Coverage for biobb_haddock/haddock/rigid_body.py: 68%

1#!/usr/bin/env python3 

2 

3"""Module containing the haddock RigidBody class and the command line interface.""" 

4 

5# import os 

6# import json 

7import argparse 

8import shutil 

9from pathlib import Path 

10from typing import Optional 

11 

12from biobb_common.configuration import settings 

13from biobb_common.generic.biobb_object import BiobbObject 

14from biobb_common.tools import file_utils as fu 

15from biobb_common.tools.file_utils import launchlogger 

16 

17from biobb_haddock.haddock.common import create_cfg, unzip_workflow_data 

18 

19 

20class RigidBody(BiobbObject): 

21 """ 

22 | biobb_haddock RigidBody 

23 | Wrapper class for the Haddock RigidBody module. 

24 | The RigidBody module. `Haddock RigidBody module <https://www.bonvinlab.org/haddock3/modules/sampling/haddock.modules.sampling.rigidbody.html>`_ compute rigid body docking between two molecules. 

25 

26 Args: 

27 input_haddock_wf_data_zip (str): Path to the input zipball containing all the current Haddock workflow data. File type: input. `Sample file <https://github.com/bioexcel/biobb_haddock/raw/master/biobb_haddock/test/data/haddock/haddock_wf_data_topology.zip>`_. Accepted formats: zip (edam:format_3987). 

28 docking_output_zip_path (str): Path to the output PDB file collection in zip format. File type: output. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_haddock/master/biobb_haddock/test/reference/haddock/ref_rigidbody.zip>`_. Accepted formats: zip (edam:format_3987). 

29 ambig_restraints_table_path (str) (Optional): Path to the input TBL file containing a list of ambiguous restraints for docking. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_haddock/master/biobb_haddock/test/data/haddock/e2a-hpr_air.tbl>`_. Accepted formats: tbl (edam:format_2330). 

30 unambig_restraints_table_path (str) (Optional): Path to the input TBL file containing a list of unambiguous restraints for docking. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_haddock/master/biobb_haddock/test/data/haddock/e2a-hpr_air.tbl>`_. Accepted formats: tbl (edam:format_2330). 

31 hb_restraints_table_path (str) (Optional): Path to the input TBL file containing a list of hydrogen bond restraints for docking. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_haddock/master/biobb_haddock/test/data/haddock/e2a-hpr_air.tbl>`_. Accepted formats: tbl (edam:format_2330). 

32 output_haddock_wf_data_zip (str) (Optional): Path to the output zipball containing all the current Haddock workflow data. File type: output. `Sample file <https://github.com/bioexcel/biobb_haddock/raw/master/biobb_haddock/test/data/haddock/haddock_wf_data_emref.zip>`_. Accepted formats: zip (edam:format_3987). 

33 haddock_config_path (str) (Optional): Haddock configuration CFG file path. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_haddock/master/biobb_haddock/test/data/haddock/run.cfg>`_. Accepted formats: cfg (edam:format_1476). 

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

35 * **cfg** (*dict*) - ({}) Haddock configuration options specification. 

36 * **global_cfg** (*dict*) - ({"postprocess": False}) `Global configuration options <https://www.bonvinlab.org/haddock3-user-manual/global_parameters.html>`_ specification. 

37 * **binary_path** (*str*) - ("haddock") Path to the haddock haddock executable binary. 

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

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

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

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

42 * **container_image** (*str*) - (None) Container Image identifier. 

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

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

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

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

47 

48 

49 Examples: 

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

51 

52 from biobb_haddock.haddock.rigid_body import rigid_body 

53 prop = { 'binary_path': 'haddock' } 

54 rigid_body(input_haddock_wf_data_zip='/path/to/myworkflowdata.zip', 

55 docking_output_zip_path='/path/to/mydockingstructures.zip', 

56 properties=prop) 

57 

58 Info: 

59 * wrapped_software: 

60 * name: Haddock3 

61 * version: 2025.5 

62 * license: Apache-2.0 

63 * ontology: 

64 * name: EDAM 

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

66 """ 

67 

68 def __init__( 

69 self, 

70 input_haddock_wf_data_zip: str, 

71 docking_output_zip_path: str, 

72 ambig_restraints_table_path: Optional[str] = None, 

73 unambig_restraints_table_path: Optional[str] = None, 

74 hb_restraints_table_path: Optional[str] = None, 

75 output_haddock_wf_data_zip: Optional[str] = None, 

76 haddock_config_path: Optional[str] = None, 

77 properties: Optional[dict] = None, 

78 **kwargs, 

79 ) -> None: 

