Coverage for biobb_analysis/ambertools/cpptraj_snapshot.py: 95%

61 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 Snapshot 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.file_utils import launchlogger 

9from 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, get_negative_mask 

10 

11 

12class CpptrajSnapshot(BiobbObject): 

13 """ 

14 | biobb_analysis CpptrajSnapshot 

15 | Wrapper of the Ambertools Cpptraj module for extracting a particular snapshot from a given cpptraj compatible trajectory. 

16 | 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>`_. 

17 

18 Args: 

19 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). 

20 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). 

21 output_cpptraj_path (str): Path to the output processed structure. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/ambertools/ref_cpptraj.snapshot.pdb>`_. 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). 

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

23 * **snapshot** (*int*) - (1) [1~100000|1] Frame to be captured for snapshot 

24 * **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 `@*`). 

25 * **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). 

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

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

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

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

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

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

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

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

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

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

36 

37 Examples: 

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

39 

40 from biobb_analysis.ambertools.cpptraj_snapshot import cpptraj_snapshot 

41 prop = { 

42 'snapshot': 12, 

43 'mask': 'c-alpha', 

44 'format': 'pdb' 

45 } 

46 cpptraj_snapshot(input_top_path='/path/to/myTopology.top', 

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

48 output_cpptraj_path='/path/to/newStructure.pdb', 

49 properties=prop) 

50 

51 Info: 

52 * wrapped_software: 

53 * name: Ambertools Cpptraj 

54 * version: >=22.5 

55 * license: GNU 

56 * ontology: 

57 * name: EDAM 

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

59 

60 """ 

61 

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

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

64 properties = properties or {} 

65 

66 # Call parent class constructor 

67 super().__init__(properties) 

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

69 

70 # Input/Output files 

71 self.io_dict = { 

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

73 "out": {"output_cpptraj_path": output_cpptraj_path} 

74 } 

75 

76 # Properties specific for BB 

77 self.instructions_file = get_default_value('instructions_file') 

78 self.snapshot = properties.get('snapshot', 1) 

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

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

81 self.properties = properties 

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

83 

84 # Check the properties 

85 self.check_init(properties) 

86 

87 def check_data_params(self, out_log, err_log): 

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

89 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__) 

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

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

92 self.in_parameters = {'snapshot': self.snapshot, 'mask': self.mask} 

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

94 

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

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

97 instructions_list = [] 

98 # different path if container execution or not 

99 if self.container_path: 

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

101 else: 

102 self.instructions_file = self.create_tmp_file(self.instructions_file) 

103 

104 # parm 

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

106 

107 # trajin 

108 in_params = get_in_parameters(self.in_parameters, out_log, 'snapshot') 

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

110 

111 # mask 

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

113 if mask: 

114 strip_mask = get_negative_mask(mask, out_log) 

115 instructions_list.append('strip ' + strip_mask) 

116 

117 # trajout 

118 out_params = get_out_parameters(self.out_parameters, out_log) 

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

120 

121 # create .in file 

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

123 for line in instructions_list: 

124 mdp.write(line.strip() + '\n') 

125 

126 return self.instructions_file 

127 

128 @launchlogger 

129 def launch(self) -> int: 

130 """Execute the :class:`CpptrajSnapshot <ambertools.cpptraj_snapshot.CpptrajSnapshot>` object.""" 

131 

132 # check input/output paths and parameters 

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

134 

135 # Setup Biobb 

136 if self.check_restart(): 

137 return 0 

138 self.stage_files() 

139 

140 # create instructions file 

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

142 

143 # create cmd and launch execution 

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

145 

146 # Run Biobb block 

147 self.run_biobb() 

148 

149 # Copy files to host 

150 self.copy_to_host() 

151 

152 # remove temporary folder(s) 

153 self.remove_tmp_files() 

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

155 

156 return self.return_code 

157 

158 

159def cpptraj_snapshot(input_top_path: str, input_traj_path: str, output_cpptraj_path: str, properties: Optional[dict] = None, **kwargs) -> int: 

160 """Execute the :class:`CpptrajSnapshot <ambertools.cpptraj_snapshot.CpptrajSnapshot>` class and 

161 execute the :meth:`launch() <ambertools.cpptraj_snapshot.CpptrajSnapshot.launch>` method.""" 

162 return CpptrajSnapshot(**dict(locals())).launch() 

163 

164 

165cpptraj_snapshot.__doc__ = CpptrajSnapshot.__doc__ 

166main = CpptrajSnapshot.get_main(cpptraj_snapshot, "Extracts a particular snapshot from a given cpptraj compatible trajectory.") 

167 

168if __name__ == '__main__': 

169 main()