Coverage for biobb_analysis/ambertools/cpptraj_strip.py: 81%

1#!/usr/bin/env python3 

2 

3"""Module containing the Cpptraj Strip class and the command line interface.""" 

4import argparse 

5from pathlib import PurePath 

6from biobb_common.generic.biobb_object import BiobbObject 

7from biobb_common.configuration import settings 

8from biobb_common.tools import file_utils as fu 

9from biobb_common.tools.file_utils import launchlogger 

10from biobb_analysis.ambertools.common import get_default_value, check_top_path, check_traj_path, check_out_path, get_binary_path, get_in_parameters, get_out_parameters, copy_instructions_file_to_container, get_mask 

11 

12 

13class CpptrajStrip(BiobbObject): 

14 """ 

15 | biobb_analysis CpptrajStrip 

16 | Wrapper of the Ambertools Cpptraj module for stripping a defined set of atoms (mask) from a given cpptraj compatible trajectory. 

17 | Cpptraj (the successor to ptraj) is the main program in Ambertools for processing coordinate trajectories and data files. The parameter names and defaults are the same as the ones in the official `Cpptraj manual <https://amber-md.github.io/cpptraj/CPPTRAJ.xhtml>`_. 

18 

19 Args: 

20 input_top_path (str): Path to the input structure or topology file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/ambertools/cpptraj.parm.top>`_. Accepted formats: top (edam:format_3881), pdb (edam:format_1476), prmtop (edam:format_3881), parmtop (edam:format_3881), zip (edam:format_3987). 

21 input_traj_path (str): Path to the input trajectory to be processed. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/ambertools/cpptraj.traj.dcd>`_. Accepted formats: mdcrd (edam:format_3878), crd (edam:format_3878), cdf (edam:format_3650), netcdf (edam:format_3650), nc (edam:format_3650), restart (edam:format_3886), ncrestart (edam:format_3886), restartnc (edam:format_3886), dcd (edam:format_3878), charmm (edam:format_3887), cor (edam:format_2033), pdb (edam:format_1476), mol2 (edam:format_3816), trr (edam:format_3910), gro (edam:format_2033), binpos (edam:format_3885), xtc (edam:format_3875), cif (edam:format_1477), arc (edam:format_2333), sqm (edam:format_2033), sdf (edam:format_3814), conflib (edam:format_2033). 

22 output_cpptraj_path (str): Path to the output processed trajectory. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/ambertools/ref_cpptraj.strip.netcdf>`_. Accepted formats: mdcrd (edam:format_3878), crd (edam:format_3878), netcdf (edam:format_3650), nc (edam:format_3650), rst7 (edam:format_3886), ncrst (edam:format_2033), dcd (edam:format_3878), pdb (edam:format_1476), mol2 (edam:format_3816), binpos (edam:format_3885), trr (edam:format_3910), xtc (edam:format_3875), sqm (edam:format_2033). 

23 properties (dic - Python dictionary object containing the tool parameters, not input/output files): 

24 * **start** (*int*) - (1) [1~100000|1] Starting frame for slicing. 

25 * **end** (*int*) - (-1) [-1~100000|1] Ending frame for slicing. 

26 * **steps** (*int*) - (1) [1~100000|1] Step for slicing. 

27 * **mask** (*str*) - ("all-atoms") Mask definition. Values: c-alpha (All c-alpha atoms; protein only), backbone (Backbone atoms), all-atoms (All system atoms), heavy-atoms (System heavy atoms; not hydrogen), side-chain (All not backbone atoms), solute (All system atoms except solvent atoms), ions (All ion molecules), solvent (All solvent atoms), AnyAmberFromatMask (Amber atom selection syntax like `@*`). 

28 * **format** (*str*) - ("netcdf") Output trajectory format. Values: crd (AMBER trajectory format), cdf (Format used by netCDF software library for writing and reading chromatography-MS data files), netcdf (Format used by netCDF software library for writing and reading chromatography-MS data files), nc (Format used by netCDF software library for writing and reading chromatography-MS data files), restart (AMBER coordinate/restart file with 6 coordinates per line), ncrestart (AMBER coordinate/restart file with 6 coordinates per line), restartnc (AMBER coordinate/restart file with 6 coordinates per line), dcd (AMBER trajectory format), charmm (Format of CHARMM Residue Topology Files (RTF)), cor (Charmm COR), pdb (Protein Data Bank format), mol2 (Complete and portable representation of a SYBYL molecule), trr (Trajectory of a simulation experiment used by GROMACS), gro (GROMACS structure), binpos (Translation of the ASCII atom coordinate format to binary code), xtc (Portable binary format for trajectories produced by GROMACS package), cif (Entry format of PDB database in mmCIF format), arc (Tinker ARC), sqm (SQM Input), sdf (One of a family of chemical-data file formats developed by MDL Information Systems), conflib (LMOD Conflib). 

