geney 1.3.9__py2.py3-none-any.whl → 1.3.11__py2.py3-none-any.whl

geney/splicing_utils.py

@@ -1,4 +1,5 @@
 import numpy as np
+import pandas as pd
 from .Gene import Gene
 from .SeqMats import MutSeqMat
 from collections import defaultdict
@@ -300,7 +301,7 @@ def find_transcript_missplicing(mut_id, transcript=None, threshold=0.5, engine='
     # missplicing = {'missed_acceptors': dap, 'missed_donors': ddp, 'discovered_acceptors': iap, 'discovered_donors': idp}
     # missplicing = {outk: {float(k): v for k, v in outv.items()} for outk, outv in missplicing.items()}
     # temp =  {outk: {int(k) if k.is_integer() else k: v for k, v in outv.items()} for outk, outv in missplicing.items()}
-    return temp
+    # return temp
 
 
 def find_transcript_missplicing_seqs(ref_seq, var_seq, donors, acceptors, threshold=0.5, engine='spliceai'):
@@ -351,6 +352,91 @@ 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):
+    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)
+
+        if fprint:
+            print(missplicing1)
+            print(missplicing2)
+            print(missplicing_both)
+
+        max_delta = 0
+        flag = {'mut_id': mid, 'corrective': 0, 'cummulative': 0}
+        cummulative_deltas, corrective_deltas = [], []
+        ms1, ms2, msb = [], [], []
+        increased_canonical_splicing = False
+        events = ['missed_acceptors', 'missed_donors', 'discovered_acceptors', 'discovered_donors']
+        for event in events:
+            m1, m2, mb = missplicing1[event], missplicing2[event], missplicing_both[event]
+
+            # Get all keys from the three dicts
+            keys = set(m1.keys()) | set(m2.keys()) | set(mb.keys())
+
+            for k in keys:
+                # Determine reference value
+                ref_val = (
+                        m1.get(k, {}).get('reference') or
+                        m2.get(k, {}).get('reference') or
+                        mb.get(k, {}).get('reference')
+                )
+
+
+                # Compute deltas
+                delta1 = m1.get(k, {'delta': 0})['delta'] # max(-1, min(10, m1.get(k, {'delta': 0})['delta'] / ref_val))
+                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))
+
+                ms1.append(delta1)
+                ms2.append(delta2)
+                msb.append(deltab)
+
+                # Corrective condition
+                # if ((abs(delta1) * 0.5 > abs(deltab) or abs(delta2) * 0.5 > abs(deltab)) and abs(deltab) == 0):
+                if (abs(deltab) < 0.25) and (
+                        (abs(delta1) > 0.25 and (abs(delta1 - deltab) > 0.25)) or
+                        (abs(delta2) > 0.25 and (abs(delta2 - deltab) > 0.25))
+                ):
+                    flag['corrective'] += 1
+                    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(delta2) < 0.25 and (abs(delta2 - deltab) > 0.25))
+                ):
+                    flag['cummulative'] += 1
+                    cummulative_deltas.append(max((deltab - delta1, deltab - delta2), key=abs))
+
+                if ((0.25 <= ref_val) <= 0.75) and (
+                        ((delta1 > 0.25 or delta2 > 0.25) and deltab < 0.25) or
+                        (delta1 < 0.25 and delta2 < 0.25 and deltab > 0.25)
+                ) and (
+                        abs(delta1 - deltab) > 0.25 or
+                        abs(delta2 - deltab) > 0.25
+                ):
+                    increased_canonical_splicing = True
+
+        vals = cummulative_deltas + corrective_deltas
+        flag['max_delta'] = max(vals, key=abs) if vals else 0
+        flag['ms1'] = max(ms1, key=abs)
+        flag['ms2'] = max(ms2, key=abs)
+        flag['msb'] = max(msb, key=abs)
+        flag['increased_canonical_splicing'] = increased_canonical_splicing
+
+        result_df = pd.Series(flag).to_frame().T
+        results.append(result_df)
+
+    if len(results) == 0:
+        return None
+
+    return pd.concat(results)
+
+
+
 class Missplicing:
     def __init__(self, splicing_dict, threshold=0.5):
         """
@@ -390,6 +476,9 @@ class Missplicing:
             for d in details.values():
                 yield d['delta']
 
+    def __getitem__(self, key):
+        return self.missplicing[key]
+
     @property
     def aberrant_splicing(self):
         """
@@ -502,45 +591,83 @@ 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_or_compute_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,
-    or compute and store it if not found or if force_recompute is True.
-
     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 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 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 = find_transcript_missplicing(mutation_id, transcript_id=transcript_id, engine=tool)  # 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))
+    cursor.execute('REPLACE INTO mutations (engine, gene, mut_id, transcript_id, data) VALUES (?, ?, ?, ?, ?)',
+                   (engine, gene, mut_id, transcript_id, data_json))
+    return computed_data
 
