geney 1.2.40__py2.py3-none-any.whl → 1.2.41__py2.py3-none-any.whl

geney/graphic_utils.py

@@ -1,9 +1,8 @@
-
 import matplotlib.pyplot as plt
 from matplotlib.patches import Rectangle
 import seaborn as sns
 from collections import namedtuple
-from geney.utils import find_files_by_gene_name, reverse_complement, unload_pickle, contains, unload_json, dump_json #, is_monotonic
+from geney.utils import unload_pickle, contains, unload_json, dump_json
 
 
 ### Graphical Stuff

geney/oncosplice.py

@@ -331,19 +331,19 @@ def OncospliceAnnotator(reference_transcript, variant_transcript, mut):
     report['primary_transcript'] = reference_transcript.primary_transcript
     report['transcript_id'] = reference_transcript.transcript_id
     # report['mut_id'] = mut.mut_id
-    report['cons_available'] = int(reference_transcript.cons_available)
+    # report['cons_available'] = int(reference_transcript.cons_available)
     # report['protein_coding'] = reference_transcript.transcript_biotype
 
     # report['reference_mrna'] = reference_transcript.transcript_seq
-    report['reference_cds_start'] = reference_transcript.TIS
+    # report['reference_cds_start'] = reference_transcript.TIS
     # report['reference_pre_mrna'] = reference_transcript.pre_mrna
     # report[
     #     'reference_orf'] = reference_transcript.orf  # pre_mrna[reference_transcript.transcript_indices.index(reference_transcript.TIS):reference_transcript.transcript_indices.index(reference_transcript.TTS)]
     report['reference_protein'] = reference_transcript.protein
-    report['reference_protein_length'] = len(reference_transcript.protein)
+    # report['reference_protein_length'] = len(reference_transcript.protein)
 
     # report['variant_mrna'] = variant_transcript.transcript_seq
-    report['variant_cds_start'] = variant_transcript.TIS
+    # report['variant_cds_start'] = variant_transcript.TIS
     # report[
     #     'variant_pre_mrna'] = variant_transcript.pre_mrna  # pre_mrna[variant_transcript.transcript_indices.index(variant_transcript.TIS):variant_transcript.transcript_indices.index(variant_transcript.TTS)]
     # report['variant_orf'] = variant_transcript.orf
@@ -363,6 +363,8 @@ def OncospliceAnnotator(reference_transcript, variant_transcript, mut):
 
 def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, primary_transcript=False, window_length=13, organism='hg38', engine='spliceai', domains=None):
     gene = Gene(mut_id.split(':')[0], organism=organism)
+    reference_gene_proteins = {tid: transcript.generate_pre_mrna().generate_mature_mrna().generate_protein() for tid, transcript in gene.run_transcripts(protein_coding=True)}
+
     mutations = [get_mutation(m, rev=gene.rev) for m in mut_id.split('|')]
 
     results = []
@@ -408,7 +410,7 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, primary_tran
             report['isoform_prevalence'] = new_boundaries['path_weight']
             report['full_missplicing'] = missplicing.aberrant_splicing
             report['missplicing'] = max(missplicing)
-            # report['reference_resemblance'] = reference_gene_proteins.get(variant_isoform.protein, None)
+            report['reference_resemblance'] = reference_gene_proteins.get(transcript.protein, None)
             results.append(report)
 
     report = pd.DataFrame(results)
@@ -445,6 +447,8 @@ async def oncosplice_prototype(mut_id, splicing_threshold=0.5, protein_coding=Tr
                          index=['domain_identifier', 'score'])
 
     gene = Gene(mut_id.split(':')[0], organism=organism)
+    reference_gene_proteins = {tid: transcript.generate_pre_mrna().generate_mature_mrna().generate_protein() for tid, transcript in gene.run_transcripts(protein_coding=True)}
+
     mutations = [get_mutation(mut_id, rev=gene.rev) for mut_id in mut_id.split('|')]
 
     results = []
@@ -501,7 +505,7 @@ async def oncosplice_prototype(mut_id, splicing_threshold=0.5, protein_coding=Tr
             report['full_missplicing'] = missplicing.aberrant_splicing
             report['missplicing'] = max(missplicing)
             report['domains_affected'] = domains_affected
-            # report['reference_resemblance'] = reference_gene_proteins.get(variant_isoform.protein, None)
+            report['reference_resemblance'] = reference_gene_proteins.get(transcript.protein, None)
             results.append(pd.Series(report))
 
     report = pd.concat(results, axis=1).T

geney/tcga_utils.py

@@ -2,6 +2,7 @@
 import pandas as pd
 import random
 from pathlib import Path
+from tqdm import tqdm
 
