Coverage for biobb_godmd/godmd/godmd_run.py: 83%

1#!/usr/bin/env python3 

2 

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

4 

5import shutil 

6from pathlib import Path, PurePath 

7from typing import Optional 

8 

9from biobb_common.generic.biobb_object import BiobbObject 

10from biobb_common.tools.file_utils import launchlogger 

11 

12from biobb_godmd.godmd.common import check_input_path, check_output_path 

13 

14 

15class GOdMDRun(BiobbObject): 

16 """ 

17 | biobb_godmd GOdMDRun 

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

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

20 

21 Args: 

22 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/main/biobb_godmd/test/data/godmd/1ake_A.pdb>`_. Accepted formats: pdb (edam:format_1476). 

23 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/main/biobb_godmd/test/data/godmd/4ake_A.pdb>`_. Accepted formats: pdb (edam:format_1476). 

24 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/main/biobb_godmd/test/data/godmd/1ake_A.aln>`_. Accepted formats: aln (edam:format_2330), txt (edam:format_2330). 

25 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/main/biobb_godmd/test/data/godmd/4ake_A.aln>`_. Accepted formats: aln (edam:format_2330), txt (edam:format_2330). 

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

27 output_log_path (str): Output log file. File type: output. `Sample file <https://github.com/bioexcel/biobb_godmd/raw/main/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). 

28 output_ene_path (str): Output energy file. File type: output. `Sample file <https://github.com/bioexcel/biobb_godmd/raw/main/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). 

29 output_trj_path (str): Output trajectory file. File type: output. `Sample file <https://github.com/bioexcel/biobb_godmd/raw/main/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). 

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

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

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

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

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

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

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

37 * **container_path** (*str*) - (None) Container path definition. 

38 * **container_image** (*str*) - ('afandiadib/ambertools:serial') Container image definition. 

39 * **container_volume_path** (*str*) - ('/tmp') Container volume path definition. 

40 * **container_working_dir** (*str*) - (None) Container working directory definition. 

41 * **container_user_id** (*str*) - (None) Container user_id definition. 

42 * **container_shell_path** (*str*) - ('/bin/bash') Path to default shell inside the container. 

43 

44 Examples: 

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

46 

47 from biobb_godmd.godmd.godmd_run import godmd_run 

48 prop = { 

49 'remove_tmp': True 

50 } 

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

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

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

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

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

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

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

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

59 properties=prop) 

60 

61 Info: 

62 * wrapped_software: 

63 * name: GOdMD 

64 * version: >=1.0 

65 * license: Apache-2.0 

66 * ontology: 

67 * name: EDAM 

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

69 

70 """ 

71 

72 def __init__( 

73 self, 

74 input_pdb_orig_path: str, 

75 input_pdb_target_path: str, 

76 input_aln_orig_path: str, 

77 input_aln_target_path: str, 

78 input_config_path: Optional[str], 

79 output_log_path: str, 

80 output_ene_path: str, 

81 output_trj_path: str, 

82 output_pdb_path: str, 

83 properties: Optional[dict] = None, 

84 **kwargs, 

85 ) -> None: 

86 properties = properties or {} 

87 

88 # Call parent class constructor 

89 super().__init__(properties) 

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

91 

92 # Input/Output files 

93 self.io_dict = { 

94 "in": { 

95 "input_pdb_orig_path": input_pdb_orig_path, 

96 "input_pdb_target_path": input_pdb_target_path, 

97 "input_aln_orig_path": input_aln_orig_path, 

98 "input_aln_target_path": input_aln_target_path, 

99 "input_config_path": input_config_path, 

100 }, 

101 "out": { 

102 "output_log_path": output_log_path, 

103 "output_ene_path": output_ene_path, 

104 "output_trj_path": output_trj_path, 

105 "output_pdb_path": output_pdb_path, 

106 }, 

107 } 

108 

109 # Properties specific for BB 

110 self.properties = properties 

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

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

113 

114 # Check the properties 

115 self.check_properties(properties) 

116 # self.check_arguments() 

117 

118 def check_data_params(self, out_log, out_err): 

119 """Checks input/output paths correctness""" 

120 

121 # Check input(s) 

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

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

124 "input_pdb_orig_path", 

125 False, 

126 out_log, 

127 self.__class__.__name__, 

128 ) 

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

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

131 "input_pdb_target_path", 

132 False, 

133 out_log, 

134 self.__class__.__name__, 

135 ) 

