geney 1.2.3__py2.py3-none-any.whl → 1.2.5__py2.py3-none-any.whl

geney/data_setup.py

@@ -7,7 +7,7 @@ from tqdm import tqdm
 import requests
 import argparse
 from sh import gunzip
-
+import shutil
 
 def download(external_url, local_path):
     print(f"Grabbing {external_url}")
@@ -94,6 +94,7 @@ def process_transcript(transcript_df, rev, chrm, cons_data):
         cds_start, cds_end = cds_start[0], cds_end[0]
         data.update({'TIS': cds_start, 'TTS': cds_end, 'protein_id': transcript.protein_id})
 
+    print(f"{transcript.transcript_id} in cons_data: {transcript.transcript_id in cons_data}")
     if transcript.transcript_id in cons_data:
         data.update({'cons_available': True, 'cons_vector': cons_data[transcript.transcript_id]['scores'], 'cons_seq': cons_data[transcript.transcript_id]['seq']})
 
@@ -104,6 +105,8 @@ def process_transcript(transcript_df, rev, chrm, cons_data):
 
 
 def retrieve_and_parse_ensembl_annotations(local_path, annotations_file, cons_data, gtex_file='', valid_biotypes=('protein_coding')):
+    print(cons_data.keys())
+
     if gtex_file:
         gtex_df = pd.read_csv(gtex_file, delimiter='\t', header=2)
         gtex_df.Name = gtex_df.apply(lambda row: row.Name.split('.')[0], axis=1)
@@ -225,21 +228,24 @@ def main():
         'TEMP': os.path.join(args.basepath, args.organism, 'temp')
     }
 
+    base_path = Path(args.basepath) / args.organism
+
     if config_file.exists():
         config_data = unload_json(config_file)
         overwrite = 'y'
         if args.organism in config_data:
             overwrite = input("Organism {args.organism} already configured... Overwrite? (y/n)")
+
         if overwrite == 'y':
             config_data[args.organism] = config_paths
             dump_json(config_file, config_data)
+            shutil.rmtree(base_path)
         else:
             raise SystemExit("Exiting configuration.")
     else:
         config_data = {args.organism: config_paths}
         dump_json(config_file, config_data)
 
-    base_path = Path(args.basepath) / args.organism
     if base_path.exists() and len(os.listdir(base_path)) > 0:
         raise FileExistsError(f"Directory {base_path} not empty.")
 

geney/oncosplice.py

@@ -35,7 +35,7 @@ import torch
 from pkg_resources import resource_filename
 from pangolin.model import *
 
-pang_model_nums = [0, 2, 4, 6]
+pang_model_nums = [0, 1, 2, 3, 4, 5, 6]
 pang_models = []
 for i in pang_model_nums:
     for j in range(1, 6):
@@ -752,7 +752,7 @@ def pangolin_predict_probs(true_seq, models):
     splicing_pred = np.array(scores).max(axis=0)
     donor_probs = [splicing_pred[i] * donor_dinucleotide[i] for i in range(len(true_seq))]
     acceptor_probs = [splicing_pred[i] * acceptor_dinucleotide[i] for i in range(len(true_seq))]
-    return donor_probs, acceptor_probs
+    return donor_probs[5000:-5000], acceptor_probs[5000:-5000]
 
 def run_spliceai_transcript(mutations, transcript_data, sai_mrg_context=5000, min_coverage=2500, sai_threshold=0.5, engine='spliceai'):
     positions = mutations.positions
@@ -803,9 +803,11 @@ def run_spliceai_transcript(mutations, transcript_data, sai_mrg_context=5000, mi
         mut_seq_acceptor_probs, mut_seq_donor_probs = mut_seq_probs_temp[0, :], mut_seq_probs_temp[1, :]
 
     elif engine == 'pangolin':
-        ref_seq_donor_probs, ref_seq_acceptor_probs = pangolin_predict_probs(ref_seq, pangolin_models)
-        mut_seq_donor_probs, mut_seq_acceptor_probs = pangolin_predict_probs(mut_seq, pangolin_models)
+        ref_seq_donor_probs, ref_seq_acceptor_probs = pangolin_predict_probs(ref_seq, pangolin_models=pang_models)
+        mut_seq_donor_probs, mut_seq_acceptor_probs = pangolin_predict_probs(mut_seq, pangolin_models=pang_models)
 
