Mercurial > repos > in_silico > cravat_annotate_mutations
comparison cravat_annotate/cravat_annotate.py @ 20:c5b3d80c43e6 draft
Uploaded
| author | in_silico |
|---|---|
| date | Tue, 12 Jun 2018 14:06:22 -0400 |
| parents | dd9181024296 |
| children |
comparison
equal
deleted
inserted
replaced
| 19:ec55c91879e8 | 20:c5b3d80c43e6 |
|---|---|
| 1 """ | |
| 2 A galaxy wrapper for the /rest/service/query API endpoint on Cravat. | |
| 3 """ | |
| 4 | |
| 5 | |
| 6 import requests | |
| 7 import json | |
| 8 import sys | |
| 9 import re | |
| 10 import argparse | |
| 11 | |
| 12 | |
| 13 # The endpoint that CravatQuerys are submitted to | |
| 14 endpoint = 'http://cravat.us/CRAVAT/rest/service/query' | |
| 15 | |
| 16 | |
| 17 # The value delimiter used in the Cravat input file to delimit values | |
| 18 delimiter = "\t" | |
| 19 | |
| 20 | |
| 21 # Defualt indices for intepretting a cravat file's row of data in to a CravatQuery | |
| 22 cr_mapping = { | |
| 23 'chromosome': 1, | |
| 24 'position': 2, | |
| 25 'strand': 3, | |
| 26 'reference': 4, | |
| 27 'alternate': 5 | |
| 28 } | |
| 29 | |
| 30 | |
| 31 # The neccessary attributes neeeded to submit a query. | |
| 32 query_keys = [ | |
| 33 'chromosome', 'position', 'strand', 'reference', 'alternate' | |
| 34 ] | |
| 35 | |
| 36 | |
| 37 # Expected response keys from server. Ordered in list so that galaxy output has uniform column ordering run-to-run. | |
| 38 # If cravat server returns additional keys, they are appended to and included in output. | |
| 39 response_keys = [ | |
| 40 "Chromosome", "Position", "Strand", "Reference base(s)", "Alternate base(s)", | |
| 41 "HUGO symbol", "S.O. transcript", "Sequence ontology protein change", "Sequence ontology", | |
| 42 "S.O. all transcripts", "gnomAD AF", "gnomAD AF (African)", "gnomAD AF (Amrican)", | |
| 43 "gnomAD AF (Ashkenazi Jewish)", "gnomAD AF (East Asian)", "gnomAD AF (Finnish)", | |
| 44 "gnomAD AF (Non-Finnish European)", "gnomAD AF (Other)", "gnomAD AF (South Asian)", | |
| 45 "1000 Genomes AF", "ESP6500 AF (average)", "ESP6500 AF (European American)", | |
| 46 "ESP6500 AF (African American)", "COSMIC transcript", "COSMIC protein change", | |
| 47 "COSMIC variant count [exact nucleotide change]", "cosmic_site_nt", "CGL driver class", | |
| 48 "TARGET", "dbSNP", "cgc_role", "cgc_inheritance", "cgc_tumor_type_somatic", | |
| 49 "cgc_tumor_type_germline", "ClinVar", "ClinVar disease identifier", "ClinVar XRef", | |
| 50 "GWAS Phenotype (GRASP)", "GWAS PMID (GRASP)", "Protein 3D variant" | |
| 51 ] | |
| 52 | |
| 53 | |
| 54 def get_args(): | |
| 55 parser = argparse.ArgumentParser() | |
| 56 parser.add_argument('--input', | |
| 57 '-i', | |
| 58 required = True, | |
| 59 help='Input path to a VCF file for conversion',) | |
| 60 parser.add_argument('--output', | |
| 61 '-o', | |
| 62 default = None, | |
| 63 help = 'Output path to write the cravat file to') | |
| 64 return parser.parse_args() | |
| 65 | |
| 66 | |
| 67 def format_chromosome(chrom): | |
| 68 """ : Ensure chromosome entry is propely formatted for use as querying attribute. """ | |
| 69 if chrom[0:3] == 'chr': | |
| 70 return chrom | |
| 71 return 'chr' + str(chrom) | |
| 72 | |
| 73 | |
| 74 def get_query_string(row): | |
| 75 """ : From a row dict, return a query string for the Cravat server. | |
| 76 : The row dict is cravat headeres associated to their values of that row. | |
| 77 """ | |
| 78 return '_'.join([ row['chromosome'], row['position'], row['strand'], row['reference'], row['alternate'] ]) | |
| 79 | |
| 80 | |
| 81 def query(in_path, out_path): | |
| 82 """ : From a Cravat the file at in_path, query each line on the Cravat server. | |
| 83 : Write the response values to file at out_path. | |
| 84 """ | |
| 85 | |
| 86 with open(in_path, 'r') as in_file, \ | |
| 87 open(out_path, 'w') as out_file: | |
| 88 | |
| 89 for line in in_file: | |
| 90 line = line.strip().split('\t') | |
| 91 # row is dict of cravat col headers assioted values in this line | |
| 92 row = { header: line[index] for header, index in cr_mapping.items() } | |
| 93 row['chromosome'] = format_chromosome(row['chromosome']) | |
| 94 query_string = get_query_string(row) | |
| 95 call = requests.get(endpoint, params={ 'mutation': query_string }) | |
| 96 if call.status_code != 200 or call.text == "": | |
| 97 raise requests.RequestException("Bad Server Response. Respone code: '{}', Response Text: '{}'".format(call.status_code, call.text)) | |
| 98 json_response = json.loads(call.text) | |
| 99 # See if server returned additional json key-val paris not expected in response_keys | |
| 100 for key in json_response: | |
| 101 if key not in response_keys: | |
| 102 response_keys.append(key) | |
| 103 # Write key in order of response_keys to standardize order of output columns | |
| 104 wrote = False | |
| 105 for key in response_keys: | |
| 106 if key not in json_response: | |
| 107 val = None | |
| 108 val = json_response[key] | |
| 109 # Format standardization for numerics | |
| 110 try: | |
| 111 val = float(val) | |
| 112 val = format(val, ".4f") | |
| 113 except: | |
| 114 pass | |
| 115 if wrote: | |
| 116 out_file.write("\t") | |
| 117 out_file.write(val) | |
| 118 wrote = True | |
| 119 out_file.write("\n") | |
| 120 | |
| 121 | |
| 122 if __name__ == "__main__": | |
| 123 cli_args = get_args() | |
| 124 if cli_args.output == None: | |
| 125 base, _ = os.path.split(cli_args.input) | |
| 126 cli_args.output = os.path.join(base, "cravat_converted.txt") | |
| 127 query(cli_args.input, cli_args.output) |
