Coverage for biobb_structure_utils / utils / extract_chain.py: 84%

1#!/usr/bin/env python3 

2 

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

4import shutil 

5from typing import Optional 

6from biobb_common.generic.biobb_object import BiobbObject 

7from biobb_common.tools import file_utils as fu 

8from biobb_common.tools.file_utils import launchlogger 

9 

10from biobb_structure_utils.utils.common import ( 

11 _from_string_to_list, 

12 check_input_path, 

13 check_output_path, 

14) 

15 

16 

17class ExtractChain(BiobbObject): 

18 """ 

19 | biobb_structure_utils ExtractAtoms 

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

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

22 

23 Args: 

24 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). 

25 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). 

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

27 * **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. 

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

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

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

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

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

33 

34 Examples: 

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

36 

37 from biobb_structure_utils.utils.extract_chain import extract_chain 

38 prop = { 

39 'chains': [ 'A', 'B' ] 

40 } 

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

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

43 properties=prop) 

44 

45 Info: 

46 * wrapped_software: 

47 * name: Structure Checking from MDWeb 

48 * version: >=3.0.3 

49 * license: Apache-2.0 

50 * ontology: 

51 * name: EDAM 

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

53 

54 """ 

55 

56 def __init__( 

57 self, input_structure_path, output_structure_path, properties=None, **kwargs 

58 ) -> None: 

59 properties = properties or {} 

60 

61 # Call parent class constructor 

62 super().__init__(properties) 

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

64 

65 # Input/Output files 

66 self.io_dict = { 

67 "in": {"input_structure_path": input_structure_path}, 

68 "out": {"output_structure_path": output_structure_path}, 

69 } 

70 

71 # Properties specific for BB 

72 self.binary_path = properties.get("binary_path", "check_structure") 

73 self.chains = _from_string_to_list(properties.get("chains", [])) 

74 self.permissive = properties.get("permissive", False) 

75 self.properties = properties 

76 

77 # Check the properties 

78 self.check_properties(properties) 

79 self.check_arguments() 

80 

81 @launchlogger 

82 def launch(self) -> int: 

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

84 

85 self.io_dict["in"]["input_structure_path"] = check_input_path( 

86 self.io_dict["in"]["input_structure_path"], 

87 self.out_log, 

88 self.__class__.__name__, 

89 ) 

90 self.io_dict["out"]["output_structure_path"] = check_output_path( 

91 self.io_dict["out"]["output_structure_path"], 

92 self.out_log, 

93 self.__class__.__name__, 

94 ) 

95 

96 # Setup Biobb 

97 if self.check_restart(): 

98 return 0 

99 self.stage_files() 

100 

101 # check if user has passed chains properly 

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

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

104 

105 if self.permissive: 

106 fu.log( 

107 "Warning: Use permissive=True is a risky option use it under your own responsability", 

108 self.out_log, 

109 self.global_log, 

110 ) 

111 if chains.upper() == "ALL": 

112 shutil.copyfile( 

113 self.io_dict["in"]["input_structure_path"], 

114 self.io_dict["out"]["output_structure_path"], 

115 ) 

116 else: 

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

118 with open( 

119 self.io_dict["in"]["input_structure_path"] 

120 ) as structure_in, open( 

121 self.io_dict["out"]["output_structure_path"], "w" 

122 ) as structure_out: 

123 for line in structure_in: 

124 if ( 

125 line.strip().upper().startswith(("ATOM", "HETATM")) and line.strip().upper()[21] in chain_list 

126 ): 

127 structure_out.write(line) 

128 

129 else: 

130 # run command line 

131 self.cmd = [ 

132 self.binary_path, 

133 "-i", 

134 self.io_dict["in"]["input_structure_path"], 

135 "-o", 

136 self.io_dict["out"]["output_structure_path"], 

137 "--force_save", 

138 "chains", 

139 "--select", 

140 chains, 

141 ] 

142 

143 # Run Biobb block 

144 self.run_biobb() 

145 

146 # Copy files to host 

147 self.copy_to_host() 

148 

149 # Remove temporal files 

150 self.remove_tmp_files() 

151 

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

153 

154 return self.return_code 

155 

156 

157def check_format_chains(chains, out_log): 

158 """Check format of chains list""" 

159 if not chains: 

160 fu.log("Empty chains parameter, all chains will be returned.", out_log) 

161 return "All" 

162 

163 if not isinstance(chains, list): 

164 fu.log( 

165 "Incorrect format of chains parameter, all chains will be returned.", 

166 out_log, 

167 ) 

168 return "All" 

169 

170 return ",".join(chains) 

171 

172 

173def extract_chain( 

174 input_structure_path: str, 

175 output_structure_path: str, 

176 properties: Optional[dict] = None, 

177 **kwargs, 

178) -> int: 

179 """Create the :class:`ExtractChain <utils.extract_chain.ExtractChain>` class and 

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

181 return ExtractChain(**dict(locals())).launch() 

182 

183 

184extract_chain.__doc__ = ExtractChain.__doc__ 

185main = ExtractChain.get_main(extract_chain, "Extract a chain from a 3D structure.") 

186 

187if __name__ == "__main__": 

188 main()