Coverage for biobb_dna / curvesplus / biobb_canion.py: 93%

1#!/usr/bin/env python3 

2 

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 

11 

12 

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. 

18 

19 Args: 

20 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). 

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 Examples: 

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

44 

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 """ 

65 

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 {} 

70 

71 # Call parent class constructor 

72 super().__init__(properties) 

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

74 

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 } 

86 

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', 0) 

98 self.itnd = properties.get('itnd', 0) 

99 self.itdel = properties.get('itdel', 1) 

100 self.rmsf = ".t." if properties.get('rmsf', False) else ".f." 

101 self.circ = ".t." if properties.get('circ', False) else ".f." 

102 self.properties = properties 

103 

104 # Check the properties 

105 self.check_properties(properties) 

106 self.check_arguments() 

107 

108 @launchlogger 

109 def launch(self) -> int: 

110 """Execute the :class:`Canion <biobb_dna.curvesplus.biobb_canion.Canion>` object.""" 

111 

112 # Setup Biobb 

113 if self.check_restart(): 

114 return 0 

115 self.stage_files() 

116 

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}")) 

137 

138 # define temporary file names 

139 input_cdi_file = Path(self.stage_io_dict['in']['input_cdi_path']).name 

140 input_afr_file = Path(self.stage_io_dict['in']['input_afr_path']).name 

141 input_avg_struc = Path(self.stage_io_dict['in']['input_avg_struc_path']).name 

142 

143 # change directory to temporary folder 

144 original_directory = os.getcwd() 

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

146 

147 # create intructions 

148 instructions = [ 

149 f"{self.binary_path} <<! ", 

150 "&inp", 

151 " lis=canion_output,", 

152 f" dat={input_cdi_file[:-4]},", 

153 f" axfrm={input_afr_file[:-4]},", 

154 f" solute={input_avg_struc[:-4]},", 

155 f" type={self.type},", 

156 f" dlow={self.dlow},", 

157 f" dhig={self.dhig},", 

158 f" rlow={self.rlow},", 

159 f" rhig={self.rhig},", 

160 f" alow={self.alow},", 

161 f" ahig={self.ahig},", 

162 f" itst={self.itst},", 

163 f" itnd={self.itnd},", 

164 f" itdel={self.itdel},", 

165 f" rmsf={self.rmsf},", 

166 f" circ={self.circ},"] 

167 if self.bases is not None: 

168 # add topology file if needed 

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

170 self.out_log, self.global_log) 

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

172 instructions.append("&end") 

173 instructions.append("!") 

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

175 

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

177 self.out_log, self.global_log) 

178 # Run Biobb block 

179 self.run_biobb() 

180 

181 # change back to original directory 

182 os.chdir(original_directory) 

183 

184 # create zipfile and write output inside 

185 zf = zipfile.ZipFile( 

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

187 "w") 

188 for curves_outfile in Path(self.stage_io_dict.get("unique_dir", "")).glob("canion_output*"): 

189 if curves_outfile.suffix not in (".zip"): 

190 zf.write(curves_outfile, arcname=curves_outfile.name) 

191 zf.close() 

192 

193 # Copy files to host 

194 self.copy_to_host() 

195 

196 # Remove temporary file(s) 

197 self.remove_tmp_files() 

198 

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

200 

201 return self.return_code 

202 

203 

204def biobb_canion( 

205 input_cdi_path: str, input_afr_path: str, input_avg_struc_path: str, 

206 output_zip_path: Optional[str] = None, properties: Optional[dict] = None, **kwargs) -> int: 

207 """Create :class:`Canion <biobb_dna.curvesplus.biobb_canion.Canion>` class and 

208 execute the :meth:`launch() <biobb_dna.curvesplus.biobb_canion.Canion.launch>` method.""" 

209 return Canion(**dict(locals())).launch() 

210 

211 

212biobb_canion.__doc__ = Canion.__doc__ 

213main = Canion.get_main(biobb_canion, "Execute Canion form the Curves+ software suite.") 

214 

215if __name__ == '__main__': 

216 main()