Coverage for biobb_godmd/godmd/godmd_run.py: 19%

1#!/usr/bin/env python3 

2 

3"""Module containing the GOdMDRun class and the command line interface.""" 

4 

5import argparse 

6import shutil 

7from pathlib import Path, PurePath 

8from typing import Optional 

9 

10from biobb_common.configuration import settings 

11from biobb_common.generic.biobb_object import BiobbObject 

12from biobb_common.tools.file_utils import launchlogger 

13 

14from biobb_godmd.godmd.common import check_input_path, check_output_path 

15 

16 

17class GOdMDRun(BiobbObject): 

18 """ 

19 | biobb_godmd GOdMDRun 

20 | Wrapper of the `GOdMD tool <http://mmb.irbbarcelona.org/GOdMD/>`_ module. 

21 | Computes conformational transition trajectories for proteins using GOdMD tool. 

22 

23 Args: 

24 input_pdb_orig_path (str): Input PDB file to be used as origin in the conformational transition. File type: input. `Sample file <https://github.com/bioexcel/biobb_godmd/raw/master/biobb_godmd/test/data/godmd/1ake_A.pdb>`_. Accepted formats: pdb (edam:format_1476). 

25 input_pdb_target_path (str): Input PDB file to be used as target in the conformational transition. File type: input. `Sample file <https://github.com/bioexcel/biobb_godmd/raw/master/biobb_godmd/test/data/godmd/4ake_A.pdb>`_. Accepted formats: pdb (edam:format_1476). 

26 input_aln_orig_path (str): Input GOdMD alignment file corresponding to the origin structure of the conformational transition. File type: input. `Sample file <https://github.com/bioexcel/biobb_godmd/raw/master/biobb_godmd/test/data/godmd/1ake_A.aln>`_. Accepted formats: aln (edam:format_2330), txt (edam:format_2330). 

27 input_aln_target_path (str): Input GOdMD alignment file corresponding to the target structure of the conformational transition. File type: input. `Sample file <https://github.com/bioexcel/biobb_godmd/raw/master/biobb_godmd/test/data/godmd/4ake_A.aln>`_. Accepted formats: aln (edam:format_2330), txt (edam:format_2330). 

28 input_config_path (str) (Optional): Input GOdMD configuration file. File type: input. `Sample file <https://github.com/bioexcel/biobb_godmd/raw/master/biobb_godmd/test/data/godmd/params.in>`_. Accepted formats: in (edam:format_2330), txt (edam:format_2330). 

29 output_log_path (str): Output log file. File type: output. `Sample file <https://github.com/bioexcel/biobb_godmd/raw/master/biobb_godmd/test/reference/godmd/godmd.log>`_. Accepted formats: log (edam:format_2330), out (edam:format_2330), txt (edam:format_2330), o (edam:format_2330). 

30 output_ene_path (str): Output energy file. File type: output. `Sample file <https://github.com/bioexcel/biobb_godmd/raw/master/biobb_godmd/test/reference/godmd/godmd_ene.out>`_. Accepted formats: log (edam:format_2330), out (edam:format_2330), txt (edam:format_2330), o (edam:format_2330). 

31 output_trj_path (str): Output trajectory file. File type: output. `Sample file <https://github.com/bioexcel/biobb_godmd/raw/master/biobb_godmd/test/reference/godmd/godmd_trj.mdcrd>`_. Accepted formats: trj (edam:format_3878), crd (edam:format_3878), mdcrd (edam:format_3878), x (edam:format_3878). 

32 output_pdb_path (str): Output structure file. File type: output. `Sample file <https://github.com/bioexcel/biobb_godmd/raw/master/biobb_godmd/test/reference/godmd/godmd_pdb.pdb>`_. Accepted formats: pdb (edam:format_1476). 

33 properties (dict - Python dictionary object containing the tool parameters, not input/output files): 

34 * **godmdin** (*dict*) - ({}) GOdMD options specification. 

35 * **binary_path** (*str*) - ("discrete") Binary path. 

36 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files. 

37 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist. 

38 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory. 

