def __get_reference_gene_map(self):
'''
:return: dict
'''
ensembl_gene_ids = []
for output_row in self.output_rows:
ensembl_gene_ids.extend(output_row[2])
ensembl_id_uniq = list(set(ensembl_gene_ids))
exec_ensembl_perl = ExecuteEnsemblPerl()
reference_gene_map = exec_ensembl_perl.get_ensembl_gene_id_ref_map(ensembl_id_uniq)
return reference_gene_map
class CollectVariantData:
def __init__(self, rs_id_file):
'''
:param rs_id_file:
:return: None
'''
self.rs_id_file = rs_id_file
self.ensembl_perl = ExecuteEnsemblPerl(rs_id_file)
def get_variants_in_ensembl_map(self):
'''
Uses the Perl Ensembl REST API to determine if input variants are in Ensembl.
:return: dict
'''
return self.ensembl_perl.get_variant_in_ensembl_map()
def get_nearest_gene_map(self):
'''
Uses the PERL Ensembl API to get the nearest gene at the 5' end for each variant.
:return: dict
'''
return self.ensembl_perl.get_nearest_gene_map()
def __chunk_list(self, input_list, chunk_size=200):
'''
Breaks the input list into chunks. Used to limit the number of variants
sent to the Ensembl REST VEP POST API call.
:param chunk_size: int
:return: generator
'''
sublist = []
for element in input_list:
sublist.append(element)
if len(sublist) == chunk_size:
yield sublist
sublist = []
if sublist:
yield sublist
def get_rest_api_vep_list(self):
'''
Uses the Ensembl REST VEP POST API to return a list of VEP JSONs.
:return: list
'''
vep_outputs = []
rs_ids = [rs_id.strip() for rs_id in open(self.rs_id_file, 'rt').read().split('\n')]
for sublist in self.__chunk_list(rs_ids):
vep_post = RsIdVepPost(sublist)
vep_post_output = vep_post.get_vep_post_output()
for entry in vep_post_output:
vep_outputs.append(entry)
return vep_outputs
def __init__(self, rs_id_file):
'''
:param rs_id_file:
:return: None
'''
self.rs_id_file = rs_id_file
self.ensembl_perl = ExecuteEnsemblPerl(rs_id_file)
:param rank: int
:return: dictionary
'''
# Sort a list of dictionaries numerically using the key "distance".
genes = sorted(self._nearest_gene_list, key=lambda x: abs(int(x['distance'])))
if len(genes) -1 < rank:
return {}
return genes[rank]
def get_nearest_gene_map(self, rank=0):
'''
Return a dictionary with required gene ID and distance information.
Default rank=0 chooses the nearest gene but can provide rank=1
to get, for example, the next nearest gene.
:param rank: int
:return: dictionary
'''
nearest_gene_map = self.get_gene_map_for_rank(rank)
return nearest_gene_map
if __name__ == '__main__':
from execute_ensembl_perl import ExecuteEnsemblPerl
test_file = './test_data/rs_id_list.txt'
exec_ensembl_perl = ExecuteEnsemblPerl(test_file)
nearest_gene_map = exec_ensembl_perl.get_nearest_gene_map()
rs_id = 'rs1000113'
nearest_gene5p = NearestGeneFivePrime(nearest_gene_map[rs_id])
print rs_id + ': ',
print nearest_gene5p.get_nearest_gene_map()