Coverage for biobb_amber / leap / leap_gen_top.py: 65%

1#!/usr/bin/env python3 

2 

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

4 

5import os 

6from pathlib import PurePath 

7from typing import List, Optional 

8 

9from biobb_common.generic.biobb_object import BiobbObject 

10from biobb_common.tools import file_utils as fu 

11from biobb_common.tools.file_utils import launchlogger 

12 

13from biobb_amber.leap.common import _from_string_to_list 

14 

15 

16class LeapGenTop(BiobbObject): 

17 """ 

18 | biobb_amber.leap.leap_gen_top LeapGenTop 

19 | Wrapper of the `AmberTools (AMBER MD Package) leap tool <https://ambermd.org/AmberTools.php>`_ module. 

20 | Generates a MD topology from a molecule structure using tLeap tool from the AmberTools MD package. 

21 

22 Args: 

23 input_pdb_path (str): Input 3D structure PDB file. File type: input. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/data/leap/structure.leapin.pdb>`_. Accepted formats: pdb (edam:format_1476). 

24 input_lib_path (str) (Optional): Input ligand library parameters file. File type: input. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/data/leap/ligand.lib>`_. Accepted formats: lib (edam:format_3889), zip (edam:format_3987). 

25 input_frcmod_path (str) (Optional): Input ligand frcmod parameters file. File type: input. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/data/leap/ligand.frcmod>`_. Accepted formats: frcmod (edam:format_3888), zip (edam:format_3987). 

26 input_params_path (str) (Optional): Additional leap parameter files to load with loadAmberParams Leap command. File type: input. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/data/leap/frcmod.ionsdang_spce.txt>`_. Accepted formats: in (edam:format_2330), leapin (edam:format_2330), txt (edam:format_2330), zip (edam:format_3987). 

27 input_prep_path (str) (Optional): Additional leap parameter files to load with loadAmberPrep Leap command. File type: input. Accepted formats: in (edam:format_2330), leapin (edam:format_2330), txt (edam:format_2330), zip (edam:format_3987). 

28 input_source_path (str) (Optional): Additional leap command files to load with source Leap command. File type: input. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/data/leap/leaprc.water.spce.txt>`_. Accepted formats: in (edam:format_2330), leapin (edam:format_2330), txt (edam:format_2330), zip (edam:format_3987). 

29 output_pdb_path (str): Output 3D structure PDB file matching the topology file. File type: output. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/reference/leap/structure.leap.pdb>`_. Accepted formats: pdb (edam:format_1476). 

30 output_top_path (str): Output topology file (AMBER ParmTop). File type: output. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/reference/leap/structure.leap.top>`_. Accepted formats: top (edam:format_3881), parmtop (edam:format_3881), prmtop (edam:format_3881). 

31 output_crd_path (str): Output coordinates file (AMBER crd). File type: output. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/reference/leap/structure.leap.crd>`_. Accepted formats: crd (edam:format_3878), mdcrd (edam:format_3878), inpcrd (edam:format_3878). 

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

33 * **forcefield** (*list*) - (["protein.ff14SB","DNA.bsc1","gaff"]) Forcefields to be used for the structure generation. Each item should be either a path to a leaprc file or a string with the leaprc file name if the force field is included with Amber (e.g. "/path/to/leaprc.protein.ff14SB" or "protein.ff14SB"). Default values: ["protein.ff14SB","DNA.bsc1","gaff"]. 

34 * **binary_path** (*str*) - ("tleap") Path to the tleap executable binary. 

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

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

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

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

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

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

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

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

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

44 

45 Examples: 

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

47 

48 from biobb_amber.leap.leap_gen_top import leap_gen_top 

49 prop = { 

50 'forcefield': ['protein.ff14SB'] 

51 } 

52 leap_gen_top(input_pdb_path='/path/to/structure.pdb', 

53 output_pdb_path='/path/to/newStructure.pdb', 

54 output_top_path='/path/to/newTopology.top', 

55 output_crd_path='/path/to/newCoordinates.crd', 

56 properties=prop) 

57 

58 Info: 

59 * wrapped_software: 

60 * name: AmberTools tLeap 

61 * version: >20.9 

62 * license: LGPL 2.1 

63 * ontology: 

64 * name: EDAM 

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

66 

67 """ 

68 

69 def __init__( 

70 self, 

71 input_pdb_path: str, 

72 output_pdb_path: str, 

73 output_top_path: str, 

74 output_crd_path: str, 

75 input_lib_path: Optional[str] = None, 

76 input_frcmod_path: Optional[str] = None, 

77 input_params_path: Optional[str] = None, 

78 input_prep_path: Optional[str] = None, 

79 input_source_path: Optional[str] = None, 

80 properties: Optional[dict] = None, 

81 **kwargs, 

82 ): 