39 

40 Examples: 

41 This is a use example of how to use the building block from Python:: 

42 

43 from biobb_godmd.godmd.godmd_run import godmd_run 

44 prop = { 

45 'remove_tmp': True 

46 } 

47 godmd_run( input_pdb_orig_path='/path/to/pdb_orig.pdb', 

48 input_pdb_target_path='/path/to/pdb_target.pdb', 

49 input_aln_orig_path='/path/to/aln_orig.aln', 

50 input_aln_target_path='/path/to/aln_target.aln', 

51 output_log_path='/path/to/godmd_log.log', 

52 output_ene_path='/path/to/godmd_ene.txt', 

53 output_trj_path='/path/to/godmd_trj.mdcrd', 

54 output_pdb_path='/path/to/godmd_pdb.pdb', 

55 properties=prop) 

56 

57 Info: 

58 * wrapped_software: 

59 * name: GOdMD 

60 * version: >=1.0 

61 * license: Apache-2.0 

62 * ontology: 

63 * name: EDAM 

64 * schema: http://edamontology.org/EDAM.owl 

65 

66 """ 

67 

68 def __init__( 

69 self, 

70 input_pdb_orig_path: str, 

71 input_pdb_target_path: str, 

72 input_aln_orig_path: str, 

73 input_aln_target_path: str, 

74 input_config_path: Optional[str], 

75 output_log_path: str, 

76 output_ene_path: str, 

77 output_trj_path: str, 

78 output_pdb_path: str, 

79 properties: Optional[dict] = None, 

80 **kwargs, 

81 ) -> None: 

82 properties = properties or {} 

83 

84 # Call parent class constructor 

85 super().__init__(properties) 

86 self.locals_var_dict = locals().copy() 

87 

88 # Input/Output files 

89 self.io_dict = { 

90 "in": { 

91 "input_pdb_orig_path": input_pdb_orig_path, 

92 "input_pdb_target_path": input_pdb_target_path, 

93 "input_aln_orig_path": input_aln_orig_path, 

94 "input_aln_target_path": input_aln_target_path, 

95 "input_config_path": input_config_path, 

96 }, 

97 "out": { 

98 "output_log_path": output_log_path, 

99 "output_ene_path": output_ene_path, 

100 "output_trj_path": output_trj_path, 

101 "output_pdb_path": output_pdb_path, 

102 }, 

103 } 

104 

105 # Properties specific for BB 

106 self.properties = properties 

107 self.godmdin = {k: str(v) for k, v in properties.get("godmdin", dict()).items()} 

108 self.binary_path = properties.get("binary_path", "discrete") 

109 

110 # Check the properties 

111 self.check_properties(properties) 

112 # self.check_arguments() 

113 

114 def check_data_params(self, out_log, out_err): 

115 """Checks input/output paths correctness""" 

116 

117 # Check input(s) 

118 self.io_dict["in"]["input_pdb_orig_path"] = check_input_path( 

119 self.io_dict["in"]["input_pdb_orig_path"], 

120 "input_pdb_orig_path", 

121 False, 

122 out_log, 

123 self.__class__.__name__, 

124 ) 

125 self.io_dict["in"]["input_pdb_target_path"] = check_input_path( 

126 self.io_dict["in"]["input_pdb_target_path"], 

127 "input_pdb_target_path", 

128 False, 

129 out_log, 

130 self.__class__.__name__, 

131 ) 

132 self.io_dict["in"]["input_aln_orig_path"] = check_input_path( 

133 self.io_dict["in"]["input_aln_orig_path"], 

134 "input_aln_orig_path", 

135 False, 

136 out_log, 

137 self.__class__.__name__, 

138 ) 

139 self.io_dict["in"]["input_aln_target_path"] = check_input_path( 

140 self.io_dict["in"]["input_aln_target_path"], 

141 "input_aln_target_path", 

142 False, 

143 out_log, 

144 self.__class__.__name__, 

145 ) 

146 self.io_dict["in"]["input_config_path"] = check_input_path( 

147 self.io_dict["in"]["input_config_path"], 

148 "input_config_path", 

149 True, 

150 out_log, 

151 self.__class__.__name__, 

152 ) 

153 

154 # Check output(s) 

155 self.io_dict["out"]["output_log_path"] = check_output_path( 

156 self.io_dict["out"]["output_log_path"], 

157 "output_log_path", 

158 False, 

159 out_log, 

160 self.__class__.__name__, 

161 ) 

162 self.io_dict["out"]["output_ene_path"] = check_output_path( 

163 self.io_dict["out"]["output_ene_path"], 

164 "output_ene_path", 

165 False, 

166 out_log, 

167 self.__class__.__name__, 

168 ) 

169 self.io_dict["out"]["output_trj_path"] = check_output_path( 

170 self.io_dict["out"]["output_trj_path"], 

171 "output_trj_path", 

172 False, 

173 out_log, 

174 self.__class__.__name__, 

175 ) 

176 self.io_dict["out"]["output_pdb_path"] = check_output_path( 

177 self.io_dict["out"]["output_pdb_path"], 

178 "output_pdb_path", 

179 False, 

180 out_log, 

181 self.__class__.__name__, 

182 ) 

183 

184 def create_godmdin(self, path: Optional[str] = None) -> str: 

185 """Creates a GOdMD configuration file (godmdin) using the properties file settings""" 

