#!/usr/bin/env python3
"""Module containing the PCAzip class and the command line interface."""
from typing import Optional
from pathlib import PurePath
from biobb_common.generic.biobb_object import BiobbObject
from biobb_common.tools.file_utils import launchlogger
[docs]
class PCZzip(BiobbObject):
"""
| biobb_flexserv PCZzip
| Wrapper of the pcazip tool from the PCAsuite FlexServ module.
| Compress Molecular Dynamics (MD) trajectories using Principal Component Analysis (PCA) algorithms.
Args:
input_pdb_path (str): Input PDB file. File type: input. `Sample file <https://github.com/bioexcel/biobb_flexserv/raw/master/biobb_flexserv/test/data/pcasuite/structure.ca.pdb>`_. Accepted formats: pdb (edam:format_1476).
input_crd_path (str): Input Trajectory file. File type: input. `Sample file <https://github.com/bioexcel/biobb_flexserv/raw/master/biobb_flexserv/test/data/pcasuite/traj.crd>`_. Accepted formats: crd (edam:format_3878), mdcrd (edam:format_3878), inpcrd (edam:format_3878).
output_pcz_path (str): Output compressed trajectory. File type: output. `Sample file <https://github.com/bioexcel/biobb_flexserv/raw/master/biobb_flexserv/test/reference/pcasuite/pcazip.pcz>`_. Accepted formats: pcz (edam:format_3874).
properties (dict - Python dictionary object containing the tool parameters, not input/output files):
* **binary_path** (*str*) - ("pcazip") pcazip binary path to be used.
* **neigenv** (*int*) - (0) Number of generated eigenvectors
* **variance** (*int*) - (90) Percentage of variance captured by the final set of eigenvectors
* **verbose** (*bool*) - (False) Make output verbose
* **gauss_rmsd** (*bool*) - (False) Use a gaussian RMSd for fitting
* **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
* **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
* **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory.
* **container_path** (*str*) - (None) Container path definition.
* **container_image** (*str*) - ('afandiadib/ambertools:serial') Container image definition.
* **container_volume_path** (*str*) - ('/tmp') Container volume path definition.
* **container_working_dir** (*str*) - (None) Container working directory definition.
* **container_user_id** (*str*) - (None) Container user_id definition.
* **container_shell_path** (*str*) - ('/bin/bash') Path to default shell inside the container.
Examples:
This is a use example of how to use the building block from Python::
from biobb_flexserv.pcasuite.pcz_zip import pcz_zip
prop = {
'variance': 90
}
pcz_zip( input_pdb_path='/path/to/pcazip_input.pdb',
input_crd_path='/path/to/pcazip_input.crd',
output_pcz_path='/path/to/pcazip_traj.pcz',
properties=prop)
Info:
* wrapped_software:
* name: FlexServ PCAsuite
* version: >=1.0
* license: Apache-2.0
* ontology:
* name: EDAM
* schema: http://edamontology.org/EDAM.owl
"""
def __init__(self, input_pdb_path: str, input_crd_path: str,
output_pcz_path: str, properties: Optional[dict] = None, **kwargs) -> None:
properties = properties or {}
# Call parent class constructor
super().__init__(properties)
self.locals_var_dict = locals().copy()
# Input/Output files
self.io_dict = {
'in': {'input_pdb_path': input_pdb_path,
'input_crd_path': input_crd_path},
'out': {'output_pcz_path': output_pcz_path}
}
# Properties specific for BB
self.properties = properties
self.binary_path = properties.get('binary_path', 'pcazip')
self.neigenv = properties.get('neigenv', 0)
# self.variance = properties.get('variance', 90)
self.variance = properties.get('variance')
self.verbose = properties.get('verbose', False)
self.gauss_rmsd = properties.get('gauss_rmsd', False)
# Check the properties
self.check_properties(properties)
self.check_arguments()
[docs]
@launchlogger
def launch(self):
"""Launches the execution of the FlexServ pcazip module."""
# Setup Biobb
if self.check_restart():
return 0
self.stage_files()
if self.container_path:
working_dir = self.container_volume_path if self.container_volume_path else "/data"
else:
working_dir = self.stage_io_dict.get("unique_dir", "")
# Command line
# pcazip -i infile -o outfile -n natoms
# [-v] [--mask maskfile] [-e nev] [-q qual] [--pdb pdbfile]
# self.cmd = [self.binary_path,
# "-p", input_pdb,
# "-i", input_crd,
# "-o", output_pcz
# ]
self.cmd = ['cd', working_dir, ';',
self.binary_path,
"-p", PurePath(self.stage_io_dict["in"]["input_pdb_path"]).name,
"-i", PurePath(self.stage_io_dict["in"]["input_crd_path"]).name,
"-o", PurePath(self.stage_io_dict["out"]["output_pcz_path"]).name
]
if self.verbose:
self.cmd.append('-v')
if self.gauss_rmsd:
self.cmd.append('-g')
if self.neigenv:
self.cmd.append('-e')
self.cmd.append(str(self.neigenv))
if self.variance:
self.cmd.append('-q')
self.cmd.append(str(self.variance))
# Run Biobb block
self.run_biobb()
# Copy files to host
self.copy_to_host()
# Remove temporary folder(s)
self.remove_tmp_files()
self.check_arguments(output_files_created=True, raise_exception=False)
return self.return_code
[docs]
def pcz_zip(input_pdb_path: str, input_crd_path: str,
output_pcz_path: str,
properties: Optional[dict] = None, **kwargs) -> int:
"""Create :class:`PCZzip <flexserv.pcasuite.PCZzip>`flexserv.pcasuite.PCZzip class and
execute :meth:`launch() <flexserv.pcasuite.PCZzip.launch>` method"""
return PCZzip(**dict(locals())).launch()
pcz_zip.__doc__ = PCZzip.__doc__
main = PCZzip.get_main(pcz_zip, "Compress Molecular Dynamics (MD) trajectories using Principal Component Analysis (PCA) algorithms.")
if __name__ == '__main__':
main()