Coverage for biobb_analysis/ambertools/cpptraj_snapshot.py: 82%
78 statements
« prev ^ index » next coverage.py v7.6.4, created at 2024-11-14 14:38 +0000
1#!/usr/bin/env python3
3"""Module containing the Cpptraj Snapshot 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_out_parameters, get_negative_mask, copy_instructions_file_to_container
14class CpptrajSnapshot(BiobbObject):
15 """
16 | biobb_analysis CpptrajSnapshot
17 | Wrapper of the Ambertools Cpptraj module for extracting a particular snapshot from a given cpptraj compatible trajectory.
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>`_.
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 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).
24 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
25 * **snapshot** (*int*) - (1) [1~100000|1] Frame to be captured for snapshot
26 * **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 `@*`).
27 * **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).
28 * **binary_path** (*str*) - ("cpptraj") Path to the cpptraj executable binary.
29 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
30 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
31 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory.
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.
39 Examples:
40 This is a use example of how to use the building block from Python::
42 from biobb_analysis.ambertools.cpptraj_snapshot import cpptraj_snapshot
43 prop = {
44 'snapshot': 12,
45 'mask': 'c-alpha',
46 'format': 'pdb'
47 }
48 cpptraj_snapshot(input_top_path='/path/to/myTopology.top',
49 input_traj_path='/path/to/myTrajectory.dcd',
50 output_cpptraj_path='/path/to/newStructure.pdb',
51 properties=prop)
53 Info:
54 * wrapped_software:
55 * name: Ambertools Cpptraj
56 * version: >=20.0
57 * license: GNU
58 * ontology:
59 * name: EDAM
60 * schema: http://edamontology.org/EDAM.owl
62 """
64 def __init__(self, input_top_path, input_traj_path, output_cpptraj_path,
65 properties=None, **kwargs) -> None:
66 properties = properties or {}
68 # Call parent class constructor
69 super().__init__(properties)
70 self.locals_var_dict = locals().copy()
72 # Input/Output files
73 self.io_dict = {
74 "in": {"input_top_path": input_top_path, "input_traj_path": input_traj_path},
75 "out": {"output_cpptraj_path": output_cpptraj_path}
76 }
78 # Properties specific for BB
79 self.instructions_file = get_default_value('instructions_file')
80 self.snapshot = properties.get('snapshot', 1)
81 self.mask = properties.get('mask', 'all-atoms')
82 self.format = properties.get('format', 'netcdf')
83 self.properties = properties
84 self.binary_path = get_binary_path(properties, 'binary_path')
86 # Check the properties
87 self.check_properties(properties)
88 self.check_arguments()
90 def check_data_params(self, out_log, err_log):
91 """ Checks all the input/output paths and parameters """
92 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__)
93 self.io_dict["in"]["input_traj_path"] = check_traj_path(self.io_dict["in"]["input_traj_path"], out_log, self.__class__.__name__)
94 self.io_dict["out"]["output_cpptraj_path"] = check_out_path(self.io_dict["out"]["output_cpptraj_path"], out_log, self.__class__.__name__)
95 self.in_parameters = {'snapshot': self.snapshot, 'mask': self.mask}
96 self.out_parameters = {'format': self.format}
98 def create_instructions_file(self, container_io_dict, out_log, err_log):
99 """Creates an input file using the properties file settings"""
100 instructions_list = []
101 # different path if container execution or not
102 if self.container_path:
103 self.instructions_file = str(PurePath(self.container_volume_path).joinpath(self.instructions_file))
104 else:
105 self.instructions_file = str(PurePath(fu.create_unique_dir()).joinpath(self.instructions_file))
106 fu.create_name(prefix=self.prefix, step=self.step, name=self.instructions_file)
108 # parm
109 instructions_list.append('parm ' + container_io_dict["in"]["input_top_path"])
111 # trajin
112 in_params = get_in_parameters(self.in_parameters, out_log, 'snapshot')
113 instructions_list.append('trajin ' + container_io_dict["in"]["input_traj_path"] + ' ' + in_params)
115 # mask
116 mask = self.in_parameters.get('mask', '')
117 if mask:
118 strip_mask = get_negative_mask(mask, out_log)
119 instructions_list.append('strip ' + strip_mask)
121 # trajout
122 out_params = get_out_parameters(self.out_parameters, out_log)
123 instructions_list.append('trajout ' + container_io_dict["out"]["output_cpptraj_path"] + ' ' + out_params)
125 # create .in file
126 with open(self.instructions_file, 'w') as mdp:
127 for line in instructions_list:
128 mdp.write(line.strip() + '\n')
130 return self.instructions_file
132 @launchlogger
133 def launch(self) -> int:
134 """Execute the :class:`CpptrajSnapshot <ambertools.cpptraj_snapshot.CpptrajSnapshot>` ambertools.cpptraj_snapshot.CpptrajSnapshot object."""
136 # check input/output paths and parameters
137 self.check_data_params(self.out_log, self.err_log)
139 # Setup Biobb
140 if self.check_restart():
141 return 0
142 self.stage_files()
144 # create instructions file
145 self.create_instructions_file(self.stage_io_dict, self.out_log, self.err_log)
147 # if container execution, copy intructions file to container
148 if self.container_path:
149 copy_instructions_file_to_container(self.instructions_file, self.stage_io_dict['unique_dir'])
151 # create cmd and launch execution
152 self.cmd = [self.binary_path, '-i', self.instructions_file]
154 # Run Biobb block
155 self.run_biobb()
157 # Copy files to host
158 self.copy_to_host()
160 # remove temporary folder(s)
161 self.tmp_files.extend([
162 self.stage_io_dict.get("unique_dir", ""),
163 str(PurePath(self.instructions_file).parent)
164 ])
165 self.remove_tmp_files()
167 self.check_arguments(output_files_created=True, raise_exception=False)
169 return self.return_code
172def cpptraj_snapshot(input_top_path: str, input_traj_path: str, output_cpptraj_path: str, properties: Optional[dict] = None, **kwargs) -> int:
173 """Execute the :class:`CpptrajSnapshot <ambertools.cpptraj_snapshot.CpptrajSnapshot>` class and
174 execute the :meth:`launch() <ambertools.cpptraj_snapshot.CpptrajSnapshot.launch>` method."""
176 return CpptrajSnapshot(input_top_path=input_top_path,
177 input_traj_path=input_traj_path,
178 output_cpptraj_path=output_cpptraj_path,
179 properties=properties, **kwargs).launch()
182def main():
183 """Command line execution of this building block. Please check the command line documentation."""
184 parser = argparse.ArgumentParser(description="Extracts a particular snapshot from a given cpptraj compatible trajectory.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
185 parser.add_argument('--config', required=True, help='Configuration file')
187 # Specific args of each building block
188 required_args = parser.add_argument_group('required arguments')
189 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.')
190 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.')
191 required_args.add_argument('--output_cpptraj_path', required=True, help='Path to the output processed structure.')
193 args = parser.parse_args()
194 args.config = args.config or "{}"
195 properties = settings.ConfReader(config=args.config).get_prop_dic()
197 # Specific call of each building block
198 cpptraj_snapshot(input_top_path=args.input_top_path,
199 input_traj_path=args.input_traj_path,
200 output_cpptraj_path=args.output_cpptraj_path,
201 properties=properties)
204if __name__ == '__main__':
205 main()