Coverage for biobb_dna/curvesplus/biobb_canion.py: 81%
85 statements
« prev ^ index » next coverage.py v7.5.1, created at 2024-05-07 09:06 +0000
1#!/usr/bin/env python3
3"""Module containing the Canion class and the command line interface."""
4import os
5import zipfile
6import argparse
7import shutil
8from pathlib import Path
9from biobb_common.generic.biobb_object import BiobbObject
10from biobb_common.configuration import settings
11from biobb_common.tools import file_utils as fu
12from biobb_common.tools.file_utils import launchlogger
15class Canion(BiobbObject):
16 """
17 | biobb_dna Canion
18 | Wrapper for the Canion executable that is part of the Curves+ software suite.
20 Args:
21 input_cdi_path (str): Trajectory input file. File type: input. `Sample file <https://mmb.irbbarcelona.org/biobb-dev/biobb-api/public/samples/THGA_K.cdi>`_. Accepted formats: cdi (edam:format_2330).
22 input_afr_path (str): Helical axis frames corresponding to the input conformation to be analyzed. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_dna/master/biobb_dna/test/data/curvesplus/THGA.afr>`_. Accepted formats: afr (edam:format_2330).
23 input_avg_struc_path (str): Average DNA conformation. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_dna/master/biobb_dna/test/data/curvesplus/THGA_avg.pdb>`_. Accepted formats: pdb (edam:format_1476).
24 output_zip_path (str) (Optional): Filename for .zip files containing Canion output files. File type: output. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_dna/master/biobb_dna/test/reference/curvesplus/canion_output.zip>`_. Accepted formats: zip (edam:format_3987).
25 properties (dict):
26 * **bases** (*str*) - (None) Sequence of bases to be analyzed (default is blank, meaning no specified sequence).
27 * **type** (*str*) - ('*') Ions (or atoms) to be analyzed. Options are 'Na+', 'K', 'K+', 'Cl', 'Cl-', 'CL', 'P', 'C1*', 'NH1', 'NH2', 'NZ', '1' for all cations, '-1' for all anions, '0' for neutral species or '*' for all available data.
28 * **dlow** (*float*) - (0) Select starting segment of the oglimer to analyze. If both dhig and dlow are 0, entire oglimer is analyzed.
29 * **dhig** (*float*) - (0) Select ending segment of the oglimer to analyze, being the maximum value the total number of base pairs in the oligomer. If both dhig and dlow are 0, entire oglimer is analyzed.
30 * **rlow** (*float*) - (0) Minimal distances from the helical axis taken into account in the analysis.
31 * **rhig** (*float*) - (0) Maximal distances from the helical axis taken into account in the analysis.
32 * **alow** (*float*) - (0) Minimal angle range to analyze.
33 * **ahig** (*float*) - (360) Maximal angle range to analyze.
34 * **itst** (*int*) - (None) Number of first snapshot to be analyzed.
35 * **itnd** (*int*) - (None) Number of last snapshot to be analyzed.
36 * **itdel** (*int*) - (None) Spacing between analyzed snapshots.
37 * **rmsf** (*bool*) - (False) If set to True uses the combination of the helical ion parameters and an average helical axis to map the ions into Cartesian space and then calculates their average position (pdb output) and their root mean square fluctuation values (rmsf output). A single pass rmsf algorithm to make this calculation possible with a single read of the trajectory file. This option is generally used for solute atoms and not for solvent molecules or ions.
38 * **circ** (*bool*) - (False) If set to True, minicircles are analyzed.
39 * **binary_path** (*str*) - (Canion) Path to Canion executable, otherwise the program wil look for Canion executable in the binaries folder.
40 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
41 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
42 Examples:
43 This is a use example of how to use the building block from Python::
45 from biobb_dna.curvesplus.biobb_canion import biobb_canion
46 prop = {
47 'type': 'K+',
48 'bases': 'G'
49 }
50 biobb_canion(
51 input_cdi_path='/path/to/input.cdi',
52 input_afr_path='/path/to/input.afr',
53 input_avg_struc_path='/path/to/input.pdb',
54 output_zip_path='/path/to/output.zip',
55 properties=prop)
56 Info:
57 * wrapped_software:
58 * name: Canion
59 * version: >=2.6
60 * license: BSD 3-Clause
61 * ontology:
62 * name: EDAM
63 * schema: http://edamontology.org/EDAM.owl
64 """
66 def __init__(
67 self, input_cdi_path, input_afr_path, input_avg_struc_path,
68 output_zip_path=None, properties=None, **kwargs) -> None:
69 properties = properties or {}
71 # Call parent class constructor
72 super().__init__(properties)
73 self.locals_var_dict = locals().copy()
75 # Input/Output files
76 self.io_dict = {
77 'in': {
78 'input_cdi_path': input_cdi_path,
79 'input_afr_path': input_afr_path,
80 'input_avg_struc_path': input_avg_struc_path,
81 },
82 'out': {
83 'output_zip_path': output_zip_path
84 }
85 }
87 # Properties specific for BB
88 self.binary_path = properties.get('binary_path', 'Canion')
89 self.bases = properties.get('bases', None)
90 self.type = properties.get('type', '*')
91 self.dlow = properties.get('dlow', 0)
92 self.dhig = properties.get('dhig', 0)
93 self.rlow = properties.get('rlow', 0)
94 self.rhig = properties.get('rhig', 0)
95 self.alow = properties.get('alow', 0)
96 self.ahig = properties.get('ahig', 360)
97 self.itst = properties.get('itst', None)
98 self.itnd = properties.get('itnd', None)
99 self.itdel = properties.get('itdel', None)
100 self.rmsf = properties.get('rmsf', '.f.')