+    else:
+        raise ValueError(f"{engine} not implemented")
 
     assert len(ref_indices) == len(ref_seq_acceptor_probs), 'Reference pos not the same'
     assert len(mut_indices) == len(mut_seq_acceptor_probs), 'Mut pos not the same'
@@ -1400,18 +1402,15 @@ def moving_average_conv(vector, window_size, factor=1):
 
     return np.convolve(vector, np.ones(window_size), mode='same') / window_size
 
-def oncosplice(mut_id, sai_threshold=0.5, protein_coding=True, primary_transcript=False, per_transcript_missplicing=False, window_length=13, save_spliceai_results=False, force_spliceai=False):
+def oncosplice(mut_id, sai_threshold=0.5, protein_coding=True, primary_transcript=False, window_length=13, save_spliceai_results=False, force_spliceai=False, organism='hg38'):
     mutation = Variations(mut_id)
-    try:
-        reference_gene = Gene(mutation.gene)
-    except FileNotFoundError:
-        return pd.DataFrame()
+    # try:
+    reference_gene = Gene(mutation.gene, organism=organism)
+    # except FileNotFoundError:
+    #     return pd.DataFrame()
 
-    reference_gene_proteines = {g.protein: g.transcript_id for g in reference_gene.run_transcripts()}
-    mutated_gene = Gene(mutation.gene, mut_id)
-    # if not per_transcript_missplicing:
-    #     missplicing_obj = PredictSpliceAI(mutation, reference_gene, threshold=sai_threshold, force=True, save_results=False)
-    #     missplicing = missplicing_obj.missplicing
+    reference_gene_proteins = {g.protein: g.transcript_id for g in reference_gene.run_transcripts()}
+    mutated_gene = Gene(mutation.gene, mut_id, organism=organism)
 
     results = []
     for variant in mutated_gene.run_transcripts(protein_coding=protein_coding, primary_transcript=primary_transcript):
@@ -1420,10 +1419,9 @@ 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)
-        # if per_transcript_missplicing:
         missplicing_obj = PredictSpliceAI(mutation, reference, threshold=sai_threshold, force=force_spliceai, save_results=save_spliceai_results)
         missplicing = missplicing_obj.apply_sai_threshold_primary(threshold=sai_threshold)
-        # print(missplicing)
+
         for i, new_boundaries in enumerate(develop_aberrant_splicing(variant, missplicing)):
             variant_isoform = deepcopy(variant)
             variant_isoform.reset_acceptors(acceptors=new_boundaries['acceptors']).reset_donors(donors=new_boundaries['donors']).organize().generate_protein()
@@ -1432,9 +1430,6 @@ def oncosplice(mut_id, sai_threshold=0.5, protein_coding=True, primary_transcrip
             modified_positions = find_modified_positions(len(reference.protein), deleted, inserted)
             temp_cons = np.convolve(cons_vector * modified_positions, np.ones(window_length)) / window_length
             affected_cons_scores = max(temp_cons)
-            # temp_cons = np.convolve(cons_vector, np.ones(window_length))
-            # print(temp_cons)
-            # print(cons_vector)
             percentile = (
                         sorted(cons_vector).index(next(x for x in sorted(cons_vector) if x >= affected_cons_scores)) / len(
                     cons_vector))
@@ -1449,7 +1444,7 @@ def oncosplice(mut_id, sai_threshold=0.5, protein_coding=True, primary_transcrip
             report['isoform_prevalence'] = new_boundaries['path_weight']
             report['full_missplicing'] = missplicing
             report['missplicing'] = max(missplicing_obj)
-            report['reference_resemblance'] = reference_gene_proteines.get(variant_isoform.protein, None)
+            report['reference_resemblance'] = reference_gene_proteins.get(variant_isoform.protein, None)
             results.append(report)
 
     report = pd.DataFrame(results)

geney/power_utils.py

@@ -38,7 +38,7 @@ def write_executors(folder_path, script='geney.power_utils', input_file='/tamir2
 
 def launch_dask_cluster(memory_size="3GB", num_workers=10, queue="tamirQ",
                         walltime="24:00:00", dashboard_address=":23154",
-                        log_directory="dask-logs", slurm=False):
+                        log_directory="dask-logs", slurm=False, organism='hg38'):
     """
     Launch a Dask cluster using PBS.
 
