Example #1
0
def get_uniprot_to_id(uniprot_file, uniprot_ids=None, only_min=True, key_function=int):
    """
    uniprot_file = %(data_dir)s/uniprot/idmapping.tab or idmapping.tab.symbol or idmapping.tab.mouse
    Can be used to convert to geneids (key_function=int) as well as symbols (key_function=len) depending on the input file
    """
    uniprot_to_gene = parse_uniprot.get_uniprot_to_geneid(uniprot_file, uniprot_ids, only_min, key_function)
    return uniprot_to_gene
Example #2
0
def main():
    mapping_file = "/home/emre/data/uniprot/idmapping.tab"
    uniprot_to_geneid = parse_uniprot.get_uniprot_to_geneid(mapping_file, uniprot_ids=None)
    file_name = "/home/emre/data/tissue/amigo_extracellular.tsv"
    #file_name = "/home/emre/data/tissue/amigo_membrane.tsv"
    geneid_to_localization = get_geneid_to_localization(file_name, mapping_file)
    print geneid_to_localization["5594"] # MAPK1
    return
Example #3
0
def get_geneid_to_localization(file_name, mapping_file):
    name_to_geneid = parse_uniprot.get_uniprot_to_geneid(mapping_file, uniprot_ids=None)
    geneid_to_localization = {}
    uniprots_unmatched = set()
    for line in open(file_name):
	words = line.strip("\n").split("\t")
	uniprot, go, evidence = words[0], words[3], words[7]
	idx = uniprot.find(":")
	uniprot = uniprot[idx+1:]
	#if evidence not in ("EXP", "IDA", "IPA", "IMP", "IGI", "IEP", "HDA"): 
	#    continue
	if uniprot in name_to_geneid:
	    geneid = name_to_geneid[uniprot]
	else:
	    #print "Unmatched id", uniprot
	    if not uniprot.startswith("URS"):
		uniprots_unmatched.add(uniprot)
	    continue
	# Store evidence type as well
	geneid_to_localization.setdefault(geneid, set()).add((go, evidence))
    print "Unmatched:", len(uniprots_unmatched) #, ", ".join(sorted(uniprots_unmatched))
    return geneid_to_localization
Example #4
0
def get_uniprot_to_symbol(uniprot_symbol_file, uniprot_ids):
    uniprot_to_geneid = parse_uniprot.get_uniprot_to_geneid(
        uniprot_symbol_file, uniprot_ids, only_min=False)
    return uniprot_to_geneid
Example #5
0
def get_uniprot_to_geneid(uniprot_file, uniprot_ids):
    uniprot_to_geneid = parse_uniprot.get_uniprot_to_geneid(
        uniprot_file, uniprot_ids)
    return uniprot_to_geneid
Example #6
0
def get_uniprot_to_geneid(uniprot_file, uniprot_ids):
    uniprot_to_geneid = parse_uniprot.get_uniprot_to_geneid(uniprot_file, uniprot_ids)
    return uniprot_to_geneid
Example #7
0
def get_uniprot_to_symbol(uniprot_symbol_file, uniprot_ids):
    uniprot_to_geneid = parse_uniprot.get_uniprot_to_geneid(uniprot_symbol_file, uniprot_ids, only_min=False)
    return uniprot_to_geneid