 class TCGACase:
     def __init__(self, df):
@@ -98,38 +99,61 @@ class TCGACase:
 class TCGAGene:
     def __init__(self, gene, cancer_path=Path('/tamir2/cancer_proj/gdc_db/data/filtered_feb_2021/AllGenes/'),
                  valid_cases=None, extra_cols=[], exclude_filters=None, include_filter=None):
-        df = pd.read_csv(cancer_path / gene / 'GeneMutTble.txt',
-                         usecols=['Variant_Type', 'FILTER', 'vcf_tumor_gt', 'vcf_normal_gt',
-                                  'COSMIC', 't_depth', 't_ref_count', 't_alt_count', 'Proj_name',
-                                  'HGVSc', 'Chromosome', 'Start_Position', 'Reference_Allele',
-                                  'Tumor_Seq_Allele2', 'case_id', 'Gene_name', 'Variant_Type'] + extra_cols,
-                         low_memory=False).sort_values('Start_Position', ascending=True)
-
-        if df.empty:
-            self.df = df
+        file_path = cancer_path / gene / 'GeneMutTble.txt'
+        if not file_path.exists():
+            self.df = pd.DataFrame()
 
         else:
-            df = df[df.Variant_Type.isin(['SNP', 'INS', 'DEL'])]
-            df = df.astype({'Start_Position': int})
-
-            if include_filter is not None:
-                df = df[df.FILTER == include_filter]
+            df = pd.read_csv(file_path,
+                             usecols=['Variant_Type', 'FILTER', 'vcf_tumor_gt', 'vcf_normal_gt',
+                                      'COSMIC', 't_depth', 't_ref_count', 't_alt_count', 'Proj_name',
+                                      'HGVSc', 'Chromosome', 'Start_Position', 'Reference_Allele',
+                                      'Tumor_Seq_Allele2', 'case_id', 'Gene_name', 'Variant_Type',
+                                      'Variant_Classification'] + extra_cols,
+                             low_memory=False).sort_values('Start_Position', ascending=True)
 
-            elif exclude_filters is not None:
-                for exclude_filter in exclude_filters:
-                    df = df[~df.FILTER.str.contains(exclude_filter)]
+            df['attention'] = True
 
-            if valid_cases is not None:
-                df = df[df.case_id.isin(valid_cases)]
+            if df.empty:
+                self.df = df
 
-            df['mut_id'] = df.apply(lambda
-                                        row: f"{row.Gene_name}:{row.Chromosome.replace('chr', '')}:{row.Start_Position}:{row.Reference_Allele}:{row.Tumor_Seq_Allele2}",
-                                    axis=1)
-
-            df['ratio'] = df.t_alt_count + df.t_ref_count
-            df = df[df.ratio > 0]
-            df['ratio'] = df.t_alt_count / df.ratio
-            self.df = df
+            else:
+                df = df[df.Variant_Type.isin(['SNP', 'INS', 'DEL'])]
+                df = df.astype({'Start_Position': int})
+
+                if include_filter is not None:
+                    # df = df[df.FILTER == include_filter]
+                    df.loc[~df['FILTER'].str.contains(include_filter), 'attention'] = False
+
+                elif exclude_filters is not None:
+                    for exclude_filter in exclude_filters:
+                        # df = df[~df.FILTER.str.contains(exclude_filter)]
+                        df.loc[df['FILTER'].str.contains(exclude_filter), 'attention'] = False
+
+                if valid_cases is not None:
+                    # df = df[df.case_id.isin(valid_cases)]
+                    df.loc[~df.case_id.isin(valid_cases), 'attention'] = False
+
+                df['mut_id'] = df.apply(lambda
+                                            row: f"{row.Gene_name}:{row.Chromosome.replace('chr', '')}:{row.Start_Position}:{row.Reference_Allele}:{row.Tumor_Seq_Allele2}",
+                                        axis=1)
+                df['mut_id_yoram'] = df.apply(lambda
+                                                  row: f"{row.Gene_name}:{row.Chromosome}:{row.Variant_Classification}:{row.Start_Position}:{row.Reference_Allele}:{row.Tumor_Seq_Allele2}",
+                                              axis=1)
+                silent_mut_classes = ["3'Flank", "3'UTR", "Silent", "Splice_Site", "Splice_Region", "Intron", "5'Flank",
+                                      "3'Flank"]
+                df['silent'] = df.apply(lambda row: row.Variant_Classification in silent_mut_classes, axis=1)
+                df['ratio'] = df.t_alt_count + df.t_ref_count
+                df = df[df.ratio > 0]
+                df['ratio'] = df.t_alt_count / df.ratio
+                self.df = df
+
+    def __repr__(self):
+        return repr(self.df[self.df.attention])
+
+    @property
+    def data(self):
+        return self.df[self.df.attention]
 
     def affected_cases(self, mut_id=None, read_ratio=0, filters=[]):
         if mut_id is None:
@@ -164,18 +188,27 @@ class TCGAGene:
     def total_prevalence(self, mut_id):
         pass
 
