Coverage for biobb_dna / curvesplus / biobb_canion.py: 92%
72 statements
« prev ^ index » next coverage.py v7.14.0, created at 2026-05-22 14:18 +0000
1#!/usr/bin/env python3
3"""Module containing the Canion class and the command line interface."""
4import os
5import zipfile
6from typing import Optional
7from pathlib import Path
8from biobb_common.generic.biobb_object import BiobbObject
9from biobb_common.tools import file_utils as fu
10from biobb_common.tools.file_utils import launchlogger
13class Canion(BiobbObject):
14 """
15 | biobb_dna Canion
16 | Wrapper for the Canion executable that is part of the Curves+ software suite.
17 | Analyzes the trajectory of ions around a DNA molecule.
19 Args:
20 input_cdi_path (str): Trajectory input file. File type: input. `Sample file <https://github.com/bioexcel/biobb_dna/releases/download/assets/THGA_K.cdi>`_. Accepted formats: cdi (edam:format_2330).
21 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).
22 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).
23 output_zip_path (str): 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).
24 properties (dict):
25 * **bases** (*str*) - (None) Sequence of bases to be analyzed (default is blank, meaning no specified sequence).
26 * **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.
27 * **dlow** (*float*) - (0) Select starting segment of the oglimer to analyze. If both dhig and dlow are 0, entire oglimer is analyzed.
28 * **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.
29 * **rlow** (*float*) - (0) Minimal distances from the helical axis taken into account in the analysis.
30 * **rhig** (*float*) - (0) Maximal distances from the helical axis taken into account in the analysis.
31 * **alow** (*float*) - (0) Minimal angle range to analyze.
32 * **ahig** (*float*) - (360) Maximal angle range to analyze.
33 * **itst** (*int*) - (0) Number of first snapshot to be analyzed.
34 * **itnd** (*int*) - (0) Number of last snapshot to be analyzed.
35 * **itdel** (*int*) - (1) Spacing between analyzed snapshots.
36 * **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.
37 * **circ** (*bool*) - (False) If set to True, minicircles are analyzed.
38 * **binary_path** (*str*) - (Canion) Path to Canion executable, otherwise the program wil look for Canion executable in the binaries folder.
39 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
40 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
41 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory.
42 * **container_path** (*str*) - (None) Path to the binary executable of your container.
43 * **container_image** (*str*) - ("cmip/cmip:latest") Container Image identifier.
44 * **container_volume_path** (*str*) - ("/data") Path to an internal directory in the container.
45 * **container_working_dir** (*str*) - (None) Path to the internal CWD in the container.
46 * **container_user_id** (*str*) - (None) User number id to be mapped inside the container.
47 * **container_shell_path** (*str*) - ("/bin/bash") Path to the binary executable of the container shell.
48 Examples:
49 This is a use example of how to use the building block from Python::
51 from biobb_dna.curvesplus.biobb_canion import biobb_canion
52 prop = {
53 'type': 'K+',
54 'bases': 'G'
55 }
56 biobb_canion(
57 input_cdi_path='/path/to/input.cdi',
58 input_afr_path='/path/to/input.afr',
59 input_avg_struc_path='/path/to/input.pdb',
60 output_zip_path='/path/to/output.zip',
61 properties=prop)
62 Info:
63 * wrapped_software:
64 * name: Canion
65 * version: >=2.6
66 * license: BSD 3-Clause
67 * ontology:
68 * name: EDAM
69 * schema: http://edamontology.org/EDAM.owl
70 """
72 def __init__(
73 self, input_cdi_path, input_afr_path, input_avg_struc_path,
74 output_zip_path=None, properties=None, **kwargs) -> None:
75 properties = properties or {}
77 # Call parent class constructor
78 super().__init__(properties)
79 self.locals_var_dict = locals().copy()
81 # Input/Output files
82 self.io_dict = {
83 'in': {
84 'input_cdi_path': input_cdi_path,
85 'input_afr_path': input_afr_path,
86 'input_avg_struc_path': input_avg_struc_path,
87 },
88 'out': {
89 'output_zip_path': output_zip_path
90 }
91 }
93 # Properties specific for BB
94 self.binary_path = properties.get('binary_path', 'Canion')
95 self.bases = properties.get('bases', None)
96 self.type = properties.get('type', '*')
97 self.dlow = properties.get('dlow', 0)
98 self.dhig = properties.get('dhig', 0)
99 self.rlow = properties.get('rlow', 0)
100 self.rhig = properties.get('rhig', 0)
101 self.alow = properties.get('alow', 0)
102 self.ahig = properties.get('ahig', 360)
103 self.itst = properties.get('itst', 0)
104 self.itnd = properties.get('itnd', 0)
105 self.itdel = properties.get('itdel', 1)
106 self.rmsf = ".t." if properties.get('rmsf', False) else ".f."
