⬅ biobb_pdb_tools/pdb_tools/biobb_pdb_splitmodel.py source

1 #!/usr/bin/env python3
2  
3 """Module containing the Pdbsplitmodel class and the command line interface."""
4  
5 import argparse
6 import glob
7 import os
8 import zipfile
9 from pathlib import Path
10 from typing import Optional
11  
12 from biobb_common.configuration import settings
13 from biobb_common.generic.biobb_object import BiobbObject
14 from biobb_common.tools import file_utils as fu
15 from biobb_common.tools.file_utils import launchlogger
16  
17  
18 class Pdbsplitmodel(BiobbObject):
19 """
20 | biobb_pdb_tools Pdbsplitmodel
21 | Splits a PDB file into several, each containing one MODEL.
22 | This tool splits a PDB file into several, each containing one MODEL. It can be used to split a PDB file into several, each containing one MODEL.
23  
24 Args:
25 input_file_path (str): PDB file. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_pdb_tools/master/biobb_pdb_tools/test/data/pdb_tools/input_pdb_splitmodel.pdb>`_. Accepted formats: pdb (edam:format_1476).
26 output_file_path (str): ZIP file containing all PDB files splited by protein model. File type: output. `Sample file <https://github.com/bioexcel/biobb_pdb_tools/blob/master/biobb_pdb_tools/test/reference/pdb_tools/ref_pdb_splitmodel.zip>`_. Accepted formats: zip (edam:format_3987).
27 properties (dic):
28 * **binary_path** (*str*) - ("pdb_splitmodel") Path to the pdb_splitmodel executable binary.
29 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
30 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
31  
32 Examples:
33 This is a use example of how to use the building block from Python::
34  
35 from biobb_pdb_tools.pdb_tools.biobb_pdb_splitmodel import biobb_pdb_splitmodel
36  
37 biobb_pdb_splitmodel(input_file_path='/path/to/input.pdb',
38 output_file_path='/path/to/output.zip)
39  
40 Info:
41 * wrapped_software:
42 * name: pdb_tools
43 * version: >=2.5.0
44 * license: Apache-2.0
45 * ontology:
46 * name: EDAM
47 * schema: http://edamontology.org/EDAM.owl
48  
49 """
50  
51 def __init__(
52 self, input_file_path, output_file_path, properties=None, **kwargs
53 ) -> None:
54 properties = properties or {}
55  
56 super().__init__(properties)
57 self.locals_var_dict = locals().copy()
58 self.io_dict = {
59 "in": {"input_file_path": input_file_path},
60 "out": {"output_file_path": output_file_path},
61 }
62  
63 self.binary_path = properties.get("binary_path", "pdb_splitmodel")
64 self.properties = properties
65  
66 self.check_properties(properties)
67 self.check_arguments()
68  
69 @launchlogger
70 def launch(self) -> int:
71 """Execute the :class:`Pdbsplitmodel <biobb_pdb_tools.pdb_tools.pdb_splitmodel>` object."""
72  
73 if self.check_restart():
74 return 0
75 self.stage_files()
76  
77 self.cmd = [
78 "cd",
79 self.stage_io_dict.get("unique_dir", ""),
80 ";",
81 self.binary_path,
82 self.stage_io_dict["in"]["input_file_path"],
83 ]
84  
85 fu.log(" ".join(self.cmd), self.out_log, self.global_log)
86  
87 fu.log(
88 "Creating command line with instructions and required arguments",
89 self.out_log,
90 self.global_log,
91 )
92 self.run_biobb()
93  
94 stem = Path(self.stage_io_dict["in"]["input_file_path"]).stem
95 pdb_files = glob.glob(
96 os.path.join(self.stage_io_dict.get("unique_dir", ""), stem + "_*.pdb")
97 )
98  
99 if len(pdb_files) > 1:
100 output_zip_path = os.path.join(
101 self.stage_io_dict.get("unique_dir", ""),
102 self.stage_io_dict["out"]["output_file_path"],
103 )
104 fu.log(
105 "Saving %d pdb model files in a zip" % len(pdb_files),
106 self.out_log,
107 self.global_log,
108 )
109 with zipfile.ZipFile(output_zip_path, "w") as zipf:
110 for pdb_file in pdb_files:
111 zipf.write(pdb_file, os.path.basename(pdb_file))
112 else:
113 fu.log("The given input file has no models.", self.out_log, self.global_log)
114 output_zip_path = os.path.join(
115 self.stage_io_dict.get("unique_dir", ""),
116 self.stage_io_dict["out"]["output_file_path"],
117 )
118 with zipfile.ZipFile(output_zip_path, "w") as zipf:
119 zipf.write(
120 self.stage_io_dict["in"]["input_file_path"],
121 os.path.basename(self.stage_io_dict["in"]["input_file_path"]),
122 )
123 pass
124  
125 self.copy_to_host()
126 self.tmp_files.extend([self.stage_io_dict.get("unique_dir", "")])
127 self.remove_tmp_files()
128 self.check_arguments(output_files_created=True, raise_exception=False)
129  
130 return self.return_code
131  
132  
133 def biobb_pdb_splitmodel(
134 input_file_path: str,
135 output_file_path: str,
136 properties: Optional[dict] = None,
137 **kwargs,
138 ) -> int:
139 """Create :class:`Pdbsplitmodel <biobb_pdb_tools.pdb_tools.pdb_splitmodel>` class and
140 execute the :meth:`launch() <biobb_pdb_tools.pdb_tools.pdb_splitmodel.launch>` method."""
141  
142 return Pdbsplitmodel(
143 input_file_path=input_file_path,
144 output_file_path=output_file_path,
145 properties=properties,
146 **kwargs,
147 ).launch()
148  
  • E305 Expected 2 blank lines after class or function definition, found 1
149 biobb_pdb_splitmodel.__doc__ = Pdbsplitmodel.__doc__
150  
151  
152 def main():
153 """Command line execution of this building block. Please check the command line documentation."""
154 parser = argparse.ArgumentParser(
155 description="Splits a PDB file into several, each containing one MODEL.",
156 formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999),
157 )
158 parser.add_argument("--config", required=True, help="Configuration file")
159  
160 required_args = parser.add_argument_group("required arguments")
161 required_args.add_argument(
162 "--input_file_path",
163 required=True,
164 help="Description for the first input file path. Accepted formats: pdb.",
165 )
166 required_args.add_argument(
167 "--output_file_path",
168 required=True,
169 help="Description for the output file path. Accepted formats: zip.",
170 )
171  
172 args = parser.parse_args()
173 args.config = args.config or "{}"
174 properties = settings.ConfReader(config=args.config).get_prop_dic()
175  
176 biobb_pdb_splitmodel(
177 input_file_path=args.input_file_path,
178 output_file_path=args.output_file_path,
179 properties=properties,
180 )
181  
182  
183 if __name__ == "__main__":
184 main()