Coverage for biobb_vs/utils/box.py: 84%

83 statements  

« prev     ^ index     » next       coverage.py v7.6.10, created at 2025-01-28 12:00 +0000

1#!/usr/bin/env python3 

2 

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

4 

5import argparse 

6from pathlib import PurePath 

7from typing import Optional 

8 

9import numpy as np 

10from biobb_common.configuration import settings 

11from biobb_common.generic.biobb_object import BiobbObject 

12from biobb_common.tools import file_utils as fu 

13from biobb_common.tools.file_utils import launchlogger 

14 

15from biobb_vs.utils.common import ( 

16 check_input_path, 

17 check_output_path, 

18 get_box_coordinates, 

19) 

20 

21 

22class Box(BiobbObject): 

23 """ 

24 | biobb_vs Box 

25 | This class sets the center and the size of a rectangular parallelepiped box around a set of residues or a pocket. 

26 | Sets the center and the size of a rectangular parallelepiped box around a set of residues from a given PDB or a pocket from a given PQR. 

27 

28 Args: 

29 input_pdb_path (str): PDB file containing a selection of residue numbers or PQR file containing the pocket. File type: input. `Sample file <https://github.com/bioexcel/biobb_vs/raw/master/biobb_vs/test/data/utils/input_box.pqr>`_. Accepted formats: pdb (edam:format_1476), pqr (edam:format_1476). 

30 output_pdb_path (str): PDB including the annotation of the box center and size as REMARKs. File type: output. `Sample file <https://github.com/bioexcel/biobb_vs/raw/master/biobb_vs/test/reference/utils/ref_output_box.pdb>`_. Accepted formats: pdb (edam:format_1476). 

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

32 * **offset** (*float*) - (2.0) [0.1~1000|0.1] Extra distance (Angstroms) between the last residue atom and the box boundary. 

33 * **box_coordinates** (*bool*) - (False) Add box coordinates as 8 ATOM records. 

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 

38 Examples: 

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

40 

41 from biobb_vs.utils.box import box 

42 prop = { 

43 'offset': 2, 

44 'box_coordinates': True 

45 } 

46 box(input_pdb_path='/path/to/myPocket.pqr', 

47 output_pdb_path='/path/to/newBox.pdb', 

48 properties=prop) 

49 

50 Info: 

51 * wrapped_software: 

52 * name: In house 

53 * license: Apache-2.0 

54 * ontology: 

55 * name: EDAM 

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

57 

58 """ 

59 

60 def __init__( 

61 self, input_pdb_path, output_pdb_path, properties=None, **kwargs 

62 ) -> None: 

63 properties = properties or {} 

64 

65 # Call parent class constructor 

66 super().__init__(properties) 

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

68 

69 # Input/Output files 

70 self.io_dict = { 

71 "in": {"input_pdb_path": input_pdb_path}, 

72 "out": {"output_pdb_path": output_pdb_path}, 

73 } 

74 

75 # Properties specific for BB 

76 self.offset = float(properties.get("offset", 2.0)) 

77 self.box_coordinates = float(properties.get("box_coordinates", False)) 

78 self.properties = properties 

79 

80 # Check the properties 

81 self.check_properties(properties) 

82 self.check_arguments() 

83 

84 def check_data_params(self, out_log, err_log): 

85 """Checks all the input/output paths and parameters""" 

86 self.io_dict["in"]["input_pdb_path"] = check_input_path( 

87 self.io_dict["in"]["input_pdb_path"], 

88 "input_pdb_path", 

89 self.out_log, 

90 self.__class__.__name__, 

91 ) 

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

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

94 "output_pdb_path", 

95 False, 

96 self.out_log, 

97 self.__class__.__name__, 

98 ) 

99 

100 @launchlogger 

101 def launch(self) -> int: 

102 """Execute the :class:`Box <utils.box.Box>` utils.box.Box object.""" 

103 

104 # check input/output paths and parameters 

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

106 

107 # Setup Biobb 

108 if self.check_restart(): 

109 return 0 

110 self.stage_files() 

111 

112 # check if cavity (pdb) or pocket (pqr) 

113 input_type = PurePath(self.io_dict["in"]["input_pdb_path"]).suffix.lstrip(".") 

114 if input_type == "pdb": 

115 fu.log( 

116 "Loading residue PDB selection from %s" 

117 % (self.io_dict["in"]["input_pdb_path"]), 

118 self.out_log, 

119 self.global_log, 

120 ) 

121 else: 

122 fu.log( 

123 "Loading pocket PQR selection from %s" 

124 % (self.io_dict["in"]["input_pdb_path"]), 

125 self.out_log, 

126 self.global_log, 

127 ) 

128 

129 # get input_pdb_path atoms coordinates 

130 selection_atoms_num = 0 

131 x_coordslist = [] 

132 y_coordslist = [] 

133 z_coordslist = [] 

134 with open(self.io_dict["in"]["input_pdb_path"]) as infile: 

135 for line in infile: 

136 if line.startswith("HETATM") or line.startswith("ATOM"): 

137 x_coordslist.append(float(line[31:38].strip())) 

138 y_coordslist.append(float(line[39:46].strip())) 

139 z_coordslist.append(float(line[47:54].strip())) 

140 selection_atoms_num = selection_atoms_num + 1 

141 

142 # Compute binding site box size 

143 

144 # compute box center 

145 selection_box_center = [ 

146 np.average(x_coordslist), 

147 np.average(y_coordslist), 

148 np.average(z_coordslist), 

149 ] 

150 fu.log( 

151 "Binding site center (Angstroms): %10.3f%10.3f%10.3f" 

152 % ( 

153 selection_box_center[0], 

154 selection_box_center[1], 

155 selection_box_center[2], 

156 ), 

157 self.out_log, 

158 self.global_log, 

159 ) 

160 

161 # compute box size 

162 selection_coords_max = np.amax( 

163 [x_coordslist, y_coordslist, z_coordslist], axis=1 

164 ) 

165 selection_box_size = selection_coords_max - selection_box_center 

166 if self.offset: 

167 fu.log( 

168 "Adding %.1f Angstroms offset" % (self.offset), 

169 self.out_log, 

170 self.global_log, 

171 ) 

172 selection_box_size = [c + self.offset for c in selection_box_size] 

173 fu.log( 

174 "Binding site size (Angstroms): %10.3f%10.3f%10.3f" 

175 % (selection_box_size[0], selection_box_size[1], selection_box_size[2]), 

176 self.out_log, 

177 self.global_log, 

178 ) 

179 

180 # compute volume 

181 vol = np.prod(selection_box_size) * 2**3 

182 fu.log("Volume (cubic Angstroms): %.0f" % (vol), self.out_log, self.global_log) 

183 

184 # add box details as PDB remarks 

185 remarks = "REMARK BOX CENTER:%10.3f%10.3f%10.3f" % ( 

186 selection_box_center[0], 

187 selection_box_center[1], 

188 selection_box_center[2], 

189 ) 

190 remarks += " SIZE:%10.3f%10.3f%10.3f" % ( 

191 selection_box_size[0], 

192 selection_box_size[1], 

193 selection_box_size[2], 

194 ) 

195 

196 selection_box_coords_txt = "" 

197 # add (optional) box coordinates as 8 ATOM records 

198 if self.box_coordinates: 

199 fu.log("Adding box coordinates", self.out_log, self.global_log) 

200 selection_box_coords_txt = get_box_coordinates( 

201 selection_box_center, selection_box_size 

202 ) 

203 

204 with open(self.io_dict["out"]["output_pdb_path"], "w") as f: 

205 f.seek(0, 0) 

206 f.write(remarks.rstrip("\r\n") + "\n" + selection_box_coords_txt) 

207 

208 fu.log( 

209 "Saving output PDB file (with box setting annotations): %s" 

210 % (self.io_dict["out"]["output_pdb_path"]), 

211 self.out_log, 

212 self.global_log, 

213 ) 

214 

215 # Copy files to host 

216 self.copy_to_host() 

217 

218 # self.tmp_files.extend([self.stage_io_dict.get("unique_dir", "")]) 

219 self.remove_tmp_files() 

220 

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

222 

223 return 0 

224 

225 

226def box( 

227 input_pdb_path: str, 

228 output_pdb_path: str, 

229 properties: Optional[dict] = None, 

230 **kwargs, 

231) -> int: 

232 """Execute the :class:`Box <utils.box.Box>` class and 

233 execute the :meth:`launch() <utils.box.Box.launch>` method.""" 

234 

235 return Box( 

236 input_pdb_path=input_pdb_path, 

237 output_pdb_path=output_pdb_path, 

238 properties=properties, 

239 **kwargs, 

240 ).launch() 

241 

242 box.__doc__ = Box.__doc__ 

243 

244 

245def main(): 

246 """Command line execution of this building block. Please check the command line documentation.""" 

247 parser = argparse.ArgumentParser( 

248 description="Sets the center and the size of a rectangular parallelepiped box around a set of residues from a given PDB or a pocket from a given PQR.", 

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

250 ) 

251 parser.add_argument("--config", required=False, help="Configuration file") 

252 

253 # Specific args of each building block 

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

255 required_args.add_argument( 

256 "--input_pdb_path", 

257 required=True, 

258 help="PDB file containing a selection of residue numbers or PQR file containing the pocket. Accepted formats: pdb, pqr.", 

259 ) 

260 required_args.add_argument( 

261 "--output_pdb_path", 

262 required=True, 

263 help="PDB including the annotation of the box center and size as REMARKs. Accepted formats: pdb.", 

264 ) 

265 

266 args = parser.parse_args() 

267 args.config = args.config or "{}" 

268 properties = settings.ConfReader(config=args.config).get_prop_dic() 

269 

270 # Specific call of each building block 

271 box( 

272 input_pdb_path=args.input_pdb_path, 

273 output_pdb_path=args.output_pdb_path, 

274 properties=properties, 

275 ) 

276 

277 

278if __name__ == "__main__": 

279 main()