29 * **binary_path** (*str*) - ("cpptraj") Path to the cpptraj executable binary. 

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

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

32 * **container_path** (*str*) - (None) Container path definition. 

33 * **container_image** (*str*) - ('afandiadib/ambertools:serial') Container image definition. 

34 * **container_volume_path** (*str*) - ('/tmp') Container volume path definition. 

35 * **container_working_dir** (*str*) - (None) Container working directory definition. 

36 * **container_user_id** (*str*) - (None) Container user_id definition. 

37 * **container_shell_path** (*str*) - ('/bin/bash') Path to default shell inside the container. 

38 

39 Examples: 

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

41 

42 from biobb_analysis.ambertools.cpptraj_strip import cpptraj_strip 

43 prop = { 

44 'start': 1, 

45 'end': -1, 

46 'steps': 1, 

47 'mask': 'c-alpha', 

48 'format': 'netcdf' 

49 } 

50 cpptraj_strip(input_top_path='/path/to/myTopology.top', 

51 input_traj_path='/path/to/myTrajectory.dcd', 

52 output_cpptraj_path='/path/to/newTrajectory.netcdf', 

53 properties=prop) 

54 

55 Info: 

56 * wrapped_software: 

57 * name: Ambertools Cpptraj 

58 * version: >=20.0 

59 * license: GNU 

60 * ontology: 

61 * name: EDAM 

62 * schema: http://edamontology.org/EDAM.owl 

63 

64 """ 

65 

66 def __init__(self, input_top_path, input_traj_path, output_cpptraj_path, 

67 properties=None, **kwargs) -> None: 

68 properties = properties or {} 

69 

70 # Call parent class constructor 

71 super().__init__(properties) 

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

73 

74 # Input/Output files 

75 self.io_dict = { 

76 "in": {"input_top_path": input_top_path, "input_traj_path": input_traj_path}, 

77 "out": {"output_cpptraj_path": output_cpptraj_path} 

78 } 

79 

80 # Properties specific for BB 

81 self.instructions_file = get_default_value('instructions_file') 

82 self.start = properties.get('start', 1) 

83 self.end = properties.get('end', -1) 

84 self.steps = properties.get('steps', 1) 

85 self.mask = properties.get('mask', 'all-atoms') 

86 self.format = properties.get('format', 'netcdf') 

87 self.properties = properties 

88 self.binary_path = get_binary_path(properties, 'binary_path') 

89 

90 # Check the properties 

91 self.check_properties(properties) 

92 self.check_arguments() 

93 

94 def check_data_params(self, out_log, err_log): 

95 """ Checks all the input/output paths and parameters """ 

96 self.io_dict["in"]["input_top_path"], self.input_top_path_orig = check_top_path(self.io_dict["in"]["input_top_path"], out_log, self.__class__.__name__) 

97 self.io_dict["in"]["input_traj_path"] = check_traj_path(self.io_dict["in"]["input_traj_path"], out_log, self.__class__.__name__) 

98 self.io_dict["out"]["output_cpptraj_path"] = check_out_path(self.io_dict["out"]["output_cpptraj_path"], out_log, self.__class__.__name__) 

99 self.in_parameters = {'start': self.start, 'end': self.end, 'step': self.steps, 'mask': self.mask} 

100 self.out_parameters = {'format': self.format} 

101 

102 def create_instructions_file(self, container_io_dict, out_log, err_log): 

103 """Creates an input file using the properties file settings""" 

104 instructions_list = [] 

105 # different path if container execution or not 

106 if self.container_path: 

107 self.instructions_file = str(PurePath(self.container_volume_path).joinpath(self.instructions_file)) 

108 else: 

109 self.instructions_file = str(PurePath(fu.create_unique_dir()).joinpath(self.instructions_file)) 

110 fu.create_name(prefix=self.prefix, step=self.step, name=self.instructions_file) 

111 

112 # parm 

113 instructions_list.append('parm ' + container_io_dict["in"]["input_top_path"]) 

114 

115 # trajin 

116 in_parameters = self.in_parameters 

117 in_params = '' 

