Coverage for biobb_dna / curvesplus / biobb_canal.py: 82%

72 statements  

« prev     ^ index     » next       coverage.py v7.13.0, created at 2025-12-15 18:49 +0000

1#!/usr/bin/env python3 

2 

3"""Module containing the Canal class and the command line interface.""" 

4import os 

5import zipfile 

6from typing import Optional 

7from pathlib import Path 

8 

9from biobb_common.generic.biobb_object import BiobbObject 

10from biobb_common.tools import file_utils as fu 

11from biobb_common.tools.file_utils import launchlogger 

12 

13 

14class Canal(BiobbObject): 

15 """ 

16 | biobb_dna Canal 

17 | Wrapper for the Canal executable that is part of the Curves+ software suite. 

18 | The Canal program is used to analyze the curvature of DNA structures. 

19 

20 Args: 

21 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). 

22 input_lis_file (str) (Optional): Input lis file, from Cur+ output. File type: input. Accepted formats: lis (edam:format_2330). 

23 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). 

24 properties (dic): 

25 * **bases** (*str*) - (None) sequence of bases to be searched for in the I/P data (default is blank, meaning no specified sequence). 

26 * **itst** (*int*) - (0) Iteration start index. 

27 * **itnd** (*int*) - (0) Iteration end index. 

28 * **itdel** (*int*) - (1) Iteration delimiter. 

29 * **lev1** (*int*) - (0) Lower base level limit (i.e. base pairs) used for analysis. 

30 * **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). 

31 * **nastr** (*str*) - ('NA') character string used to indicate missing data in .ser files. 

32 * **cormin** (*float*) - (0.6) minimal absolute value for printing linear correlation coefficients between pairs of analyzed variables. 

33 * **series** (*bool*) - (False) if True then output spatial or time series data. Only possible for the analysis of single structures or single trajectories. 

34 * **histo** (*bool*) - (False) if True then output histogram data. 

35 * **corr** (*bool*) - (False) if True than output linear correlation coefficients between all variables. 

36 * **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. 

37 * **binary_path** (*str*) - ('Canal') Path to Canal executable, otherwise the program wil look for Canal executable in the binaries folder. 

38 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files. 

39 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist. 

40 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory. 

41 Examples: 

42 This is a use example of how to use the building block from Python:: 

43 

44 from biobb_dna.curvesplus.biobb_canal import biobb_canal 

45 prop = { 

46 'series': 'True', 

47 'histo': 'True', 

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 """ 

63 

64 def __init__(self, input_cda_file, input_lis_file=None, 

65 output_zip_path=None, properties=None, **kwargs) -> None: 

66 properties = properties or {} 

67 

68 # Call parent class constructor 

69 super().__init__(properties) 

70 self.locals_var_dict = locals().copy() 

71 

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 } 

82 

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 

98 

99 # Check the properties 

100 self.check_properties(properties) 

101 self.check_arguments() 

102 

103 @launchlogger 

104 def launch(self) -> int: 

105 """Execute the :class:`Canal <biobb_dna.curvesplus.biobb_canal.Canal>` object.""" 

106 

107 # Setup Biobb 

108 if self.check_restart(): 

109 return 0 

110 self.stage_files() 

111 

112 if self.sequence is None: 

113 if self.stage_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.stage_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.stage_io_dict['in']['input_lis_file']}", 

126 self.out_log) 

127 

128 # define temporary file name 

129 tmp_cda_path = Path(self.stage_io_dict['in']['input_cda_file']).name 

130 

131 # change directory to temporary folder 

132 original_directory = os.getcwd() 

133 os.chdir(self.stage_io_dict.get("unique_dir", "")) 

134 

135 # create intructions 

136 instructions = [ 

137 f"{self.binary_path} <<! ", 

138 "&inp", 

139 " lis=canal_output,"] 

140 if self.bases is not None: 

141 # add topology file if needed 

142 fu.log('Appending sequence of bases to be searched to command', 

143 self.out_log, self.global_log) 

144 instructions.append(f" seq={self.bases},") 

145 if self.nastr is not None: 

146 # add topology file if needed 

147 fu.log('Adding null values string specification to command', 

148 self.out_log, self.global_log) 

149 instructions.append(f" nastr={self.nastr},") 

150 

151 instructions = instructions + [ 

152 f" cormin={self.cormin},", 

153 f" lev1={self.lev1},lev2={self.lev2},", 

154 f" itst={self.itst},itnd={self.itnd},itdel={self.itdel},", 

155 f" histo={self.histo},", 

156 f" series={self.series},", 

157 f" corr={self.corr},", 

158 "&end", 

159 f"{tmp_cda_path} {self.sequence}", 

160 "!"] 

161 

162 self.cmd = ["\n".join(instructions)] 

163 fu.log('Creating command line with instructions and required arguments', 

164 self.out_log, self.global_log) 

165 

166 # Run Biobb block 

167 self.run_biobb() 

168 

169 # change back to original directory 

170 os.chdir(original_directory) 

171 

172 # create zipfile and write output inside 

173 zf = zipfile.ZipFile( 

174 Path(self.stage_io_dict["out"]["output_zip_path"]), "w") 

175 for canal_outfile in Path(self.stage_io_dict.get("unique_dir", "")).glob("canal_output*"): 

176 if canal_outfile.suffix not in (".zip"): 

177 zf.write( 

178 canal_outfile, 

179 arcname=canal_outfile.name) 

180 zf.close() 

181 

182 # Copy files to host 

183 self.copy_to_host() 

184 

185 # Remove temporary file(s) 

186 self.remove_tmp_files() 

187 

188 self.check_arguments(output_files_created=True, raise_exception=False) 

189 

190 return self.return_code 

191 

192 

193def biobb_canal( 

194 input_cda_file: str, 

195 output_zip_path: str, 

196 input_lis_file: Optional[str] = None, 

197 properties: Optional[dict] = None, 

198 **kwargs) -> int: 

199 """Create :class:`Canal <biobb_dna.curvesplus.biobb_canal.Canal>` class and 

200 execute the :meth:`launch() <biobb_dna.curvesplus.biobb_canal.Canal.launch>` method.""" 

201 return Canal(**dict(locals())).launch() 

202 

203 

204biobb_canal.__doc__ = Canal.__doc__ 

205main = Canal.get_main(biobb_canal, "Execute Canal from the Curves+ software suite.") 

206 

207 

208if __name__ == '__main__': 

209 main()