Coverage for biobb_dna/curvesplus/biobb_canal.py: 73%
88 statements
« prev ^ index » next coverage.py v7.5.1, created at 2024-05-07 09:06 +0000
« 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 Canal class and the command line interface."""
4import os
5import shutil
6import zipfile
7import argparse
8from pathlib import Path
10from biobb_common.generic.biobb_object import BiobbObject
11from biobb_common.configuration import settings
12from biobb_common.tools import file_utils as fu
13from biobb_common.tools.file_utils import launchlogger
16class Canal(BiobbObject):
17 """
18 | biobb_dna Canal
19 | Wrapper for the Canal executable that is part of the Curves+ software suite.
21 Args:
22 input_cda_file (str): Input cda file, from Cur+ output. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_dna/master/biobb_dna/test/data/curvesplus/curves_output.cda>`_. Accepted formats: cda (edam:format_2330).
23 input_lis_file (str) (Optional): Input lis file, from Cur+ output. File type: input. Accepted formats: lis (edam:format_2330).
24 output_zip_path (str): zip filename for output files. File type: output. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_dna/master/biobb_dna/test/reference/curvesplus/canal_output.zip>`_. Accepted formats: zip (edam:format_3987).
25 properties (dic):
26 * **bases** (*str*) - (None) sequence of bases to be searched for in the I/P data (default is blank, meaning no specified sequence).
27 * **itst** (*int*) - (0) Iteration start index.
28 * **itnd** (*int*) - (0) Iteration end index.
29 * **itdel** (*int*) - (1) Iteration delimiter.
30 * **lev1** (*int*) - (0) Lower base level limit (i.e. base pairs) used for analysis.
31 * **lev2** (*int*) - (0) Upper base level limit used for analysis. If lev1 > 0 and lev2 = 0, lev2 is set to lev1 (i.e. analyze lev1 only). If lev1=lev2=0, lev1 is set to 1 and lev2 is set to the length of the oligmer (i.e. analyze all levels).
32 * **nastr** (*str*) - ('NA') character string used to indicate missing data in .ser files.
33 * **cormin** (*float*) - (0.6) minimal absolute value for printing linear correlation coefficients between pairs of analyzed variables.
34 * **series** (*str*) - (False) if True then output spatial or time series data. Only possible for the analysis of single structures or single trajectories.
35 * **histo** (*str*) - (False) if True then output histogram data.
36 * **corr** (*str*) - (False) if True than output linear correlation coefficients between all variables.
37 * **sequence** (*str*) - (Optional) sequence of the first strand of the corresponding DNA fragment, for each .cda file. If not given it will be parsed from .lis file.
38 * **binary_path** (*str*) - ('Canal') Path to Canal executable, otherwise the program wil look for Canal 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 Examples:
42 This is a use example of how to use the building block from Python::
44 from biobb_dna.curvesplus.biobb_canal import biobb_canal
45 prop = {
46 'series': '.t.',
47 'histo': '.t.',
48 'sequence': 'CGCGAATTCGCG'
49 }
50 biobb_canal(
51 input_cda_file='/path/to/curves/output.cda',
52 output_zip_path='/path/to/output.zip',
53 properties=prop)
54 Info:
55 * wrapped_software:
56 * name: Canal
57 * version: >=2.6
58 * license: BSD 3-Clause
59 * ontology:
60 * name: EDAM
61 * schema: http://edamontology.org/EDAM.owl
62 """
64 def __init__(self, input_cda_file, input_lis_file=None,
65 output_zip_path=None, properties=None, **kwargs) -> None:
66 properties = properties or {}
68 # Call parent class constructor
69 super().__init__(properties)
70 self.locals_var_dict = locals().copy()
72 # Input/Output files
73 self.io_dict = {
74 'in': {
75 'input_cda_file': input_cda_file,
76 'input_lis_file': input_lis_file,
77 },
78 'out': {
79 'output_zip_path': output_zip_path
80 }
81 }
83 # Properties specific for BB
84 self.bases = properties.get('bases', None)
85 self.nastr = properties.get('nastr', None)
86 self.cormin = properties.get('cormin', 0.6)
87 self.lev1 = properties.get('lev1', 0)
88 self.lev2 = properties.get('lev2', 0)
89 self.itst = properties.get('itst', 0)
90 self.itnd = properties.get('itnd', 0)
91 self.itdel = properties.get('itdel', 1)
92 self.series = ".t." if properties.get('series', False) else ".f."
93 self.histo = ".t." if properties.get('histo', False) else ".f."
94 self.corr = ".t." if properties.get('corr', False) else ".f."
95 self.sequence = properties.get('sequence', None)
96 self.binary_path = properties.get('binary_path', 'Canal')
97 self.properties = properties
99 # Check the properties
100 self.check_properties(properties)
101 self.check_arguments()
103 @launchlogger
104 def launch(self) -> int:
105 """Execute the :class:`Canal <biobb_dna.curvesplus.biobb_canal.Canal>` object."""