186 godmdin_list = [] 

187 

188 self.output_godmdin_path = path 

189 

190 if self.io_dict["in"]["input_config_path"]: 

191 # GOdMD input parameters read from an input godmdin file 

192 with open(self.io_dict["in"]["input_config_path"]) as input_params: 

193 for line in input_params: 

194 if "=" in line: 

195 godmdin_list.append(line.upper()) 

196 else: 

197 # Pre-configured simulation type parameters 

198 godmdin_list.append(" TSNAP = 500 ! BioBB GOdMD default params \n") 

199 godmdin_list.append(" TEMP = 300 ! BioBB GOdMD default params \n") 

200 godmdin_list.append(" SEED = 2525 ! BioBB GOdMD default params \n") 

201 godmdin_list.append(" ENER_EVO_SIZE = 20 ! BioBB GOdMD default params \n") 

202 godmdin_list.append(" NBLOC = 10000 ! BioBB GOdMD default params \n") 

203 godmdin_list.append( 

204 " ERRORACCEPTABLE = 1.5 ! BioBB GOdMD default params \n" 

205 ) 

206 

207 # Adding the rest of parameters in the config file to the mdin file 

208 # if the parameter has already been added replace the value 

209 parameter_keys = [parameter.split("=")[0].strip() for parameter in godmdin_list] 

210 for k, v in self.godmdin.items(): 

211 config_parameter_key = str(k).strip().upper() 

212 if config_parameter_key in parameter_keys: 

213 godmdin_list[parameter_keys.index(config_parameter_key)] = ( 

214 "\t" + config_parameter_key + " = " + str(v) + " ! BioBB property \n" 

215 ) 

216 else: 

217 godmdin_list.append( 

218 "\t" + config_parameter_key + " = " + str(v) + " ! BioBB property \n" 

219 ) 

220 

221 # Writing MD configuration file (mdin) 

222 with open(str(self.output_godmdin_path), "w") as godmdin: 

223 # GOdMDIN parameters added by the biobb_godmd module 

224 godmdin.write( 

225 "!This godmdin file has been created by the biobb_godmd module from the BioBB library \n\n" 

226 ) 

227 

228 godmdin.write("&INPUT\n") 

229 

230 # MD config parameters 

231 for line in godmdin_list: 

232 godmdin.write(line) 

233 

234 godmdin.write("&END\n") 

235 

236 return str(self.output_godmdin_path) 

237 

238 @launchlogger 

239 def launch(self): 

240 """Launches the execution of the GOdMDRun module.""" 

241 

242 # check input/output paths and parameters 

243 self.check_data_params(self.out_log, self.err_log) 

244 

245 # Setup Biobb 

246 if self.check_restart(): 

247 return 0 

248 self.stage_files() 

249 

250 # Creating GOdMD input file 

251 self.output_godmdin_path = self.create_godmdin( 

252 path=str(Path(self.stage_io_dict["unique_dir"]).joinpath("godmd.in")) 

253 ) 

254 

255 # Command line 

256 # discrete -i $fileName.in -pdbin $pdbch1 -pdbtarg $pdbch2 -ener $fileName.ene -trj $fileName.crd -p1 $alignFile1 -p2 $alignFile2 -o $fileName.log >& $fileName.out 

257 self.cmd = [ 

258 "cd", 

259 self.stage_io_dict["unique_dir"], 

260 ";", 

261 self.binary_path, 

262 "-i", 

263 "godmd.in", 

264 "-pdbin", 

265 PurePath(self.stage_io_dict["in"]["input_pdb_orig_path"]).name, 

266 "-pdbtarg", 

267 PurePath(self.stage_io_dict["in"]["input_pdb_target_path"]).name, 

268 "-p1", 

269 PurePath(self.stage_io_dict["in"]["input_aln_orig_path"]).name, 

270 "-p2", 

271 PurePath(self.stage_io_dict["in"]["input_aln_target_path"]).name, 

272 "-o", 

273 PurePath(self.stage_io_dict["out"]["output_log_path"]).name, 

274 "-ener", 

275 PurePath(self.stage_io_dict["out"]["output_ene_path"]).name, 

276 "-trj", 

277 PurePath(self.stage_io_dict["out"]["output_trj_path"]).name, 

278 ] 

279 

280 # Run Biobb block 

281 self.run_biobb() 

282 

283 # Copy outputs from temporary folder to output path 

284 shutil.copy2( 

285 str(Path(self.stage_io_dict["unique_dir"]).joinpath("reference.pdb")), 

286 PurePath(self.io_dict["out"]["output_pdb_path"]), 

287 ) 

288 

289 # Copy files to host 

290 self.copy_to_host() 