83 properties = properties or {} 

84 

85 # Call parent class constructor 

86 super().__init__(properties) 

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

88 

89 # Input/Output files 

90 self.io_dict = { 

91 "in": { 

92 "input_pdb_path": input_pdb_path, 

93 "input_lib_path": input_lib_path, 

94 "input_frcmod_path": input_frcmod_path, 

95 "input_params_path": input_params_path, 

96 "input_prep_path": input_prep_path, 

97 "input_source_path": input_source_path, 

98 }, 

99 "out": { 

100 "output_pdb_path": output_pdb_path, 

101 "output_top_path": output_top_path, 

102 "output_crd_path": output_crd_path, 

103 }, 

104 } 

105 

106 # # Ligand Parameter lists 

107 # self.ligands_lib_list = [] 

108 # if input_lib_path: 

109 # self.ligands_lib_list.append(input_lib_path) 

110 # 

111 # self.ligands_frcmod_list = [] 

112 # if input_frcmod_path: 

113 # self.ligands_frcmod_list.append(input_frcmod_path) 

114 

115 # Set default forcefields 

116 amber_home_path = os.getenv("AMBERHOME") 

117 protein_ff14SB_path = os.path.join(amber_home_path, 'dat', 'leap', 'cmd', 'leaprc.protein.ff14SB') 

118 dna_bsc1_path = os.path.join(amber_home_path, 'dat', 'leap', 'cmd', 'leaprc.DNA.bsc1') 

119 gaff_path = os.path.join(amber_home_path, 'dat', 'leap', 'cmd', 'leaprc.gaff') 

120 

121 # Properties specific for BB 

122 self.properties = properties 

123 self.forcefield = _from_string_to_list( 

124 properties.get("forcefield", [protein_ff14SB_path, dna_bsc1_path, gaff_path]) 

125 ) 

126 # Find the paths of the leaprc files if only the force field names are provided 

127 self.forcefield = self.find_leaprc_paths(self.forcefield) 

128 

129 self.binary_path = properties.get("binary_path", "tleap") 

130 

131 # Check the properties 

132 self.check_properties(properties) 

133 self.check_arguments() 

134 

135 def find_leaprc_paths(self, forcefields: List[str]) -> List[str]: 

136 """ 

137 Find the leaprc paths for the force fields provided. 

138 

139 For each item in the forcefields list, the function checks if the str is a path to an existing file. 

140 If not, it tries to find the file in the $AMBERHOME/dat/leap/cmd/ directory or the $AMBERHOME/dat/leap/cmd/oldff/ 

141 directory with and without the leaprc prefix. 

142 

143 Args: 

144 forcefields (List[str]): List of force fields to find the leaprc files for. 

145 

146 Returns: 

147 List[str]: List of leaprc file paths. 

148 """ 

149 

150 leaprc_paths = [] 

151 

152 for forcefield in forcefields: 

153 

154 num_paths = len(leaprc_paths) 

155 

156 # Check if the forcefield is a path to an existing file 

157 if os.path.exists(forcefield): 

158 leaprc_paths.append(forcefield) 

159 continue 

160 

161 # Check if the forcefield is in the leaprc directory 

162 leaprc_path = os.path.join(os.environ.get('AMBERHOME', ''), 'dat', 'leap', 'cmd', f"leaprc.{forcefield}") 

163 if os.path.exists(leaprc_path): 

164 leaprc_paths.append(leaprc_path) 

165 continue 

166 

167 # Check if the forcefield is in the oldff directory 

168 leaprc_path = os.path.join(os.environ.get('AMBERHOME', ''), 'dat', 'leap', 'cmd', 'oldff', f"leaprc.{forcefield}") 

169 if os.path.exists(leaprc_path): 

170 leaprc_paths.append(leaprc_path) 

171 continue 

172 

173 # Check if the forcefield is in the leaprc directory without the leaprc prefix 

174 leaprc_path = os.path.join(os.environ.get('AMBERHOME', ''), 'dat', 'leap', 'cmd', f"{forcefield}") 

175 if os.path.exists(leaprc_path): 

176 leaprc_paths.append(leaprc_path) 

177 continue 

178 

179 # Check if the forcefield is in the oldff directory without the leaprc prefix 

180 leaprc_path = os.path.join(os.environ.get('AMBERHOME', ''), 'dat', 'leap', 'cmd', 'oldff', f"{forcefield}") 

181 if os.path.exists(leaprc_path): 

182 leaprc_paths.append(leaprc_path) 

183 continue 

184 

185 new_num_paths = len(leaprc_paths) 

186 

187 if new_num_paths == num_paths: 

188 raise ValueError(f"Force field {forcefield} not found. Check the $AMBERHOME/dat/leap/cmd/ directory for available force fields or provide the path to an existing leaprc file.") 

