Coverage for biobb_chemistry/babelm/babel_remove_hydrogens.py: 84%
87 statements
« prev ^ index » next coverage.py v7.6.12, created at 2025-03-12 09:28 +0000
« prev ^ index » next coverage.py v7.6.12, created at 2025-03-12 09:28 +0000
1#!/usr/bin/env python3
3"""Module containing the BabelRemoveHydrogens class and the command line interface."""
5import argparse
6from typing import Optional
8from biobb_common.configuration import settings
9from biobb_common.generic.biobb_object import BiobbObject
10from biobb_common.tools.file_utils import launchlogger
12from biobb_chemistry.babelm.common import (
13 _from_string_to_list,
14 check_input_path,
15 check_output_path,
16 get_coordinates,
17 get_input_format,
18 get_output_format,
19 get_ph,
20)
23class BabelRemoveHydrogens(BiobbObject):
24 """
25 | biobb_chemistry BabelRemoveHydrogens
26 | This class is a wrapper of the Open Babel tool.
27 | Removes hydrogens to a given structure or trajectory. Open Babel is a chemical toolbox designed to speak the many languages of chemical data. It's an open, collaborative project allowing anyone to search, convert, analyze, or store data from molecular modeling, chemistry, solid-state materials, biochemistry, or related areas. `Visit the official page <http://openbabel.org/wiki/Main_Page>`_.
29 Args:
30 input_path (str): Path to the input file. File type: input. `Sample file <https://github.com/bioexcel/biobb_chemistry/raw/master/biobb_chemistry/test/data/babel/babel.H.pdb>`_. Accepted formats: dat (edam:format_1637), ent (edam:format_1476), fa (edam:format_1929), fasta (edam:format_1929), gro (edam:format_2033), inp (edam:format_3878), log (edam:format_2030), mcif (edam:format_1477), mdl (edam:format_3815), mmcif (edam:format_1477), mol (edam:format_3815), mol2 (edam:format_3816), pdb (edam:format_1476), pdbqt (edam:format_1476), png (edam:format_3603), sdf (edam:format_3814), smi (edam:format_1196), smiles (edam:format_1196), txt (edam:format_2033), xml (edam:format_2332), xtc (edam:format_3875).
31 output_path (str): Path to the output file. File type: output. `Sample file <https://github.com/bioexcel/biobb_chemistry/raw/master/biobb_chemistry/test/reference/babel/ref_babel.nohydrogens.pdb>`_. Accepted formats: ent (edam:format_1476), fa (edam:format_1929), fasta (edam:format_1929), gro (edam:format_2033), inp (edam:format_3878), mcif (edam:format_1477), mdl (edam:format_3815), mmcif (edam:format_1477), mol (edam:format_3815), mol2 (edam:format_3816), pdb (edam:format_1476), pdbqt (edam:format_1476), png (edam:format_3603), sdf (edam:format_3814), smi (edam:format_1196), smiles (edam:format_1196), txt (edam:format_2033).
32 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
33 * **input_format** (*str*) - (None) Format of input file. If not provided, input_path extension will be taken. Values: dat (Information represented in a data record), ent (Protein Data Bank format), fa (FASTA sequence format), fasta (FASTA sequence format), gro (GROMACS structure), inp (AMBER trajectory format), log (Events file), mcif (Entry format of PDB database in mmCIF format), mdl (file format for holding information about the atoms; bonds; connectivity and coordinates of a molecule), mmcif (Entry format of PDB database in mmCIF format), mol (file format for holding information about the atoms; bonds; connectivity and coordinates of a molecule), mol2 (Complete and portable representation of a SYBYL molecule), pdb (Protein Data Bank format), pdbqt (Protein Data Bank format with charges), png (File format for image compression), sdf (One of a family of chemical-data file formats developed by MDL Information Systems), smi (Chemical structure specified in Simplified Molecular Input Line Entry System line notation.), smiles (Chemical structure specified in Simplified Molecular Input Line Entry System line notation.), txt (Textual format), xml (eXtensible Markup Language), xtc (Portable binary format for trajectories produced by GROMACS package).
