing(mut_id, transcript=transcript_id, engine=engine).missplicing) # Replace with your actual function
     # Store computed data in DB
     data_json = json.dumps(computed_data)
-    cursor.execute('REPLACE INTO mutations (tool, gene, mutation_id, transcript_id, data) VALUES (?, ?, ?, ?, ?)',
-                   (tool, gene, mutation_id, transcript_id, data_json))
-    return Missplicing(computed_data)
+    cursor.execute('REPLACE INTO mutations (engine, gene, mut_id, transcript_id, data) VALUES (?, ?, ?, ?, ?)',
+                   (engine, gene, mut_id, transcript_id, data_json))
+    return computed_data
 
 
 def convert_numpy_to_native(obj):

{geney-1.3.10.dist-info → geney-1.3.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.3.10
+Version: 1.3.12
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.3.10.dist-info → geney-1.3.12.dist-info}/RECORD

@@ -16,7 +16,7 @@ geney/pangolin_utils.py,sha256=i5j5vEMCWOTIa1mRP2377BAhlUFZjHBzTQBips4lA_4,2934
 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=DXX-q9G0IcmPx-gI6h3b6P8x4CTPVIGVM0HXyPz4r8g,31848
+geney/splicing_utils.py,sha256=ZLuUUeIX_Qg8hD6fGRqAbIphzfsWnxXu6wds3ZIwQdY,32229
 geney/survival_utils.py,sha256=KnAzEviMuXh6SnVXId9PgsFLSbgkduTvYoIthxN7FPA,6886
 geney/tcga_utils.py,sha256=D_BNHm-D_K408dlcJm3hzH2c6QNFjQsKvUcOPiQRk7g,17612
 geney/tis_utils.py,sha256=2makfGfVlDFVIbxzXE85AY9jmAjcNmxyIAxjvkRA5LY,7396
@@ -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-1.3.10.dist-info/METADATA,sha256=mNFs019vfrWS0iciRjkA2CcLgycPDaEuH2utIrerZdA,971
-geney-1.3.10.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
-geney-1.3.10.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.3.10.dist-info/RECORD,,
+geney-1.3.12.dist-info/METADATA,sha256=QZlovXzCoFEcElIZNHvXX2MBnbjzdUGtKcpcftakqqk,971
+geney-1.3.12.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
+geney-1.3.12.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.3.12.dist-info/RECORD,,