Coverage for biobb_flexdyn/flexdyn/concoord_disco.py: 69%

1#!/usr/bin/env python3 

2 

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

4from typing import Optional 

5import os 

6import shutil 

7from pathlib import Path, PurePath 

8from biobb_common.tools import file_utils as fu 

9from biobb_common.generic.biobb_object import BiobbObject 

10from biobb_common.tools.file_utils import launchlogger 

11 

12 

13class ConcoordDisco(BiobbObject): 

14 """ 

15 | biobb_flexdyn ConcoordDisco 

16 | Wrapper of the Disco tool from the Concoord package. 

17 | Structure generation based on a set of geometric constraints extracted with the Concoord Dist tool. 

18 

19 Args: 

20 input_pdb_path (str): Input structure file in PDB format. File type: input. `Sample file <https://github.com/bioexcel/biobb_flexdyn/raw/master/biobb_flexdyn/test/data/flexdyn/structure.pdb>`_. Accepted formats: pdb (edam:format_1476). 

21 input_dat_path (str): Input dat with structure interpretation and bond definitions. File type: input. `Sample file <https://github.com/bioexcel/biobb_flexdyn/raw/master/biobb_flexdyn/test/data/flexdyn/dist.dat>`_. Accepted formats: dat (edam:format_1637), txt (edam:format_2330). 

22 output_traj_path (str): Output trajectory file. File type: output. `Sample file <https://github.com/bioexcel/biobb_flexdyn/raw/master/biobb_flexdyn/test/reference/flexdyn/disco_trj.pdb>`_. Accepted formats: pdb (edam:format_1476), xtc (edam:format_3875), gro (edam:format_2033). 

23 output_rmsd_path (str): Output rmsd file. File type: output. `Sample file <https://github.com/bioexcel/biobb_flexdyn/raw/master/biobb_flexdyn/test/reference/flexdyn/disco_rmsd.dat>`_. Accepted formats: dat (edam:format_1637). 

24 output_bfactor_path (str): Output B-factor file. File type: output. `Sample file <https://github.com/bioexcel/biobb_flexdyn/raw/master/biobb_flexdyn/test/reference/flexdyn/disco_bfactor.pdb>`_. Accepted formats: pdb (edam:format_1476). 

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

26 * **binary_path** (*str*) - ("disco") Concoord disco binary path to be used. 

27 * **vdw** (*int*) - (1) Select a set of Van der Waals parameters. Values: 1 (OPLS-UA -united atoms- parameters), 2 (OPLS-AA -all atoms- parameters), 3 (PROLSQ repel parameters), 4 (Yamber2 parameters), 5 (Li et al. parameters), 6 (OPLS-X parameters -recommended for NMR structure determination-) 

28 * **concoord_lib_path** (*str*) - (None) Path to Concoord library files. If not specified will look for CONCOORDLIB conda environment variable. 

29 * **num_structs** (*int*) - (500) Number of structures to be generated 

30 * **num_iterations** (*int*) - (2500) Maximum number of iterations per structure 

31 * **chirality_check** (*int*) - (2) Chirality check. Values: 0 (no chirality checks), 1 (only check afterwards), 2 (check on the fly) 

32 * **bs** (*int*) - (0) Number of rounds of triangular bound smoothing (default 0), (if >= 6, tetragonal BS is activated) 

33 * **nofit** (*bool*) - (False) Do not fit generated structures to reference 

34 * **seed** (*int*) - (741265) Initial random seed 

35 * **violation** (*float*) - (1.0) Maximal acceptable sum of violations (nm) 

36 * **nofit** (*bool*) - (False) Do not fit generated structures to reference 

37 * **convergence** (*int*) - (50) Consider convergence failed after this number of non-productive iterations 

38 * **trials** (*int*) - (25) Maximum number of trials per run 

39 * **damp** (*int*) - (1) Damping factor for distance corrections. Values: 1 (default), 2 (for cases with convergence problems) 

40 * **dyn** (*int*) - (1) Number of rounds to dynamically set tolerances 

41 * **bump** (*bool*) - (False) Do extra bump check 

42 * **pairlist_freq** (*int*) - (10) Pairlist update frequency in steps (only valid together with bump) 

43 * **cutoff** (*float*) - (0.5) Cut-off radius for pairlist (nm) (only valid together with bump) 

44 * **ref** (*bool*) - (False) Use input coordinates instead of random starting coordinates 

45 * **scale** (*int*) - (1) Pre-scale coordinates with this factor 

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

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

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

49 * **container_path** (*str*) - (None) Path to the binary executable of your container. 

50 * **container_image** (*str*) - ("cmip/cmip:latest") Container Image identifier. 

51 * **container_volume_path** (*str*) - ("/data") Path to an internal directory in the container. 

52 * **container_working_dir** (*str*) - (None) Path to the internal CWD in the container. 

53 * **container_user_id** (*str*) - (None) User number id to be mapped inside the container. 