107 self.circ = ".t." if properties.get('circ', False) else ".f."
108 self.properties = properties
110 # Check the properties
111 self.check_properties(properties)
112 self.check_arguments()
114 @launchlogger
115 def launch(self) -> int:
116 """Execute the :class:`Canion <biobb_dna.curvesplus.biobb_canion.Canion>` object."""
118 # Setup Biobb
119 if self.check_restart():
120 return 0
121 self.stage_files()
123 ion_type_options = [
124 'Na+',
125 'K',
126 'K+',
127 'Cl',
128 'Cl-',
129 'CL',
130 'P',
131 'C1*',
132 'NH1',
133 'NH2',
134 'NZ',
135 '1',
136 '-1',
137 '0',
138 '*'
139 ]
140 if self.type not in ion_type_options:
141 raise ValueError(("Invalid value for property type! "
142 f"Option include: {ion_type_options}"))
144 # define temporary file names
145 input_cdi_file = Path(self.stage_io_dict['in']['input_cdi_path']).name
146 input_afr_file = Path(self.stage_io_dict['in']['input_afr_path']).name
147 input_avg_struc = Path(self.stage_io_dict['in']['input_avg_struc_path']).name
149 # change directory to temporary folder
150 original_directory = os.getcwd()
152 if self.container_path:
153 os.chdir(self.container_working_dir)
154 else:
155 os.chdir(self.stage_io_dict.get("unique_dir", ""))
157 # create intructions
158 instructions = [
159 f"{self.binary_path} <<! ",
160 "&inp",
161 " lis=canion_output,",
162 f" dat={input_cdi_file[:-4]},",
163 f" axfrm={input_afr_file[:-4]},",
164 f" solute={input_avg_struc[:-4]},",
165 f" type={self.type},",
166 f" dlow={self.dlow},",
167 f" dhig={self.dhig},",
168 f" rlow={self.rlow},",
169 f" rhig={self.rhig},",
170 f" alow={self.alow},",
171 f" ahig={self.ahig},",
172 f" itst={self.itst},",
173 f" itnd={self.itnd},",
174 f" itdel={self.itdel},",
175 f" rmsf={self.rmsf},",
176 f" circ={self.circ},"]
177 if self.bases is not None:
178 # add topology file if needed
179 fu.log('Appending sequence of bases to be searched to command',
180 self.out_log, self.global_log)
181 instructions.append(f" seq={self.bases},")
182 instructions.append("&end")
183 instructions.append("!")
184 self.cmd = ["\n".join(instructions)]
186 fu.log('Creating command line with instructions and required arguments',
187 self.out_log, self.global_log)
188 # Run Biobb block
189 self.run_biobb()
191 # change back to original directory
192 os.chdir(original_directory)
194 workdir = self.stage_io_dict.get("unique_dir", "")
195 zip_host_path = Path(workdir) / Path(self.io_dict["out"]["output_zip_path"]).name
197 # create zipfile and write output inside
198 with zipfile.ZipFile(zip_host_path, "w") as zf:
199 for curves_outfile in Path(workdir).glob("canion_output*"):
200 fu.log(f"Adding {curves_outfile} to zip file", self.out_log, self.global_log)
201 if curves_outfile.suffix != ".zip":
202 zf.write(
203 curves_outfile,
204 arcname=curves_outfile.name)
206 # Copy files to host
207 self.copy_to_host()
209 # Remove temporary file(s)
210 self.remove_tmp_files()
212 self.check_arguments(output_files_created=True, raise_exception=False)
214 return self.return_code
217def biobb_canion(
218 input_cdi_path: str, input_afr_path: str, input_avg_struc_path: str,
219 output_zip_path: Optional[str] = None, properties: Optional[dict] = None, **kwargs) -> int:
220 """Create :class:`Canion <biobb_dna.curvesplus.biobb_canion.Canion>` class and
221 execute the :meth:`launch() <biobb_dna.curvesplus.biobb_canion.Canion.launch>` method."""
222 return Canion(**dict(locals())).launch()
225biobb_canion.__doc__ = Canion.__doc__
226main = Canion.get_main(biobb_canion, "Execute Canion form the Curves+ software suite.")
228if __name__ == '__main__':
229 main()