Spaces:
No application file
No application file
File size: 10,967 Bytes
b7731cd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 |
# Copyright 2014 by Kevin Wu.
# Revisions copyright 2014 by Peter Cock.
# All rights reserved.
#
# This file is part of the Biopython distribution and governed by your
# choice of the "Biopython License Agreement" or the "BSD 3-Clause License".
# Please see the LICENSE file that should have been included as part of this
# package.
"""Provides code to access the REST-style KEGG online API.
This module aims to make the KEGG online REST-style API easier to use. See:
https://www.kegg.jp/kegg/rest/keggapi.html
The KEGG REST-style API provides simple access to a range of KEGG databases.
This works using simple URLs (which this module will construct for you),
with any errors indicated via HTTP error levels.
The functionality is somewhat similar to Biopython's Bio.TogoWS and Bio.Entrez
modules.
Currently KEGG does not provide any usage guidelines (unlike the NCBI whose
requirements are reasonably clear). To avoid risking overloading the service,
Biopython will only allow three calls per second.
References:
Kanehisa, M. and Goto, S.; KEGG: Kyoto Encyclopedia of Genes and Genomes.
Nucleic Acids Res. 28, 29-34 (2000).
"""
import io
from urllib.request import urlopen
def _q(op, arg1, arg2=None, arg3=None):
URL = "https://rest.kegg.jp/%s"
if arg2 and arg3:
args = f"{op}/{arg1}/{arg2}/{arg3}"
elif arg2:
args = f"{op}/{arg1}/{arg2}"
else:
args = f"{op}/{arg1}"
resp = urlopen(URL % (args))
if "image" == arg2:
return resp
handle = io.TextIOWrapper(resp, encoding="UTF-8")
handle.url = resp.url
return handle
# https://www.kegg.jp/kegg/rest/keggapi.html
def kegg_info(database):
"""KEGG info - Displays the current statistics of a given database.
db - database or organism (string)
The argument db can be a KEGG database name (e.g. 'pathway' or its
official abbreviation, 'path'), or a KEGG organism code or T number
(e.g. 'hsa' or 'T01001' for human).
A valid list of organism codes and their T numbers can be obtained
via kegg_info('organism') or https://rest.kegg.jp/list/organism
"""
# TODO - return a string (rather than the handle?)
# TODO - cache and validate the organism code / T numbers?
# TODO - can we parse the somewhat formatted output?
#
# https://rest.kegg.jp/info/<database>
#
# <database> = pathway | brite | module | disease | drug | environ |
# ko | genome |<org> | compound | glycan | reaction |
# rpair | rclass | enzyme | genomes | genes | ligand | kegg
# <org> = KEGG organism code or T number
return _q("info", database)
def kegg_list(database, org=None):
"""KEGG list - Entry list for database, or specified database entries.
db - database or organism (string)
org - optional organism (string), see below.
For the pathway and module databases the optional organism can be
used to restrict the results.
"""
# TODO - split into two functions (dbentries seems separate)?
#
# https://rest.kegg.jp/list/<database>/<org>
#
# <database> = pathway | module
# <org> = KEGG organism code
if database in ("pathway", "module") and org:
resp = _q("list", database, org)
elif isinstance(database, str) and database and org:
raise ValueError("Invalid database arg for kegg list request.")
# https://rest.kegg.jp/list/<database>
#
# <database> = pathway | brite | module | disease | drug | environ |
# ko | genome | <org> | compound | glycan | reaction |
# rpair | rclass | enzyme | organism
# <org> = KEGG organism code or T number
#
#
# https://rest.kegg.jp/list/<dbentries>
#
# <dbentries> = KEGG database entries involving the following <database>
# <database> = pathway | brite | module | disease | drug | environ |
# ko | genome | <org> | compound | glycan | reaction |
# rpair | rclass | enzyme
# <org> = KEGG organism code or T number
else:
if isinstance(database, list):
if len(database) > 100:
raise ValueError(
"Maximum number of databases is 100 for kegg list query"
)
database = ("+").join(database)
resp = _q("list", database)
return resp
def kegg_find(database, query, option=None):
"""KEGG find - Data search.
Finds entries with matching query keywords or other query data in
a given database.
db - database or organism (string)
query - search terms (string)
option - search option (string), see below.
For the compound and drug database, set option to the string 'formula',
'exact_mass' or 'mol_weight' to search on that field only. The
chemical formula search is a partial match irrespective of the order
of atoms given. The exact mass (or molecular weight) is checked by
rounding off to the same decimal place as the query data. A range of
values may also be specified with the minus(-) sign.
"""
# TODO - return list of tuples?
#
# https://rest.kegg.jp/find/<database>/<query>/<option>
#
# <database> = compound | drug
# <option> = formula | exact_mass | mol_weight
if database in ["compound", "drug"] and option in [
"formula",
"exact_mass",
"mol_weight",
]:
resp = _q("find", database, query, option)
elif option:
raise ValueError("Invalid option arg for kegg find request.")