@@ -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['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['BASE']}"]
+                job_script_prologue=[f"cd {config_setup[organism]['BASE']}"]
             )
 
         dask_cluster.scale(num_workers)

geney/tcga_utils.py

@@ -363,8 +363,8 @@ class TCGAGene:
 #     return cases
 #
 #
-# def create_mut_id(row):
-#     return f"{row.Gene_name}:{row['Chromosome']}:{row['Start_Position']}:{row['Reference_Allele']}:{row['Tumor_Seq_Allele2']}"
+def create_mut_id(row):
+    return f"{row.Gene_name}:{row['Chromosome']}:{row['Start_Position']}:{row['Reference_Allele']}:{row['Tumor_Seq_Allele2']}"
 #
 #
 # def is_in_exon(mut_id, tid):

{geney-1.2.3.dist-info → geney-1.2.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.2.3
+Version: 1.2.5
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn
@@ -17,7 +17,7 @@ Requires-Dist: numpy ==1.26.4
 Requires-Dist: pandas ==2.2.1
 Requires-Dist: networkx ==3.2.1
 Requires-Dist: viennarna ==2.6.4
-Requires-Dist: tqdm ==4.66.1
+Requires-Dist: tqdm >=4.66.1
 Requires-Dist: spliceai ==1.3.1
 Requires-Dist: scikit-learn ==1.0.2
 Requires-Dist: biopython ==1.81

{geney-1.2.3.dist-info → geney-1.2.5.dist-info}/RECORD

@@ -4,20 +4,20 @@ geney/__init__.py,sha256=r-Yvpo_Tc236DcsqsFyexT21iVoYCVl9zoJj5pFuWEE,407
 geney/benchmark_clinvar.py,sha256=LLl77e95Qbg9Kd-m2yL8ilmzubSz9SKogeARwssT4Ks,5532
 geney/compare_sets.py,sha256=TcgL57V7BUPxBoW9lv3xr8qK2Acmykn85Ev3avicQr8,2977
 geney/config_setup.py,sha256=VA6mhVGMRadwlpEx4m1wrssmDM8qpfKT21MAijIwjyQ,428
-geney/data_setup.py,sha256=mV_sSCMT8C41q_PD_G34MIBvsBKA0Czrpw17-DcYmT4,12052
+geney/data_setup.py,sha256=LTiJMYPgv9KnIgUNw-D57Fu4nxL4OojXMpmdhE8QSYU,12228
 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=xDzCLivFyurx-qlQo9cyrV-9KJ9VykYAb8lY9DDWl7Q,71810
+geney/oncosplice.py,sha256=9oZs9W_bI6O5h3284WvatkerhSCaxMZWfs1xVc1lJO0,71524
 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=GtEvKAbz34S-ILQST6tabt3g0M4L8_aa50HIAQZ7byM,7266
+geney/power_utils.py,sha256=nppfT1-bOC1dnvfRs55LipjoWDlRrOqWiuCMH0v1auU,7303
 geney/survival.py,sha256=gNKZGcwxDZ00ixVBHf3ZdjbY_AHQOCU9kKpBC_dokbM,5572
 geney/survival_utils.py,sha256=2CAkC2LsspicHIdrqsiPnjgvpr5KHDUfLFFqnRbPJqs,5762
 geney/tcga_annotations.py,sha256=DjRl6Pk5VAOL1yhbt8SXD6FZhYbcYNu3FtXYMeveGB0,15016
-geney/tcga_utils.py,sha256=uAjejr7F-XqcXS5uANGlsHLOlzMmGo4CTbWhMO0E318,15589
+geney/tcga_utils.py,sha256=vXSMf1OxoF_AdE_rMguy_BoYaart_E1t4FFMx2DS1Ak,15585
 geney/utils.py,sha256=xJi7fk3g7DkR2rKOb8WePLQNM1ib83rcHecwRdwd5lA,2036
 geney/analyzers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 geney/analyzers/benchmark_clinvar.py,sha256=ZAxvZ-Ue5T6au5mGbk8clfvbAYl13NIY7U92KzL0lXI,5531
@@ -45,7 +45,7 @@ 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-1.2.3.dist-info/METADATA,sha256=K6ufQEQw0PTbczOxkWFW26U4URgwy92Q9Aqp8BhsKIA,1198
-geney-1.2.3.dist-info/WHEEL,sha256=iYlv5fX357PQyRT2o6tw1bN-YcKFFHKqB_LwHO5wP-g,110
-geney-1.2.3.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.2.3.dist-info/RECORD,,
+geney-1.2.5.dist-info/METADATA,sha256=9UptuZVJWZvVN6Y9KgPUxrC4gnijFVW4CtkkESxrY9E,1198
+geney-1.2.5.dist-info/WHEEL,sha256=iYlv5fX357PQyRT2o6tw1bN-YcKFFHKqB_LwHO5wP-g,110
+geney-1.2.5.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.2.5.dist-info/RECORD,,