geney 1.3.14__py2.py3-none-any.whl → 1.3.16__py2.py3-none-any.whl

geney/splicing_utils.py

@@ -4,6 +4,12 @@ from .Gene import Gene
 from .SeqMats import MutSeqMat
 from collections import defaultdict
 from . import config
+import sqlite3
+import json
+import os
+from typing import Dict, Any
+
+DB_PATH = os.path.join(config['hg38']['splicing_db'], 'mutation_data.db')
 
 def generate_adjacency_list(acceptors, donors, transcript_start, transcript_end, max_distance=50, rev=False):
     # Append the transcript end to donors to allow connection to the end point
@@ -205,9 +211,15 @@ def find_transcript_splicing(transcript, engine: str = 'spliceai') -> Tuple[Dict
     return donor_probs, acceptor_probs
 
 
-def find_transcript_missplicing(mut_id, transcript=None, threshold=0.5, engine='spliceai', organism='hg38'):
+def find_transcript_missplicing(mut_id, transcript=None, threshold=0.5, engine='spliceai', organism='hg38', db=None, force_recompute=False):
     gene = Gene.from_file(mut_id.split(':')[0], organism=organism)
     reference_transcript = gene.transcript(transcript) if transcript is not None else gene.transcript()
+
+    if db is not None:
+        cached_data = db.get_mutation_data(engine, gene.gene_name, mut_id, reference_transcript.transcript_id)
+        if cached_data and not force_recompute:
+            return cached_data
+
     variant_transcript = reference_transcript.clone()
     mutations = [MutSeqMat.from_mutid(m) for m in mut_id.split('|')]
     mutations = [m for m in mutations if m in reference_transcript]
@@ -218,8 +230,12 @@ def find_transcript_missplicing(mut_id, transcript=None, threshold=0.5, engine='
     for mutation in mutations:
         variant_transcript.mutate(mutation, inplace=True)
 
-    return find_transcript_missplicing_seqs(reference_transcript.pre_mrna.get_context(center, 7500), variant_transcript.pre_mrna.get_context(center, 7500), reference_transcript.donors, reference_transcript.acceptors, threshold=threshold, engine=engine)
+    missplicing = find_transcript_missplicing_seqs(reference_transcript.pre_mrna.get_context(center, 7500, padding='N'), variant_transcript.pre_mrna.get_context(center, 7500, padding='N'), reference_transcript.donors, reference_transcript.acceptors, threshold=threshold, engine=engine)
 
+    if db is not None:
+        db.store_mutation_data(engine, gene.gene_name, mut_id, reference_transcript.transcript_id, missplicing.missplicing)
+
+    return missplicing
 
     # from functools import reduce
     # ref = transcript.pre_mrna
@@ -352,7 +368,7 @@ def find_transcript_missplicing_seqs(ref_seq, var_seq, donors, acceptors, thresh
     return Missplicing(temp, threshold=threshold)
 
 
-def process_pairwise_epistasis(mids, engine='pangolin', fprint=False):
+def process_pairwise_epistasis(mids, engine='pangolin', fprint=False, db=None):
     results = []
     for mid in mids:
         m1, m2 = mid.split('|')
@@ -360,9 +376,9 @@ def process_pairwise_epistasis(mids, engine='pangolin', fprint=False):
         # 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)
+        missplicing1 = Missplicing(find_transcript_missplicing(m1, engine=engine, db=db), threshold=0.25)
+        missplicing2 = Missplicing(find_transcript_missplicing(m2, engine=engine, db=db), threshold=0.25)
+        missplicing_both = Missplicing(find_transcript_missplicing(mid, engine=engine, db=db), threshold=0.25)
 
         if fprint:
             print(missplicing1)
@@ -586,85 +602,162 @@ def benchmark_splicing(gene, organism='hg38', engine='spliceai'):
     return len(correct_donor_preds) / num_introns, len(correct_acceptor_preds) / num_introns, len(transcript.introns)
 
