Coverage for biobb_haddock/haddock/sele_top.py: 75%
72 statements
« prev ^ index » next coverage.py v7.10.2, created at 2025-08-07 08:48 +0000
1#!/usr/bin/env python3
3"""Module containing the haddock class and the command line interface."""
5import jsonpickle
6import argparse
7import shutil
8from pathlib import Path
9from typing import Optional
11from biobb_common.configuration import settings
12from biobb_common.generic.biobb_object import BiobbObject
13from biobb_common.tools import file_utils as fu
14from biobb_common.tools.file_utils import launchlogger
16from biobb_haddock.haddock.common import create_cfg, unzip_workflow_data
19class SeleTop(BiobbObject):
20 """
21 | biobb_haddock SeleTop
22 | Wrapper class for the Haddock SeleTop module.
23 | The SeleTop module. `Haddock SeleTop module <https://www.bonvinlab.org/haddock3/modules/analysis/haddock.modules.analysis.seletop.html>`_ selects the top models of a docking.
25 Args:
26 input_haddock_wf_data_zip (str): Path to the input zipball containing all the current Haddock workflow data. File type: input. `Sample file <https://github.com/bioexcel/biobb_haddock/raw/master/biobb_haddock/test/data/haddock/haddock_wf_data_rigid.zip>`_. Accepted formats: zip (edam:format_3987).
27 output_selection_zip_path (str): Path to the output PDB file collection in zip format. File type: output. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_haddock/master/biobb_haddock/test/reference/haddock/ref_seletop.zip>`_. Accepted formats: zip (edam:format_3987).
28 output_haddock_wf_data_zip (str) (Optional): Path to the output zipball containing all the current Haddock workflow data. File type: output. `Sample file <https://github.com/bioexcel/biobb_haddock/raw/master/biobb_haddock/test/data/haddock/haddock_wf_data_emref.zip>`_. Accepted formats: zip (edam:format_3987).
29 haddock_config_path (str) (Optional): Haddock configuration CFG file path. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_haddock/master/biobb_haddock/test/data/haddock/run.cfg>`_. Accepted formats: cfg (edam:format_1476).
30 properties (dict - Python dictionary object containing the tool parameters, not input/output files):
31 * **cfg** (*dict*) - ({}) Haddock configuration options specification.
32 * **global_cfg** (*dict*) - ({"postprocess": False}) `Global configuration options <https://www.bonvinlab.org/haddock3-user-manual/global_parameters.html>`_ specification.
33 * **binary_path** (*str*) - ("haddock") Path to the haddock haddock executable binary.
34 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
35 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
36 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory.
37 * **container_path** (*str*) - (None) Path to the binary executable of your container.
38 * **container_image** (*str*) - (None) Container Image identifier.
39 * **container_volume_path** (*str*) - ("/data") Path to an internal directory in the container.
40 * **container_working_dir** (*str*) - (None) Path to the internal CWD in the container.
41 * **container_user_id** (*str*) - (None) User number id to be mapped inside the container.
42 * **container_shell_path** (*str*) - ("/bin/bash") Path to the binary executable of the container shell.
45 Examples:
46 This is a use example of how to use the building block from Python::
48 from biobb_haddock.haddock.sele_top import sele_top
49 prop = { 'binary_path': 'haddock' }
50 sele_top(input_haddock_wf_data_zip='/path/to/myworkflowdata.zip',
51 output_evaluation_zip='/path/to/myevalfiles.zip',
52 properties=prop)
54 Info:
55 * wrapped_software:
56 * name: Haddock3
57 * version: 2025.5
58 * license: Apache-2.0
59 * ontology:
60 * name: EDAM
61 * schema: http://edamontology.org/EDAM.owl
62 """
64 def __init__(
65 self,
66 input_haddock_wf_data_zip: str,
67 output_selection_zip_path: str,
68 reference_pdb_path: Optional[str] = None,
69 output_haddock_wf_data_zip: Optional[str] = None,
70 haddock_config_path: Optional[str] = None,
71 properties: Optional[dict] = None,
72 **kwargs,
73 ) -> None:
74 properties = properties or {}
76 # Call parent class constructor
77 super().__init__(properties)
79 # Input/Output files
80 self.io_dict = {
81 "in": {"haddock_config_path": haddock_config_path},
82 "out": {
83 "output_haddock_wf_data_zip": output_haddock_wf_data_zip,
84 "output_selection_zip_path": output_selection_zip_path,
85 },
86 }
87 # Should not be copied inside container
88 self.input_haddock_wf_data_zip = input_haddock_wf_data_zip
90 # Properties specific for BB
91 self.haddock_step_name = "seletop"
92 self.output_cfg_path = properties.get("output_cfg_path", "haddock.cfg")
93 self.cfg = {k: v for k, v in properties.get("cfg", dict()).items()}
94 self.global_cfg = properties.get("global_cfg", dict(postprocess=False))
96 # Properties specific for BB
97 self.binary_path = properties.get("binary_path", "haddock3")
99 # Check the properties
100 self.check_properties(properties)
102 @launchlogger
103 def launch(self) -> int:
104 """Execute the :class:`SeleTop <biobb_haddock.haddock.sele_top>` object."""
