Coverage for biobb_structure_utils/utils/renumber_structure.py: 86%

1#!/usr/bin/env python3 

2 

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

4import json 

5import argparse 

6from pathlib import Path 

7from biobb_common.configuration import settings 

8from biobb_common.generic.biobb_object import BiobbObject 

9from biobb_common.tools import file_utils as fu 

10from biobb_common.tools.file_utils import launchlogger 

11from biobb_structure_utils.gro_lib.gro import Gro 

12from biobb_structure_utils.utils.common import PDB_SERIAL_RECORDS 

13 

14 

15class RenumberStructure(BiobbObject): 

16 """ 

17 | biobb_structure_utils RenumberStructure 

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

19 | Renumber atomic indexes from a 3D structure. 

20 

21 Args: 

22 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). 

23 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). 

24 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). 

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

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

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

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

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

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

31 

32 Examples: 

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

34 

35 from biobb_structure_utils.utils.renumber_structure import renumber_structure 

36 prop = { 

37 'renumber_residues': True, 

38 'renumber_residues_per_chain': True 

39 } 

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

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

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

43 properties=prop) 

44 

45 Info: 

46 * wrapped_software: 

47 * name: In house 

48 * license: Apache-2.0 

49 * ontology: 

50 * name: EDAM 

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

52 

53 """ 

54 

55 def __init__(self, input_structure_path, output_structure_path, output_mapping_json_path, properties=None, **kwargs) -> None: 

56 properties = properties or {} 

57 

58 # Call parent class constructor 

59 super().__init__(properties) 

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

61 

62 # Input/Output files 

63 self.io_dict = { 

64 "in": {"input_structure_path": input_structure_path}, 

65 "out": {"output_structure_path": output_structure_path, 

66 "output_mapping_json_path": output_mapping_json_path} 

67 } 

68 

69 # Properties specific for BB 

70 self.renumber_residues = properties.get('renumber_residues', True) 

71 self.renumber_residues_per_chain = properties.get('renumber_residues_per_chain', True) 

72 

73 # Common in all BB 

74 self.can_write_console_log = properties.get('can_write_console_log', True) 

75 self.global_log = properties.get('global_log', None) 

76 self.prefix = properties.get('prefix', None) 

77 self.step = properties.get('step', None) 

78 self.path = properties.get('path', '') 

79 self.remove_tmp = properties.get('remove_tmp', True) 

80 self.restart = properties.get('restart', False) 

81 

82 # Check the properties 

83 self.check_properties(properties) 

84 self.check_arguments() 

85 

86 @launchlogger 

87 def launch(self) -> int: 

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

89 

90 # Setup Biobb 

91 if self.check_restart(): 

92 return 0 

93 self.stage_files() 

94 

95 # Business code 

96 extension = Path(self.stage_io_dict['in']['input_structure_path']).suffix.lower() 

97 if extension.lower() == '.gro': 

98 fu.log('GRO format detected, reenumerating atoms', self.out_log) 

99 gro_st = Gro() 

100 gro_st.read_gro_file(self.stage_io_dict['in']['input_structure_path']) 

101 residue_mapping, atom_mapping = gro_st.renumber_atoms(renumber_residues=self.renumber_residues, renumber_residues_per_chain=self.renumber_residues_per_chain) 

102 gro_st.write_gro_file(self.stage_io_dict['out']['output_structure_path']) 

103 

104 else: 

105 fu.log('PDB format detected, reenumerating atoms', self.out_log) 

106 atom_mapping = {} 

107 atom_count = 0 

108 residue_mapping = {} 

109 residue_count = 0 

110 with open(self.stage_io_dict['in']['input_structure_path'], "r") as input_pdb, open(self.stage_io_dict['out']['output_structure_path'], "w") as output_pdb: 

111 for line in input_pdb: 

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

113 if len(line) > 10 and record in PDB_SERIAL_RECORDS: # Avoid MODEL, ENDMDL records and empty lines 

114 # Renumbering atoms 

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

116 if not atom_mapping.get(pdb_atom_number): # ANISOU records should have the same numeration as ATOM records 

117 atom_count += 1 

118 atom_mapping[pdb_atom_number] = str(atom_count) 

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

120 # Renumbering residues 

121 if self.renumber_residues: 

122 chain = line[21] 

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

124 if not residue_mapping.get(chain): 

125 residue_mapping[chain] = {} 

126 if self.renumber_residues_per_chain: 

127 residue_count = 0 

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

129 residue_count += 1 

130 residue_mapping[chain][pdb_residue_number] = str(residue_count) 

131 line = line[:22] + '{: >4d}'.format(residue_count) + line[26:] 

132 output_pdb.write(line) 

133 

134 with open(self.stage_io_dict['out']['output_mapping_json_path'], "w") as output_json: 

135 output_json.write(json.dumps({'residues': residue_mapping, 'atoms': atom_mapping})) 

136 

137 self.return_code = 0 

138 ########## 

139 

140 # Copy files to host 

141 self.copy_to_host() 

142 

143 # Remove temporal files 

144 self.tmp_files.append(self.stage_io_dict.get("unique_dir")) 

145 self.remove_tmp_files() 

146 

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

148 

149 return self.return_code 

150 

151 

152def renumber_structure(input_structure_path: str, output_structure_path: str, output_mapping_json_path: str, properties: dict = None, **kwargs) -> int: 

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

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

155 

156 return RenumberStructure(input_structure_path=input_structure_path, 

157 output_structure_path=output_structure_path, 

158 output_mapping_json_path=output_mapping_json_path, 

159 properties=properties, **kwargs).launch() 

160 

161 

162def main(): 

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

164 parser = argparse.ArgumentParser(description="Renumber atoms and residues from a 3D structure.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999)) 

165 parser.add_argument('-c', '--config', required=False, help="This file can be a YAML file, JSON file or JSON string") 

166 

167 # Specific args of each building block 

168 required_args = parser.add_argument_group('required arguments') 

169 required_args.add_argument('-i', '--input_structure_path', required=True, help="Input structure file name") 

170 required_args.add_argument('-o', '--output_structure_path', required=True, help="Output structure file name") 

171 required_args.add_argument('-j', '--output_mapping_json_path', required=True, help="Output mapping json file name") 

172 

173 args = parser.parse_args() 

174 config = args.config if args.config else None 

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

176 

177 # Specific call of each building block 

178 renumber_structure(input_structure_path=args.input_structure_path, 

179 output_structure_path=args.output_structure_path, 

180 output_mapping_json_path=args.output_mapping_json_path, 

181 properties=properties) 

182 

183 

184if __name__ == '__main__': 

185 main()