107 # Setup Biobb
108 if self.check_restart():
109 return 0
110 self.stage_files()
112 if self.sequence is None:
113 if self.io_dict['in']['input_lis_file'] is None:
114 raise RuntimeError(
115 "if no sequence is passed in the configuration, "
116 "you must at least specify `input_lis_file` "
117 "so sequence can be parsed from there")
118 lis_lines = Path(
119 self.io_dict['in']['input_lis_file']).read_text().splitlines()
120 for line in lis_lines:
121 if line.strip().startswith("Strand 1"):
122 self.sequence = line.split(" ")[-1]
123 fu.log(
124 f"using sequence {self.sequence} "
125 f"from {self.io_dict['in']['input_lis_file']}",
126 self.out_log)
128 # Creating temporary folder
129 self.tmp_folder = fu.create_unique_dir(prefix="canal_")
130 fu.log('Creating %s temporary folder' % self.tmp_folder, self.out_log)
132 # copy input files to temporary folder
133 shutil.copy(
134 self.io_dict['in']['input_cda_file'],
135 self.tmp_folder)
136 tmp_cda_path = Path(self.io_dict['in']['input_cda_file']).name
137 if self.io_dict['in']['input_lis_file'] is not None:
138 shutil.copy(
139 self.io_dict['in']['input_lis_file'],
140 self.tmp_folder)
142 # change directory to temporary folder
143 original_directory = os.getcwd()
144 os.chdir(self.tmp_folder)
146 # create intructions
147 instructions = [
148 f"{self.binary_path} <<! ",
149 "&inp",
150 " lis=canal_output,"]
151 if self.bases is not None:
152 # add topology file if needed
153 fu.log('Appending sequence of bases to be searched to command',
154 self.out_log, self.global_log)
155 instructions.append(f" seq={self.bases},")
156 if self.nastr is not None:
157 # add topology file if needed
158 fu.log('Adding null values string specification to command',
159 self.out_log, self.global_log)
160 instructions.append(f" nastr={self.nastr},")
162 instructions = instructions + [
163 f" cormin={self.cormin},",
164 f" lev1={self.lev1},lev2={self.lev2},",
165 f" itst={self.itst},itnd={self.itnd},itdel={self.itdel},",
166 f" histo={self.histo},",
167 f" series={self.series},",
168 f" corr={self.corr},",
169 "&end",
170 f"{tmp_cda_path} {self.sequence}",
171 "!"]
173 self.cmd = ["\n".join(instructions)]
174 fu.log('Creating command line with instructions and required arguments',
175 self.out_log, self.global_log)
177 # Run Biobb block
178 self.run_biobb()
180 # change back to original directory
181 os.chdir(original_directory)
183 # create zipfile and write output inside
184 zf = zipfile.ZipFile(
185 Path(self.io_dict["out"]["output_zip_path"]), "w")
186 for canal_outfile in Path(self.tmp_folder).glob("canal_output*"):
187 zf.write(
188 canal_outfile,
189 arcname=canal_outfile.name)
190 zf.close()
192 # Remove temporary file(s)
193 self.tmp_files.extend([
194 self.stage_io_dict.get("unique_dir"),
195 self.tmp_folder
196 ])
197 self.remove_tmp_files()
199 self.check_arguments(output_files_created=True, raise_exception=False)
201 return self.return_code
204def biobb_canal(
205 input_cda_file: str,
206 output_zip_path: str,
207 input_lis_file: str = None,
208 properties: dict = None,
209 **kwargs) -> int:
210 """Create :class:`Canal <biobb_dna.curvesplus.biobb_canal.Canal>` class and
211 execute the :meth:`launch() <biobb_dna.curvesplus.biobb_canal.Canal.launch>` method."""
213 return Canal(
214 input_cda_file=input_cda_file,
215 input_lis_file=input_lis_file,
216 output_zip_path=output_zip_path,
217 properties=properties, **kwargs).launch()
220def main():
221 """Command line execution of this building block. Please check the command line documentation."""
222 parser = argparse.ArgumentParser(description='Execute Canal from the Curves+ software suite.',
223 formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
224 parser.add_argument('--config', required=False, help='Configuration file')
226 required_args = parser.add_argument_group('required arguments')
227 required_args.add_argument('--input_cda_file', required=True,
228 help='cda input file from Curves+ output. Accepted formats: cda.')
229 required_args.add_argument('--output_zip_path', required=True,
230 help='Filename for .zip file with Canal output. Accepted formats: zip.')
231 parser.add_argument('--input_lis_file', required=False,
232 help='lis input file from Curves+ output. Accepted formats: lis.')
234 args = parser.parse_args()
235 args.config = args.config or "{}"
236 properties = settings.ConfReader(config=args.config).get_prop_dic()
238 biobb_canal(
239 input_cda_file=args.input_cda_file,
240 input_lis_file=args.input_lis_file,
241 output_zip_path=args.output_zip_path,
242 properties=properties)
245if __name__ == '__main__':
246 main()