118 if in_parameters: 

119 in_params = get_in_parameters(self.in_parameters, out_log, 'strip') 

120 instructions_list.append('trajin ' + container_io_dict["in"]["input_traj_path"] + ' ' + in_params) 

121 

122 # mask 

123 mask = self.in_parameters.get('mask', '') 

124 if not mask or mask == 'None': 

125 fu.log('No mask provided, exiting', out_log, self.global_log) 

126 raise SystemExit('Mask parameter is mandatory') 

127 strip_mask = get_mask(mask, out_log) 

128 instructions_list.append('strip ' + strip_mask) 

129 

130 # trajout 

131 out_params = get_out_parameters(self.out_parameters, out_log) 

132 instructions_list.append('trajout ' + container_io_dict["out"]["output_cpptraj_path"] + ' ' + out_params) 

133 

134 # create .in file 

135 with open(self.instructions_file, 'w') as mdp: 

136 for line in instructions_list: 

137 mdp.write(line.strip() + '\n') 

138 

139 return self.instructions_file 

140 

141 @launchlogger 

142 def launch(self) -> int: 

143 """Execute the :class:`CpptrajStrip <ambertools.cpptraj_strip.CpptrajStrip>` ambertools.cpptraj_strip.CpptrajStrip object.""" 

144 

145 # check input/output paths and parameters 

146 self.check_data_params(self.out_log, self.err_log) 

147 

148 # Setup Biobb 

149 if self.check_restart(): 

150 return 0 

151 self.stage_files() 

152 

153 # create instructions file 

154 self.create_instructions_file(self.stage_io_dict, self.out_log, self.err_log) 

155 

156 # if container execution, copy intructions file to container 

157 if self.container_path: 

158 copy_instructions_file_to_container(self.instructions_file, self.stage_io_dict['unique_dir']) 

159 

160 # create cmd and launch execution 

161 self.cmd = [self.binary_path, '-i', self.instructions_file] 

162 

163 # Run Biobb block 

164 self.run_biobb() 

165 

166 # Copy files to host 

167 self.copy_to_host() 

168 

169 # remove temporary folder(s) 

170 self.tmp_files.extend([ 

171 self.stage_io_dict.get("unique_dir"), 

172 PurePath(self.instructions_file).parent 

173 ]) 

174 self.remove_tmp_files() 

175 

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

177 

178 return self.return_code 

179 

180 

181def cpptraj_strip(input_top_path: str, input_traj_path: str, output_cpptraj_path: str, properties: dict = None, **kwargs) -> int: 

182 """Execute the :class:`CpptrajStrip <ambertools.cpptraj_strip.CpptrajStrip>` class and 

183 execute the :meth:`launch() <ambertools.cpptraj_strip.CpptrajStrip.launch>` method.""" 

184 

185 return CpptrajStrip(input_top_path=input_top_path, 

186 input_traj_path=input_traj_path, 

187 output_cpptraj_path=output_cpptraj_path, 

188 properties=properties, **kwargs).launch() 

189 

190 

191def main(): 

192 """Command line execution of this building block. Please check the command line documentation.""" 

193 parser = argparse.ArgumentParser(description="Strips a defined set of atoms (mask) from a given cpptraj compatible trajectory.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999)) 

194 parser.add_argument('--config', required=False, help='Configuration file') 

195 

196 # Specific args of each building block 

197 required_args = parser.add_argument_group('required arguments') 

198 required_args.add_argument('--input_top_path', required=True, help='Path to the input structure or topology file. Accepted formats: top, pdb, prmtop, parmtop, zip.') 

199 required_args.add_argument('--input_traj_path', required=True, help='Path to the input trajectory to be processed. Accepted formats: crd, cdf, netcdf, restart, ncrestart, restartnc, dcd, charmm, cor, pdb, mol2, trr, gro, binpos, xtc, cif, arc, sqm, sdf, conflib.') 

200 required_args.add_argument('--output_cpptraj_path', required=True, help='Path to the output processed trajectory.') 

201 

202 args = parser.parse_args() 

203 args.config = args.config or "{}" 

204 properties = settings.ConfReader(config=args.config).get_prop_dic() 

205 

206 # Specific call of each building block 

207 cpptraj_strip(input_top_path=args.input_top_path, 

208 input_traj_path=args.input_traj_path, 

209 output_cpptraj_path=args.output_cpptraj_path, 

210 properties=properties) 

211 

212 

213if __name__ == '__main__': 

214 main()