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.""" 

4 

5import argparse 

6import shutil 

7from typing import Optional 

8 

9from biobb_common.configuration import settings 

10from biobb_common.generic.biobb_object import BiobbObject 

11from biobb_common.tools import file_utils as fu 

12from biobb_common.tools.file_utils import launchlogger 

13 

14from biobb_structure_utils.utils.common import check_input_path, check_output_path 

15 

16 

17class ExtractModel(BiobbObject): 

18 """ 

19 | biobb_structure_utils ExtractModel 

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

21 | Wrapper for the `Structure Checking <https://github.com/bioexcel/biobb_structure_checking>`_ tool to extract a model 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_model.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_model.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 * **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. 

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_model import extract_model 

37 prop = { 

38 'models': [ 1, 2, 3 ] 

39 } 

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

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

42 properties=prop) 

43 

44 Info: 

45 * wrapped_software: 

46 * name: Structure Checking from MDWeb 

47 * version: >=3.0.3 

48 * license: Apache-2.0 

49 * ontology: 

50 * name: EDAM 

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

52 

53 """ 

54 

55 def __init__( 

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

57 ) -> None: 

58 properties = properties or {} 

59 

60 # Call parent class constructor 

61 super().__init__(properties) 

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

63 

64 # Input/Output files 

65 self.io_dict = { 

66 "in": {"input_structure_path": input_structure_path}, 

67 "out": {"output_structure_path": output_structure_path}, 

68 } 

69 

70 # Properties specific for BB 

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

72 self.models = properties.get("models", []) 

73 self.properties = properties 

74 

75 # Check the properties 

76 self.check_properties(properties) 

77 self.check_arguments() 

78 

79 @launchlogger 

80 def launch(self) -> int: 

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

82 

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

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

85 self.out_log, 

86 self.__class__.__name__, 

87 ) 

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

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

90 self.out_log, 

91 self.__class__.__name__, 

92 ) 

93 

94 # Setup Biobb 

95 if self.check_restart(): 

96 return 0 

97 self.stage_files() 

98 

99 # check if user has passed models properly 

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

101 

102 if models == "All": 

103 shutil.copyfile( 

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

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

106 ) 

107 

108 return 0 

109 else: 

110 # create temporary folder 

111 tmp_folder = fu.create_unique_dir() 

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

113 

114 filenames = [] 

115 

116 for model in models: 

117 tmp_file = tmp_folder + "/model" + str(model) + ".pdb" 

118 

119 self.cmd = [ 

120 self.binary_path, 

121 "-i", 

122 self.stage_io_dict["in"]["input_structure_path"], 

123 "-o", 

124 tmp_file, 

125 "--force_save", 

126 "models", 

127 "--select", 

128 str(model), 

129 ] 

130 

131 # Run Biobb block 

132 self.run_biobb() 

133 

134 filenames.append(tmp_file) 

135 

136 # concat tmp_file and save them into output file 

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

138 for i, fname in enumerate(filenames): 

139 with open(fname) as infile: 

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

141 for line in infile: 

142 if not line.startswith("END"): 

143 outfile.write(line) 

144 else: 

145 outfile.write("ENDMDL\n") 

146 

147 # Copy files to host 

148 self.copy_to_host() 

149 

150 # Remove temporal files 

151 self.tmp_files.extend([ 

152 # self.stage_io_dict.get("unique_dir", ""), 

153 tmp_folder 

154 ]) 

155 self.remove_tmp_files() 

156 

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

158 

159 return self.return_code 

160 

161 

162def check_format_models(models, out_log): 

163 """Check format of models list""" 

164 if not models: 

165 fu.log("Empty models parameter, all models will be returned.", out_log) 

166 return "All" 

167 

168 if not isinstance(models, list): 

169 fu.log( 

170 "Incorrect format of models parameter, all models will be returned.", 

171 out_log, 

172 ) 

173 return "All" 

174 

175 return models 

176 

177 

178def extract_model( 

179 input_structure_path: str, 

180 output_structure_path: str, 

181 properties: Optional[dict] = None, 

182 **kwargs, 

183) -> int: 

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

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

186 

187 return ExtractModel( 

188 input_structure_path=input_structure_path, 

189 output_structure_path=output_structure_path, 

190 properties=properties, 

191 **kwargs, 

192 ).launch() 

193 

194 extract_model.__doc__ = ExtractModel.__doc__ 

195 

196 

197def main(): 

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

199 parser = argparse.ArgumentParser( 

200 description="Extract a model from a 3D structure.", 

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

202 ) 

203 parser.add_argument( 

204 "-c", 

205 "--config", 

206 required=False, 

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

208 ) 

209 

210 # Specific args of each building block 

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

212 required_args.add_argument( 

213 "-i", 

214 "--input_structure_path", 

215 required=True, 

216 help="Input structure file path. Accepted formats: pdb.", 

217 ) 

218 required_args.add_argument( 

219 "-o", 

220 "--output_structure_path", 

221 required=True, 

222 help="Output structure file path. Accepted formats: pdb.", 

223 ) 

224 

225 args = parser.parse_args() 

226 config = args.config if args.config else None 

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

228 

229 # Specific call of each building block 

230 extract_model( 

231 input_structure_path=args.input_structure_path, 

232 output_structure_path=args.output_structure_path, 

233 properties=properties, 

234 ) 

235 

236 

237if __name__ == "__main__": 

238 main()