geney 1.2.17__py2.py3-none-any.whl → 1.2.19__py2.py3-none-any.whl

geney/oncosplice.py

@@ -50,15 +50,21 @@ for i in pang_model_nums:
         model.eval()
         pang_models.append(model)
 
+
+# def is_monotonic(A):
+#     x, y = [], []
+#     x.extend(A)
+#     y.extend(A)
+#     x.sort()
+#     y.sort(reverse=True)
+#     if (x == A or y == A):
+#         return True
+#     return False
+
+
 def is_monotonic(A):
-    x, y = [], []
-    x.extend(A)
-    y.extend(A)
-    x.sort()
-    y.sort(reverse=True)
-    if (x == A or y == A):
-        return True
-    return False
+    return all(x <= y for x, y in zip(A, A[1:])) or all(x >= y for x, y in zip(A, A[1:]))
+
 
 def sai_predict_probs(seq: str, models: list) -> list:
     '''
@@ -824,7 +830,7 @@ def find_transcript_missplicing(mutations, ref_transcript, var_transcript, conte
     visible_acceptors = np.intersect1d(ref_transcript.acceptors, ref_indices)
     # print(ref_indices.index(visible_donors[0]), ref_seq_donor_probs[ref_indices.index(visible_donors[0])], mut_seq_donor_probs[mut_indices.index(visible_donors[0])])
 
-    print(len(ref_seq_donor_probs), len(ref_seq_acceptor_probs), len(mut_seq_donor_probs), len(mut_seq_acceptor_probs), len(ref_indices), len(mut_indices))
+    # print(len(ref_seq_donor_probs), len(ref_seq_acceptor_probs), len(mut_seq_donor_probs), len(mut_seq_acceptor_probs), len(ref_indices), len(mut_indices))
     # print(ref_seq_donor_probs)
 
     assert len(ref_indices) == len(ref_seq_acceptor_probs), 'Reference pos not the same'
@@ -856,7 +862,7 @@ def find_transcript_missplicing(mutations, ref_transcript, var_transcript, conte
     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()}
-    print(temp)
+    # print(temp)
     return temp
 
 
@@ -1018,11 +1024,11 @@ def find_transcript_missplicing(mutations, ref_transcript, var_transcript, conte
 #     missplicing = {outk: {float(k): v for k, v in outv.items()} for outk, outv in missplicing.items()}
 #
 #     return {outk: {int(k) if k.is_integer() else k: v for k, v in outv.items()} for outk, outv in missplicing.items()}
-#
+
 
 class PredictSpliceAI:
     def __init__(self, mutation, gene_data,
-                threshold=0.5, force=False,  save_results=False, sai_mrg_context=5000, min_coverage=2500, engine='spliceai'):
+                threshold=0.5, force=False,  save_results=False, sai_mrg_context=5000, min_coverage=2500, engine='spliceai', organism='hg38'):
         self.modification = mutation
         self.threshold = threshold
         self.transcript_id = gene_data.transcript_id
@@ -1043,8 +1049,8 @@ class PredictSpliceAI:
 
             # self.missplicing = run_spliceai_transcript(self.modification, transcript_data=gene_data, sai_mrg_context=sai_mrg_context, min_coverage=min_coverage, sai_threshold=0.1)
             # print(f"RUNNING: {mutation.mut_id}")
-            ref_transcript, var_transcript = Gene(mutation.mut_id.split(':')[0], organism='mm39').transcript(gene_data.transcript_id), Gene(mutation.mut_id.split(':')[0], mutation.mut_id, organism='mm39').transcript(gene_data.transcript_id)
-            print(f"Second check : {ref_transcript.pre_mrna == var_transcript.pre_mrna}")
+            ref_transcript, var_transcript = Gene(mutation.mut_id.split(':')[0], organism=organism).transcript(gene_data.transcript_id), Gene(mutation.mut_id.split(':')[0], mutation.mut_id, organism='mm39').transcript(gene_data.transcript_id)
+            # print(f"Second check : {ref_transcript.pre_mrna == var_transcript.pre_mrna}")
             self.missplicing = find_transcript_missplicing(self.modification, ref_transcript, var_transcript, context=sai_mrg_context+min_coverage, threshold=threshold,
                                 engine=engine)
             if save_results:
@@ -1531,7 +1537,7 @@ def oncosplice(mut_id, sai_threshold=0.5, protein_coding=True, primary_transcrip
             continue
 
         cons_vector = transform_conservation_vector(reference.cons_vector, window=window_length)
-        missplicing_obj = PredictSpliceAI(mutation, reference, threshold=sai_threshold, force=force_spliceai, save_results=save_spliceai_results, engine=engine)
+        missplicing_obj = PredictSpliceAI(mutation, reference, threshold=sai_threshold, force=force_spliceai, save_results=save_spliceai_results, engine=engine, organism=organism)
         missplicing = missplicing_obj.apply_sai_threshold_primary(threshold=sai_threshold)
 
         for i, new_boundaries in enumerate(develop_aberrant_splicing(variant, missplicing)):

geney/power_utils.py

@@ -12,6 +12,7 @@ import gc
 import pandas as pd
 import argparse
 
+print("remote this")
 tqdm.pandas()
 warnings.filterwarnings('ignore')
 
@@ -63,7 +64,7 @@ def launch_dask_cluster(memory_size="3GB", num_workers=10, queue="tamirQ",
                 walltime='7200',
                 scheduler_options={"dashboard_address": dashboard_address},
                 log_directory=log_directory,
-                job_script_prologue=[f"cd {config_setup[organism]['BASE']}"]
+                # job_script_prologue=[f"cd {config_setup[organism]['BASE']}"]
             )
 
         else:
@@ -75,7 +76,7 @@ def launch_dask_cluster(memory_size="3GB", num_workers=10, queue="tamirQ",
                 walltime=walltime,
                 scheduler_options={"dashboard_address": dashboard_address},
                 log_directory=log_directory,
-                job_script_prologue=[f"cd {config_setup[organism]['BASE']}"]
+                # job_script_prologue=[f"cd {config_setup[organism]['BASE']}"]
             )
 
         dask_cluster.scale(num_workers)
@@ -87,6 +88,8 @@ def launch_dask_cluster(memory_size="3GB", num_workers=10, queue="tamirQ",
         return None, None
 
 
+
+
 def process_and_save_tasks(tasks, dask_client, funct, save_loc=None, num_workers=10, save_increment=20, file_index=0):
     """
     Process a list of tasks using Dask, saving the results incrementally.

