Coverage for biobb_structure_utils / utils / extract_molecule.py: 90%

1#!/usr/bin/env python3 

2 

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

4from typing import Optional 

5from biobb_common.generic.biobb_object import BiobbObject 

6from biobb_common.tools import file_utils as fu 

7from biobb_common.tools.file_utils import launchlogger 

8 

9from biobb_structure_utils.utils.common import ( 

10 _from_string_to_list, 

11 check_input_path, 

12 check_output_path, 

13) 

14 

15 

16class ExtractMolecule(BiobbObject): 

17 """ 

18 | biobb_structure_utils ExtractMolecule 

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

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

21 

22 Args: 

23 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_molecule.pdb>`_. Accepted formats: pdb (edam:format_1476), pdbqt (edam:format_1476). 

24 output_molecule_path (str): Output molecule file path. File type: output. `Sample file <https://github.com/bioexcel/biobb_structure_utils/raw/master/biobb_structure_utils/test/reference/utils/ref_extract_molecule.pdb>`_. Accepted formats: pdb (edam:format_1476), pdbqt (edam:format_1476). 

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

26 * **molecule_type** (*string*) - ("all") type of molecule to be extracted. If all, only waters and ligands will be removed from the original structure. Values: all, protein, na, dna, rna, chains. 

27 * **chains** (*list*) - (None) if chains selected in **molecule_type**, specify them here, e.g: ["A", "C", "N"]. 

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

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

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

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

32 

33 Examples: 

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

35 

36 from biobb_structure_utils.utils.extract_molecule import extract_molecule 

37 prop = { 

38 'molecule_type': 'chains', 

39 'chains': ['A', 'N', 'F'] 

40 } 

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

42 output_molecule_path='/path/to/newMolecule.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_molecule_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_molecule_path": output_molecule_path}, 

69 } 

70 

71 # Properties specific for BB 

72 self.molecule_type = properties.get("molecule_type", "all") 

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

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

75 self.properties = properties 

76 

77 # Check the properties 

78 self.check_properties(properties) 

79 self.check_arguments() 

80 

81 def create_command_list(self, command_list_path): 

82 """Creates a command list file as a input for structure checking""" 

83 instructions_list = ["ligands --remove All", "water --remove Yes"] 

84 

85 if self.molecule_type != "all": 

86 if self.molecule_type == "chains": 

87 instructions_list.append("chains --select " + ",".join(self.chains)) 

88 else: 

89 instructions_list.append("chains --select " + self.molecule_type) 

90 

91 with open(command_list_path, "w") as clp: 

92 for line in instructions_list: 

93 clp.write(line.strip() + "\n") 

94 

95 return command_list_path 

96 

97 @launchlogger 

98 def launch(self) -> int: 

99 """Execute the :class:`ExtractMolecule <utils.extract_molecule.ExtractMolecule>` utils.extract_molecule.ExtractMolecule object.""" 

100 

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

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

103 self.out_log, 

104 self.__class__.__name__, 

105 ) 

106 self.io_dict["out"]["output_molecule_path"] = check_output_path( 

107 self.io_dict["out"]["output_molecule_path"], 

108 self.out_log, 

109 self.__class__.__name__, 

110 ) 

111 

112 # Setup Biobb 

113 if self.check_restart(): 

114 return 0 

115 self.stage_files() 

116 

117 # create temporary folder 

118 tmp_folder = fu.create_unique_dir() 

119 fu.log("Creating %s temporary folder" % tmp_folder, self.out_log) 

120 

121 # create command list file 

122 command_list_file = self.create_command_list(tmp_folder + "/extract_prot.lst") 

123 

124 # run command line 

125 self.cmd = [ 

126 self.binary_path, 

127 "-i", 

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

129 "-o", 

130 self.io_dict["out"]["output_molecule_path"], 

131 "--force_save", 

132 "--non_interactive", 

133 "command_list", 

134 "--list", 

135 command_list_file, 

136 ] 

137 

138 # Run Biobb block 

139 self.run_biobb() 

140 

141 # Copy files to host 

142 self.copy_to_host() 

143 

144 # Remove temporal files 

145 self.tmp_files.append(tmp_folder) 

146 self.remove_tmp_files() 

147 

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

149 

150 return self.return_code 

151 

152 

153def extract_molecule( 

154 input_structure_path: str, 

155 output_molecule_path: str, 

156 properties: Optional[dict] = None, 

157 **kwargs, 

158) -> int: 

159 """Create the :class:`ExtractMolecule <utils.extract_molecule.ExtractMolecule>` class and 

160 execute the :meth:`launch() <utils.extract_molecule.ExtractMolecule.launch>` method.""" 

161 return ExtractMolecule(**dict(locals())).launch() 

162 

163 

164extract_molecule.__doc__ = ExtractMolecule.__doc__ 

165main = ExtractMolecule.get_main(extract_molecule, "Extract a molecule from a 3D structure.") 

166 

167if __name__ == "__main__": 

168 main()