34 * **output_format** (*str*) - (None) Format of output file. If not provided, output_path extension will be taken. Values: ent (Protein Data Bank format), fa (FASTA sequence format), fasta (FASTA sequence format), gro (GROMACS structure), inp (AMBER trajectory format), mcif (Entry format of PDB database in mmCIF format), mdl (file format for holding information about the atoms; bonds; connectivity and coordinates of a molecule), mmcif (Entry format of PDB database in mmCIF format), mol (file format for holding information about the atoms; bonds; connectivity and coordinates of a molecule), mol2 (Complete and portable representation of a SYBYL molecule), pdb (Protein Data Bank format), pdbqt (Protein Data Bank format with charges), png (File format for image compression), sdf (One of a family of chemical-data file formats developed by MDL Information Systems), smi (Chemical structure specified in Simplified Molecular Input Line Entry System line notation.), smiles (Chemical structure specified in Simplified Molecular Input Line Entry System line notation.), txt (Textual format), xtc (Portable binary format for trajectories produced by GROMACS package).
35 * **fs_input** (*list*) - (None) Format-specific input options. Values: b (disable automatic bonding), d (input file is in dlg -AutoDock docking log- format).
36 * **fs_output** (*list*) - (None) Format-specific output options. Values: b (enable automatic bonding), r (output as a rigid molecule), c (combine separate molecular pieces of input into a single rigid molecule), s (output as a flexible residue), p (preserve atom indices from input file), h (preserve hydrogens), n (preserve atom names).
37 * **coordinates** (*int*) - (None) Type of coordinates: 2D or 3D. Values: 2 (2D coordinates), 3 (3D coordinates).
38 * **effort** (*str*) - ("medium") Computational effort wanted to dedicate for the conformer generation coordinates calculations, only for 3D coordinates. Values: fastest (only generate coordinates, no force field or conformer search), fast (perform quick forcefield optimization), medium (forcefield optimization + fast conformer search), better (more optimization + fast conformer search), best (more optimization + significant conformer search).
39 * **ph** (*float*) - (7.4) [0~14|0.1] Add hydrogens appropriate for pH.
40 * **binary_path** (*str*) - ("obabel") Path to the obabel executable binary.
41 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
42 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
43 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory.
44 * **container_path** (*str*) - (None) Container path definition.
45 * **container_image** (*str*) - ('informaticsmatters/obabel:latest') Container image definition.
46 * **container_volume_path** (*str*) - ('/tmp') Container volume path definition.
47 * **container_working_dir** (*str*) - (None) Container working directory definition.
48 * **container_user_id** (*str*) - (None) Container user_id definition.
49 * **container_shell_path** (*str*) - ('/bin/bash') Path to default shell inside the container.
51 Examples:
52 This is a use example of how to use the building block from Python::
54 from biobb_chemistry.babelm.babel_remove_hydrogens import babel_remove_hydrogens
55 prop = {
56 'input_format': 'pdb',
57 'output_format': 'pdb',
58 'coordinates': 3,
59 'ph': 7.4
60 }
61 babel_remove_hydrogens(input_path='/path/to/myStructure.pdb',
62 output_path='/path/to/newStructure.pdb',
63 properties=prop)
65 Info:
66 * wrapped_software:
67 * name: Open Babel
68 * version: 2.4.1
69 * license: GNU
70 * ontology:
71 * name: EDAM
72 * schema: http://edamontology.org/EDAM.owl
74 """
76 def __init__(self, input_path, output_path, properties=None, **kwargs) -> None:
77 properties = properties or {}
79 # Call parent class constructor
80 super().__init__(properties)
81 self.locals_var_dict = locals().copy()
83 # Input/Output files
84 self.io_dict = {
85 "in": {"input_path": input_path},
86 "out": {"output_path": output_path},
87 }
89 # Properties specific for BB
90 self.input_format = properties.get("input_format", "")
91 self.output_format = properties.get("output_format", "")
92 self.fs_input = _from_string_to_list(properties.get("fs_input", None))
93 self.fs_output = _from_string_to_list(properties.get("fs_output", None))
94 self.coordinates = properties.get("coordinates", "")
95 self.effort = properties.get("effort", "medium")
96 self.ph = properties.get("ph", "")
97 self.binary_path = properties.get("binary_path", "obabel")
98 self.properties = properties
100 # Check the properties
101 self.check_properties(properties)
102 self.check_arguments()
