Coverage for biobb_analysis/ambertools/cpptraj_snapshot.py: 82%
78 statements
« prev ^ index » next coverage.py v7.5.1, created at 2024-05-06 15:22 +0000
« prev ^ index » next coverage.py v7.5.1, created at 2024-05-06 15:22 +0000
1#!/usr/bin/env python3
3"""Module containing the Cpptraj Snapshot 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, get_negative_mask, copy_instructions_file_to_container
13class CpptrajSnapshot(BiobbObject):
14 """
15 | biobb_analysis CpptrajSnapshot
16 | Wrapper of the Ambertools Cpptraj module for extracting a particular snapshot 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>`_.
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 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).
23 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
24 * **snapshot** (*int*) - (1) [1~100000|1] Frame to be captured for snapshot
25 * **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 `@*`).
26 * **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).
27 * **binary_path** (*str*) - ("cpptraj") Path to the cpptraj executable binary.
28 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
29 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
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.
37 Examples:
38 This is a use example of how to use the building block from Python::
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)
51 Info:
52 * wrapped_software:
53 * name: Ambertools Cpptraj
54 * version: >=20.0
55 * license: GNU
56 * ontology:
57 * name: EDAM
58 * schema: http://edamontology.org/EDAM.owl
60 """
62 def __init__(self, input_top_path, input_traj_path, output_cpptraj_path,
63 properties=None, **kwargs) -> None:
64 properties = properties or {}
66 # Call parent class constructor
67 super().__init__(properties)
68 self.locals_var_dict = locals().copy()
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 }
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')
84 # Check the properties
85 self.check_properties(properties)
86 self.check_arguments()
88 def check_data_params(self, out_log, err_log):
89 """ Checks all the input/output paths and parameters """
90 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__)
91 self.io_dict["in"]["input_traj_path"] = check_traj_path(self.io_dict["in"]["input_traj_path"], out_log, self.__class__.__name__)
92 self.io_dict["out"]["output_cpptraj_path"] = check_out_path(self.io_dict["out"]["output_cpptraj_path"], out_log, self.__class__.__name__)
93 self.in_parameters = {'snapshot': self.snapshot, 'mask': self.mask}
94 self.out_parameters = {'format': self.format}
96 def create_instructions_file(self, container_io_dict, out_log, err_log):
97 """Creates an input file using the properties file settings"""
98 instructions_list = []
99 # different path if container execution or not
100 if self.container_path:
101 self.instructions_file = str(PurePath(self.container_volume_path).joinpath(self.instructions_file))
102 else:
103 self.instructions_file = str(PurePath(fu.create_unique_dir()).joinpath(self.instructions_file))
104 fu.create_name(prefix=self.prefix, step=self.step, name=self.instructions_file)
106 # parm
107 instructions_list.append('parm ' + container_io_dict["in"]["input_top_path"])
109 # trajin
110 in_params = get_in_parameters(self.in_parameters, out_log, 'snapshot')
111 instructions_list.append('trajin ' + container_io_dict["in"]["input_traj_path"] + ' ' + in_params)
113 # mask
114 mask = self.in_parameters.get('mask', '')
115 if mask:
116 strip_mask = get_negative_mask(mask, out_log)
117 instructions_list.append('strip ' + strip_mask)
119 # trajout
120 out_params = get_out_parameters(self.out_parameters, out_log)
121 instructions_list.append('trajout ' + container_io_dict["out"]["output_cpptraj_path"] + ' ' + out_params)
123 # create .in file
124 with open(self.instructions_file, 'w') as mdp:
125 for line in instructions_list:
126 mdp.write(line.strip() + '\n')
128 return self.instructions_file
130 @launchlogger
131 def launch(self) -> int:
132 """Execute the :class:`CpptrajSnapshot <ambertools.cpptraj_snapshot.CpptrajSnapshot>` ambertools.cpptraj_snapshot.CpptrajSnapshot object."""
134 # check input/output paths and parameters
135 self.check_data_params(self.out_log, self.err_log)
137 # Setup Biobb
138 if self.check_restart():
139 return 0
140 self.stage_files()
142 # create instructions file
143 self.create_instructions_file(self.stage_io_dict, self.out_log, self.err_log)
145 # if container execution, copy intructions file to container
146 if self.container_path:
147 copy_instructions_file_to_container(self.instructions_file, self.stage_io_dict['unique_dir'])
149 # create cmd and launch execution
150 self.cmd = [self.binary_path, '-i', self.instructions_file]
152 # Run Biobb block
153 self.run_biobb()
155 # Copy files to host
156 self.copy_to_host()
158 # remove temporary folder(s)
159 self.tmp_files.extend([
160 self.stage_io_dict.get("unique_dir"),
161 PurePath(self.instructions_file).parent
162 ])
163 self.remove_tmp_files()
165 self.check_arguments(output_files_created=True, raise_exception=False)
167 return self.return_code
170def cpptraj_snapshot(input_top_path: str, input_traj_path: str, output_cpptraj_path: str, properties: dict = None, **kwargs) -> int:
171 """Execute the :class:`CpptrajSnapshot <ambertools.cpptraj_snapshot.CpptrajSnapshot>` class and
172 execute the :meth:`launch() <ambertools.cpptraj_snapshot.CpptrajSnapshot.launch>` method."""
174 return CpptrajSnapshot(input_top_path=input_top_path,
175 input_traj_path=input_traj_path,
176 output_cpptraj_path=output_cpptraj_path,
177 properties=properties, **kwargs).launch()
180def main():
181 """Command line execution of this building block. Please check the command line documentation."""
182 parser = argparse.ArgumentParser(description="Extracts a particular snapshot from a given cpptraj compatible trajectory.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
183 parser.add_argument('--config', required=True, help='Configuration file')
185 # Specific args of each building block
186 required_args = parser.add_argument_group('required arguments')
187 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.')
188 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.')
189 required_args.add_argument('--output_cpptraj_path', required=True, help='Path to the output processed structure.')
191 args = parser.parse_args()
192 args.config = args.config or "{}"
193 properties = settings.ConfReader(config=args.config).get_prop_dic()
195 # Specific call of each building block
196 cpptraj_snapshot(input_top_path=args.input_top_path,
197 input_traj_path=args.input_traj_path,
198 output_cpptraj_path=args.output_cpptraj_path,
199 properties=properties)
202if __name__ == '__main__':
203 main()