geney 1.3.1__py2.py3-none-any.whl → 1.3.3__py2.py3-none-any.whl

geney/oncosplice.py

@@ -4,7 +4,7 @@ import hashlib
 from tqdm import tqdm
 import pandas as pd
 import numpy as np
-from seqmats import SeqMat, MutSeqMat
+from .SeqMats import SeqMat, MutSeqMat
 from .splicing_utils import find_transcript_missplicing_seqs, develop_aberrant_splicing
 from .tis_utils import find_tis
 

geney/splicing_utils.py

@@ -1,6 +1,6 @@
 import numpy as np
-from .mutation_utils import get_mutation
-from .seqmat_utils import Gene
+from ._mutation_utils import get_mutation
+from .Gene import Gene
 
 from collections import defaultdict
 
@@ -176,6 +176,7 @@ def find_transcript_missplicing(transcript, mutations, context=5000, window=2500
     center_index = var.rel_pos(center)
     if center_index is None:
         raise IndexError("Center index must not be none... Issue with mutations... They must not be within the transcript.")
+
     var_start_pad = max(0, total_context - center_index)
     var_end_pad = max(0, total_context - (length - center_index))
 
@@ -238,6 +239,59 @@ def find_transcript_missplicing(transcript, mutations, context=5000, window=2500
     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
 
+def find_transcript_missplicing_seqs(ref_seq, var_seq, donors, acceptors, threshold=0.5, engine='spliceai', just_ss=False):
+    if ref_seq.seq == var_seq.seq:
+        return {'missed_acceptors': {}, 'missed_donors': {}, 'discovered_acceptors': {}, 'discovered_donors': {}}
+
+    if engine == 'spliceai':
+        from .spliceai_utils import sai_predict_probs, sai_models
+        ref_seq_acceptor_probs, ref_seq_donor_probs = sai_predict_probs(ref_seq.seq, models=sai_models)
+        mut_seq_acceptor_probs, mut_seq_donor_probs = sai_predict_probs(var_seq.seq, models=sai_models)
+
+    elif engine == 'pangolin':
+        from .pangolin_utils import pangolin_predict_probs, pang_models
+        ref_seq_donor_probs, ref_seq_acceptor_probs = pangolin_predict_probs(ref_seq.seq , models=pang_models, just_ss=just_ss)
+        mut_seq_donor_probs, mut_seq_acceptor_probs = pangolin_predict_probs(var_seq.seq, models=pang_models, just_ss=just_ss)
+
+    else:
+        raise ValueError(f"{engine} not implemented")
+
+    ref_indices = ref_seq.indices[5000:-5000]
+    mut_indices = var_seq.indices[5000:-5000]
+    visible_donors = np.intersect1d(donors, ref_indices)
+    visible_acceptors = np.intersect1d(acceptors, ref_indices)
+
+    assert len(ref_indices) == len(ref_seq_acceptor_probs), f'Reference pos ({len(ref_indices)}) not the same as probs ({len(ref_seq_acceptor_probs)})'
+    assert len(mut_indices) == len(mut_seq_acceptor_probs), f'Mut pos ({len(mut_indices)}) not the same as probs ({len(mut_seq_acceptor_probs)})'
+
+    iap, dap = find_ss_changes({p: v for p, v in list(zip(ref_indices, ref_seq_acceptor_probs))},
+                               {p: v for p, v in list(zip(mut_indices, mut_seq_acceptor_probs))},
+                               visible_acceptors,
+                               threshold=0.1)
+
+    assert len(ref_indices) == len(ref_seq_donor_probs), 'Reference pos not the same'
+    assert len(mut_indices) == len(mut_seq_donor_probs), 'Mut pos not the same'
+
+    idp, ddp = find_ss_changes({p: v for p, v in list(zip(ref_indices, ref_seq_donor_probs))},
+                               {p: v for p, v in list(zip(mut_indices, mut_seq_donor_probs))},
+                               visible_donors,
+                               threshold=0.1)
+
+    ref_acceptors = {a: b for a, b in list(zip(ref_indices, ref_seq_acceptor_probs))}
+    ref_donors = {a: b for a, b in list(zip(ref_indices, ref_seq_donor_probs))}
+
+    lost_acceptors = {int(p): {'absolute': np.float64(0), 'delta': round(float(-ref_acceptors[p]), 3)} for p in
+                      visible_acceptors if p not in mut_indices and p not in dap}
+    lost_donors = {int(p): {'absolute': np.float64(0), 'delta': round(float(-ref_donors[p]), 3)} for p in visible_donors
+                   if p not in mut_indices and p not in ddp}
+    dap.update(lost_acceptors)
+    ddp.update(lost_donors)
+
+    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 Missplicing(temp, threshold=threshold)
+
 
 class Missplicing:
     def __init__(self, splicing_dict, threshold=0.5):
@@ -378,36 +432,36 @@ def missplicing(mut_id, splicing_threshold=0.5, primary_transcript=True, organis
 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
+# 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-1.3.1.dist-info → geney-1.3.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.3.1
+Version: 1.3.3
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.3.1.dist-info → geney-1.3.3.dist-info}/RECORD

@@ -10,12 +10,12 @@ geney/graphic_utils.py,sha256=oMsBpB9YeEn96gGpKh4MmtagJffWZbk-xPrIwHvkFhA,11016
 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=kzXeZ-4aYo1O1v83PkQZcnDa1JR6BqVeQaJ3Vg54jzU,22105
+geney/oncosplice.py,sha256=FdvuROk2G7wwLoB5lLzYia8Smw9hHZeVs-J2MUoAwlU,22106
 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=4xYXy_dIbqdbVfxsEj_OCuM-MsQ24gi4fIv0vQjAYcQ,19215
+geney/splicing_utils.py,sha256=GK0ZzI-eBVxUvuI_bV7-WckvXTmhO83Yx0wS83tyI-w,22524
 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 +24,7 @@ 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-1.3.1.dist-info/METADATA,sha256=uXhxk4kbe7lBIGqOVvUNuIpUgTrhcUm9lz6uv9N9AGw,994
-geney-1.3.1.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
-geney-1.3.1.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.3.1.dist-info/RECORD,,
+geney-1.3.3.dist-info/METADATA,sha256=aEuwIsdWgmM-Gmdk4jON64JBr0vj7ify5PBQul57RmQ,994
+geney-1.3.3.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
+geney-1.3.3.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.3.3.dist-info/RECORD,,