Coverage for biobb_io/api/pdb.py: 94%

35 statements  

« prev     ^ index     » next       coverage.py v7.10.6, created at 2025-09-04 08:31 +0000

1#!/usr/bin/env python 

2 

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

4 

5from typing import Optional 

6from biobb_common.generic.biobb_object import BiobbObject 

7from biobb_common.tools.file_utils import launchlogger 

8 

9from biobb_io.api.common import ( 

10 check_mandatory_property, 

11 check_output_path, 

12 download_pdb, 

13 write_pdb, 

14) 

15 

16 

17class Pdb(BiobbObject): 

18 """ 

19 | biobb_io Pdb 

20 | This class is a wrapper for downloading a PDB structure from the Protein Data Bank. 

21 | Wrapper for the `Protein Data Bank in Europe <https://www.ebi.ac.uk/pdbe/>`_, the `Protein Data Bank <https://www.rcsb.org/>`_ and the `MMB PDB mirror <http://mmb.irbbarcelona.org/api/>`_ for downloading a single PDB structure. 

22 

23 Args: 

24 output_pdb_path (str): Path to the output PDB file. File type: output. `Sample file <https://github.com/bioexcel/biobb_io/raw/master/biobb_io/test/reference/api/output_pdb.pdb>`_. Accepted formats: pdb (edam:format_1476). 

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

26 * **pdb_code** (*str*) - (None) RSCB PDB code. 

27 * **filter** (*str*) - (["ATOM", "MODEL", "ENDMDL"]) Array of groups to be kept. If value is None or False no filter will be applied. All the possible values are defined in the `official PDB specification <http://www.wwpdb.org/documentation/file-format-content/format33/v3.3.html)>`_. 

28 * **api_id** (*str*) - ("pdbe") Identifier of the PDB REST API from which the PDB structure will be downloaded. Values: pdbe (`PDB in Europe REST API <https://www.ebi.ac.uk/pdbe/pdbe-rest-api>`_), pdb (`RCSB PDB REST API <https://data.rcsb.org/>`_), mmb (`MMB PDB mirror API <http://mmb.irbbarcelona.org/api/>`_). 

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_io.api.pdb import pdb 

37 prop = { 

38 'pdb_code': '2VGB', 

39 'filter': ['ATOM', 'MODEL', 'ENDMDL'], 

40 'api_id': 'pdbe' 

41 } 

42 pdb(output_pdb_path='/path/to/newStructure.pdb', 

43 properties=prop) 

44 

45 Info: 

46 * wrapped_software: 

47 * name: Protein Data Bank 

48 * license: Apache-2.0 

49 * ontology: 

50 * name: EDAM 

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

52 

53 """ 

54 

55 def __init__(self, output_pdb_path, properties=None, **kwargs) -> None: 

56 properties = properties or {} 

57 

58 # Call parent class constructor 

59 super().__init__(properties) 

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

61 

62 # Input/Output files 

63 self.io_dict = {"out": {"output_pdb_path": output_pdb_path}} 

64 

65 # Properties specific for BB 

66 self.api_id = properties.get("api_id", "pdbe") 

67 self.pdb_code = properties.get("pdb_code", None) 

68 self.filter = properties.get("filter", ["ATOM", "MODEL", "ENDMDL"]) 

69 self.properties = properties 

70 

71 # Check the properties 

72 self.check_properties(properties) 

73 self.check_arguments() 

74 

75 def check_data_params(self, out_log, err_log): 

76 """Checks all the input/output paths and parameters""" 

77 self.output_pdb_path = check_output_path( 

78 self.io_dict["out"]["output_pdb_path"], 

79 "output_pdb_path", 

80 False, 

81 out_log, 

82 self.__class__.__name__, 

83 ) 

84 

85 @launchlogger 

86 def launch(self) -> int: 

87 """Execute the :class:`Pdb <api.pdb.Pdb>` api.pdb.Pdb object.""" 

88 

89 # check input/output paths and parameters 

90 self.check_data_params(self.out_log, self.err_log) 

91 

92 # Setup Biobb 

93 if self.check_restart(): 

94 return 0 

95 

96 check_mandatory_property( 

97 self.pdb_code, "pdb_code", self.out_log, self.__class__.__name__ 

98 ) 

99 

100 self.pdb_code = self.pdb_code.strip().lower() 

101 

102 # Downloading PDB file 

103 pdb_string = download_pdb( 

104 self.pdb_code, self.api_id, self.out_log, self.global_log 

105 ) 

106 write_pdb( 

107 pdb_string, self.output_pdb_path, self.filter, self.out_log, self.global_log 

108 ) 

109 

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

111 

112 return 0 

113 

114 

115def pdb(output_pdb_path: str, properties: Optional[dict] = None, **kwargs) -> int: 

116 """Execute the :class:`Pdb <api.pdb.Pdb>` class and 

117 execute the :meth:`launch() <api.pdb.Pdb.launch>` method.""" 

118 return Pdb(**dict(locals())).launch() 

119 

120 

121pdb.__doc__ = Pdb.__doc__ 

122main = Pdb.get_main(pdb, "This class is a wrapper for downloading a PDB structure from the Protein Data Bank.") 

123 

124if __name__ == "__main__": 

125 main()