Coverage for biobb_analysis/ambertools/cpptraj_mask.py: 93%

69 statements  

« prev     ^ index     » next       coverage.py v7.10.6, created at 2025-09-08 10:47 +0000

1#!/usr/bin/env python3 

2 

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

4 

5from typing import Optional 

6from pathlib import PurePath 

7from biobb_common.generic.biobb_object import BiobbObject 

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_negative_mask, get_out_parameters 

11 

12 

13class CpptrajMask(BiobbObject): 

14 """ 

15 | biobb_analysis CpptrajMask 

16 | Wrapper of the Ambertools Cpptraj module for extracting a selection of atoms 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://raw.githubusercontent.com/Amber-MD/cpptraj/master/doc/CpptrajManual.pdf>`_. 

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

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

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

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

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

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

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

39 

40 Examples: 

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

42 

43 from biobb_analysis.ambertools.cpptraj_mask import cpptraj_mask 

44 prop = { 

45 'start': 1, 

46 'end': -1, 

47 'steps': 1, 

48 'mask': 'c-alpha', 

49 'format': 'netcdf' 

50 } 

51 cpptraj_mask(input_top_path='/path/to/myTopology.top', 

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

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

54 properties=prop) 

55 

56 Info: 

57 * wrapped_software: 

58 * name: Ambertools Cpptraj 

59 * version: >=22.5 

60 * license: GNU 

61 * ontology: 

62 * name: EDAM 

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

64 

65 """ 

66 

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

68 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": {"input_top_path": input_top_path, "input_traj_path": input_traj_path}, 

78 "out": {"output_cpptraj_path": output_cpptraj_path} 

79 } 

80 

81 # Properties specific for BB 

82 self.instructions_file = get_default_value('instructions_file') 

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

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

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

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

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

88 self.properties = properties 

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

90 

91 # Check the properties 

92 self.check_init(properties) 

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 = self.create_tmp_file(self.instructions_file) 

110 

111 # parm 

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

113 

114 # trajin 

115 in_parameters = self.in_parameters 

116 in_params = '' 

117 if in_parameters: 

118 in_params = get_in_parameters(self.in_parameters, out_log, 'mask') 

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

120 

121 # mask 

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

123 if not mask or mask == 'None': 

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

125 raise SystemExit('Mask parameter is mandatory') 

126 strip_mask = get_negative_mask(mask, out_log) 

127 instructions_list.append('strip ' + strip_mask) 

128 

129 # trajout 

130 out_params = get_out_parameters(self.out_parameters, out_log) 

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

132 

133 # create .in file 

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

135 for line in instructions_list: 

136 mdp.write(line.strip() + '\n') 

137 

138 return self.instructions_file 

139 

140 @launchlogger 

141 def launch(self) -> int: 

142 """Execute the :class:`CpptrajMask <ambertools.cpptraj_mask.CpptrajMask>` object.""" 

143 

144 # check input/output paths and parameters 

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

146 

147 # Setup Biobb 

148 if self.check_restart(): 

149 return 0 

150 self.stage_files() 

151 

152 # create instructions file 

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

154 

155 # create cmd and launch execution 

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

157 

158 # Run Biobb block 

159 self.run_biobb() 

160 

161 # Copy files to host 

162 self.copy_to_host() 

163 

164 # remove temporary folder(s) 

165 self.remove_tmp_files() 

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

167 

168 return self.return_code 

169 

170 

171def cpptraj_mask(input_top_path: str, input_traj_path: str, output_cpptraj_path: str, properties: Optional[dict] = None, **kwargs) -> int: 

172 """Execute the :class:`CpptrajMask <ambertools.cpptraj_mask.CpptrajMask>` class and 

173 execute the :meth:`launch() <ambertools.cpptraj_mask.CpptrajMask.launch>` method.""" 

174 return CpptrajMask(**dict(locals())).launch() 

175 

176 

177cpptraj_mask.__doc__ = CpptrajMask.__doc__ 

178main = CpptrajMask.get_main(cpptraj_mask, "Extracts a selection of atoms from a given cpptraj compatible trajectory.") 

179 

180if __name__ == '__main__': 

181 main()