Coverage for biobb_flexserv/pcasuite/pcz_evecs.py: 95%
63 statements
« prev ^ index » next coverage.py v7.14.1, created at 2026-05-28 11:28 +0000
1#!/usr/bin/env python3
3"""Module containing the PCZevecs class and the command line interface."""
4from typing import Optional
5import json
6import math
7from pathlib import Path, PurePath
8from biobb_common.generic.biobb_object import BiobbObject
9from biobb_common.tools.file_utils import launchlogger
12class PCZevecs(BiobbObject):
13 """
14 | biobb_flexserv PCZevecs
15 | Extract PCA Eigen Vectors from a compressed PCZ file.
16 | Wrapper of the pczdump tool from the PCAsuite FlexServ module.
18 Args:
19 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).
20 output_json_path (str): Output json file with PCA Eigen Vectors. File type: output. `Sample file <https://github.com/bioexcel/biobb_flexserv/raw/master/biobb_flexserv/test/reference/pcasuite/pcz_evecs.json>`_. Accepted formats: json (edam:format_3464).
21 properties (dict - Python dictionary object containing the tool parameters, not input/output files):
22 * **binary_path** (*str*) - ("pczdump") pczdump binary path to be used.
23 * **eigenvector** (*int*) - (1) PCA mode (eigenvector) from which to extract eigen vectors.
24 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
25 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
26 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory.
27 * **container_path** (*str*) - (None) Container path definition.
28 * **container_image** (*str*) - ('afandiadib/ambertools:serial') Container image definition.
29 * **container_volume_path** (*str*) - ('/tmp') Container volume path definition.
30 * **container_working_dir** (*str*) - (None) Container working directory definition.
31 * **container_user_id** (*str*) - (None) Container user_id definition.
32 * **container_shell_path** (*str*) - ('/bin/bash') Path to default shell inside the container.
34 Examples:
35 This is a use example of how to use the building block from Python::
37 from biobb_flexserv.pcasuite.pcz_evecs import pcz_evecs
39 prop = {
40 'eigenvector': 1
41 }
43 pcz_evecs( input_pcz_path='/path/to/pcazip_input.pcz',
44 output_json_path='/path/to/pcz_evecs.json',
45 properties=prop)
47 Info:
48 * wrapped_software:
49 * name: FlexServ PCAsuite
50 * version: >=1.0
51 * license: Apache-2.0
52 * ontology:
53 * name: EDAM
54 * schema: http://edamontology.org/EDAM.owl
56 """
58 def __init__(self, input_pcz_path: str,
59 output_json_path: str, properties: Optional[dict] = None, **kwargs) -> None:
61 properties = properties or {}
63 # Call parent class constructor
64 super().__init__(properties)
65 self.locals_var_dict = locals().copy()
67 # Input/Output files
68 self.io_dict = {
69 'in': {'input_pcz_path': input_pcz_path},
70 'out': {'output_json_path': output_json_path}
71 }
73 # Properties specific for BB
74 self.properties = properties
75 self.binary_path = properties.get('binary_path', 'pczdump')
76 self.eigenvector = properties.get('eigenvector', 1)
78 # Check the properties
79 self.check_properties(properties)
80 self.check_arguments()
82 @launchlogger
83 def launch(self):
84 """Launches the execution of the FlexServ pcz_evecs module."""
86 # Setup Biobb
87 if self.check_restart():
88 return 0
89 self.stage_files()
91 if self.container_path:
92 working_dir = self.container_volume_path if self.container_volume_path else "/data"
93 else:
94 working_dir = self.stage_io_dict.get("unique_dir", "")
96 unique_dir = Path(self.stage_io_dict.get("unique_dir", ""))
98 # Temporary output
99 # temp_out = str(Path(self.stage_io_dict.get("unique_dir", "")).joinpath("output.dat"))
100 temp_out = "output.dat"
101 temp_out_path = unique_dir.joinpath(temp_out)
102 staged_output_json_path = unique_dir.joinpath(Path(self.stage_io_dict["out"]["output_json_path"]).name)
104 # Command line
105 # pczdump -i structure.ca.std.pcz --evecs -o pcz.evecs
106 # self.cmd = [self.binary_path,
107 # "-i", input_pcz,
108 # "-o", temp_out,
109 # "--evec={}".format(self.eigenvector)
110 # ]
112 self.cmd = ['cd', working_dir, ';',
113 self.binary_path,
114 '-i', PurePath(self.stage_io_dict["in"]["input_pcz_path"]).name,
115 '-o', temp_out,
116 "--evec={}".format(self.eigenvector)
117 ]
119 # Run Biobb block
120 self.run_biobb()
122 # Parse output evecs
123 # 0.180 -0.069 0.168 0.204 -0.054 0.235 0.145 -0.001 0.260 0.183
124 # -0.041 0.231 0.174 -0.077 0.144 0.097 -0.022 0.143 0.069 0.008
126 info_dict = {}
127 info_dict['evecs'] = []
128 with open(temp_out_path, 'r') as file:
129 for line in file:
130 info = line.strip().split(' ')
131 for nums in info:
132 if nums:
133 info_dict['evecs'].append(nums)
135 # Computing Projections
136 info_dict['projs'] = []
137 module = 1
138 proj = 0
139 for num in info_dict['evecs']:
140 val = float(num) * float(num)
141 proj = proj + val
142 if module % 3 == 0:
143 proj = math.sqrt(proj)
144 module = 1
145 info_dict['projs'].append(float("{:.4f}".format(proj)))
146 proj = 0
147 else:
148 module = module + 1
150 with open(staged_output_json_path, 'w') as out_file:
151 out_file.write(json.dumps(info_dict, indent=4))
153 # Copy files to host
154 self.copy_to_host()
156 # Remove temporary folder(s)
157 self.remove_tmp_files()
159 self.check_arguments(output_files_created=True, raise_exception=False)
161 return self.return_code
164def pcz_evecs(input_pcz_path: str, output_json_path: str,
165 properties: Optional[dict] = None, **kwargs) -> int:
166 """Create :class:`PCZevecs <flexserv.pcasuite.pcz_evecs>`flexserv.pcasuite.PCZevecs class and
167 execute :meth:`launch() <flexserv.pcasuite.pcz_evecs.launch>` method"""
168 return PCZevecs(**dict(locals())).launch()
171pcz_evecs.__doc__ = PCZevecs.__doc__
172main = PCZevecs.get_main(pcz_evecs, "Extract PCA Eigen Vectors from a compressed PCZ file.")
174if __name__ == '__main__':
175 main()