geney 1.3.27__py2.py3-none-any.whl → 1.3.29__py2.py3-none-any.whl

geney/splicing_utils.py

@@ -8,6 +8,9 @@ import sqlite3
 import json
 import os
 from typing import Dict, Any
+from typing import Dict, Any
+from redis import Redis
+
 
 DB_PATH = os.path.join(config['hg38']['splicing_db'], 'mutation_data.db')
 
@@ -382,7 +385,7 @@ def process_pairwise_epistasis(mids, engine='pangolin', fprint=False, db=None):
             print(missplicing_both)
 
         max_delta = 0
-        flag = {'mut_id': mid, 'corrective': 0, 'cummulative': 0}
+        flag = {'mut_id': mid, 'corrective': 0, 'cumulative': 0}
         cummulative_deltas, corrective_deltas = [], []
         ms1, ms2, msb = [], [], []
         increased_canonical_splicing = False
@@ -409,6 +412,7 @@ def process_pairwise_epistasis(mids, engine='pangolin', fprint=False, db=None):
                 delta2 = m2.get(k, {'delta': 0})['delta'] # max(-1, min(10, m2.get(k, {'delta': 0})['delta'] / ref_val))
                 deltab = mb.get(k, {'delta': 0})['delta'] # max(-1, min(10, mb.get(k, {'delta': 0})['delta'] / ref_val))
 
+                print(event, k, delta1, delta2, deltab)
                 ms1.append(delta1)
                 ms2.append(delta2)
                 msb.append(deltab)
@@ -423,10 +427,10 @@ def process_pairwise_epistasis(mids, engine='pangolin', fprint=False, db=None):
                     corrective_deltas.append(max((deltab - delta1, deltab - delta2), key=abs))
 
                 if (abs(deltab) > 0.25) and (
-                        (abs(delta1) < 0.25 and (abs(delta1 - deltab) > 0.25)) or
+                        (abs(delta1) < 0.25 and (abs(delta1 - deltab) > 0.25)) and
                         (abs(delta2) < 0.25 and (abs(delta2 - deltab) > 0.25))
                 ):
-                    flag['cummulative'] += 1
+                    flag['cumulative'] += 1
                     cummulative_deltas.append(max((deltab - delta1, deltab - delta2), key=abs))
 
                 if (0.4 <= ref_val <= 0.75) and (
@@ -600,6 +604,76 @@ def benchmark_splicing(gene, organism='hg38', engine='spliceai'):
     return len(correct_donor_preds) / num_introns, len(correct_acceptor_preds) / num_introns, len(transcript.introns)
 
 
+class SplicingDatabaseRedis:
+    """
+    A class to handle interactions with Redis for storing mutation data.
+    Designed for concurrency and parallel reads/writes across multiple Dask workers or threads.
+    """
+
+    def __init__(self, host='localhost', port=6379, db=0):
+        """
+        Initialize the Redis-based SplicingDatabase.
+
+        Args:
+            host (str): Redis host.
+            port (int): Redis port.
+            db (int): Redis database index.
+        """
+        # Create a Redis client. By default, this client is thread-safe and uses a connection pool.
+        self.client = Redis(host=host, port=port, db=db, decode_responses=True)
+
+    def _make_key(self, engine: str, gene: str, mut_id: str, transcript_id: str) -> str:
+        """
+        Construct a unique key for identifying a mutation record in Redis.
+        """
+        return f"{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 Redis.
+
+        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.
+        """
+        key = self._make_key(engine, gene, mut_id, transcript_id)
+        data_json = self.client.get(key)
+        if data_json:
+            return json.loads(data_json)
+        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 Redis.
+
+        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.
+            data (Dict[str, Any]): The mutation data to store.
+        """
+        data_native = convert_numpy_to_native(data)
+        data_json = json.dumps(data_native)
+        key = self._make_key(engine, gene, mut_id, transcript_id)
+        self.client.set(key, data_json)
+
+    def close(self):
+        """
+        Close the Redis connection.
+        Since Redis uses a connection pool by default, closing isn't strictly necessary.
+        We provide this method for API consistency.
+        """
+        # Redis client connections are managed by the pool, no explicit close required.
+        pass
+
+
+
 class SplicingDatabase:
     """
     A class to handle interactions with the splicing SQLite database.
@@ -622,6 +696,8 @@ class SplicingDatabase:
         """
         Create the mutations table if it doesn't exist.
         """
+        self.cursor.execute('PRAGMA journal_mode=WAL;')  # Enable WAL mode
+        self.cursor.execute('PRAGMA synchronous=NORMAL;')  # Set synchronous to NORMAL for better performance
         self.cursor.execute('''
             CREATE TABLE IF NOT EXISTS mutations (
                 engine TEXT,

{geney-1.3.27.dist-info → geney-1.3.29.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.3.27
+Version: 1.3.29
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn
@@ -12,7 +12,7 @@ Classifier: License :: Free for non-commercial use
 Classifier: Operating System :: POSIX :: Linux
 Classifier: Operating System :: MacOS
 Classifier: Programming Language :: Python :: 3.9
-Requires-Python: >3.9
+Requires-Python: >3.10
 Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: networkx
@@ -30,4 +30,5 @@ Requires-Dist: gffutils
 Requires-Dist: pyfastx
 Requires-Dist: tensorflow
 Requires-Dist: keras
+Requires-Dist: redis
 

{geney-1.3.27.dist-info → geney-1.3.29.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=srjvWJi_XqizOiXAVMCjszZ92kK46_YIC7iYDqCyebA,35563
+geney/splicing_utils.py,sha256=elu5KtkcNGTWhviimIRt0DRWNcjwZrshDphM5XFPImA,38485
 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-1.3.27.dist-info/METADATA,sha256=Z9E9IeMrdmc9FkQpS-9AcD0Evm4EriRFB7x2L8R34rc,968
-geney-1.3.27.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
-geney-1.3.27.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.3.27.dist-info/RECORD,,
+geney-1.3.29.dist-info/METADATA,sha256=Chxu6iycgZPwhUI1X7-VrCdFoZC3TQqF3MMnX6SS9Ps,990
+geney-1.3.29.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
+geney-1.3.29.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.3.29.dist-info/RECORD,,