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

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

138 "input_aln_orig_path", 

139 False, 

140 out_log, 

141 self.__class__.__name__, 

142 ) 

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

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

145 "input_aln_target_path", 

146 False, 

147 out_log, 

148 self.__class__.__name__, 

149 ) 

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

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

152 "input_config_path", 

153 True, 

154 out_log, 

155 self.__class__.__name__, 

156 ) 

157 

158 # Check output(s) 

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

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

161 "output_log_path", 

162 False, 

163 out_log, 

164 self.__class__.__name__, 

165 ) 

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

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

168 "output_ene_path", 

169 False, 

170 out_log, 

171 self.__class__.__name__, 

172 ) 

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

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

175 "output_trj_path", 

176 False, 

177 out_log, 

178 self.__class__.__name__, 

179 ) 

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

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

182 "output_pdb_path", 

183 False, 

184 out_log, 

185 self.__class__.__name__, 

186 ) 

187 

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

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

190 godmdin_list = [] 

191 

192 self.output_godmdin_path = path 

193 

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

195 # GOdMD input parameters read from an input godmdin file 

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

197 for line in input_params: 

198 if "=" in line: 

199 godmdin_list.append(line.upper()) 

200 else: 

201 # Pre-configured simulation type parameters 

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

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

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

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

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

207 godmdin_list.append( 

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

209 ) 

210 

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

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

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

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

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

216 if config_parameter_key in parameter_keys: 

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

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

219 ) 

220 else: 

221 godmdin_list.append( 

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

223 ) 

224 

225 # Writing MD configuration file (mdin) 

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

227 # GOdMDIN parameters added by the biobb_godmd module 

228 godmdin.write( 

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

230 ) 

231 

232 godmdin.write("&INPUT\n") 

233 

234 # MD config parameters 

235 for line in godmdin_list: 

236 godmdin.write(line) 

237 

238 godmdin.write("&END\n") 

239 

240 return str(self.output_godmdin_path) 

241 

242 @launchlogger 

243 def launch(self): 

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

245 

246 # check input/output paths and parameters 

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

248 

249 # Setup Biobb 

250 if self.check_restart(): 

251 return 0 

252 self.stage_files() 

253 

254 if self.container_path: 

255 working_dir = self.container_volume_path if self.container_volume_path else "/data" 

256 else: 

257 working_dir = self.stage_io_dict.get("unique_dir", "") 

258 

259 # Creating GOdMD input file 

260 self.output_godmdin_path = self.create_godmdin( 

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

262 ) 

263 

264 # Command line 

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

266 self.cmd = [ 

267 "cd", 

268 working_dir, 

269 ";", 

270 self.binary_path, 

271 "-i", 

272 PurePath(self.output_godmdin_path).name, 

273 "-pdbin", 

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

275 "-pdbtarg", 

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

277 "-p1", 

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

279 "-p2", 

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

281 "-o", 

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

283 "-ener", 

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

285 "-trj", 

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

287 ] 

288 

289 # Run Biobb block 

290 self.run_biobb() 

291 

292 # Stage the fixed-name output file so copy_to_host can remap it correctly. 

293 generated_output = Path(self.stage_io_dict.get("unique_dir", "")).joinpath("reference.pdb") 

294 staged_output = Path(self.stage_io_dict.get("unique_dir", "")).joinpath( 

295 Path(self.stage_io_dict["out"]["output_pdb_path"]).name 

296 ) 

297 shutil.copy2(str(generated_output), str(staged_output)) 

298 

299 # Copy files to host 

300 self.copy_to_host() 

301 

302 # Remove temporary folder(s) 

303 self.remove_tmp_files() 

304 

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

306 

307 return self.return_code 

308 

309 

310def godmd_run( 

311 input_pdb_orig_path: str, 

312 input_pdb_target_path: str, 

313 input_aln_orig_path: str, 

314 input_aln_target_path: str, 

315 output_log_path: str, 

316 output_ene_path: str, 

317 output_trj_path: str, 

318 output_pdb_path: str, 

319 input_config_path: Optional[str] = None, 

320 properties: Optional[dict] = None, 

321 **kwargs, 

322) -> int: 

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

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

325 return GOdMDRun(**dict(locals())).launch() 

326 

327 

328godmd_run.__doc__ = GOdMDRun.__doc__ 

329main = GOdMDRun.get_main(godmd_run, "Computing conformational transition trajectories for proteins using GOdMD tool.") 

330 

331if __name__ == "__main__": 

332 main()