54 * **container_shell_path** (*str*) - ("/bin/bash") Path to the binary executable of the container shell. 

55 

56 Examples: 

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

58 

59 from biobb_flexdyn.flexdyn.concoord_disco import concoord_disco 

60 prop = { 

61 'vdw' : 4, 

62 'num_structs' : 20 

63 } 

64 concoord_disco( input_pdb_path='/path/to/dist_input.pdb', 

65 input_dat_path='/path/to/dist_input.dat', 

66 output_traj_path='/path/to/disco_out_traj.pdb', 

67 output_rmsd_path='/path/to/disco_out_rmsd.dat', 

68 output_bfactor_path='/path/to/disco_out_bfactor.pdb', 

69 properties=prop) 

70 

71 Info: 

72 * wrapped_software: 

73 * name: Concoord 

74 * version: >=2.1.2 

75 * license: other 

76 * ontology: 

77 * name: EDAM 

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

79 

80 """ 

81 

82 def __init__(self, input_pdb_path: str, input_dat_path: str, output_traj_path: str, 

83 output_rmsd_path: str, output_bfactor_path: str, properties: Optional[dict] = None, **kwargs) -> None: 

84 

85 properties = properties or {} 

86 

87 # Call parent class constructor 

88 super().__init__(properties) 

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

90 

91 # Input/Output files 

92 self.io_dict = { 

93 'in': {'input_pdb_path': input_pdb_path, 

94 'input_dat_path': input_dat_path}, 

95 'out': {'output_traj_path': output_traj_path, 

96 'output_rmsd_path': output_rmsd_path, 

97 'output_bfactor_path': output_bfactor_path} 

98 } 

99 

100 # Properties specific for BB 

101 self.properties = properties 

102 self.binary_path = properties.get('binary_path', 'disco') 

103 

104 self.vdw = properties.get('vdw') 

105 self.concoord_lib_path = properties.get('concoord_lib_path', None) 

106 self.num_structs = properties.get('num_structs') 

107 self.num_iterations = properties.get('num_iterations') 

108 self.chirality_check = properties.get('chirality_check') 

109 self.bs = properties.get('bs') 

110 self.nofit = properties.get('nofit') 

111 self.seed = properties.get('seed') 

112 self.violation = properties.get('violation') 

113 self.convergence = properties.get('convergence') 

114 self.trials = properties.get('trials') 

115 self.damp = properties.get('damp') 

116 self.dyn = properties.get('dyn') 

117 self.bump = properties.get('bump') 

118 self.pairlist_freq = properties.get('pairlist_freq') 

119 self.cutoff = properties.get('cutoff') 

120 self.ref = properties.get('ref') 

121 self.scale = properties.get('scale') 

122 

123 # Check the properties 

124 self.check_properties(properties) 

125 self.check_arguments() 

126 

127 @launchlogger 

128 def launch(self): 

129 """Launches the execution of the FlexDyn ConcoordDisco module.""" 

130 

131 # Setup Biobb 

132 if self.check_restart(): 

133 return 0 

134 self.stage_files() 

135 

136 # Copy auxiliary files (MARGINS, ATOMS, BONDS) according to the VdW property to the working dir 

137 if self.concoord_lib_path is None: 

138 concoord_lib = os.getenv("CONCOORDLIB") 

139 else: 

140 concoord_lib = self.concoord_lib_path 

141 

142 # MARGINS_li.DAT, MARGINS_oplsaa.DAT, MARGINS_oplsua.DAT, MARGINS_oplsx.DAT, MARGINS_repel.DAT, MARGINS_yamber2.DAT 

143 # 1 (OPLS-UA -united atoms- parameters), 2 (OPLS-AA -all atoms- parameters), 3 (PROLSQ repel parameters), 4 (Yamber2 parameters), 5 (Li et al. parameters), 6 (OPLS-X parameters -recommended for NMR structure determination-). 

144 vdw_values = ["vdw_values", "oplsua", "oplsaa", "repel", "yamber2", "li", "oplsx"] 

145 if self.vdw is None: 

146 raise ValueError("The 'vdw' property cannot be None") 

147 vdw_index = int(self.vdw) 

148 margins_file = str(concoord_lib) + "/MARGINS_" + vdw_values[vdw_index] + ".DAT" 

149 atoms_file = str(concoord_lib) + "/ATOMS_" + vdw_values[vdw_index] + ".DAT" 

150 bonds_file = str(concoord_lib) + "/BONDS.DAT" 

151 shutil.copy2(margins_file, self.stage_io_dict.get("unique_dir", "")) 

152 shutil.copy2(margins_file, self.stage_io_dict.get("unique_dir", "")+"/MARGINS.DAT") 

153 shutil.copy2(atoms_file, self.stage_io_dict.get("unique_dir", "")) 

154 shutil.copy2(bonds_file, self.stage_io_dict.get("unique_dir", "")) 

155 

156 # Determine working directory (host unique_dir or container volume path) 