105 # tmp_files = []
107 # Setup Biobb
108 if self.check_restart():
109 return 0
110 self.stage_files()
112 # Unzip workflow data to workflow_data_out
113 run_dir = unzip_workflow_data(
114 zip_file=self.input_haddock_wf_data_zip, out_log=self.out_log
115 )
117 workflow_dict = {"haddock_step_name": self.haddock_step_name}
118 workflow_dict.update(self.global_cfg)
120 # Create data dir
121 cfg_dir = fu.create_unique_dir()
122 self.output_cfg_path = create_cfg(
123 output_cfg_path=str(Path(cfg_dir).joinpath(self.output_cfg_path)),
124 workflow_dict=workflow_dict,
125 input_cfg_path=self.stage_io_dict["in"].get("haddock_config_path"),
126 cfg_properties_dict=self.cfg,
127 )
129 if self.container_path:
130 fu.log("Container execution enabled", self.out_log)
132 shutil.copy2(self.output_cfg_path, self.stage_io_dict.get("unique_dir", ""))
133 self.output_cfg_path = str(
134 Path(self.container_volume_path).joinpath(
135 Path(self.output_cfg_path).name
136 )
137 )
139 shutil.copytree(
140 run_dir,
141 str(
142 Path(self.stage_io_dict.get("unique_dir", "")).joinpath(
143 Path(run_dir).name
144 )
145 ),
146 )
147 run_dir = str(
148 Path(self.stage_io_dict.get("unique_dir", "")).joinpath(
149 Path(run_dir).name
150 )
151 )
153 self.cmd = [self.binary_path, self.output_cfg_path, "--extend-run", run_dir]
155 # Run Biobb block
156 self.run_biobb()
158 # Copy files to host
159 # self.copy_to_host()
161 # Copy output
162 haddock_output_list = [
163 str(path)
164 for path in Path(run_dir).iterdir()
165 if path.is_dir() and str(path).endswith(workflow_dict["haddock_step_name"])
166 ]
167 haddock_output_list.sort(reverse=True)
168 output_file_list = [
169 str(path)
170 for path in Path(haddock_output_list[0]).iterdir()
171 if path.is_file() and str(path.name) not in ["io.json", "params.cfg"]
172 ]
173 with open(haddock_output_list[0]+'/io.json') as json_file:
174 content = jsonpickle.decode(json_file.read())
175 output = content["output"]
176 for file in output:
177 rel_path = str(file.rel_path).split('/')
178 output_file_list.extend(list(Path(run_dir+'/'+rel_path[-2]).glob(rel_path[-1]+'*')))
179 fu.zip_list(
180 self.io_dict["out"]["output_selection_zip_path"],
181 output_file_list,
182 self.out_log,
183 )
185 # Create zip output
186 if self.io_dict["out"].get("output_haddock_wf_data_zip"):
187 fu.log(
188 f"Zipping {run_dir} to {str(Path(self.io_dict['out']['output_haddock_wf_data_zip']).with_suffix(''))} ",
189 self.out_log,
190 self.global_log,
191 )
192 shutil.make_archive(
193 str(
194 Path(self.io_dict["out"]["output_haddock_wf_data_zip"]).with_suffix(
195 ""
196 )
197 ),
198 "zip",
199 run_dir,
200 )
202 # Remove temporal files
203 self.tmp_files.extend([run_dir,
204 cfg_dir,
205 self.stage_io_dict.get("unique_dir")
206 ])
207 self.remove_tmp_files()
209 return self.return_code
212def sele_top(
213 input_haddock_wf_data_zip: str,
214 output_selection_zip_path: str,
215 output_haddock_wf_data_zip: Optional[str] = None,
216 haddock_config_path: Optional[str] = None,
217 properties: Optional[dict] = None,
218 **kwargs,
219) -> int:
220 """Create :class:`SeleTop <biobb_haddock.haddock.sele_top>` class and
221 execute the :meth:`launch() <biobb_haddock.haddock.sele_top.launch>` method."""
223 return SeleTop(
224 input_haddock_wf_data_zip=input_haddock_wf_data_zip,
225 output_selection_zip_path=output_selection_zip_path,
226 output_haddock_wf_data_zip=output_haddock_wf_data_zip,
227 addock_config_path=haddock_config_path,
228 properties=properties,
229 **kwargs,
230 ).launch()
233def main():
234 parser = argparse.ArgumentParser(
235 description="Wrapper of the haddock SeleTop module.",
236 formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999),
237 )
238 parser.add_argument(
239 "-c",
240 "--config",
241 required=False,
242 help="This file can be a YAML file, JSON file or JSON string",
243 )
245 # Specific args of each building block
246 required_args = parser.add_argument_group("required arguments")
247 required_args.add_argument("--input_haddock_wf_data_zip", required=True)
248 required_args.add_argument("--output_selection_zip_path", required=True)
249 parser.add_argument("--output_haddock_wf_data_zip", required=False)
250 parser.add_argument("--haddock_config_path", required=False)
252 args = parser.parse_args()
253 config = args.config if args.config else None
254 properties = settings.ConfReader(config=config).get_prop_dic()
256 # Specific call of each building block
257 sele_top(
258 input_haddock_wf_data_zip=args.input_haddock_wf_data_zip,
259 output_selection_zip_path=args.output_selection_zip_path,
260 reference_pdb_path=args.reference_pdb_path,
261 output_haddock_wf_data_zip=args.output_haddock_wf_data_zip,
262 haddock_config_path=args.haddock_config_path,
263 properties=properties,
264 )
267if __name__ == "__main__":
268 main()