291 

292 # remove temporary folder(s) 

293 # self.tmp_files.extend([ 

294 # self.stage_io_dict.get("unique_dir", ""), 

295 # ]) 

296 self.remove_tmp_files() 

297 

298 self.check_arguments(output_files_created=True, raise_exception=False) 

299 

300 return self.return_code 

301 

302 

303def godmd_run( 

304 input_pdb_orig_path: str, 

305 input_pdb_target_path: str, 

306 input_aln_orig_path: str, 

307 input_aln_target_path: str, 

308 output_log_path: str, 

309 output_ene_path: str, 

310 output_trj_path: str, 

311 output_pdb_path: str, 

312 input_config_path: Optional[str] = None, 

313 properties: Optional[dict] = None, 

314 **kwargs, 

315) -> int: 

316 """Create :class:`GOdMDRun <godmd.godmd_run.GOdMDRun>`godmd.godmd_run.GOdMDRun class and 

317 execute :meth:`launch() <godmd.godmd_run.GOdMDRun.launch>` method""" 

318 

319 return GOdMDRun( 

320 input_pdb_orig_path=input_pdb_orig_path, 

321 input_pdb_target_path=input_pdb_target_path, 

322 input_aln_orig_path=input_aln_orig_path, 

323 input_aln_target_path=input_aln_target_path, 

324 input_config_path=input_config_path, 

325 output_log_path=output_log_path, 

326 output_ene_path=output_ene_path, 

327 output_trj_path=output_trj_path, 

328 output_pdb_path=output_pdb_path, 

329 properties=properties, 

330 ).launch() 

331 

332 godmd_run.__doc__ = GOdMDRun.__doc__ 

333 

334 

335def main(): 

336 parser = argparse.ArgumentParser( 

337 description="Computing conformational transition trajectories for proteins using GOdMD tool.", 

338 formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999), 

339 ) 

340 parser.add_argument("--config", required=False, help="Configuration file") 

341 

342 # Specific args 

343 required_args = parser.add_argument_group("required arguments") 

344 required_args.add_argument( 

345 "--input_pdb_orig_path", 

346 required=True, 

347 help="Input PDB file to be used as origin in the conformational transition. Accepted formats: pdb.", 

348 ) 

349 required_args.add_argument( 

350 "--input_pdb_target_path", 

351 required=True, 

352 help="Input PDB file to be used as target in the conformational transition. Accepted formats: pdb.", 

353 ) 

354 required_args.add_argument( 

355 "--input_aln_orig_path", 

356 required=True, 

357 help="Input GOdMD alignment file corresponding to the origin structure of the conformational transition. Accepted formats: aln, txt.", 

358 ) 

359 required_args.add_argument( 

360 "--input_aln_target_path", 

361 required=True, 

362 help="Input GOdMD alignment file corresponding to the target structure of the conformational transition. Accepted formats: aln, txt.", 

363 ) 

364 required_args.add_argument( 

365 "--input_config_path", 

366 required=False, 

367 help="Input configuration file (GOdMD run options). Accepted formats: in, txt.", 

368 ) 

369 required_args.add_argument( 

370 "--output_log_path", 

371 required=True, 

372 help="Output log file. Accepted formats: log, out, txt.", 

373 ) 

374 required_args.add_argument( 

375 "--output_ene_path", 

376 required=True, 

377 help="Output energy file. Accepted formats: log, out, txt.", 

378 ) 

379 required_args.add_argument( 

380 "--output_trj_path", 

381 required=True, 

382 help="Output trajectory file. Accepted formats: mdcrd.", 

383 ) 

384 required_args.add_argument( 

385 "--output_pdb_path", 

386 required=True, 

387 help="Output structure file. Accepted formats: pdb.", 

388 ) 

389 

390 args = parser.parse_args() 

391 # config = args.config if args.config else None 

392 args.config = args.config or "{}" 

393 # properties = settings.ConfReader(config=config).get_prop_dic() 

394 properties = settings.ConfReader(config=args.config).get_prop_dic() 

395 

396 # Specific call 

397 godmd_run( 

398 input_pdb_orig_path=args.input_pdb_orig_path, 

399 input_pdb_target_path=args.input_pdb_target_path, 

400 input_aln_orig_path=args.input_aln_orig_path, 

401 input_aln_target_path=args.input_aln_target_path, 

402 input_config_path=args.input_config_path, 

403 output_log_path=args.output_log_path, 

404 output_ene_path=args.output_ene_path, 

405 output_trj_path=args.output_trj_path, 

406 output_pdb_path=args.output_pdb_path, 

407 properties=properties, 

408 ) 

409 

410 

411if __name__ == "__main__": 

412 main()