{geney-1.2.17.dist-info → geney-1.2.19.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.2.17
+Version: 1.2.19
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn
@@ -19,7 +19,6 @@ Requires-Dist: networkx ==3.2.1
 Requires-Dist: viennarna ==2.6.4
 Requires-Dist: tqdm >=4.66.1
 Requires-Dist: spliceai ==1.3.1
-Requires-Dist: scikit-learn ==1.0.2
 Requires-Dist: biopython ==1.81
 Requires-Dist: tensorflow ==2.15.0
 Requires-Dist: keras ==2.15.0

{geney-1.2.17.dist-info → geney-1.2.19.dist-info}/RECORD

@@ -9,11 +9,11 @@ geney/gtex.py,sha256=asL2lHyU5KsbWpV096vkf1Ka7hSo_RRfZqw7p5nERmE,1919
 geney/gtex_utils.py,sha256=asL2lHyU5KsbWpV096vkf1Ka7hSo_RRfZqw7p5nERmE,1919
 geney/immune_utils.py,sha256=ZRni5ttrhpYBnmNr0d0ZatIbNPYs4nmQuoUO00SpsS4,5271
 geney/netchop.py,sha256=AMiy9YsdTmX4B3k3Y5Yh7EmoGAojM1O3AzhPKOiB--g,3050
-geney/oncosplice.py,sha256=Ram8jY69AxVspa13jN4eQD0iUX5dUuz9fXQzG3QoJl0,78052
+geney/oncosplice.py,sha256=YW0GEJqyZHJ8Loi1I488NpMHKSqjkyIb0rB3YzGUQTM,78228
 geney/oncosplice_mouse.py,sha256=LYLOukI9qI1IBkyl1qVRFR5d1NAw7Orlj8Zth-4xCW8,12962
 geney/oncosplice_pipeline.py,sha256=hpGqFHOdn8i8tvvs1-t3-G9Ko18zInwoDXBJbbrfbC4,68036
 geney/performance_utils.py,sha256=FQt7rA4r-Wuq3kceCxsSuMfj3wU1tMG8QnbL59aBohs,4700
-geney/power_utils.py,sha256=nppfT1-bOC1dnvfRs55LipjoWDlRrOqWiuCMH0v1auU,7303
+geney/power_utils.py,sha256=MehZFUdkJ2EFUot709yPEDxSkXmH5XevMebX2HD768A,7330
 geney/survival.py,sha256=gNKZGcwxDZ00ixVBHf3ZdjbY_AHQOCU9kKpBC_dokbM,5572
 geney/survival_utils.py,sha256=2CAkC2LsspicHIdrqsiPnjgvpr5KHDUfLFFqnRbPJqs,5762
 geney/tcga_annotations.py,sha256=DjRl6Pk5VAOL1yhbt8SXD6FZhYbcYNu3FtXYMeveGB0,15016
@@ -33,6 +33,7 @@ geney/immunotherapy/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSu
 geney/immunotherapy/netchop.py,sha256=vLy-ahEKxU6IzwmnnqefXDJjZOeGIprLWbKU3t-M7sc,2800
 geney/mutations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 geney/mutations/variant_utils.py,sha256=4exIP02lviMmsZTq8UYkjlunLpnBruGM4GLz0C7P0wM,4285
+geney/oncosplice/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 geney/pipelines/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 geney/pipelines/dask_utils.py,sha256=J68bpbikdUGGirPERczu1cf_ajZmEvDfWEj8GIMJvII,5641
 geney/splicing/__init__.py,sha256=0x9Rt0znGnf3Hs92BYRBjdHZHOMsd_27QNTRlfohzLY,60
@@ -45,7 +46,7 @@ geney/translation_initiation/resources/kozak_pssm.json,sha256=pcd0Olziutq-6H3mFW
 geney/translation_initiation/resources/tis_regressor_model.joblib,sha256=IXb4DUDhJ5rBDKcqMk9zE3ECTZZcdj7Jixz3KpoZ7OA,2592025
 geney/translation_termination/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 geney/translation_termination/tts_utils.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-geney-1.2.17.dist-info/METADATA,sha256=-fToNRmK9zXLOqq-LRzgPHk8E0_d4ecgfukN35KHlso,1199
-geney-1.2.17.dist-info/WHEEL,sha256=iYlv5fX357PQyRT2o6tw1bN-YcKFFHKqB_LwHO5wP-g,110
-geney-1.2.17.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.2.17.dist-info/RECORD,,
+geney-1.2.19.dist-info/METADATA,sha256=7nrc6newZc-UnO7hU56B8pg0Xvskze2Ad1f-eFUuHME,1163
+geney-1.2.19.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
+geney-1.2.19.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.2.19.dist-info/RECORD,,

{geney-1.2.17.dist-info → geney-1.2.19.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.41.2)
+Generator: setuptools (75.1.0)
 Root-Is-Purelib: true
 Tag: py2-none-any
 Tag: py3-none-any