Coverage for biobb_amber/leap/leap_gen_top.py: 57%
137 statements
« prev ^ index » next coverage.py v7.6.10, created at 2025-01-28 08:28 +0000
1#!/usr/bin/env python3
3"""Module containing the LeapGenTop class and the command line interface."""
5import os
6import argparse
7from pathlib import PurePath
8from typing import List, Optional
10from biobb_common.configuration import settings
11from biobb_common.generic.biobb_object import BiobbObject
12from biobb_common.tools import file_utils as fu
13from biobb_common.tools.file_utils import launchlogger
15from biobb_amber.leap.common import _from_string_to_list
18class LeapGenTop(BiobbObject):
19 """
20 | biobb_amber.leap.leap_gen_top LeapGenTop
21 | Wrapper of the `AmberTools (AMBER MD Package) leap tool <https://ambermd.org/AmberTools.php>`_ module.
22 | Generates a MD topology from a molecule structure using tLeap tool from the AmberTools MD package.
24 Args:
25 input_pdb_path (str): Input 3D structure PDB file. File type: input. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/data/leap/structure.leapin.pdb>`_. Accepted formats: pdb (edam:format_1476).
26 input_lib_path (str) (Optional): Input ligand library parameters file. File type: input. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/data/leap/ligand.lib>`_. Accepted formats: lib (edam:format_3889), zip (edam:format_3987).
27 input_frcmod_path (str) (Optional): Input ligand frcmod parameters file. File type: input. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/data/leap/ligand.frcmod>`_. Accepted formats: frcmod (edam:format_3888), zip (edam:format_3987).
28 input_params_path (str) (Optional): Additional leap parameter files to load with loadAmberParams Leap command. File type: input. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/data/leap/frcmod.ionsdang_spce.txt>`_. Accepted formats: in (edam:format_2330), leapin (edam:format_2330), txt (edam:format_2330), zip (edam:format_3987).
29 input_prep_path (str) (Optional): Additional leap parameter files to load with loadAmberPrep Leap command. File type: input. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/data/leap/heme_all.in>`_. Accepted formats: in (edam:format_2330), leapin (edam:format_2330), txt (edam:format_2330), zip (edam:format_3987).
30 input_source_path (str) (Optional): Additional leap command files to load with source Leap command. File type: input. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/data/leap/leaprc.water.spce.txt>`_. Accepted formats: in (edam:format_2330), leapin (edam:format_2330), txt (edam:format_2330), zip (edam:format_3987).
31 output_pdb_path (str): Output 3D structure PDB file matching the topology file. File type: output. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/reference/leap/structure.leap.pdb>`_. Accepted formats: pdb (edam:format_1476).
32 output_top_path (str): Output topology file (AMBER ParmTop). File type: output. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/reference/leap/structure.leap.top>`_. Accepted formats: top (edam:format_3881), parmtop (edam:format_3881), prmtop (edam:format_3881).
33 output_crd_path (str): Output coordinates file (AMBER crd). File type: output. `Sample file <https://github.com/bioexcel/biobb_amber/raw/master/biobb_amber/test/reference/leap/structure.leap.crd>`_. Accepted formats: crd (edam:format_3878), mdcrd (edam:format_3878), inpcrd (edam:format_3878).
34 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
35 * **forcefield** (*list*) - (["protein.ff14SB","DNA.bsc1","gaff"]) Forcefields to be used for the structure generation. Each item should be either a path to a leaprc file or a string with the leaprc file name if the force field is included with Amber (e.g. "/path/to/leaprc.protein.ff14SB" or "protein.ff14SB"). Default values: ["protein.ff14SB","DNA.bsc1","gaff"].
36 * **binary_path** (*str*) - ("tleap") Path to the tleap executable binary.
37 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
38 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
39 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory.
40 * **container_path** (*str*) - (None) Container path definition.
41 * **container_image** (*str*) - ('afandiadib/ambertools:serial') Container image definition.
42 * **container_volume_path** (*str*) - ('/tmp') Container volume path definition.
43 * **container_working_dir** (*str*) - (None) Container working directory definition.
44 * **container_user_id** (*str*) - (None) Container user_id definition.
45 * **container_shell_path** (*str*) - ('/bin/bash') Path to default shell inside the container.
