#!/usr/bin/env python3
"""Module containing the PCZcollectivity class and the command line interface."""
from typing import Optional
from pathlib import Path, PurePath
import json
from biobb_common.generic.biobb_object import BiobbObject
from biobb_common.tools.file_utils import launchlogger
[docs]
class PCZcollectivity(BiobbObject):
"""
| biobb_flexserv PCZcollectivity
| Extract PCA collectivity (numerical measure of how many atoms are affected by a given mode) from a compressed PCZ file.
| Wrapper of the pczdump tool from the PCAsuite FlexServ module.
Args:
input_pcz_path (str): Input compressed trajectory file. File type: input. `Sample file <https://github.com/bioexcel/biobb_flexserv/raw/master/biobb_flexserv/test/data/pcasuite/pcazip.pcz>`_. Accepted formats: pcz (edam:format_3874).
output_json_path (str): Output json file with PCA Collectivity indexes per mode. File type: output. `Sample file <https://github.com/bioexcel/biobb_flexserv/raw/master/biobb_flexserv/test/reference/pcasuite/pcz_collectivity.json>`_. Accepted formats: json (edam:format_3464).
properties (dict - Python dictionary object containing the tool parameters, not input/output files):
* **eigenvector** (*int*) - (0) PCA mode (eigenvector) from which to extract stiffness.
* **binary_path** (*str*) - ("pczdump") pczdump binary path to be used.
* **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_collectivity import pcz_collectivity
prop = {
'eigenvector': 1
}
pcz_collectivity( input_pcz_path='/path/to/pcazip_input.pcz',
output_json_path='/path/to/pcz_collectivity.json',
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_pcz_path: str,
output_json_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_pcz_path': input_pcz_path},
'out': {'output_json_path': output_json_path}
}
# Properties specific for BB
self.properties = properties
self.binary_path = properties.get('binary_path', 'pczdump')
self.eigenvector = properties.get('eigenvector', 0)
# Check the properties
self.check_properties(properties)
self.check_arguments()
[docs]
@launchlogger
def launch(self):
"""Launches the execution of the FlexServ pcz_collectivity 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", "")
unique_dir = Path(self.stage_io_dict.get("unique_dir", ""))
# Temporary output
# temp_out = str(Path(self.stage_io_dict.get("unique_dir", "")).joinpath("output.dat"))
temp_out = "output.dat"
temp_out_path = unique_dir.joinpath(temp_out)
staged_output_json_path = unique_dir.joinpath(Path(self.stage_io_dict["out"]["output_json_path"]).name)
# Command line
# pczdump -i structure.ca.std.pcz --collectivity -o pcz.collectivity
# self.cmd = [self.binary_path,
# "-i", input_pcz,
# "-o", temp_out,
# "--collectivity={}".format(self.eigenvector)
# ]
self.cmd = ['cd', working_dir, ';',
self.binary_path,
'-i', PurePath(self.stage_io_dict["in"]["input_pcz_path"]).name,
'-o', temp_out,
"--collectivity={}".format(self.eigenvector)
]
# Run Biobb block
self.run_biobb()
# Parse output collectivity
# 0.132891
# 0.165089
# 0.147202
info_dict = {}
info_dict['collectivity'] = []
with open(temp_out_path, 'r') as file:
for line in file:
info = float(line.strip())
info_dict['collectivity'].append(info)
with open(staged_output_json_path, 'w') as out_file:
out_file.write(json.dumps(info_dict, indent=4))
# 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_collectivity(input_pcz_path: str, output_json_path: str,
properties: Optional[dict] = None, **kwargs) -> int:
"""Create :class:`PCZcollectivity <flexserv.pcasuite.pcz_collectivity>`flexserv.pcasuite.PCZcollectivity class and
execute :meth:`launch() <flexserv.pcasuite.pcz_collectivity.launch>` method"""
return PCZcollectivity(**dict(locals())).launch()
pcz_collectivity.__doc__ = PCZcollectivity.__doc__
main = PCZcollectivity.get_main(pcz_collectivity, "Extract PCA collectivity (numerical measure of how many atoms are affected by a given mode) from a compressed PCZ file.")
if __name__ == '__main__':
main()