 
-import sqlite3
-import json
-import os
+class SplicingDatabase:
+    """
+    A class to handle interactions with the splicing SQLite database.
+    Each instance maintains its own connection, suitable for multi-threaded environments.
+    """
+
+    def __init__(self, db_path: str):
+        """
+        Initialize the SplicingDatabase with a connection to the SQLite database.
+
+        Args:
+            db_path (str): Path to the SQLite database file.
+        """
+        self.db_path = db_path
+        self.conn = sqlite3.connect(self.db_path, isolation_level=None, check_same_thread=False)  # Disable thread check
+        self.cursor = self.conn.cursor()
+        self._initialize_table()
+
+    def _initialize_table(self):
+        """
+        Create the mutations table if it doesn't exist.
+        """
+        self.cursor.execute('''
+            CREATE TABLE IF NOT EXISTS mutations (
+                engine TEXT,
+                gene TEXT,
+                mut_id TEXT,
+                transcript_id TEXT,
+                data TEXT,
+                PRIMARY KEY (engine, gene, mut_id, transcript_id)
+            )
+        ''')
+
+    def get_mutation_data(self, engine: str, gene: str, mut_id: str, transcript_id: str) -> Dict[str, Any]:
+        """
+        Retrieve mutation data from the database.
+
+        Args:
+            engine (str): Name of the tool used for computation.
+            gene (str): Gene name or identifier.
+            mut_id (str): A unique identifier for the mutation.
+            transcript_id (str): ID for the transcript.
+
+        Returns:
+            Dict[str, Any]: The mutation data if found, else None.
+        """
+        self.cursor.execute('''
+            SELECT data FROM mutations 
+            WHERE engine=? AND gene=? AND mut_id=? AND transcript_id=?
+        ''', (engine, gene, mut_id, transcript_id))
+        row = self.cursor.fetchone()
+        if row:
+            return json.loads(row[0])
+        return None
+
+    def store_mutation_data(self, engine: str, gene: str, mut_id: str, transcript_id: str, data: Dict[str, Any]):
+        """
+        Store mutation data in the database.
+
+        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.
+            transcript_id (str): ID for the transcript.
+            data (Dict[str, Any]): The mutation data to store.
+        """
+        # Convert NumPy types to native Python types
+        data_native = convert_numpy_to_native(data)
+        data_json = json.dumps(data_native)
+        self.cursor.execute('''
+            REPLACE INTO mutations (engine, gene, mut_id, transcript_id, data) 
+            VALUES (?, ?, ?, ?, ?)
+        ''', (engine, gene, mut_id, transcript_id, data_json))
+
+    def close(self):
+        """
+        Close the database connection.
+        """
+        self.conn.close()
+
+
 
 # Global connection and cursor (adjust to your architecture)
 # Ideally, initialize this once in your application startup code.
-DB_PATH = os.path.join(config['hg38']['splicing_db'], 'mutation_data.db')
-conn = sqlite3.connect(DB_PATH, isolation_level=None)  # autocommit mode
-cursor = conn.cursor()
-
-# Create table once at startup, not in the function
-cursor.execute('''
-CREATE TABLE IF NOT EXISTS mutations (
-    engine TEXT,
-    gene TEXT,
-    mut_id TEXT,
-    transcript_id TEXT,
-    data TEXT,
-    PRIMARY KEY (engine, gene, mut_id, transcript_id)
-)''')
-
-
-def get_splicing(engine, gene, mut_id, transcript_id, force_recompute=False):
-    """
-    Retrieve computed splicing data for a given mutation from a database,
-    Args:
-        engine (str): Name of the tool used for computation.
-        gene (str): Gene name or identifier.
-        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 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(engine, gene, mut_id, transcript_id, splicing):
-    data_json = json.dumps(convert_numpy_to_native(splicing))
-    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(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:
-        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 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(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 (engine, gene, mut_id, transcript_id, data) VALUES (?, ?, ?, ?, ?)',
-                   (engine, gene, mut_id, transcript_id, data_json))
-    return computed_data
+# conn = sqlite3.connect(DB_PATH, isolation_level=None)  # autocommit mode
+# cursor = conn.cursor()
+#
+# # Create table once at startup, not in the function
+# cursor.execute('''
+# CREATE TABLE IF NOT EXISTS mutations (
+#     engine TEXT,
+#     gene TEXT,
+#     mut_id TEXT,
+#     transcript_id TEXT,
+#     data TEXT,
+#     PRIMARY KEY (engine, gene, mut_id, transcript_id)
+# )''')
+# #
+#
+# def get_splicing(engine, gene, mut_id, transcript_id, force_recompute=False):
+#     """
+#     Retrieve computed splicing data for a given mutation from a database,
+#     Args:
+#         engine (str): Name of the tool used for computation.
+#         gene (str): Gene name or identifier.
+#         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 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(engine, gene, mut_id, transcript_id, splicing):
+#     data_json = json.dumps(convert_numpy_to_native(splicing))
+#     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(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:
+#         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 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(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 (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-1.3.14.dist-info → geney-1.3.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.3.14
+Version: 1.3.16
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.3.14.dist-info → geney-1.3.16.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=OLes_xEoD5RZvcxyc8kwlUlWpTbJgl9AgA2PFRyOtdE,32286
+geney/splicing_utils.py,sha256=VLSUJ1SFsnz9-Tt3Ywqp786WeVSJY7-VmwtdTgT2cXk,35828
 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-1.3.14.dist-info/METADATA,sha256=fdwqYA-nm1pUEIeZIECpRZ0oEjPyWKIGuNSIuwy3_v4,971
-geney-1.3.14.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
-geney-1.3.14.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.3.14.dist-info/RECORD,,
+geney-1.3.16.dist-info/METADATA,sha256=UFbVToYRg7aFtUlIwXnsQPqP78-eEpQ5AwGKys4feqQ,971
+geney-1.3.16.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
+geney-1.3.16.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.3.16.dist-info/RECORD,,