geney 1.2.1__py2.py3-none-any.whl → 1.2.2__py2.py3-none-any.whl

geney/oncosplice.py

@@ -210,7 +210,7 @@ def generate_mut_variant(seq: str, indices: list, mut: Mutation):
 
 
 class Gene:
-    def __init__(self, gene_name, variation=None):
+    def __init__(self, gene_name, variation=None, organism='hg38'):
         self.gene_name = gene_name
         self.gene_id = ''
         self.rev = None
@@ -218,9 +218,10 @@ class Gene:
         self.gene_start = 0
         self.gene_end = 0
         self.transcripts = {}
-        self.load_from_file(find_files_by_gene_name(gene_name))
+        self.load_from_file(find_files_by_gene_name(gene_name, organism=organism))
         self.variations = variation
         self.primary_tid = None
+        self.organism = organism
         tids = [k for k, v in self.transcripts.items() if v['primary_transcript'] and v['transcript_biotype'] == 'protein_coding']
         if tids:
             self.primary_tid = tids[0]
@@ -279,11 +280,11 @@ class Gene:
             if protein_coding and annotations['transcript_biotype'] != 'protein_coding':
                 continue
 
-            yield Transcript(self.transcripts[tid], variations=self.variations)
+            yield Transcript(self.transcripts[tid], variations=self.variations, organism=self.organism)
 
 
 class Transcript:
-    def __init__(self, d=None, variations=None):
+    def __init__(self, d=None, variations=None, organism='hg38'):
         self.transcript_id = None
         self.transcript_start = None                # transcription
         self.transcript_end = None                  # transcription
@@ -304,6 +305,7 @@ class Transcript:
         self.cons_seq = ''
         self.cons_vector = ''
         self.variations = None
+        self.organism = organism
         if variations:
             self.variations = Variations(variations)
 
@@ -508,7 +510,7 @@ class Transcript:
     # Related to transcript seq generation
     def pull_pre_mrna_pos(self):
         fasta_obj = Fasta_segment()
-        return fasta_obj.read_segment_endpoints(config_setup['CHROM_SOURCE'] / f'chr{self.chrm}.fasta',
+        return fasta_obj.read_segment_endpoints(config_setup[self.organism]['CHROM_SOURCE'] / f'chr{self.chrm}.fasta',
                                                 self.transcript_lower,
                                                 self.transcript_upper)
 
@@ -762,7 +764,7 @@ def run_spliceai_transcript(mutations, transcript_data, sai_mrg_context=5000, mi
 
     fasta_obj = Fasta_segment()
     ref_seq, ref_indices = fasta_obj.read_segment_endpoints(
-        config_setup['CHROM_SOURCE'] / f'chr{mutations.chrom}.fasta',
+        config_setup[transcript_data.organism]['CHROM_SOURCE'] / f'chr{mutations.chrom}.fasta',
         seq_start_pos,
         seq_end_pos)
 
@@ -916,7 +918,7 @@ class PredictSpliceAI:
         self.modification = mutation
         self.threshold = threshold
         self.transcript_id = gene_data.transcript_id
-        self.spliceai_db = config_setup['MISSPLICING_PATH'] / f'spliceai_epistatic'
+        self.spliceai_db = config_setup[gene_data.organism]['MISSPLICING_PATH'] / f'spliceai_epistatic'
         self.missplicing = {}
 
         if self.prediction_file_exists() and not force: # need to do a check for the filename length

geney/utils.py

@@ -16,9 +16,9 @@ def is_monotonic(A):
 
 
 
-def available_genes():
+def available_genes(organism='hg38'):
     from geney import config_setup
-    annotation_path = config_setup['MRNA_PATH'] / 'protein_coding'
+    annotation_path = config_setup[organism]['MRNA_PATH'] / 'protein_coding'
     return sorted(list(set([m.stem.split('_')[-1] for m in annotation_path.glob('*')])))
 
 def contains(a, x):
@@ -54,7 +54,7 @@ def dump_pickle(file_path, payload):
 
 def find_files_by_gene_name(gene_name, organism='hg38'):
     from geney import config_setup
-    mrna_path = config_setup['MRNA_PATH'] / organism / 'protein_coding'
+    mrna_path = config_setup[organism]['MRNA_PATH'] / 'protein_coding'
     matching_files = [f for f in mrna_path.glob(f'*_{gene_name}.pkl')]
     if len(matching_files) > 1:
         print(f"Multiple files available ({[f.name for f in matching_files]}).")

{geney-1.2.1.dist-info → geney-1.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.2.1
+Version: 1.2.2
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.2.1.dist-info → geney-1.2.2.dist-info}/RECORD

@@ -9,7 +9,7 @@ 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=PzeQFy8k2xCSIl07kY19rGZ6U5ljyrJ0REC_Qgf-IN0,71582
+geney/oncosplice.py,sha256=_uQ13nuOFNNVsl_7EzCmJtC9WLbzX9zEcqoA7PvkQWY,71786
 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
@@ -18,7 +18,7 @@ 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/utils.py,sha256=CgQQ8sy5g7g75cy-NEgYprink8a6pUreBgs-BhpyJt8,2012
+geney/utils.py,sha256=xJi7fk3g7DkR2rKOb8WePLQNM1ib83rcHecwRdwd5lA,2036
 geney/analyzers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 geney/analyzers/benchmark_clinvar.py,sha256=ZAxvZ-Ue5T6au5mGbk8clfvbAYl13NIY7U92KzL0lXI,5531
 geney/analyzers/characterize_epistasis.py,sha256=MvcYQMRwZ-qqlX9mn41vmr0Uxb5dIrrcaE3oiZMTYm8,648
@@ -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-1.2.1.dist-info/METADATA,sha256=HgySFYXNAhqjuBEJU8_I5oSKq2Rf6v-0hNIQmaqKbEE,1198
-geney-1.2.1.dist-info/WHEEL,sha256=iYlv5fX357PQyRT2o6tw1bN-YcKFFHKqB_LwHO5wP-g,110
-geney-1.2.1.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.2.1.dist-info/RECORD,,
+geney-1.2.2.dist-info/METADATA,sha256=M-hFK8XG5ZbWtH0gsZvGgDBH18l6iGuDKT8xOCGYDSs,1198
+geney-1.2.2.dist-info/WHEEL,sha256=iYlv5fX357PQyRT2o6tw1bN-YcKFFHKqB_LwHO5wP-g,110
+geney-1.2.2.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.2.2.dist-info/RECORD,,