Coverage for biobb_analysis/ambertools/cpptraj_rmsf.py: 83%
87 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 Rmsf 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_negative_mask, copy_instructions_file_to_container, setup_structure, get_mask, get_reference
14class CpptrajRmsf(BiobbObject):
15 """
16 | biobb_analysis CpptrajRmsf
17 | Wrapper of the Ambertools Cpptraj module for calculating the Root Mean Square fluctuations (RMSf) of 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 input_exp_path (str) (Optional): Path to the experimental reference file (required if reference = experimental). File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/ambertools/experimental.1e5t.pdb>`_. Accepted formats: pdb (edam:format_1476).
24 output_cpptraj_path (str): Path to the output processed analysis. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/ambertools/ref_cpptraj.rmsf.first.dat>`_. Accepted formats: dat (edam:format_1637), agr (edam:format_2033), xmgr (edam:format_2033), gnu (edam:format_2033).
25 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
26 * **start** (*int*) - (1) [1~100000|1] Starting frame for slicing
27 * **end** (*int*) - (-1) [-1~100000|1] Ending frame for slicing
28 * **steps** (*int*) - (1) [1~100000|1] Step for slicing
29 * **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 `@*`).
30 * **reference** (*str*) - ("first") Reference definition. Values: first (Use the first trajectory frame as reference), average (Use the average of all trajectory frames as reference), experimental (Use the experimental structure as reference).
31 * **binary_path** (*str*) - ("cpptraj") Path to the cpptraj executable binary.
32 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
33 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
34 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory.
35 * **container_path** (*str*) - (None) Container path definition.
36 * **container_image** (*str*) - ('afandiadib/ambertools:serial') Container image definition.
37 * **container_volume_path** (*str*) - ('/tmp') Container volume path definition.
38 * **container_working_dir** (*str*) - (None) Container working directory definition.
39 * **container_user_id** (*str*) - (None) Container user_id definition.
40 * **container_shell_path** (*str*) - ('/bin/bash') Path to default shell inside the container.
42 Examples:
43 This is a use example of how to use the building block from Python::
45 from biobb_analysis.ambertools.cpptraj_rmsf import cpptraj_rmsf
46 prop = {
47 'start': 1,
48 'end': -1,
49 'steps': 1,
50 'mask': 'c-alpha',
51 'reference': 'first'
52 }
53 cpptraj_rmsf(input_top_path='/path/to/myTopology.top',
54 input_traj_path='/path/to/myTrajectory.dcd',
55 output_cpptraj_path='/path/to/newAnalysis.dat',
56 input_exp_path= '/path/to/myExpStructure.pdb',
57 properties=prop)
59 Info:
60 * wrapped_software:
61 * name: Ambertools Cpptraj
62 * version: >=20.0
63 * license: GNU
64 * ontology:
65 * name: EDAM
66 * schema: http://edamontology.org/EDAM.owl
68 """
70 def __init__(self, input_top_path, input_traj_path, output_cpptraj_path,
71 input_exp_path=None, properties=None, **kwargs) -> None:
72 properties = properties or {}
74 # Call parent class constructor
75 super().__init__(properties)
76 self.locals_var_dict = locals().copy()
78 # Input/Output files
79 self.io_dict = {
80 "in": {"input_top_path": input_top_path, "input_traj_path": input_traj_path, "input_exp_path": input_exp_path},
81 "out": {"output_cpptraj_path": output_cpptraj_path}
82 }
84 # Properties specific for BB
85 self.instructions_file = get_default_value('instructions_file')
86 self.start = properties.get('start', 1)
87 self.end = properties.get('end', -1)
88 self.steps = properties.get('steps', 1)
89 self.mask = properties.get('mask', 'all-atoms')
90 self.reference = properties.get('reference', 'first')
91 self.properties = properties
92 self.binary_path = get_binary_path(properties, 'binary_path')
94 # Check the properties
95 self.check_properties(properties)
96 self.check_arguments()
98 def check_data_params(self, out_log, err_log):
99 """ Checks all the input/output paths and parameters """
100 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__)
101 self.io_dict["in"]["input_traj_path"] = check_traj_path(self.io_dict["in"]["input_traj_path"], out_log, self.__class__.__name__)
102 self.io_dict["out"]["output_cpptraj_path"] = check_out_path(self.io_dict["out"]["output_cpptraj_path"], out_log, self.__class__.__name__)
103 self.in_parameters = {'start': self.start, 'end': self.end, 'step': self.steps, 'mask': self.mask, 'reference': self.reference}
105 def create_instructions_file(self, container_io_dict, out_log, err_log):
