geney 1.2.16__py2.py3-none-any.whl → 1.2.18__py2.py3-none-any.whl

geney/oncosplice.py

@@ -219,6 +219,7 @@ class Gene:
         self.gene_end = 0
         self.transcripts = {}
         self.load_from_file(find_files_by_gene_name(gene_name, organism=organism))
+        # print(f"In Gene: {variation}")
         self.variations = variation
         self.primary_tid = None
         self.organism = organism
@@ -271,7 +272,7 @@ class Gene:
 
         if tid not in self.transcripts:
             raise AttributeError(f"Transcript '{tid}' not found in gene '{self.gene_name}'.")
-        return Transcript(self.transcripts[tid], organism=self.organism)
+        return Transcript(self.transcripts[tid], organism=self.organism, variations=self.variations)
 
     def run_transcripts(self, primary_transcript=False, protein_coding=False):
         for tid, annotations in self.transcripts.items():
@@ -306,7 +307,7 @@ class Transcript:
         self.cons_vector = ''
         self.variations = None
         self.organism = organism
-        print(f"Variations: {variations}")
+        # print(f"Variations: {variations}")
         if variations:
             self.variations = Variations(variations)
 
@@ -520,7 +521,7 @@ class Transcript:
         seq, indices = self.pull_pre_mrna_pos()
         if self.variations:
             for mutation in self.variations.variants:
-                print(f"Implementing {mutation}")
+                # print(f"Implementing {mutation}")
                 seq, indices = generate_mut_variant(seq, indices, mut=mutation)
         return seq, indices
 
@@ -793,7 +794,7 @@ def find_transcript_missplicing(mutations, ref_transcript, var_transcript, conte
     start_pad, end_pad = max(0, context - (center_index - start_cutoff)), max(0, context - (end_cutoff - center_index))
     mut_seq = 'N' * start_pad + mut_seq[start_cutoff:end_cutoff] + 'N' * end_pad
     mut_indices = [-1] * start_pad + mut_indices[start_cutoff:end_cutoff] + [-1] * end_pad
-    print(f"Mut and Ref are equal: {mut_seq == ref_seq}")
+    # print(f"Mut and Ref are equal: {mut_seq == ref_seq}")
 
     copy_mut_indices = mut_indices.copy()
 
@@ -823,7 +824,7 @@ 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'
@@ -855,7 +856,7 @@ 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
 
 
@@ -1017,7 +1018,7 @@ 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,
@@ -1041,9 +1042,9 @@ class PredictSpliceAI:
             # elif isinstance(gene_data, Transcript):
 
             # 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}")
+            # 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}")
+            # 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:

geney/power_utils.py

@@ -63,7 +63,7 @@ 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 +75,7 @@ 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 +87,8 @@ 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-1.2.16.dist-info → geney-1.2.18.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.2.16
+Version: 1.2.18
 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-1.2.16.dist-info → geney-1.2.18.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=MbupurEf0v5WYFHggbvnhEKWCyT_MpTvXgFocTESXpk,77975
+geney/oncosplice.py,sha256=MA8z8D2kZCrIeXJwu0D6rM_VvryldvkNkzETkE29cts,78057
 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=_B5DIKfwQGb1Gy9xbIUrOCiTf5y_Nq10OMtaFjEo3i8,7309
 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-1.2.16.dist-info/METADATA,sha256=wEwQVKYPCLnaNi5FsnM3CTQ_RrnZe7fVPs3NLFgTkos,1199
-geney-1.2.16.dist-info/WHEEL,sha256=iYlv5fX357PQyRT2o6tw1bN-YcKFFHKqB_LwHO5wP-g,110
-geney-1.2.16.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.2.16.dist-info/RECORD,,
+geney-1.2.18.dist-info/METADATA,sha256=TR4c2Ytss-agQ850EcaSjgKkHqbC0VsMsRxNnnUxEHU,1163
+geney-1.2.18.dist-info/WHEEL,sha256=iYlv5fX357PQyRT2o6tw1bN-YcKFFHKqB_LwHO5wP-g,110
+geney-1.2.18.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.2.18.dist-info/RECORD,,