101 self.circ = properties.get('circ', '.f.')
102 self.properties = properties
104 # Check the properties
105 self.check_properties(properties)
106 self.check_arguments()
108 @launchlogger
109 def launch(self) -> int:
110 """Execute the :class:`Canion <biobb_dna.curvesplus.biobb_canion.Canion>` object."""
112 # Setup Biobb
113 if self.check_restart():
114 return 0
115 self.stage_files()
117 ion_type_options = [
118 'Na+',
119 'K',
120 'K+',
121 'Cl',
122 'Cl-',
123 'CL',
124 'P',
125 'C1*',
126 'NH1',
127 'NH2',
128 'NZ',
129 '1',
130 '-1',
131 '0',
132 '*'
133 ]
134 if self.type not in ion_type_options:
135 raise ValueError(("Invalid value for property type! "
136 f"Option include: {ion_type_options}"))
138 # Creating temporary folder
139 self.tmp_folder = fu.create_unique_dir(prefix="canion_")
140 fu.log('Creating %s temporary folder' % self.tmp_folder, self.out_log)
142 # copy input files to temporary folder
143 shutil.copy(self.io_dict['in']['input_cdi_path'], self.tmp_folder)
144 shutil.copy(self.io_dict['in']['input_afr_path'], self.tmp_folder)
145 shutil.copy(
146 self.io_dict['in']['input_avg_struc_path'], self.tmp_folder)
147 input_cdi_file = Path(self.io_dict['in']['input_cdi_path']).name
148 input_afr_file = Path(self.io_dict['in']['input_afr_path']).name
149 input_avg_struc = Path(self.io_dict['in']['input_avg_struc_path']).name
151 # change directory to temporary folder
152 original_directory = os.getcwd()
153 os.chdir(self.tmp_folder)
155 # create intructions
156 instructions = [
157 f"{self.binary_path} <<! ",
158 "&inp",
159 " lis=canion_output,",
160 f" dat={input_cdi_file[:-4]},",
161 f" axfrm={input_afr_file[:-4]},",
162 f" solute={input_avg_struc[:-4]},",
163 f" type={self.type},",
164 f" dlow={self.dlow},",
165 f" dhig={self.dhig},",
166 f" rlow={self.rlow},",
167 f" rhig={self.rhig},",
168 f" alow={self.alow},",
169 f" ahig={self.ahig},"]
170 if self.bases is not None:
171 # add topology file if needed
172 fu.log('Appending sequence of bases to be searched to command',
173 self.out_log, self.global_log)
174 instructions.append(f" seq={self.bases},")
175 instructions.append("&end")
176 instructions.append("!")
177 self.cmd = ["\n".join(instructions)]
179 fu.log('Creating command line with instructions and required arguments',
180 self.out_log, self.global_log)
181 # Run Biobb block
182 self.run_biobb()
184 # change back to original directory
185 os.chdir(original_directory)
187 # create zipfile and write output inside
188 zf = zipfile.ZipFile(
189 Path(self.io_dict["out"]["output_zip_path"]),
190 "w")
191 for curves_outfile in Path(self.tmp_folder).glob("canion_output*"):
192 zf.write(curves_outfile, arcname=curves_outfile.name)
193 zf.close()
195 # Remove temporary file(s)
196 self.tmp_files.extend([
197 self.stage_io_dict.get("unique_dir"),
198 self.tmp_folder
199 ])
200 self.remove_tmp_files()
202 self.check_arguments(output_files_created=True, raise_exception=False)
204 return self.return_code
207def biobb_canion(
208 input_cdi_path: str, input_afr_path: str, input_avg_struc_path: str,
209 output_zip_path: str = None, properties: dict = None, **kwargs) -> int:
210 """Create :class:`Canion <biobb_dna.curvesplus.biobb_canion.Canion>` class and
211 execute the :meth:`launch() <biobb_dna.curvesplus.biobb_canion.Canion.launch>` method."""
213 return Canion(
214 input_cdi_path=input_cdi_path,
215 input_afr_path=input_afr_path,
216 input_avg_struc_path=input_avg_struc_path,
217 output_zip_path=output_zip_path,
218 properties=properties, **kwargs).launch()
221def main():
222 """Command line execution of this building block. Please check the command line documentation."""
223 parser = argparse.ArgumentParser(description='Execute Canion form the Curves+ software suite.',
224 formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
225 parser.add_argument('--config', required=False, help='Configuration file')
227 required_args = parser.add_argument_group('required arguments')
228 required_args.add_argument('--input_cdi_path', required=True,
229 help='Ion position data file. Accepted formats: cdi.')
230 required_args.add_argument('--input_afr_path', required=True,
231 help='Helical axis frames data. Accepted formats: afr.')
232 required_args.add_argument('--input_avg_struc_path', required=True,
233 help='Average DNA conformation fike file. Accepted formats: pdb.')
234 parser.add_argument('--output_zip_path', required=False,
235 help='Filename to give to output files. Accepted formats: zip.')
237 args = parser.parse_args()
238 args.config = args.config or "{}"
239 properties = settings.ConfReader(config=args.config).get_prop_dic()
241 biobb_canion(
242 input_cdi_path=args.input_cdi_path,
243 input_afr_path=args.input_afr_path,
244 input_avg_struc_path=args.input_avg_struc_path,
245 output_zip_path=args.output_zip_path,
246 properties=properties)
249if __name__ == '__main__':
250 main()