def helper(symbolset=annot[colname][1]):
if len(symbolset) == 0:
return (dict())
d = dict()
for sym in symbolset:
try:
description = ensembl_rest.symbol_lookup(
'h**o sapiens', sym, expand=1)['description']
except Exception:
description = 'No valid lookup found for symbol ' + sym
d[sym] = description
return (d)
def getSequence(gene):
"Get the protein sequence coded by the given gene"
q = ensembl_rest.symbol_lookup(species='h**o sapiens',
symbol=gene,
params={'expand': True})
try:
is_canonical = [t["is_canonical"] for t in q["Transcript"]]
t = q["Transcript"][np.argmax(is_canonical)]
seq = ensembl_rest.sequence_id(t["Translation"]["id"])["seq"]
return seq
except:
return ""
def get_coords(x, args):
g = x.gene
if '-' in g and ':' in g:
(chrom, loc) = g.split(':')
(start, stop) = loc.split('-')
(start, stop) = (int(start), int(stop))
# gene name
else:
try:
gene = ensembl_rest.symbol_lookup(species=args.species, symbol=g)
except:
sys.exit('Something went wrong with ENSEMBL gene name query')
# radius + TSS
chrom = 'chr' + gene['seq_region_name']
temp1 = gene['start'] - 5000
temp2 = gene['start'] + 5000
start = min(temp1, temp2)
stop = max(temp1, temp2)
# # testing
# print(g)
# print('start: {}'.format(gene['start']))
# print('region start: {}'.format(start))
# print('region end: {}'.format(stop))
# # radius + whole gene body
# chrom = 'chr'+gene['seq_region_name']
# start = min([gene['start'], gene['end']])
# stop = max([gene['start'], gene['end']])
# if args.radius:
# temp_start = start - args.radius
# if temp_start >= 0: start = temp_start
# stop = stop + args.radius
# # testing
# print('new start: {}'.format(start))
# print('new stop: {}'.format(stop))
return pd.Series([chrom, start, stop])
import ensembl_rest
r = ensembl_rest.symbol_lookup(species='h**o sapiens', symbol='BRCA2')
print(r)
r = ensembl_rest.variant_recoder(species='h**o sapiens',
id='NC_000007.13:101837173:C:T')
print(r)
import ensembl_rest
import requests, sys
from pyensembl import EnsemblRelease
from collections import OrderedDict
import json
data=EnsemblRelease(95)
keys=['id','description','display_name','biotype']
ids=data.gene_names()
keys1=['display_name','len']
out=[]
dom=[]
for id in ids:
try:
a=ensembl_rest.symbol_lookup('h**o sapiens', id)
res = dict((k, a[k]) for k in keys if k in a)
inp=res['id']
server = "https://rest.ensembl.org"
ext = "/sequence/id/"+inp+"?"
r = requests.get(server+ext, headers={ "Content-Type" : "text/plain"})
if not r.ok:
r.raise_for_status()
sys.exit()
a=r.text
res['seq']=a
res['len']=len(res['seq'])
gene_len = dict((k, res[k]) for k in keys1 if k in res)
print(gene_len)
out.append(res)
dom.append(gene_len)
except :