189 

190 return leaprc_paths 

191 

192 # def check_data_params(self, out_log, err_log): 

193 # """ Checks input/output paths correctness """ 

194 

195 # # Check input(s) 

196 # self.io_dict["in"]["input_pdb_path"] = check_input_path(self.io_dict["in"]["input_pdb_path"], "input_pdb_path", False, out_log, self.__class__.__name__) 

197 # self.io_dict["in"]["input_lib_path"] = check_input_path(self.io_dict["in"]["input_lib_path"], "input_lib_path", True, out_log, self.__class__.__name__) 

198 # self.io_dict["in"]["input_frcmod_path"] = check_input_path(self.io_dict["in"]["input_frcmod_path"], "input_frcmod_path", True, out_log, self.__class__.__name__) 

199 # # self.io_dict["in"]["input_params_path"] = check_input_path(self.io_dict["in"]["input_params_path"], "input_params_path", True, out_log, self.__class__.__name__) 

200 # # self.io_dict["in"]["input_prep_path"] = check_input_path(self.io_dict["in"]["input_params_path"], "input_params_path", True, out_log, self.__class__.__name__) 

201 # # self.io_dict["in"]["input_source_path"] = check_input_path(self.io_dict["in"]["input_source_path"], "input_source_path", True, out_log, self.__class__.__name__) 

202 

203 # # Check output(s) 

204 # self.io_dict["out"]["output_pdb_path"] = check_output_path(self.io_dict["out"]["output_pdb_path"], "output_pdb_path", False, out_log, self.__class__.__name__) 

205 # self.io_dict["out"]["output_top_path"] = check_output_path(self.io_dict["out"]["output_top_path"], "output_top_path", False, out_log, self.__class__.__name__) 

206 # self.io_dict["out"]["output_crd_path"] = check_output_path(self.io_dict["out"]["output_crd_path"], "output_crd_path", False, out_log, self.__class__.__name__) 

207 

208 @launchlogger 

209 def launch(self): 

210 """Launches the execution of the LeapGenTop module.""" 

211 

212 # check input/output paths and parameters 

213 # self.check_data_params(self.out_log, self.err_log) 

214 

215 # Setup Biobb 

216 if self.check_restart(): 

217 return 0 

218 self.stage_files() 

219 

220 # Creating temporary folder & Leap configuration (instructions) file 

221 if self.container_path: 

222 instructions_file = str( 

223 PurePath(self.stage_io_dict["unique_dir"]).joinpath("leap.in") 

224 ) 

225 instructions_file_path = str( 

226 PurePath(self.container_volume_path).joinpath("leap.in") 

227 ) 

228 self.tmp_folder = None 

229 else: 

230 self.tmp_folder = fu.create_unique_dir() 

231 instructions_file = str(PurePath(self.tmp_folder).joinpath("leap.in")) 

232 fu.log("Creating %s temporary folder" % self.tmp_folder, self.out_log) 

233 instructions_file_path = instructions_file 

234 

235 ligands_lib_list = [] 

236 if self.io_dict["in"]["input_lib_path"] is not None: 

237 if self.io_dict["in"]["input_lib_path"].endswith(".zip"): 

238 ligands_lib_list = fu.unzip_list( 

239 self.stage_io_dict["in"]["input_lib_path"], 

240 dest_dir=self.tmp_folder, 

241 out_log=self.out_log, 

242 ) 

243 else: 

244 ligands_lib_list.append(self.stage_io_dict["in"]["input_lib_path"]) 

245 

246 ligands_frcmod_list = [] 

247 if self.io_dict["in"]["input_frcmod_path"] is not None: 

248 if self.io_dict["in"]["input_frcmod_path"].endswith(".zip"): 

249 ligands_frcmod_list = fu.unzip_list( 

250 self.stage_io_dict["in"]["input_frcmod_path"], 

251 dest_dir=self.tmp_folder, 

252 out_log=self.out_log, 

253 ) 

254 else: 

255 ligands_frcmod_list.append( 

256 self.stage_io_dict["in"]["input_frcmod_path"] 

257 ) 

258 

259 amber_params_list = [] 

260 if self.io_dict["in"]["input_params_path"] is not None: 

261 if self.io_dict["in"]["input_params_path"].endswith(".zip"): 

262 amber_params_list = fu.unzip_list( 

263 self.stage_io_dict["in"]["input_params_path"], 

264 dest_dir=self.tmp_folder, 

265 out_log=self.out_log, 

266 ) 

267 else: 

268 amber_params_list.append(self.stage_io_dict["in"]["input_params_path"]) 

269 

270 amber_prep_list = [] 

271 if self.io_dict["in"]["input_prep_path"] is not None: 

272 if self.io_dict["in"]["input_prep_path"].endswith(".zip"): 

