Coverage for biobb_model/model/fix_pdb.py: 73%

1#!/usr/bin/env python3 

2 

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

4 

5import argparse 

6from typing import Optional 

7 

8from biobb_common.configuration import settings 

9from biobb_common.generic.biobb_object import BiobbObject 

10from biobb_common.tools.file_utils import launchlogger 

11 

12from biobb_model.model.fix_pdb_utils import Structure, generate_map_online 

13 

14 

15class FixPdb(BiobbObject): 

16 """ 

17 | biobb_model FixPdb 

18 | Class to renumerate residues in a PDB structure according to a reference sequence from UniProt. 

19 | Fix the residue numbering in a PDB structure according to a reference sequence from UniProt. 

20 

21 Args: 

22 input_pdb_path (str): Input PDB file path. File type: input. `Sample file <https://github.com/bioexcel/biobb_model/raw/master/biobb_model/test/data/model/2ki5.pdb>`_. Accepted formats: pdb (edam:format_1476). 

23 output_pdb_path (str): Output PDB file path. File type: output. `Sample file <https://github.com/bioexcel/biobb_model/raw/master/biobb_model/test/reference/model/output_pdb_path.pdb>`_. Accepted formats: pdb (edam:format_1476). 

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

25 * **forced_uniprot_references** (*str*) - (None) Set the UniProt accessions for sequences to be used as reference. 

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

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

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

29 Examples: 

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

31 from biobb_model.model.fix_pdb import fix_pdb 

32 prop = { 'forced_uniprot_references': ["P00533"] } 

33 fix_pdb(input_pdb_path='/path/to/myStructure.pdb', output_pdb_path='/path/to/newStructure.pdb', properties=prop) 

34 Info: 

35 * wrapped_software: 

36 * name: In house 

37 * license: Apache-2.0 

38 * ontology: 

39 * name: EDAM 

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

41 """ 

42 

43 def __init__( 

44 self, 

45 input_pdb_path: str, 

46 output_pdb_path: str, 

47 properties: Optional[dict] = None, 

48 **kwargs, 

49 ) -> None: 

50 properties = properties or {} 

51 

52 # Call parent class constructor 

53 super().__init__(properties) 

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

55 

56 # Input/Output files 

57 self.io_dict = { 

58 "in": {"input_pdb_path": input_pdb_path}, 

59 "out": {"output_pdb_path": output_pdb_path}, 

60 } 

61 

62 # Properties specific for BB 

63 self.forced_uniprot_references = properties.get("forced_uniprot_references") 

64 # If input forced uniprot references is a string and not a list then convert it 

65 if isinstance(self.forced_uniprot_references, str): 

66 self.forced_uniprot_references = self.forced_uniprot_references.split(" ") 

67 

68 # Check the properties 

69 self.check_properties(properties) 

70 self.check_arguments() 

71 

72 @launchlogger 

73 def launch(self) -> int: 

74 """Execute the :class:`FixPdb <model.fix_pdb.FixPdb>` object.""" 

75 

76 # Setup Biobb 

77 if self.check_restart(): 

78 return 0 

79 

80 # Run code 

81 self.return_code = 0 

82 

83 # Get the user arguments 

84 input_pdb_path = self.io_dict["in"]["input_pdb_path"] 

85 output_pdb_path = self.io_dict["out"]["output_pdb_path"] 

86 forced_uniprot_references = self.forced_uniprot_references 

87 

88 # Read and parse the input pdb file 

89 structure = Structure.from_pdb_file(input_pdb_path) 

90 

91 # Add protein chains in case they are missing 

92 chains = structure.chains 

93 if len(chains) == 0 or ( 

94 len(chains) == 1 and (chains[0].name == " " or chains[0].name == "X") 

95 ): 

96 structure.raw_protein_chainer() 

97 

98 # Run all the mapping function 

99 # mapping: Optional[dict[Any, Any]] = {} 

100 # if forced_uniprot_references: 

101 mapping = generate_map_online(structure, forced_uniprot_references) # type: ignore 

102 

103 # In case something went wrong with the mapping stop here 

104 if not mapping: 

105 self.return_code = -1 

106 return self.return_code 

107 

108 # Change residue numbers in the structure according to the mapping results 

109 mapped_residue_numbers = mapping["residue_reference_numbers"] 

110 for r, residue in enumerate(structure.residues): 

111 mapped_residue_number = mapped_residue_numbers[r] 

112 if mapped_residue_number is None: 

113 continue 

114 residue.number = mapped_residue_number 

115 

116 # Write the modified structure to a new pdb file 

117 structure.generate_pdb_file(output_pdb_path) 

118 

119 print("Fixed :)") 

120 

121 # Remove temporal files 

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

123 self.remove_tmp_files() 

124 

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

126 return self.return_code 

127 

128 

129def fix_pdb( 

130 input_pdb_path: str, 

131 output_pdb_path: str, 

132 properties: Optional[dict] = None, 

133 **kwargs, 

134) -> int: 

135 """Create :class:`FixPdb <model.fix_pdb.FixPdb>` class and 

136 execute the :meth:`launch() <model.fix_pdb.FixPdb.launch>` method.""" 

137 return FixPdb( 

138 input_pdb_path=input_pdb_path, 

139 output_pdb_path=output_pdb_path, 

140 properties=properties, 

141 **kwargs, 

142 ).launch() 

143 

144 fix_pdb.__doc__ = FixPdb.__doc__ 

145 

146 

147def main(): 

148 parser = argparse.ArgumentParser( 

149 description="Model the missing atoms in the backbone of a PDB structure.", 

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

151 ) 

152 parser.add_argument( 

153 "-c", 

154 "--config", 

155 required=False, 

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

157 ) 

158 

159 # Specific args of each building block 

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

161 required_args.add_argument( 

162 "-i", "--input_pdb_path", required=True, help="Input PDB file name" 

163 ) 

164 required_args.add_argument( 

165 "-o", "--output_pdb_path", required=True, help="Output PDB file name" 

166 ) 

167 

168 args = parser.parse_args() 

169 config = args.config if args.config else None 

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

171 

172 # Specific call of each building block 

173 fix_pdb( 

174 input_pdb_path=args.input_pdb_path, 

175 output_pdb_path=args.output_pdb_path, 

176 properties=properties, 

177 ) 

178 

179 

180if __name__ == "__main__": 

181 main()