-    return computed_data
+
+def convert_numpy_to_native(obj):
+    """
+    Recursively convert NumPy data types to native Python types.
+    """
+    if isinstance(obj, dict):
+        return {key: convert_numpy_to_native(value) for key, value in obj.items()}
+    elif isinstance(obj, list):
+        return [convert_numpy_to_native(item) for item in obj]
+    elif isinstance(obj, np.generic):  # Check for NumPy scalar types
+        return round(obj.item(), 3)
+    else:
+        return round(obj, 3)

{geney-1.3.9.dist-info → geney-1.3.11.dist-info}/METADATA

@@ -1,12 +1,11 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.3.9
+Version: 1.3.11
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn
 Author-email: nicolasalynn@gmail.com
 License: Free for non-commercial use
-Platform: UNKNOWN
 Classifier: Development Status :: 1 - Planning
 Classifier: Intended Audience :: Science/Research
 Classifier: License :: Free for non-commercial use
@@ -20,9 +19,9 @@ Requires-Dist: networkx
 Requires-Dist: viennarna
 Requires-Dist: tqdm
 Requires-Dist: spliceai
-Requires-Dist: biopython==1.81
-Requires-Dist: gtfparse==1.3.0
-Requires-Dist: sh==2.0.6
+Requires-Dist: biopython ==1.81
+Requires-Dist: gtfparse ==1.3.0
+Requires-Dist: sh ==2.0.6
 Requires-Dist: torch
 Requires-Dist: lifelines
 Requires-Dist: notebook
@@ -32,5 +31,3 @@ Requires-Dist: pyfastx
 Requires-Dist: tensorflow
 Requires-Dist: keras
 
-UNKNOWN
-

{geney-1.3.9.dist-info → geney-1.3.11.dist-info}/RECORD

@@ -4,6 +4,7 @@ geney/SeqMats.py,sha256=jkXmXAs0OpnFeyCfiJcKKpHHSi9JpKgiOIwsu63e1CQ,18557
 geney/Transcript.py,sha256=eRZXVVxDVBbv0l385bnAOBFRBSzBwppXcbBq8KXkwlo,14443
 geney/__init__.py,sha256=eBdDl42N6UhcYeZDjOnv199Z88fI5_8Y6xW8447OKXM,755
 geney/_mutation_utils.py,sha256=dHssUsnii_mf-wuRoMmF13UlD7k3ml_VwQMItTYnXpU,1132
+geney/allele_linkage.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 geney/config_setup.py,sha256=nblcGU3HIt8YjdrAoGfbEVKRxwJKv0PikJ5-7AL6axQ,723
 geney/data_setup.py,sha256=2RHmuvcGUQbEglXQEZr0C2QPDTQYRZOEm0EcmyfQJgU,12229
 geney/graphic_utils.py,sha256=oMsBpB9YeEn96gGpKh4MmtagJffWZbk-xPrIwHvkFhA,11016
@@ -15,7 +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=YDhYtns6pVHmOfk4Z1AC-acA1kKAqKZmJ-P2EZS946k,26378
+geney/splicing_utils.py,sha256=Bj5YV-LHs684afjriep7N2QaRAAKdidFS-adihfDzfI,31887
 geney/survival_utils.py,sha256=KnAzEviMuXh6SnVXId9PgsFLSbgkduTvYoIthxN7FPA,6886
 geney/tcga_utils.py,sha256=D_BNHm-D_K408dlcJm3hzH2c6QNFjQsKvUcOPiQRk7g,17612
 geney/tis_utils.py,sha256=2makfGfVlDFVIbxzXE85AY9jmAjcNmxyIAxjvkRA5LY,7396
@@ -24,7 +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-1.3.9.dist-info/METADATA,sha256=tkuruBdfjmOTkAz6lM3xZ_nAEXm5Vh4wpaP5FihlTvk,994
-geney-1.3.9.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
-geney-1.3.9.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.3.9.dist-info/RECORD,,
+geney-1.3.11.dist-info/METADATA,sha256=Por9VSaGxOGXy61knApS-3BefXSrh8hhQQQ0ULGQn2I,971
+geney-1.3.11.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
+geney-1.3.11.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.3.11.dist-info/RECORD,,

{geney-1.3.9.dist-info → geney-1.3.11.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.44.0)
+Generator: setuptools (75.1.0)
 Root-Is-Purelib: true
 Tag: py2-none-any
 Tag: py3-none-any