106 """Creates an input file using the properties file settings"""
107 instructions_list = []
108 # different path if container execution or not
109 if self.container_path:
110 self.instructions_file = str(PurePath(self.container_volume_path).joinpath(self.instructions_file))
111 else:
112 self.instructions_file = str(PurePath(fu.create_unique_dir()).joinpath(self.instructions_file))
113 fu.create_name(prefix=self.prefix, step=self.step, name=self.instructions_file)
115 # parm
116 instructions_list.append('parm ' + container_io_dict["in"]["input_top_path"])
118 # trajin
119 in_params = get_in_parameters(self.in_parameters, out_log)
120 instructions_list.append('trajin ' + container_io_dict["in"]["input_traj_path"] + ' ' + in_params)
122 # Set up
123 instructions_list += setup_structure(self)
125 # mask
126 mask = self.in_parameters.get('mask', '')
127 ref_mask = ''
128 if mask:
129 strip_mask = get_negative_mask(mask, out_log)
130 ref_mask = get_mask(mask, out_log)
131 instructions_list.append('strip ' + strip_mask)
133 # reference
134 reference = self.in_parameters.get('reference', '')
135 inp_exp_pth = None
136 if "input_exp_path" in container_io_dict["in"]:
137 inp_exp_pth = container_io_dict["in"]["input_exp_path"]
138 instructions_list += get_reference(reference, container_io_dict["out"]["output_cpptraj_path"], inp_exp_pth, ref_mask, False, self.__class__.__name__, out_log)
139 instructions_list.append('atomicfluct out ' + container_io_dict["out"]["output_cpptraj_path"] + ' byres')
141 # create .in file
142 with open(self.instructions_file, 'w') as mdp:
143 for line in instructions_list:
144 mdp.write(line.strip() + '\n')
146 return self.instructions_file
148 @launchlogger
149 def launch(self) -> int:
150 """Execute the :class:`CpptrajRmsf <ambertools.cpptraj_rmsf.CpptrajRmsf>` ambertools.cpptraj_rmsf.CpptrajRmsf object."""
152 # check input/output paths and parameters
153 self.check_data_params(self.out_log, self.err_log)
155 # Setup Biobb
156 if self.check_restart():
157 return 0
158 self.stage_files()
160 # create instructions file
161 self.create_instructions_file(self.stage_io_dict, self.out_log, self.err_log)
163 # if container execution, copy intructions file to container
164 if self.container_path:
165 copy_instructions_file_to_container(self.instructions_file, self.stage_io_dict['unique_dir'])
167 # create cmd and launch execution
168 self.cmd = [self.binary_path, '-i', self.instructions_file]
170 # Run Biobb block
171 self.run_biobb()
173 # Copy files to host
174 self.copy_to_host()
176 # remove temporary folder(s)
177 self.tmp_files.extend([
178 self.stage_io_dict.get("unique_dir", ""),
179 str(PurePath(self.instructions_file).parent)
180 ])
181 self.remove_tmp_files()
183 self.check_arguments(output_files_created=True, raise_exception=False)
185 return self.return_code
188def cpptraj_rmsf(input_top_path: str, input_traj_path: str, output_cpptraj_path: str, input_exp_path: Optional[str] = None, properties: Optional[dict] = None, **kwargs) -> int:
189 """Execute the :class:`CpptrajRmsf <ambertools.cpptraj_rmsf.CpptrajRmsf>` class and
190 execute the :meth:`launch() <ambertools.cpptraj_rmsf.CpptrajRmsf.launch>` method."""
192 return CpptrajRmsf(input_top_path=input_top_path,
193 input_traj_path=input_traj_path,
194 output_cpptraj_path=output_cpptraj_path,
195 input_exp_path=input_exp_path,
196 properties=properties, **kwargs).launch()
199def main():
200 """Command line execution of this building block. Please check the command line documentation."""
201 parser = argparse.ArgumentParser(description="Calculates the Root Mean Square fluctuations (RMSf) of a given cpptraj compatible trajectory.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
202 parser.add_argument('--config', required=False, help='Configuration file')
204 # Specific args of each building block
205 required_args = parser.add_argument_group('required arguments')
206 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.')
207 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.')
208 parser.add_argument('--input_exp_path', required=False, help='Path to the experimental reference file (required if reference = experimental).')
209 required_args.add_argument('--output_cpptraj_path', required=True, help='Path to the output processed analysis.')
211 args = parser.parse_args()
212 args.config = args.config or "{}"
213 properties = settings.ConfReader(config=args.config).get_prop_dic()
215 # Specific call of each building block
216 cpptraj_rmsf(input_top_path=args.input_top_path,
217 input_traj_path=args.input_traj_path,
218 output_cpptraj_path=args.output_cpptraj_path,
219 input_exp_path=args.input_exp_path,
220 properties=properties)
223if __name__ == '__main__':
224 main()