Coverage for biobb_haddock/haddock/haddock3_run.py: 67%

1#!/usr/bin/env python3 

2 

3"""Module containing the haddock3 run 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 

18 

19 

20class Haddock3Run(BiobbObject): 

21 """ 

22 | biobb_haddock Haddock3Run 

23 | Wrapper class for the Haddock3 run module. 

24 | The Haddock3 run module launches the HADDOCK3 execution for docking. 

25 

26 Args: 

27 mol1_input_pdb_path (str): Path to the input PDB file. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_haddock/master/biobb_haddock/test/data/haddock/e2aP_1F3G.pdb>`_. Accepted formats: pdb (edam:format_1476). 

28 mol2_input_pdb_path (str): Path to the input PDB file. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_haddock/master/biobb_haddock/test/data/haddock/hpr_ensemble.pdb>`_. Accepted formats: pdb (edam:format_1476). 

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

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

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

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

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

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

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

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

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

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

46 

47 

48 Examples: 

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

50 

51 from biobb_haddock.haddock.haddock3_run import haddock3_run 

52 haddock3_run(mol1_input_pdb_path='/path/to/myStructure1.pdb', 

53 mol2_input_pdb_path='/path/to/myStructure2.pdb, 

54 haddock_config_path='/path/to/myHaddockConfig.cfg', 

55 output_haddock_wf_data_zip='/path/to/haddock_output.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 mol1_input_pdb_path: str, 

71 mol2_input_pdb_path: str, 

72 output_haddock_wf_data_zip: str, 

73 ambig_restraints_table_path: Optional[str] = None, 

74 unambig_restraints_table_path: Optional[str] = None, 

75 hb_restraints_table_path: 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 "mol1_input_pdb_path": mol1_input_pdb_path, 

89 "mol2_input_pdb_path": mol2_input_pdb_path, 

90 "ambig_restraints_table_path": ambig_restraints_table_path, 

91 "unambig_restraints_table_path": unambig_restraints_table_path, 

92 "hb_restraints_table_path": hb_restraints_table_path, 

93 "haddock_config_path": haddock_config_path, 

94 

95 }, 

96 "out": { 

97 "output_haddock_wf_data_zip": output_haddock_wf_data_zip, 

98 }, 

99 } 

100 

101 # Properties specific for BB 

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

103 self.cfg = {k: str(v) 

104 for k, v in properties.get("cfg", dict()).items()} 

105 

106 # Properties specific for BB 

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

108 

109 # Check the properties 

110 self.check_properties(properties) 

111 

112 @launchlogger 

113 def launch(self) -> int: 

114 """Execute the :class:`Haddock3Run <biobb_haddock.haddock.haddock3_run>` object.""" 

115 # tmp_files = [] 

116 

117 # Setup Biobb 

118 if self.check_restart(): 

119 return 0 

120 self.stage_files() 

121 

122 workflow_dict = { 

123 "run_dir": fu.create_unique_dir(self.stage_io_dict["unique_dir"]), 

124 "molecules": [self.stage_io_dict["in"]["mol1_input_pdb_path"], self.stage_io_dict["in"]["mol2_input_pdb_path"]], 

125 } 

126 

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

128 workflow_dict["ambig_restraints_table_path"] = ambig_restraints_table_path 

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

130 workflow_dict["unambig_restraints_table_path"] = unambig_restraints_table_path 

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

132 workflow_dict["hb_restraints_table_path"] = hb_restraints_table_path 

133 

134 # Create data dir 

135 cfg_dir = fu.create_unique_dir(self.stage_io_dict["unique_dir"]) 

136 self.output_cfg_path = create_cfg( 

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

138 workflow_dict=workflow_dict, 

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

140 cfg_properties_dict=self.cfg, 

141 ) 

142 

143 if self.container_path: 

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

145 

146 shutil.copy2(self.output_cfg_path, 

147 self.stage_io_dict.get("unique_dir", "")) 

148 self.output_cfg_path = str( 

149 Path(self.container_volume_path).joinpath( 

150 Path(self.output_cfg_path).name 

151 ) 

152 ) 

153 

154 self.cmd = [self.binary_path, self.output_cfg_path] 

155 

156 # Run Biobb block 

157 self.run_biobb() 

158 

159 # Copy files to host 

160 # self.copy_to_host() 

161 

162 # Create zip output 

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

164 fu.log( 

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

166 self.out_log, 

167 self.global_log, 

168 ) 

169 shutil.make_archive( 

170 str( 

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

172 "" 

173 ) 

174 ), 

175 "zip", 

176 str(workflow_dict["run_dir"]), 

177 ) 

178 

179 # Remove temporal files 

180 self.tmp_files.extend([cfg_dir, self.stage_io_dict.get("unique_dir")]) 

181 self.remove_tmp_files() 

182 

183 return self.return_code 

184 

185 

186def haddock3_run( 

187 mol1_input_pdb_path: str, 

188 mol2_input_pdb_path: str, 

189 output_haddock_wf_data_zip: str, 

190 ambig_restraints_table_path: Optional[str] = None, 

191 unambig_restraints_table_path: Optional[str] = None, 

192 hb_restraints_table_path: Optional[str] = None, 

193 haddock_config_path: Optional[str] = None, 

194 properties: Optional[dict] = None, 

195 **kwargs, 

196) -> int: 

197 """Create :class:`Haddock3Run <biobb_haddock.haddock.haddock3_run>` class and 

198 execute the :meth:`launch() <biobb_haddock.haddock.haddock3_run.launch>` method.""" 

199 

200 return Haddock3Run( 

201 mol1_input_pdb_path=mol1_input_pdb_path, 

202 mol2_input_pdb_path=mol2_input_pdb_path, 

203 output_haddock_wf_data_zip=output_haddock_wf_data_zip, 

204 ambig_restraints_table_path=ambig_restraints_table_path, 

205 unambig_restraints_table_path=unambig_restraints_table_path, 

206 hb_restraints_table_path=hb_restraints_table_path, 

207 haddock_config_path=haddock_config_path, 

208 properties=properties, 

209 **kwargs, 

210 ).launch() 

211 

212 

213haddock3_run.__doc__ = Haddock3Run.__doc__ 

214 

215 

216def main(): 

217 parser = argparse.ArgumentParser( 

218 description="Wrapper of the haddock3 HADDOCK3 module.", 

219 formatter_class=lambda prog: argparse.RawTextHelpFormatter( 

220 prog, width=99999), 

221 ) 

222 parser.add_argument( 

223 "-c", 

224 "--config", 

225 required=False, 

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

227 ) 

228 

229 # Specific args of each building block 

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

231 required_args.add_argument("--mol1_input_pdb_path", required=True) 

232 required_args.add_argument("--mol2_input_pdb_path", required=True) 

233 required_args.add_argument("--output_haddock_wf_data_zip", required=True) 

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

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

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

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

238 

239 args = parser.parse_args() 

240 config = args.config if args.config else None 

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

242 

243 # Specific call of each building block 

244 haddock3_run( 

245 mol1_input_pdb_path=args.mol1_input_pdb_path, 

246 mol2_input_pdb_path=args.mol2_input_pdb_path, 

247 output_haddock_wf_data_zip=args.output_haddock_wf_data_zip, 

248 ambig_restraints_table_path=args.ambig_restraints_table_path, 

249 unambig_restraints_table_path=args.unambig_restraints_table_path, 

250 hb_restraints_table_path=args.hb_restraints_table_path, 

251 haddock_config_path=args.haddock_config_path, 

252 properties=properties, 

253 ) 

254 

255 

256if __name__ == "__main__": 

257 main()