157 if self.container_path: 

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

159 else: 

160 working_dir = self.stage_io_dict.get('unique_dir', '') 

161 

162 # Command line 

163 # (concoord) OROZCO67:biobb_flexdyn hospital$ disco -d biobb_flexdyn/test/reference/flexdyn/dist.dat 

164 # -p biobb_flexdyn/test/reference/flexdyn/dist.pdb -op patata.pdb 

165 self.cmd = ["cd", working_dir, ";", self.binary_path, 

166 "-p", PurePath(self.stage_io_dict["in"]["input_pdb_path"]).name, 

167 "-d", PurePath(self.stage_io_dict["in"]["input_dat_path"]).name, 

168 "-or", PurePath(self.stage_io_dict["out"]["output_rmsd_path"]).name, 

169 "-of", PurePath(self.stage_io_dict["out"]["output_bfactor_path"]).name 

170 ] 

171 

172 # Output structure formats: 

173 file_extension = Path(self.stage_io_dict["out"]["output_traj_path"]).suffix 

174 if file_extension == ".pdb": 

175 self.cmd.append('-on') # NMR-PDB format (multi-model) 

176 self.cmd.append(PurePath(self.stage_io_dict["out"]["output_traj_path"]).name) 

177 elif file_extension == ".gro": 

178 self.cmd.append('-ot') 

179 self.cmd.append(PurePath(self.stage_io_dict["out"]["output_traj_path"]).name) 

180 elif file_extension == ".xtc": 

181 self.cmd.append('-ox') 

182 self.cmd.append(PurePath(self.stage_io_dict["out"]["output_traj_path"]).name) 

183 else: 

184 fu.log("ERROR: output_traj_path ({}) must be a PDB, GRO or XTC formatted file ({})".format(self.io_dict["out"]["output_traj_path"], file_extension), self.out_log, self.global_log) 

185 

186 # Properties 

187 if self.num_structs: 

188 self.cmd.append('-n') 

189 self.cmd.append(str(self.num_structs)) 

190 

191 if self.num_iterations: 

192 self.cmd.append('-i') 

193 self.cmd.append(str(self.num_iterations)) 

194 

195 if self.chirality_check: 

196 self.cmd.append('-c') 

197 self.cmd.append(str(self.chirality_check)) 

198 

199 if self.bs: 

200 self.cmd.append('-bs') 

201 self.cmd.append(str(self.bs)) 

202 

203 if self.cutoff: 

204 self.cmd.append('-rc') 

205 self.cmd.append(str(self.cutoff)) 

206 

207 if self.seed: 

208 self.cmd.append('-s') 

209 self.cmd.append(str(self.seed)) 

210 

211 if self.damp: 

212 self.cmd.append('-damp') 

213 self.cmd.append(str(self.damp)) 

214 

215 if self.violation: 

216 self.cmd.append('-viol') 

217 self.cmd.append(str(self.violation)) 

218 

219 if self.convergence: 

220 self.cmd.append('-con') 

221 self.cmd.append(str(self.convergence)) 

222 

223 if self.trials: 

224 self.cmd.append('-t') 

225 self.cmd.append(str(self.trials)) 

226 

227 if self.dyn: 

228 self.cmd.append('-dyn') 

229 self.cmd.append(str(self.dyn)) 

230 

231 if self.pairlist_freq: 

232 self.cmd.append('-l') 

233 self.cmd.append(str(self.pairlist_freq)) 

234 

235 if self.scale: 

236 self.cmd.append('-is') 

237 self.cmd.append(str(self.scale)) 

238 

239 if self.nofit: 

240 self.cmd.append('-f') 

241 

242 if self.bump: 

243 self.cmd.append('-bump') 

244 

245 if self.ref: 

246 self.cmd.append('-ref') 

247 

248 # Run Biobb block 

249 self.run_biobb() 

250 

251 # Copy files to host 

252 self.copy_to_host() 

253 

254 # remove temporary folder(s) 

255 self.remove_tmp_files() 

256 

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

258 

259 return self.return_code 

260 

261 

262def concoord_disco(input_pdb_path: str, input_dat_path: str, 

263 output_traj_path: str, output_rmsd_path: str, output_bfactor_path: str, 

264 properties: Optional[dict] = None, **kwargs) -> int: 

265 """Create :class:`ConcoordDisco <flexdyn.concoord_disco.ConcoordDisco>`flexdyn.concoord_disco.ConcoordDisco class and 

266 execute :meth:`launch() <flexdyn.concoord_disco.ConcoordDisco.launch>` method""" 

267 return ConcoordDisco(**dict(locals())).launch() 

268 

269 

270concoord_disco.__doc__ = ConcoordDisco.__doc__ 

271main = ConcoordDisco.get_main(concoord_disco, "Structure generation based on a set of geometric constraints extracted with the Concoord Dist tool.") 

272 

273if __name__ == '__main__': 

274 main()