# https://rest.kegg.jp/find/<database>/<query>
#
# <database> = pathway | module | disease | drug | environ | ko |
# genome | <org> | compound | glycan | reaction | rpair |
# rclass | enzyme | genes | ligand
# <org> = KEGG organism code or T number
else:
if isinstance(query, list):
query = "+".join(query)
resp = _q("find", database, query)
return resp
def kegg_get(dbentries, option=None):
"""KEGG get - Data retrieval.
dbentries - Identifiers (single string, or list of strings), see below.
option - One of "aaseq", "ntseq", "mol", "kcf", "image", "kgml" (string)
The input is limited up to 10 entries.
The input is limited to one pathway entry with the image or kgml option.
The input is limited to one compound/glycan/drug entry with the image option.
Returns a handle.
"""
if isinstance(dbentries, list) and len(dbentries) <= 10:
dbentries = "+".join(dbentries)
elif isinstance(dbentries, list) and len(dbentries) > 10:
raise ValueError("Maximum number of dbentries is 10 for kegg get query")
# https://rest.kegg.jp/get/<dbentries>[/<option>]
#
# <dbentries> = KEGG database entries involving the following <database>
# <database> = pathway | brite | module | disease | drug | environ |
# ko | genome | <org> | compound | glycan | reaction |
# rpair | rclass | enzyme
# <org> = KEGG organism code or T number
#
# <option> = aaseq | ntseq | mol | kcf | image
if option in ["aaseq", "ntseq", "mol", "kcf", "image", "kgml", "json"]:
resp = _q("get", dbentries, option)
elif option:
raise ValueError("Invalid option arg for kegg get request.")
else:
resp = _q("get", dbentries)
return resp
def kegg_conv(target_db, source_db, option=None):
"""KEGG conv - convert KEGG identifiers to/from outside identifiers.
Arguments:
- target_db - Target database
- source_db_or_dbentries - source database or database entries
- option - Can be "turtle" or "n-triple" (string).
"""
# https://rest.kegg.jp/conv/<target_db>/<source_db>[/<option>]
#
# (<target_db> <source_db>) = (<kegg_db> <outside_db>) |
# (<outside_db> <kegg_db>)
#
# For gene identifiers:
# <kegg_db> = <org>
# <org> = KEGG organism code or T number
# <outside_db> = ncbi-gi | ncbi-geneid | uniprot
#
# For chemical substance identifiers:
# <kegg_db> = drug | compound | glycan
# <outside_db> = pubchem | chebi
#
# <option> = turtle | n-triple
#
# https://rest.kegg.jp/conv/<target_db>/<dbentries>[/<option>]
#
# For gene identifiers:
# <dbentries> = database entries involving the following <database>
# <database> = <org> | ncbi-gi | ncbi-geneid | uniprot
# <org> = KEGG organism code or T number
#
# For chemical substance identifiers:
# <dbentries> = database entries involving the following <database>
# <database> = drug | compound | glycan | pubchem | chebi
#
# <option> = turtle | n-triple
if option and option not in ["turtle", "n-triple"]:
raise ValueError("Invalid option arg for kegg conv request.")
if isinstance(source_db, list):
source_db = "+".join(source_db)
if (
target_db in ["ncbi-gi", "ncbi-geneid", "uniprot"]
or source_db in ["ncbi-gi", "ncbi-geneid", "uniprot"]
or (
target_db in ["drug", "compound", "glycan"]
and source_db in ["pubchem", "glycan"]
)
or (
target_db in ["pubchem", "glycan"]
and source_db in ["drug", "compound", "glycan"]
)
):
if option:
resp = _q("conv", target_db, source_db, option)
else:
resp = _q("conv", target_db, source_db)
return resp
else:
raise ValueError("Bad argument target_db or source_db for kegg conv request.")
def kegg_link(target_db, source_db, option=None):
"""KEGG link - find related entries by using database cross-references.
target_db - Target database
source_db_or_dbentries - source database
option - Can be "turtle" or "n-triple" (string).
"""
# https://rest.kegg.jp/link/<target_db>/<source_db>[/<option>]
#
# <target_db> = <database>
# <source_db> = <database>
#
# <database> = pathway | brite | module | ko | genome | <org> | compound |
# glycan | reaction | rpair | rclass | enzyme | disease |
# drug | dgroup | environ
#
# <option> = turtle | n-triple
# https://rest.kegg.jp/link/<target_db>/<dbentries>[/<option>]
#
# <dbentries> = KEGG database entries involving the following <database>
# <database> = pathway | brite | module | ko | genome | <org> | compound |
# glycan | reaction | rpair | rclass | enzyme | disease |
# drug | dgroup | environ | genes
#
# <option> = turtle | n-triple
if option and option not in ["turtle", "n-triple"]:
raise ValueError("Invalid option arg for kegg conv request.")
if isinstance(source_db, list):
source_db = "+".join(source_db)
if option:
resp = _q("link", target_db, source_db, option)
else:
resp = _q("link", target_db, source_db)
return resp
|