80 properties = properties or {} 

81 

82 # Call parent class constructor 

83 super().__init__(properties) 

84 

85 # Input/Output files 

86 self.io_dict = { 

87 "in": { 

88 "ambig_restraints_table_path": ambig_restraints_table_path, 

89 "unambig_restraints_table_path": unambig_restraints_table_path, 

90 "hb_restraints_table_path": hb_restraints_table_path, 

91 "haddock_config_path": haddock_config_path, 

92 }, 

93 "out": { 

94 "output_haddock_wf_data_zip": output_haddock_wf_data_zip, 

95 "docking_output_zip_path": docking_output_zip_path, 

96 }, 

97 } 

98 # Should not be copied inside container 

99 self.input_haddock_wf_data_zip = input_haddock_wf_data_zip 

100 

101 # Properties specific for BB 

102 self.haddock_step_name = "rigidbody" 

103 self.output_cfg_path = properties.get("output_cfg_path", "haddock.cfg") 

104 # self.cfg = {k: str(v) for k, v in properties.get('cfg', dict()).items()} 

105 self.cfg = {k: v for k, v in properties.get("cfg", dict()).items()} 

106 self.global_cfg = properties.get("global_cfg", dict(postprocess=False)) 

107 

108 # Properties specific for BB 

109 self.binary_path = properties.get("binary_path", "haddock3") 

110 

111 # Check the properties 

112 self.check_properties(properties) 

113 

114 @launchlogger 

115 def launch(self) -> int: 

116 """Execute the :class:`RigidBody <biobb_haddock.haddock.rigid_body>` object.""" 

117 # tmp_files = [] 

118 

119 # Setup Biobb 

120 if self.check_restart(): 

121 return 0 

122 self.stage_files() 

123 

124 # Unzip workflow data to workflow_data_out 

125 run_dir = unzip_workflow_data( 

126 zip_file=self.input_haddock_wf_data_zip, out_log=self.out_log 

127 ) 

128 

129 workflow_dict = {"haddock_step_name": self.haddock_step_name} 

130 workflow_dict.update(self.global_cfg) 

131 

132 if ambig_path := self.stage_io_dict["in"].get("ambig_restraints_table_path"): 

133 self.cfg["ambig_fname"] = ambig_path 

134 

135 if unambig_fname := self.stage_io_dict["in"].get("unambig_restraints_table_path"): 

136 self.cfg["unambig_fname"] = unambig_fname 

137 

138 if hbond_fname := self.stage_io_dict["in"].get("hb_restraints_table_path"): 

139 self.cfg["hbond_fname"] = hbond_fname 

140 

141 # Create data dir 

142 cfg_dir = fu.create_unique_dir() 

143 self.output_cfg_path = create_cfg( 

144 output_cfg_path=str(Path(cfg_dir).joinpath(self.output_cfg_path)), 

145 workflow_dict=workflow_dict, 

146 input_cfg_path=self.stage_io_dict["in"].get("haddock_config_path"), 

147 cfg_properties_dict=self.cfg, 

148 local_log=self.out_log, 

149 global_log=self.global_log, 

150 ) 

151 

152 if self.container_path: 

153 fu.log("Container execution enabled", self.out_log) 

154 

155 shutil.copy2(self.output_cfg_path, self.stage_io_dict.get("unique_dir", "")) 

156 self.output_cfg_path = str( 

157 Path(self.container_volume_path).joinpath( 

158 Path(self.output_cfg_path).name 

159 ) 

160 ) 

161 

162 shutil.copytree( 

163 run_dir, 

164 str( 

165 Path(self.stage_io_dict.get("unique_dir", "")).joinpath( 

166 Path(run_dir).name 

167 ) 

168 ), 

169 ) 

170 run_dir = str( 

171 Path(self.stage_io_dict.get("unique_dir", "")).joinpath( 

172 Path(run_dir).name 

173 ) 

174 ) 

175 

176 self.cmd = [self.binary_path, self.output_cfg_path, "--extend-run", run_dir] 

177 

178 # Run Biobb block 

179 self.run_biobb() 

180 

181 # Copy files to host 

182 # self.copy_to_host() 

183 

184 # Copy output 

185 

186 haddock_output_list = [ 

187 str(path) 

188 for path in Path(run_dir).iterdir() 

