Coverage for biobb_io/api/pdb_cluster_zip.py: 82%
57 statements
« prev ^ index » next coverage.py v7.6.9, created at 2024-12-10 15:33 +0000
1#!/usr/bin/env python
3"""PdbClusterZip Module"""
5import argparse
6import os
7from typing import Optional
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
14from biobb_io.api.common import (
15 check_mandatory_property,
16 check_output_path,
17 download_pdb,
18 get_cluster_pdb_codes,
19 write_pdb,
20)
23class PdbClusterZip(BiobbObject):
24 """
25 | biobb_io PdbClusterZip
26 | This class is a wrapper for downloading a PDB cluster from the Protein Data Bank.
27 | 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 PDB cluster.
29 Args:
30 output_pdb_zip_path (str): Path to the ZIP file containing the output PDB files. File type: output. `Sample file <https://github.com/bioexcel/biobb_io/raw/master/biobb_io/test/reference/api/output_pdb_cluster.zip>`_. Accepted formats: zip (edam:format_3987).
31 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
32 * **pdb_code** (*str*) - (None) RSCB PDB code.
33 * **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)
34 * **cluster** (*int*) - (90) Sequence Similarity Cutoff. Values: 50 (structures having less than 50% sequence identity to each other), 70 (structures having less than 70% sequence identity to each other), 90 (structures having less than 90% sequence identity to each other), 95 (structures having less than 95% sequence identity to each other).
35 * **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/>`_).
36 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
37 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
38 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory.
40 Examples:
41 This is a use example of how to use the building block from Python::
43 from biobb_io.api.pdb_cluster_zip import pdb_cluster_zip
44 prop = {
45 'pdb_code': '2VGB',
46 'filter': ['ATOM', 'MODEL', 'ENDMDL'],
47 'cluster': 90,
48 'api_id': 'pdbe'
49 }
50 pdb_cluster_zip(output_pdb_zip_path='/path/to/newStructures.zip',
51 properties=prop)
53 Info:
54 * wrapped_software:
55 * name: Protein Data Bank
56 * license: Apache-2.0
57 * ontology:
58 * name: EDAM
59 * schema: http://edamontology.org/EDAM.owl
61 """
63 def __init__(self, output_pdb_zip_path, properties=None, **kwargs) -> None:
64 properties = properties or {}
66 # Call parent class constructor
67 super().__init__(properties)
68 self.locals_var_dict = locals().copy()
70 # Input/Output files
71 self.io_dict = {"out": {"output_pdb_zip_path": output_pdb_zip_path}}
73 # Properties specific for BB
74 self.api_id = properties.get("api_id", "pdbe")
75 self.pdb_code = properties.get("pdb_code", None)
76 self.filter = properties.get("filter", ["ATOM", "MODEL", "ENDMDL"])
77 self.cluster = properties.get("cluster", 90)
78 self.properties = properties
80 # Check the properties
81 self.check_properties(properties)
82 self.check_arguments()
84 def check_data_params(self, out_log, err_log):
85 """Checks all the input/output paths and parameters"""
86 self.output_pdb_zip_path = check_output_path(
87 self.io_dict["out"]["output_pdb_zip_path"],
88 "output_pdb_zip_path",
89 False,
90 out_log,
91 self.__class__.__name__,
92 )
94 @launchlogger
95 def launch(self) -> int:
96 """Execute the :class:`PdbClusterZip <api.pdb_cluster_zip.PdbClusterZip>` api.pdb_cluster_zip.PdbClusterZip object."""
98 # check input/output paths and parameters
99 self.check_data_params(self.out_log, self.err_log)
101 # Setup Biobb
102 if self.check_restart():
103 return 0
105 check_mandatory_property(
106 self.pdb_code, "pdb_code", self.out_log, self.__class__.__name__
107 )
109 self.pdb_code = self.pdb_code.strip().lower()
111 file_list = []
112 # Downloading PDB_files
113 pdb_code_list = get_cluster_pdb_codes(
114 pdb_code=self.pdb_code,
115 cluster=self.cluster,
116 out_log=self.out_log,
117 global_log=self.global_log,
118 )
119 unique_dir = fu.create_unique_dir()
120 for pdb_code in pdb_code_list:
121 pdb_file = os.path.join(unique_dir, pdb_code + ".pdb")
122 pdb_string = download_pdb(
123 pdb_code=pdb_code,
124 api_id=self.api_id,
125 out_log=self.out_log,
126 global_log=self.global_log,
127 )
128 write_pdb(pdb_string, pdb_file, self.filter, self.out_log, self.global_log)
129 file_list.append(os.path.abspath(pdb_file))
131 # Zipping files
132 fu.log("Zipping the pdb files to: %s" % self.output_pdb_zip_path)
133 fu.zip_list(self.output_pdb_zip_path, file_list, out_log=self.out_log)
135 self.tmp_files.extend([self.stage_io_dict.get("unique_dir", ""), unique_dir])
136 self.remove_tmp_files()
138 self.check_arguments(output_files_created=True, raise_exception=False)
140 return 0
143def pdb_cluster_zip(
144 output_pdb_zip_path: str, properties: Optional[dict] = None, **kwargs
145) -> int:
146 """Execute the :class:`PdbClusterZip <api.pdb_cluster_zip.PdbClusterZip>` class and
147 execute the :meth:`launch() <api.pdb_cluster_zip.PdbClusterZip.launch>` method."""
149 return PdbClusterZip(
150 output_pdb_zip_path=output_pdb_zip_path, properties=properties, **kwargs
151 ).launch()
154def main():
155 """Command line execution of this building block. Please check the command line documentation."""
156 parser = argparse.ArgumentParser(
157 description="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 PDB cluster.",
158 formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999),
159 )
160 parser.add_argument(
161 "-c",
162 "--config",
163 required=False,
164 help="This file can be a YAML file, JSON file or JSON string",
165 )
167 # Specific args of each building block
168 required_args = parser.add_argument_group("required arguments")
169 required_args.add_argument(
170 "-o",
171 "--output_pdb_zip_path",
172 required=True,
173 help="Path to the ZIP or PDB file containing the output PDB files. Accepted formats: pdb, zip.",
174 )
176 args = parser.parse_args()
177 config = args.config if args.config else None
178 properties = settings.ConfReader(config=config).get_prop_dic()
180 # Specific call of each building block
181 pdb_cluster_zip(output_pdb_zip_path=args.output_pdb_zip_path, properties=properties)
184if __name__ == "__main__":
185 main()