Skip to content

Instantly share code, notes, and snippets.

@leebird
Created April 6, 2016 18:08
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save leebird/c614c8e0a2a13e3dbc99c44fe59659bd to your computer and use it in GitHub Desktop.
Save leebird/c614c8e0a2a13e3dbc99c44fe59659bd to your computer and use it in GitHub Desktop.
Example of using miRTex miRNA NER API
from __future__ import print_function, unicode_literals
import json
import urllib
import urllib2
# The API URL.
api_url = 'http://research.bioinformatics.udel.edu/miRTex/ner'
# The documents to be processed.
documents = {
'doc1': 'Endogenous KLF4 bound to the promoter regions and promoted the expression of two microRNAs (miRs), miR-206 and miR-21 (i.e., miR-206/21).',
'doc2': 'We determined the hub CDK6, BCL2, E2F3, PTEN, MYC, RB, and ERBB3 target genes and hub hsa-let-7c, hsa-miR-195-5p, hsa-miR-141-3p, hsa-miR-26a-5p, hsa-miR-23b-3p, and hsa-miR-125b-5p miRNAs of the constructed networks.',
'doc3': 'MicroRNAs 206 and 21 cooperate to promote RAS-extracellular signal-regulated kinase signaling by suppressing the translation of RASA1 and SPRED1.',
}
# Dump the documents to a json string.
json_string = json.dumps(documents)
# Set the 'request' field value to the json string.
values = {'request': json_string}
data = urllib.urlencode(values)
# Send request and receive response.
req = urllib2.Request(api_url, data)
response = urllib2.urlopen(req)
json_return = response.read()
# Load result from the returned json string.
result = json.loads(json_return)
# Print result.
# Result is a hash table of <doc_id, mentions>. Each doc_id is
# mapped to a list of mentions. In the list of mentions, each mention
# is a 4-element tuple, <miRNA name, begin offset, end offset, miRNA numbers>.
# The begin offset is the mention's first character offset in the original
# text, while the end offset is the mention's last character offset in the
# original text + 1.
# The element of miRNA numbers is also a list, containing the number suffixes
# for the recognized miRNA. For example, for the name 'miR-206/21', the numbers
# are 206 and 21.
for doc_id, mentions in result.items():
for mention in mentions:
mention, begin, end, numbers = mention
print(doc_id, mention, begin, end, '|'.join(numbers), sep='\t')
'''
Printed results:
doc2 hsa-miR-195-5p 98 112 195-5p
doc2 hsa-miR-141-3p 114 128 141-3p
doc2 hsa-miR-26a-5p 130 144 26a-5p
doc2 hsa-miR-23b-3p 146 160 23b-3p
doc2 hsa-miR-125b-5p 166 181 125b-5p
doc2 hsa-let-7c 86 96 let7c
doc3 MicroRNAs 206 and 21 0 20 206|21
doc1 miR-206 99 106 206
doc1 miR-21 111 117 21
doc1 miR-206/21 125 135 206|21
'''
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment