Coverage for biobb_structure_utils/utils/renumber_structure.py: 85%

1#!/usr/bin/env python3 

2 

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

4 

5import argparse 

6import json 

7from pathlib import Path 

8from typing import Optional 

9 

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_structure_utils.gro_lib.gro import Gro 

16from biobb_structure_utils.utils.common import PDB_SERIAL_RECORDS 

17 

18 

19class RenumberStructure(BiobbObject): 

20 """ 

21 | biobb_structure_utils RenumberStructure 

22 | Class to renumber atomic indexes from a 3D structure. 

23 | Renumber atomic indexes from a 3D structure. 

24 

25 Args: 

26 input_structure_path (str): Input structure file path. File type: input. `Sample file <https://github.com/bioexcel/biobb_structure_utils/raw/master/biobb_structure_utils/test/data/utils/cl3.noH.pdb>`_. Accepted formats: pdb (edam:format_1476), gro (edam:format_2033). 

27 output_structure_path (str): Output structure file path. File type: output. `Sample file <https://github.com/bioexcel/biobb_structure_utils/raw/master/biobb_structure_utils/test/reference/utils/renum_cl3_noH.pdb>`_. Accepted formats: pdb (edam:format_1476), gro (edam:format_2033). 

28 output_mapping_json_path (str): Output mapping json file path. File type: output. `Sample file <https://github.com/bioexcel/biobb_structure_utils/raw/master/biobb_structure_utils/test/reference/utils/cl3_output_mapping_json_path.json>`_. Accepted formats: json (edam:format_3464). 

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

30 * **renumber_residues** (*bool*) - (True) Residue code of the ligand to be removed. 

31 * **renumber_residues_per_chain** (*bool*) - (True) Restart residue enumeration every time a new chain is detected. 

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

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

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

35 

36 Examples: 

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

38 

39 from biobb_structure_utils.utils.renumber_structure import renumber_structure 

40 prop = { 

41 'renumber_residues': True, 

42 'renumber_residues_per_chain': True 

43 } 

44 renumber_structure(input_structure_path='/path/to/myInputStr.pdb', 

45 output_structure_path='/path/to/newStructure.pdb', 

46 output_mapping_json_path='/path/to/newMapping.json', 

47 properties=prop) 

48 

49 Info: 

50 * wrapped_software: 

51 * name: In house 

52 * license: Apache-2.0 

53 * ontology: 

54 * name: EDAM 

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

56 

57 """ 

58 

59 def __init__( 

60 self, 

61 input_structure_path, 

62 output_structure_path, 

63 output_mapping_json_path, 

64 properties=None, 

65 **kwargs, 

66 ) -> None: 

67 properties = properties or {} 

68 

69 # Call parent class constructor 

70 super().__init__(properties) 

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

72 

73 # Input/Output files 

74 self.io_dict = { 

75 "in": {"input_structure_path": input_structure_path}, 

76 "out": { 

77 "output_structure_path": output_structure_path, 

78 "output_mapping_json_path": output_mapping_json_path, 

79 }, 

80 } 

81 

82 # Properties specific for BB 

83 self.renumber_residues = properties.get("renumber_residues", True) 

84 self.renumber_residues_per_chain = properties.get( 

85 "renumber_residues_per_chain", True 

86 ) 

87 

88 # Common in all BB 

89 self.can_write_console_log = properties.get("can_write_console_log", True) 

90 self.global_log = properties.get("global_log", None) 

91 self.prefix = properties.get("prefix", None) 

92 self.step = properties.get("step", None) 

93 self.path = properties.get("path", "") 

94 self.remove_tmp = properties.get("remove_tmp", True) 

95 self.restart = properties.get("restart", False) 

96 

97 # Check the properties 

98 self.check_properties(properties) 

99 self.check_arguments() 

100 

101 @launchlogger 

102 def launch(self) -> int: 

103 """Execute the :class:`RenumberStructure <utils.renumber_structure.RenumberStructure>` utils.renumber_structure.RenumberStructure object.""" 

104 

105 # Setup Biobb 

106 if self.check_restart(): 

107 return 0 

108 self.stage_files() 

109 

110 # Business code 

111 extension = Path( 

112 self.stage_io_dict["in"]["input_structure_path"] 

113 ).suffix.lower() 

114 if extension.lower() == ".gro": 

115 fu.log("GRO format detected, reenumerating atoms", self.out_log) 

116 gro_st = Gro() 

117 gro_st.read_gro_file(self.stage_io_dict["in"]["input_structure_path"]) 

118 residue_mapping, atom_mapping = gro_st.renumber_atoms( 

119 renumber_residues=self.renumber_residues, 

120 renumber_residues_per_chain=self.renumber_residues_per_chain, 

121 ) 

122 gro_st.write_gro_file(self.stage_io_dict["out"]["output_structure_path"]) 

123 

124 else: 

125 fu.log("PDB format detected, reenumerating atoms", self.out_log) 

126 atom_mapping = {} 

127 atom_count = 0 

128 residue_mapping = {} 

129 residue_count = 0 

130 with open( 

131 self.stage_io_dict["in"]["input_structure_path"], "r" 

132 ) as input_pdb, open( 

133 self.stage_io_dict["out"]["output_structure_path"], "w" 

134 ) as output_pdb: 

135 for line in input_pdb: 

136 record = line[:6].upper().strip() 

137 if ( 

138 len(line) > 10 and record in PDB_SERIAL_RECORDS 

139 ): # Avoid MODEL, ENDMDL records and empty lines 

140 # Renumbering atoms 

141 pdb_atom_number = line[6:11].strip() 

142 if not atom_mapping.get( 

143 pdb_atom_number 

144 ): # ANISOU records should have the same numeration as ATOM records 

145 atom_count += 1 

146 atom_mapping[pdb_atom_number] = str(atom_count) 

147 line = line[:6] + "{: >5d}".format(atom_count) + line[11:] 

148 # Renumbering residues 

149 if self.renumber_residues: 

150 chain = line[21] 

151 pdb_residue_number = line[22:26].strip() 

152 if not residue_mapping.get(chain): 

153 residue_mapping[chain] = {} 

154 if self.renumber_residues_per_chain: 

155 residue_count = 0 

156 if not residue_mapping[chain].get(pdb_residue_number): 

157 residue_count += 1 

158 residue_mapping[chain][pdb_residue_number] = str( 

159 residue_count 

160 ) 

161 line = ( 

162 line[:22] + "{: >4d}".format(residue_count) + line[26:] 

163 ) 

164 output_pdb.write(line) 

165 

166 with open( 

167 self.stage_io_dict["out"]["output_mapping_json_path"], "w" 

168 ) as output_json: 

169 output_json.write( 

170 json.dumps({"residues": residue_mapping, "atoms": atom_mapping}) 

171 ) 

172 

173 self.return_code = 0 

174 ########## 

175 

176 # Copy files to host 

177 self.copy_to_host() 

178 

179 # Remove temporal files 

180 # self.tmp_files.append(self.stage_io_dict.get("unique_dir", "")) 

181 self.remove_tmp_files() 

182 

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

184 

185 return self.return_code 

186 

187 

188def renumber_structure( 

189 input_structure_path: str, 

190 output_structure_path: str, 

191 output_mapping_json_path: str, 

192 properties: Optional[dict] = None, 

193 **kwargs, 

194) -> int: 

195 """Execute the :class:`RenumberStructure <utils.renumber_structure.RenumberStructure>` class and 

196 execute the :meth:`launch() <utils.renumber_structure.RenumberStructure.launch>` method.""" 

197 

198 return RenumberStructure( 

199 input_structure_path=input_structure_path, 

200 output_structure_path=output_structure_path, 

201 output_mapping_json_path=output_mapping_json_path, 

202 properties=properties, 

203 **kwargs, 

204 ).launch() 

205 

206 renumber_structure.__doc__ = RenumberStructure.__doc__ 

207 

208 

209def main(): 

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

211 parser = argparse.ArgumentParser( 

212 description="Renumber atoms and residues from a 3D structure.", 

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

214 ) 

215 parser.add_argument( 

216 "-c", 

217 "--config", 

218 required=False, 

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

220 ) 

221 

222 # Specific args of each building block 

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

224 required_args.add_argument( 

225 "-i", "--input_structure_path", required=True, help="Input structure file name" 

226 ) 

227 required_args.add_argument( 

228 "-o", 

229 "--output_structure_path", 

230 required=True, 

231 help="Output structure file name", 

232 ) 

233 required_args.add_argument( 

234 "-j", 

235 "--output_mapping_json_path", 

236 required=True, 

237 help="Output mapping json file name", 

238 ) 

239 

240 args = parser.parse_args() 

241 config = args.config if args.config else None 

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

243 

244 # Specific call of each building block 

245 renumber_structure( 

246 input_structure_path=args.input_structure_path, 

247 output_structure_path=args.output_structure_path, 

248 output_mapping_json_path=args.output_mapping_json_path, 

249 properties=properties, 

250 ) 

251 

252 

253if __name__ == "__main__": 

254 main()