jbnara

library(ontologyIndex)

phe_dat = as.matrix(read.csv('/home/starjjbang/Storage/part1/SAAVpedia/data/anno_file/tmp/9_ESP_1000G_pheno_drug_PTM_ontology_function.txt',sep='\t',header = FALSE, row.names = NULL))

of = '/home/starjjbang/Storage/part1/SAAVpedia/data/ontology/efo.obo'

efo = get_OBO(of, propagate_relationships = "is_a", extract_tags = "everything")

data(hpo)

tmp1 = rep('NA',nrow(phe_dat))

for(i in 1:nrow(phe_dat))

{

  term = phe_dat[i,41]

  if (is.na(term)==FALSE)

  {

    if(term=="COSMIC"){ tmp1[i] = "cancer"  }

    else if ( grepl('^Orphanet',term)) { tmp1[i] = "rare disease" }

    else if ( grepl('^EFO',term)) 

      {

        p_id =get_term_property(ontology=efo, property="ancestors", term=term, as_names=TRUE)

        if("EFO:0000408" %in% names(p_id)){tmp1[i] = p_id[which(names(p_id) == "EFO:0000408") +1]}

        else if ("EFO:0004725" %in% names(p_id)){tmp1[i] = p_id[which(names(p_id) == "EFO:0004725") +1]}

        else {tmp1[i] = 'ETC'}

      }

    else if ( grepl('^HP',term)) 

      {

        if(is.na(hpo$id["HP:0025268"]) == FALSE)

        {

          p_id =get_term_property(ontology=hpo, property="ancestors", term=term, as_names=TRUE)

          if("HP:0000118" %in% names(p_id)){tmp1[i] = p_id[which(names(p_id) == "HP:0000118") +1]}

          else {tmp1[i] = 'ETC'}          

        }

      }

    else {tmp1[i] = 'ETC'}

  }

 }

import sys
import urllib
import json
def readRSNumToJson(sRSNum):
    sURL = "http://grch37.rest.ensembl.org/variation/human/"+sRSNum+"?content-type=application/json"
    dRSNum = json.loads(urllib.urlopen(sURL).read().decode('utf-8'))
    return dRSNum
#end: def readRSNumToJson
if __name__ == "__main__":
	i = 0
	re = open('/Users/lsy/Desktop/neXtProt_rs_map.txt','a')
	f = open('/Users/lsy/Desktop/neXtProt_XML_MTsort_2.txt','r')
	for f_line in f.xreadlines():
		if i > 12871:
			f_sp = f_line.strip().split('\t')
			if f_sp[1].startswith('rs'):
				sRSNum = f_sp[1]
		    	dRSNum = readRSNumToJson(sRSNum)
		    	if len(dRSNum['mappings']) > 0:
		    		a = str(dRSNum['mappings'][0]['location'])
		    		b = str(dRSNum['mappings'][0]['allele_string'])
		    		re.write('\t'.join(f_sp + [a,b]) + '\n')
	    	print i
	    	i+= 1
	re.close()