104 def check_data_params(self, out_log, err_log):
105 """Checks all the input/output paths and parameters"""
106 self.io_dict["in"]["input_path"] = check_input_path(
107 self.io_dict["in"]["input_path"], out_log, self.__class__.__name__
108 )
109 self.io_dict["out"]["output_path"] = check_output_path(
110 self.io_dict["out"]["output_path"], out_log, self.__class__.__name__
111 )
113 def create_cmd(self, container_io_dict, out_log, err_log):
114 """Creates the command line instruction using the properties file settings"""
115 instructions_list = []
117 # executable path
118 instructions_list.append(self.binary_path)
120 # generating input
121 infr = get_input_format(
122 self.input_format, container_io_dict["in"]["input_path"], out_log
123 )
124 iformat = "-i" + infr
125 instructions_list.append(iformat)
126 ipath = container_io_dict["in"]["input_path"]
127 instructions_list.append(ipath)
129 # generating output
130 oufr = get_output_format(
131 self.output_format, container_io_dict["out"]["output_path"], out_log
132 )
133 oformat = "-o" + oufr
134 instructions_list.append(oformat)
135 opath = "-O" + container_io_dict["out"]["output_path"]
136 instructions_list.append(opath)
138 # adding coordinates
139 crd = get_coordinates(self.coordinates, out_log)
140 coordinates = ""
141 if crd:
142 coordinates = "--gen" + crd + "d"
143 instructions_list.append(coordinates)
145 hydrogens = "-d"
147 instructions_list.append(hydrogens)
149 # adding pH
150 p = get_ph(self.ph, out_log)
151 ph = ""
152 if p:
153 ph = "-p " + p
154 instructions_list.append(ph)
156 # fs_input
157 if self.fs_input is not None:
158 for fsi in self.fs_input:
159 instructions_list.append("-a" + fsi)
161 # fs_output
162 if self.fs_output is not None:
163 for fso in self.fs_output:
164 instructions_list.append("-x" + fso)
166 # adding effort (only for 3D coordinates)
167 if crd == "3":
168 instructions_list.append("--" + self.effort)
170 return instructions_list
172 @launchlogger
173 def launch(self) -> int:
174 """Execute the :class:`BabelRemoveHydrogens <babelm.babel_remove_hydrogens.BabelRemoveHydrogens>` babelm.babel_remove_hydrogens.BabelRemoveHydrogens object."""
176 # check input/output paths and parameters
177 self.check_data_params(self.out_log, self.err_log)
179 # Setup Biobb
180 if self.check_restart():
181 return 0
182 self.stage_files()
184 # create command line instruction
185 self.cmd = self.create_cmd(self.stage_io_dict, self.out_log, self.err_log)
187 # Run Biobb block
188 self.run_biobb()
190 # Copy files to host
191 self.copy_to_host()
193 # remove temporary folder(s)
194 # self.tmp_files.extend([self.stage_io_dict.get("unique_dir", "")])
195 self.remove_tmp_files()
197 self.check_arguments(output_files_created=True, raise_exception=False)
199 return self.return_code
202def babel_remove_hydrogens(
203 input_path: str, output_path: str, properties: Optional[dict] = None, **kwargs
204) -> int:
205 """Execute the :class:`BabelRemoveHydrogens <babelm.babel_remove_hydrogens.BabelRemoveHydrogens>` class and
206 execute the :meth:`launch() <babelm.babel_remove_hydrogens.BabelRemoveHydrogens.launch>` method."""
208 return BabelRemoveHydrogens(
209 input_path=input_path, output_path=output_path, properties=properties, **kwargs
210 ).launch()
212 babel_remove_hydrogens.__doc__ = BabelRemoveHydrogens.__doc__
215def main():
216 """Command line execution of this building block. Please check the command line documentation."""
217 parser = argparse.ArgumentParser(
218 description="Removes hydrogen atoms to small molecules.",
219 formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999),
220 )
221 parser.add_argument("--config", required=False, help="Configuration file")
223 # Specific args of each building block
224 required_args = parser.add_argument_group("required arguments")
225 required_args.add_argument(
226 "--input_path",
227 required=True,
228 help="Path to the input file. Accepted formats: dat, ent, fa, fasta, gro, inp, log, mcif, mdl, mmcif, mol, mol2, pdb, pdbqt, png, sdf, smi, smiles, txt, xml, xtc.",
229 )
230 required_args.add_argument(
231 "--output_path",
232 required=True,
233 help="Path to the output file. Accepted formats: ent, fa, fasta, gro, inp, mcif, mdl, mmcif, mol, mol2, pdb, pdbqt, png, sdf, smi, smiles, txt.",
234 )
236 args = parser.parse_args()
237 args.config = args.config or "{}"
238 properties = settings.ConfReader(config=args.config).get_prop_dic()
240 # Specific call of each building block
241 babel_remove_hydrogens(
242 input_path=args.input_path, output_path=args.output_path, properties=properties
243 )
246if __name__ == "__main__":
247 main()