Coverage for biobb_structure_utils/utils/extract_chain.py: 73%

1#!/usr/bin/env python3 

2 

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

4import argparse 

5import shutil 

6from biobb_common.configuration import settings 

7from biobb_common.generic.biobb_object import BiobbObject 

8from biobb_common.tools import file_utils as fu 

9from biobb_common.tools.file_utils import launchlogger 

10from biobb_structure_utils.utils.common import check_input_path, check_output_path 

11 

12 

13class ExtractChain(BiobbObject): 

14 """ 

15 | biobb_structure_utils ExtractAtoms 

16 | This class is a wrapper of the Structure Checking tool to extract a chain from a 3D structure. 

17 | Wrapper for the `Structure Checking <https://github.com/bioexcel/biobb_structure_checking>`_ tool to extract a chain from a 3D structure. 

18 

19 Args: 

20 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/extract_chain.pdb>`_. Accepted formats: pdb (edam:format_1476), pdbqt (edam:format_1476). 

21 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/ref_extract_chain.pdb>`_. Accepted formats: pdb (edam:format_1476), pdbqt (edam:format_1476). 

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

23 * **chains** (*list*) - (None) List of chains to be extracted from the input_structure_path file. If empty, all the chains of the structure will be returned. 

24 * **permissive** (*bool*) - (False) Use non standard PDB files. 

25 * **binary_path** (*string*) - ("check_structure") path to the check_structure application 

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 

30 Examples: 

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

32 

33 from biobb_structure_utils.utils.extract_chain import extract_chain 

34 prop = { 

35 'chains': [ 'A', 'B' ] 

36 } 

37 extract_chain(input_structure_path='/path/to/myStructure.pdb', 

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

39 properties=prop) 

40 

41 Info: 

42 * wrapped_software: 

43 * name: Structure Checking from MDWeb 

44 * version: >=3.0.3 

45 * license: Apache-2.0 

46 * ontology: 

47 * name: EDAM 

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

49 

50 """ 

51 

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

53 properties = properties or {} 

54 

55 # Call parent class constructor 

56 super().__init__(properties) 

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

58 

59 # Input/Output files 

60 self.io_dict = { 

61 "in": {"input_structure_path": input_structure_path}, 

62 "out": {"output_structure_path": output_structure_path} 

63 } 

64 

65 # Properties specific for BB 

66 self.binary_path = properties.get('binary_path', 'check_structure') 

67 self.chains = properties.get('chains', []) 

68 self.permissive = properties.get('permissive', False) 

69 self.properties = properties 

70 

71 # Check the properties 

72 self.check_properties(properties) 

73 self.check_arguments() 

74 

75 @launchlogger 

76 def launch(self) -> int: 

77 """Execute the :class:`ExtractChain <utils.extract_chain.ExtractChain>` utils.extract_chain.ExtractChain object.""" 

78 

79 self.io_dict['in']['input_structure_path'] = check_input_path(self.io_dict['in']['input_structure_path'], 

80 self.out_log, self.__class__.__name__) 

81 self.io_dict['out']['output_structure_path'] = check_output_path(self.io_dict['out']['output_structure_path'], 

82 self.out_log, self.__class__.__name__) 

83 

84 # Setup Biobb 

85 if self.check_restart(): 

86 return 0 

87 self.stage_files() 

88 

89 # check if user has passed chains properly 

90 chains = check_format_chains(self.chains, self.out_log) 

91 fu.log(f"Selected Chains: {chains}", self.out_log, self.global_log) 

92 

93 if self.permissive: 

94 fu.log('Warning: Use permissive=True is a risky option use it under your own responsability', self.out_log, self.global_log) 

95 if chains.upper() == 'ALL': 

96 shutil.copyfile(self.io_dict['in']['input_structure_path'], self.io_dict['out']['output_structure_path']) 

97 else: 

98 chain_list = chains.upper().replace(" ", "").split(",") 

99 with open(self.io_dict['in']['input_structure_path']) as structure_in, open(self.io_dict['out']['output_structure_path'], 'w') as structure_out: 

100 for line in structure_in: 

101 if line.strip().upper().startswith(('ATOM', 'HETATM')) and line.strip().upper()[21] in chain_list: 

102 structure_out.write(line) 

103 

104 else: 

105 # run command line 

106 self.cmd = [self.binary_path, 

107 '-i', self.io_dict['in']['input_structure_path'], 

108 '-o', self.io_dict['out']['output_structure_path'], 

109 '--force_save', 

110 'chains', '--select', chains] 

111 

112 # Run Biobb block 

113 self.run_biobb() 

114 

115 # Copy files to host 

116 self.copy_to_host() 

117 

118 # Remove temporal files 

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

120 self.remove_tmp_files() 

121 

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

123 

124 return self.return_code 

125 

126 

127def check_format_chains(chains, out_log): 

128 """ Check format of chains list """ 

129 if not chains: 

130 fu.log('Empty chains parameter, all chains will be returned.', out_log) 

131 return 'All' 

132 

133 if not isinstance(chains, list): 

134 fu.log('Incorrect format of chains parameter, all chains will be returned.', out_log) 

135 return 'All' 

136 

137 return ','.join(chains) 

138 

139 

140def extract_chain(input_structure_path: str, output_structure_path: str, properties: dict = None, **kwargs) -> int: 

141 """Execute the :class:`ExtractChain <utils.extract_chain.ExtractChain>` class and 

142 execute the :meth:`launch() <utils.extract_chain.ExtractChain.launch>` method.""" 

143 

144 return ExtractChain(input_structure_path=input_structure_path, 

145 output_structure_path=output_structure_path, 

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

147 

148 

149def main(): 

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

151 parser = argparse.ArgumentParser(description="Extract a chain from a 3D structure.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999)) 

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

153 

154 # Specific args of each building block 

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

156 required_args.add_argument('-i', '--input_structure_path', required=True, help="Input structure file path. Accepted formats: pdb.") 

157 required_args.add_argument('-o', '--output_structure_path', required=True, help="Output structure file path. Accepted formats: pdb.") 

158 

159 args = parser.parse_args() 

160 config = args.config if args.config else None 

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

162 

163 # Specific call of each building block 

164 extract_chain(input_structure_path=args.input_structure_path, 

165 output_structure_path=args.output_structure_path, 

166 properties=properties) 

167 

168 

169if __name__ == '__main__': 

170 main()