47 Examples:
48 This is a use example of how to use the building block from Python::
50 from biobb_amber.leap.leap_gen_top import leap_gen_top
51 prop = {
52 'forcefield': ['protein.ff14SB']
53 }
54 leap_gen_top(input_pdb_path='/path/to/structure.pdb',
55 output_pdb_path='/path/to/newStructure.pdb',
56 output_top_path='/path/to/newTopology.top',
57 output_crd_path='/path/to/newCoordinates.crd',
58 properties=prop)
60 Info:
61 * wrapped_software:
62 * name: AmberTools tLeap
63 * version: >20.9
64 * license: LGPL 2.1
65 * ontology:
66 * name: EDAM
67 * schema: http://edamontology.org/EDAM.owl
69 """
71 def __init__(
72 self,
73 input_pdb_path: str,
74 output_pdb_path: str,
75 output_top_path: str,
76 output_crd_path: str,
77 input_lib_path: Optional[str] = None,
78 input_frcmod_path: Optional[str] = None,
79 input_params_path: Optional[str] = None,
80 input_prep_path: Optional[str] = None,
81 input_source_path: Optional[str] = None,
82 properties: Optional[dict] = None,
83 **kwargs,
84 ):
85 properties = properties or {}
87 # Call parent class constructor
88 super().__init__(properties)
89 self.locals_var_dict = locals().copy()
91 # Input/Output files
92 self.io_dict = {
93 "in": {
94 "input_pdb_path": input_pdb_path,
95 "input_lib_path": input_lib_path,
96 "input_frcmod_path": input_frcmod_path,
97 "input_params_path": input_params_path,
98 "input_prep_path": input_prep_path,
99 "input_source_path": input_source_path,
100 },
101 "out": {
102 "output_pdb_path": output_pdb_path,
103 "output_top_path": output_top_path,
104 "output_crd_path": output_crd_path,
105 },
106 }
108 # # Ligand Parameter lists
109 # self.ligands_lib_list = []
110 # if input_lib_path:
111 # self.ligands_lib_list.append(input_lib_path)
112 #
113 # self.ligands_frcmod_list = []
114 # if input_frcmod_path:
115 # self.ligands_frcmod_list.append(input_frcmod_path)
117 # Set default forcefields
118 amber_home_path = os.getenv("AMBERHOME")
119 protein_ff14SB_path = os.path.join(amber_home_path, 'dat', 'leap', 'cmd', 'leaprc.protein.ff14SB')
120 dna_bsc1_path = os.path.join(amber_home_path, 'dat', 'leap', 'cmd', 'leaprc.DNA.bsc1')
121 gaff_path = os.path.join(amber_home_path, 'dat', 'leap', 'cmd', 'leaprc.gaff')
123 # Properties specific for BB
124 self.properties = properties
125 self.forcefield = _from_string_to_list(
126 properties.get("forcefield", [protein_ff14SB_path, dna_bsc1_path, gaff_path])
127 )
128 # Find the paths of the leaprc files if only the force field names are provided
129 self.forcefield = self.find_leaprc_paths(self.forcefield)
131 self.binary_path = properties.get("binary_path", "tleap")
133 # Check the properties
134 self.check_properties(properties)
135 self.check_arguments()
137 def find_leaprc_paths(self, forcefields: List[str]) -> List[str]:
138 """
139 Find the leaprc paths for the force fields provided.
141 For each item in the forcefields list, the function checks if the str is a path to an existing file.
142 If not, it tries to find the file in the $AMBERHOME/dat/leap/cmd/ directory or the $AMBERHOME/dat/leap/cmd/oldff/
143 directory with and without the leaprc prefix.
145 Args:
146 forcefields (List[str]): List of force fields to find the leaprc files for.
148 Returns:
149 List[str]: List of leaprc file paths.
150 """
152 leaprc_paths = []
154 for forcefield in forcefields:
156 num_paths = len(leaprc_paths)
158 # Check if the forcefield is a path to an existing file
159 if os.path.exists(forcefield):
160 leaprc_paths.append(forcefield)
161 continue
163 # Check if the forcefield is in the leaprc directory
164 leaprc_path = os.path.join(os.environ.get('AMBERHOME', ''), 'dat', 'leap', 'cmd', f"leaprc.{forcefield}")
165 if os.path.exists(leaprc_path):
166 leaprc_paths.append(leaprc_path)
167 continue
169 # Check if the forcefield is in the oldff directory
170 leaprc_path = os.path.join(os.environ.get('AMBERHOME', ''), 'dat', 'leap', 'cmd', 'oldff', f"leaprc.{forcefield}")
171 if os.path.exists(leaprc_path):
172 leaprc_paths.append(leaprc_path)
173 continue
175 # Check if the forcefield is in the leaprc directory without the leaprc prefix
176 leaprc_path = os.path.join(os.environ.get('AMBERHOME', ''), 'dat', 'leap', 'cmd', f"{forcefield}")
177 if os.path.exists(leaprc_path):
178 leaprc_paths.append(leaprc_path)
179 continue
181 # Check if the forcefield is in the oldff directory without the leaprc prefix
182 leaprc_path = os.path.join(os.environ.get('AMBERHOME', ''), 'dat', 'leap', 'cmd', 'oldff', f"{forcefield}")
183 if os.path.exists(leaprc_path):
184 leaprc_paths.append(leaprc_path)
185 continue
187 new_num_paths = len(leaprc_paths)
189 if new_num_paths == num_paths:
190 raise ValueError(f"Force field {forcefield} not found. Check the $AMBERHOME/dat/leap/cmd/ directory for available force fields or provide the path to an existing leaprc file.")
