Coverage for biobb_structure_utils/utils/extract_model.py: 76%

1#!/usr/bin/env python3 

2 

3"""Module containing the ExtractModel 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 ExtractModel(BiobbObject): 

14 """ 

15 | biobb_structure_utils ExtractModel 

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

17 | Wrapper for the `Structure Checking <https://github.com/bioexcel/biobb_structure_checking>`_ tool to extract a model 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_model.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_model.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 * **models** (*list*) - (None) List of models to be extracted from the input_structure_path file. If empty, all the models of the structure will be returned. 

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

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

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

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

28 

29 Examples: 

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

31 

32 from biobb_structure_utils.utils.extract_model import extract_model 

33 prop = { 

34 'models': [ 1, 2, 3 ] 

35 } 

36 extract_model(input_structure_path='/path/to/myStructure.pdb', 

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

38 properties=prop) 

39 

40 Info: 

41 * wrapped_software: 

42 * name: Structure Checking from MDWeb 

43 * version: >=3.0.3 

44 * license: Apache-2.0 

45 * ontology: 

46 * name: EDAM 

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

48 

49 """ 

50 

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

52 properties = properties or {} 

53 

54 # Call parent class constructor 

55 super().__init__(properties) 

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

57 

58 # Input/Output files 

59 self.io_dict = { 

60 "in": {"input_structure_path": input_structure_path}, 

61 "out": {"output_structure_path": output_structure_path} 

62 } 

63 

64 # Properties specific for BB 

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

66 self.models = properties.get('models', []) 

67 self.properties = properties 

68 

69 # Check the properties 

70 self.check_properties(properties) 

71 self.check_arguments() 

72 

73 @launchlogger 

74 def launch(self) -> int: 

75 """Execute the :class:`ExtractModel <utils.extract_model.ExtractModel>` utils.extract_model.ExtractModel object.""" 

76 

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

78 self.out_log, self.__class__.__name__) 

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

80 self.out_log, self.__class__.__name__) 

81 

82 # Setup Biobb 

83 if self.check_restart(): 

84 return 0 

85 self.stage_files() 

86 

87 # check if user has passed models properly 

88 models = check_format_models(self.models, self.out_log) 

89 

90 if models == 'All': 

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

92 

93 return 0 

94 else: 

95 # create temporary folder 

96 tmp_folder = fu.create_unique_dir() 

97 fu.log('Creating %s temporary folder' % tmp_folder, self.out_log) 

98 

99 filenames = [] 

100 

101 for model in models: 

102 

103 tmp_file = tmp_folder + '/model' + str(model) + '.pdb' 

104 

105 self.cmd = [self.binary_path, 

106 '-i', self.stage_io_dict['in']['input_structure_path'], 

107 '-o', tmp_file, 

108 '--force_save', 

109 'models', '--select', str(model)] 

110 

111 # Run Biobb block 

112 self.run_biobb() 

113 

114 filenames.append(tmp_file) 

115 

116 # concat tmp_file and save them into output file 

117 with open(self.io_dict['out']['output_structure_path'], 'w') as outfile: 

118 for i, fname in enumerate(filenames): 

119 with open(fname) as infile: 

120 outfile.write('MODEL ' + "{:>4}".format(str(i + 1)) + '\n') 

121 for line in infile: 

122 if not line.startswith("END"): 

123 outfile.write(line) 

124 else: 

125 outfile.write('ENDMDL\n') 

126 

127 # Copy files to host 

128 self.copy_to_host() 

129 

130 # Remove temporal files 

131 self.tmp_files.extend([self.stage_io_dict.get("unique_dir"), tmp_folder]) 

132 self.remove_tmp_files() 

133 

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

135 

136 return self.return_code 

137 

138 

139def check_format_models(models, out_log): 

140 """ Check format of models list """ 

141 if not models: 

142 fu.log('Empty models parameter, all models will be returned.', out_log) 

143 return 'All' 

144 

145 if not isinstance(models, list): 

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

147 return 'All' 

148 

149 return models 

150 

151 

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

153 """Execute the :class:`ExtractModel <utils.extract_model.ExtractModel>` class and 

154 execute the :meth:`launch() <utils.extract_model.ExtractModel.launch>` method.""" 

155 

156 return ExtractModel(input_structure_path=input_structure_path, 

157 output_structure_path=output_structure_path, 

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

159 

160 

161def main(): 

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

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

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

165 

166 # Specific args of each building block 

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

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

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

170 

171 args = parser.parse_args() 

172 config = args.config if args.config else None 

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

174 

175 # Specific call of each building block 

176 extract_model(input_structure_path=args.input_structure_path, 

177 output_structure_path=args.output_structure_path, 

178 properties=properties) 

179 

180 

181if __name__ == '__main__': 

182 main()