273 amber_prep_list = fu.unzip_list( 

274 self.stage_io_dict["in"]["input_prep_path"], 

275 dest_dir=self.tmp_folder, 

276 out_log=self.out_log, 

277 ) 

278 else: 

279 amber_prep_list.append(self.stage_io_dict["in"]["input_prep_path"]) 

280 

281 leap_source_list = [] 

282 if self.io_dict["in"]["input_source_path"] is not None: 

283 if self.io_dict["in"]["input_source_path"].endswith(".zip"): 

284 leap_source_list = fu.unzip_list( 

285 self.stage_io_dict["in"]["input_source_path"], 

286 dest_dir=self.tmp_folder, 

287 out_log=self.out_log, 

288 ) 

289 else: 

290 leap_source_list.append(self.stage_io_dict["in"]["input_source_path"]) 

291 

292 with open(instructions_file, "w") as leapin: 

293 # Forcefields loaded by default: 

294 # Protein: ff14SB (PARM99 + frcmod.ff99SB + frcmod.parmbsc0 + OL3 for RNA) 

295 # leapin.write("source leaprc.protein.ff14SB \n") 

296 # DNA: parmBSC1 (ParmBSC1 (ff99 + bsc0 + bsc1) for DNA. Ivani et al. Nature Methods 13: 55, 2016) 

297 # leapin.write("source leaprc.DNA.bsc1 \n") 

298 # Ligands: GAFF (General Amber Force field, J. Comput. Chem. 2004 Jul 15;25(9):1157-74) 

299 # leapin.write("source leaprc.gaff \n") 

300 

301 # Forcefields loaded from input forcefield property 

302 for t in self.forcefield: 

303 leapin.write("source {}\n".format(t)) 

304 

305 # Additional Leap commands 

306 for leap_commands in leap_source_list: 

307 leapin.write("source " + leap_commands + "\n") 

308 

309 # Additional Amber parameters 

310 for amber_params in amber_params_list: 

311 leapin.write("loadamberparams " + amber_params + "\n") 

312 

313 # Additional Amber prep files 

314 for amber_prep in amber_prep_list: 

315 leapin.write("loadamberprep " + amber_prep + "\n") 

316 

317 # Ions libraries 

318 leapin.write("loadOff atomic_ions.lib \n") 

319 

320 # Ligand(s) libraries (if any) 

321 for amber_lib in ligands_lib_list: 

322 leapin.write("loadOff " + amber_lib + "\n") 

323 for amber_frcmod in ligands_frcmod_list: 

324 leapin.write("loadamberparams " + amber_frcmod + "\n") 

325 

326 # Loading PDB file 

327 leapin.write( 

328 "mol = loadpdb " + self.stage_io_dict["in"]["input_pdb_path"] + " \n" 

329 ) 

330 

331 # Saving output PDB file, coordinates and topology 

332 leapin.write( 

333 "savepdb mol " + self.stage_io_dict["out"]["output_pdb_path"] + " \n" 

334 ) 

335 leapin.write( 

336 "saveAmberParm mol " + self.stage_io_dict["out"]["output_top_path"] + " " + self.stage_io_dict["out"]["output_crd_path"] + "\n" 

337 ) 

338 leapin.write("quit \n") 

339 

340 # Command line 

341 self.cmd = [self.binary_path, "-f", instructions_file_path] 

342 

343 # Run Biobb block 

344 self.run_biobb() 

345 

346 # Copy files to host 

347 self.copy_to_host() 

348 

349 # remove temporary folder(s) 

350 self.tmp_files.extend([str(self.tmp_folder), "leap.log"]) 

351 self.remove_tmp_files() 

352 

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

354 

355 return self.return_code 

356 

357 

358def leap_gen_top( 

359 input_pdb_path: str, 

360 output_pdb_path: str, 

361 output_top_path: str, 

362 output_crd_path: str, 

363 input_lib_path: Optional[str] = None, 

364 input_frcmod_path: Optional[str] = None, 

365 input_params_path: Optional[str] = None, 

366 input_prep_path: Optional[str] = None, 

367 input_source_path: Optional[str] = None, 

368 properties: Optional[dict] = None, 

369 **kwargs, 

370) -> int: 

371 """Create the :class:`LeapGenTop <leap.leap_gen_top.LeapGenTop>` class and 

372 execute the :meth:`launch() <leap.leap_gen_top.LeapGenTop.launch>` method.""" 

373 return LeapGenTop(**dict(locals())).launch() 

374 

375 

376leap_gen_top.__doc__ = LeapGenTop.__doc__ 

377main = LeapGenTop.get_main(leap_gen_top, "Generating a MD topology from a molecule structure using tLeap program from AmberTools MD package.") 

378 

379if __name__ == "__main__": 

380 main()