189 if path.is_dir() and str(path).endswith(workflow_dict["haddock_step_name"]) 

190 ] 

191 haddock_output_list.sort(reverse=True) 

192 output_file_list = list( 

193 Path(haddock_output_list[0]).glob( 

194 workflow_dict["haddock_step_name"] + r"*.pdb*" 

195 ) 

196 ) 

197 fu.zip_list( 

198 self.io_dict["out"]["docking_output_zip_path"], 

199 output_file_list, 

200 self.out_log, 

201 ) 

202 

203 # Create zip output 

204 if self.io_dict["out"].get("output_haddock_wf_data_zip"): 

205 fu.log( 

206 f"Zipping {run_dir} to {str(Path(self.io_dict['out']['output_haddock_wf_data_zip']).with_suffix(''))} ", 

207 self.out_log, 

208 self.global_log, 

209 ) 

210 shutil.make_archive( 

211 str( 

212 Path(self.io_dict["out"]["output_haddock_wf_data_zip"]).with_suffix( 

213 "" 

214 ) 

215 ), 

216 "zip", 

217 run_dir, 

218 ) 

219 

220 # Remove temporal files 

221 self.tmp_files.extend([ 

222 run_dir, 

223 cfg_dir, 

224 self.stage_io_dict.get("unique_dir")]) 

225 self.remove_tmp_files() 

226 

227 return self.return_code 

228 

229 

230def rigid_body( 

231 input_haddock_wf_data_zip: str, 

232 docking_output_zip_path: str, 

233 ambig_restraints_table_path: Optional[str] = None, 

234 unambig_restraints_table_path: Optional[str] = None, 

235 hb_restraints_table_path: Optional[str] = None, 

236 output_haddock_wf_data_zip: Optional[str] = None, 

237 haddock_config_path: Optional[str] = None, 

238 properties: Optional[dict] = None, 

239 **kwargs, 

240) -> int: 

241 """Create :class:`RigidBody <biobb_haddock.haddock.rigid_body>` class and 

242 execute the :meth:`launch() <biobb_haddock.haddock.rigid_body.launch>` method.""" 

243 

244 return RigidBody( 

245 input_haddock_wf_data_zip=input_haddock_wf_data_zip, 

246 docking_output_zip_path=docking_output_zip_path, 

247 ambig_restraints_table_path=ambig_restraints_table_path, 

248 unambig_restraints_table_path=unambig_restraints_table_path, 

249 hb_restraints_table_path=hb_restraints_table_path, 

250 output_haddock_wf_data_zip=output_haddock_wf_data_zip, 

251 haddock_config_path=haddock_config_path, 

252 properties=properties, 

253 **kwargs, 

254 ).launch() 

255 

256 

257rigid_body.__doc__ = RigidBody.__doc__ 

258 

259 

260def main(): 

261 parser = argparse.ArgumentParser( 

262 description="Wrapper of the haddock RigidBody module.", 

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

264 ) 

265 parser.add_argument( 

266 "-c", 

267 "--config", 

268 required=False, 

269 help="This file can be a YAML file, JSON file or JSON string", 

270 ) 

271 

272 # Specific args of each building block 

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

274 required_args.add_argument("--input_haddock_wf_data_zip", required=True) 

275 required_args.add_argument("--docking_output_zip_path", required=True) 

276 parser.add_argument("--ambig_restraints_table_path", required=False) 

277 parser.add_argument("--unambig_restraints_table_path", required=False) 

278 parser.add_argument("--hb_restraints_table_path", required=False) 

279 parser.add_argument("--output_haddock_wf_data_zip", required=False) 

280 parser.add_argument("--haddock_config_path", required=False) 

281 

282 args = parser.parse_args() 

283 config = args.config if args.config else None 

284 properties = settings.ConfReader(config=config).get_prop_dic() 

285 

286 # Specific call of each building block 

287 rigid_body( 

288 input_haddock_wf_data_zip=args.input_haddock_wf_data_zip, 

289 docking_output_zip_path=args.docking_output_zip_path, 

290 ambig_restraints_table_path=args.restraints_table_path, 

291 unambig_restraints_table_path=args.restraints_table_path, 

292 hb_restraints_table_path=args.restraints_table_path, 

293 output_haddock_wf_data_zip=args.output_haddock_wf_data_zip, 

294 haddock_config_path=args.haddock_config_path, 

295 properties=properties, 

296 ) 

297 

298 

299if __name__ == "__main__": 

300 main()