Coverage for biobb_analysis/ambertools/cpptraj_dry.py: 83%

1#!/usr/bin/env python3 

2 

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

4import argparse 

5from typing import Optional 

6from pathlib import PurePath 

7from biobb_common.generic.biobb_object import BiobbObject 

8from biobb_common.configuration import settings 

9from biobb_common.tools import file_utils as fu 

10from biobb_common.tools.file_utils import launchlogger 

11from biobb_analysis.ambertools.common import get_default_value, check_top_path, check_traj_path, check_out_path, get_binary_path, get_in_parameters, get_mask, get_negative_mask, copy_instructions_file_to_container, get_out_parameters 

12 

13 

14class CpptrajDry(BiobbObject): 

15 """ 

16 | biobb_analysis CpptrajDry 

17 | Wrapper of the Ambertools Cpptraj module for dehydrating a given cpptraj compatible trajectory stripping out solvent molecules and ions. 

18 | 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>`_. 

19 

20 Args: 

21 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). 

22 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). 

23 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.dry.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). 

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

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

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

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

28 * **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 `@*`). 

29 * **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). 

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

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

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

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

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

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

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

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

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

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

40 

41 Examples: 

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

43 

44 from biobb_analysis.ambertools.cpptraj_dry import cpptraj_dry 

45 prop = { 

46 'start': 1, 

47 'end': -1, 

48 'steps': 1, 

49 'mask': 'c-alpha', 

50 'format': 'netcdf' 

51 } 

52 cpptraj_dry(input_top_path='/path/to/myTopology.top', 

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

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

55 properties=prop) 

56 

57 Info: 

58 * wrapped_software: 

59 * name: Ambertools Cpptraj 

60 * version: >=20.0 

61 * license: GNU 

62 * ontology: 

63 * name: EDAM 

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

65 

66 """ 

67 

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

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

70 properties = properties or {} 

71 

72 # Call parent class constructor 

73 super().__init__(properties) 

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

75 

76 # Input/Output files 

77 self.io_dict = { 

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

79 "out": {"output_cpptraj_path": output_cpptraj_path} 

80 } 

81 

82 # Properties specific for BB 

83 self.instructions_file = get_default_value('instructions_file') 

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

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

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

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

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

89 self.properties = properties 

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

91 

92 # Check the properties 

93 self.check_properties(properties) 

94 self.check_arguments() 

95 

96 def check_data_params(self, out_log, err_log): 

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

98 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__) 

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

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

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

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

103 

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

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

106 instructions_list = [] 

107 # different path if container execution or not 

108 if self.container_path: 

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

110 else: 

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

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

113 

114 # parm 

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

116 

117 # trajin 

118 in_params = get_in_parameters(self.in_parameters, out_log) 

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

120 

121 # dry 

122 mask_dry1 = get_negative_mask('solute', out_log) 

123 instructions_list.append('strip ' + mask_dry1) 

124 mask_dry2 = get_mask('heavy-atoms', out_log) 

125 instructions_list.append('strip ' + mask_dry2) 

126 

127 # mask 

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

129 if mask: 

130 strip_mask = get_negative_mask(mask, out_log) 

131 instructions_list.append('strip ' + strip_mask) 

132 

133 # trajout 

134 out_params = get_out_parameters(self.out_parameters, out_log) 

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

136 

137 # create .in file 

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

139 for line in instructions_list: 

140 mdp.write(line.strip() + '\n') 

141 

142 return self.instructions_file 

143 

144 @launchlogger 

145 def launch(self) -> int: 

146 """Execute the :class:`CpptrajDry <ambertools.cpptraj_dry.CpptrajDry>` ambertools.cpptraj_dry.CpptrajDry object.""" 

147 

148 # check input/output paths and parameters 

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

150 

151 # Setup Biobb 

152 if self.check_restart(): 

153 return 0 

154 self.stage_files() 

155 

156 # create instructions file 

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

158 

159 # if container execution, copy intructions file to container 

160 if self.container_path: 

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

162 

163 # create cmd and launch execution 

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

165 

166 # Run Biobb block 

167 self.run_biobb() 

168 

169 # Copy files to host 

170 self.copy_to_host() 

171 

172 # remove temporary folder(s) 

173 self.tmp_files.extend([ 

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

175 str(PurePath(self.instructions_file).parent) 

176 ]) 

177 self.remove_tmp_files() 

178 

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

180 

181 return self.return_code 

182 

183 

184def cpptraj_dry(input_top_path: str, input_traj_path: str, output_cpptraj_path: str, properties: Optional[dict] = None, **kwargs) -> int: 

185 """Execute the :class:`CpptrajDry <ambertools.cpptraj_dry.CpptrajDry>` class and 

186 execute the :meth:`launch() <ambertools.cpptraj_dry.CpptrajDry.launch>` method.""" 

187 

188 return CpptrajDry(input_top_path=input_top_path, 

189 input_traj_path=input_traj_path, 

190 output_cpptraj_path=output_cpptraj_path, 

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

192 

193 

194def main(): 

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

196 parser = argparse.ArgumentParser(description="Dehydrates a given cpptraj compatible trajectory stripping out solvent molecules and ions.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999)) 

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

198 

199 # Specific args of each building block 

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

201 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.') 

202 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.') 

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

204 

205 args = parser.parse_args() 

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

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

208 

209 # Specific call of each building block 

210 cpptraj_dry(input_top_path=args.input_top_path, 

211 input_traj_path=args.input_traj_path, 

212 output_cpptraj_path=args.output_cpptraj_path, 

213 properties=properties) 

214 

215 

216if __name__ == '__main__': 

217 main()