-    def project_prevalence(self, mut_id):
-        pass
+    def project_prevalence(self, mut_id, df_p_proc):
+        mut_prevalence = {}
+        for i, g in tqdm(self.data.groupby(['mut_id', 'Transcript_ID'])):
+            mut_prevalence[i] = series_to_pretty_string((df_p_proc[g.case_id].value_counts() / project_counts).dropna())
+        return pd.Series(mut_prevalence)
 
     def project_counts(self, mut_id):
         pass
 
+    def filter_silent_muts(self):
+        self.df.loc[self.df.silent, 'attention'] = False
+        return self
 
 
-
-
-
-
+def series_to_pretty_string(series):
+    # Format each index-value pair, applying scientific notation to floats with 3 significant figures
+    pretty_str = "\n".join([
+        f"{index}: {value:.3e}" if isinstance(value, float) else f"{index}: {value}"
+        for index, value in series.items()
+    ])
+    return pretty_str
 
 
 # CLINICAL_DATA_FILE = Path('/tamir2/nicolaslynn/data/TCGA/cancer_reports/new_df_p_proc.pkl')

{geney-1.2.40.dist-info → geney-1.2.41.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.2.40
+Version: 1.2.41
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.2.40.dist-info → geney-1.2.41.dist-info}/RECORD

@@ -2,25 +2,25 @@ geney/Fasta_segment.py,sha256=0zCdzPUbDeM9Rz642woH5Q94pwI46O0fE3H8w0XWebc,11255
 geney/__init__.py,sha256=eBdDl42N6UhcYeZDjOnv199Z88fI5_8Y6xW8447OKXM,755
 geney/config_setup.py,sha256=klm_k7Ca_703DpeGBcGoDqz1XwHQhNXENPKjj_xfSQw,608
 geney/data_setup.py,sha256=2RHmuvcGUQbEglXQEZr0C2QPDTQYRZOEm0EcmyfQJgU,12229
-geney/graphic_utils.py,sha256=tjm6IDQ1BdfSeuPYzjlqAUHFQoDYH9jXTzJjKFS4Hh4,11078
+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=J_nFs_xBSJtgMqeHv628QodRL0B2d-Zi1Ke7Pk7S4R4,22595
+geney/oncosplice.py,sha256=1K8p-sytnMUKTYwO_z_YJLelLosKj8TZpM0i5lHcMFI,22941
 geney/pangolin_utils.py,sha256=lLmnjJdJjqwWS85-1jlPLIjD2z14sWjzU87hS-8xxpQ,2873
 geney/power_utils.py,sha256=MehZFUdkJ2EFUot709yPEDxSkXmH5XevMebX2HD768A,7330
 geney/seqmat_utils.py,sha256=YV5DFLbfjXLIswPGvqK1-eEfwn9TUby0b2kewdGAKws,18372
 geney/spliceai_utils.py,sha256=gIGPC8u3J15A7EQrk2Elho5PbF9MmUUNopGGH-eEV8s,1873
 geney/splicing_utils.py,sha256=lGBNknnAdKhcJ3MqPQ5c9oz_NKcL2lcFAr78StjKa6o,16151
 geney/survival_utils.py,sha256=2CAkC2LsspicHIdrqsiPnjgvpr5KHDUfLFFqnRbPJqs,5762
-geney/tcga_utils.py,sha256=vXSMf1OxoF_AdE_rMguy_BoYaart_E1t4FFMx2DS1Ak,15585
+geney/tcga_utils.py,sha256=wM52QZ1M_54CrXZ_uj05R14ycZh23gTZUI8b0ZMtPd0,17615
 geney/tis_utils.py,sha256=vA2ci4gNfwwQZlCjPpO5ehvL2NRVeM7lHI_VyfT-_10,8049
 geney/utils.py,sha256=EsKvBM-Nz2a3_4ZAhF4Dxd4PwT7_6YYKpxEN4LLgg10,2174
 geney/translation_initiation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 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-1.2.40.dist-info/METADATA,sha256=ja7ULYnyNPbYYj-wloXQzHDH86TL2mg4LfgEmZaMcbE,948
-geney-1.2.40.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
-geney-1.2.40.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.2.40.dist-info/RECORD,,
+geney-1.2.41.dist-info/METADATA,sha256=e7eHu8HlNdNuNXLWxK17ok3lAetzKTJ7ie-8MRct1T8,948
+geney-1.2.41.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
+geney-1.2.41.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.2.41.dist-info/RECORD,,