192 return leaprc_paths
194 # def check_data_params(self, out_log, err_log):
195 # """ Checks input/output paths correctness """
197 # # Check input(s)
198 # self.io_dict["in"]["input_pdb_path"] = check_input_path(self.io_dict["in"]["input_pdb_path"], "input_pdb_path", False, out_log, self.__class__.__name__)
199 # self.io_dict["in"]["input_lib_path"] = check_input_path(self.io_dict["in"]["input_lib_path"], "input_lib_path", True, out_log, self.__class__.__name__)
200 # self.io_dict["in"]["input_frcmod_path"] = check_input_path(self.io_dict["in"]["input_frcmod_path"], "input_frcmod_path", True, out_log, self.__class__.__name__)
201 # # self.io_dict["in"]["input_params_path"] = check_input_path(self.io_dict["in"]["input_params_path"], "input_params_path", True, out_log, self.__class__.__name__)
202 # # self.io_dict["in"]["input_prep_path"] = check_input_path(self.io_dict["in"]["input_params_path"], "input_params_path", True, out_log, self.__class__.__name__)
203 # # self.io_dict["in"]["input_source_path"] = check_input_path(self.io_dict["in"]["input_source_path"], "input_source_path", True, out_log, self.__class__.__name__)
205 # # Check output(s)
206 # self.io_dict["out"]["output_pdb_path"] = check_output_path(self.io_dict["out"]["output_pdb_path"], "output_pdb_path", False, out_log, self.__class__.__name__)
207 # self.io_dict["out"]["output_top_path"] = check_output_path(self.io_dict["out"]["output_top_path"], "output_top_path", False, out_log, self.__class__.__name__)
208 # self.io_dict["out"]["output_crd_path"] = check_output_path(self.io_dict["out"]["output_crd_path"], "output_crd_path", False, out_log, self.__class__.__name__)
210 @launchlogger
211 def launch(self):
212 """Launches the execution of the LeapGenTop module."""
214 # check input/output paths and parameters
215 # self.check_data_params(self.out_log, self.err_log)
217 # Setup Biobb
218 if self.check_restart():
219 return 0
220 self.stage_files()
222 # Creating temporary folder & Leap configuration (instructions) file
223 if self.container_path:
224 instructions_file = str(
225 PurePath(self.stage_io_dict["unique_dir"]).joinpath("leap.in")
226 )
227 instructions_file_path = str(
228 PurePath(self.container_volume_path).joinpath("leap.in")
229 )
230 self.tmp_folder = None
231 else:
232 self.tmp_folder = fu.create_unique_dir()
233 instructions_file = str(PurePath(self.tmp_folder).joinpath("leap.in"))
234 fu.log("Creating %s temporary folder" % self.tmp_folder, self.out_log)
235 instructions_file_path = instructions_file
237 ligands_lib_list = []
238 if self.io_dict["in"]["input_lib_path"] is not None:
239 if self.io_dict["in"]["input_lib_path"].endswith(".zip"):
240 ligands_lib_list = fu.unzip_list(
241 self.stage_io_dict["in"]["input_lib_path"],
242 dest_dir=self.tmp_folder,
243 out_log=self.out_log,
244 )
245 else:
246 ligands_lib_list.append(self.stage_io_dict["in"]["input_lib_path"])
248 ligands_frcmod_list = []
249 if self.io_dict["in"]["input_frcmod_path"] is not None:
250 if self.io_dict["in"]["input_frcmod_path"].endswith(".zip"):
251 ligands_frcmod_list = fu.unzip_list(
252 self.stage_io_dict["in"]["input_frcmod_path"],
253 dest_dir=self.tmp_folder,
254 out_log=self.out_log,
255 )
256 else:
257 ligands_frcmod_list.append(
258 self.stage_io_dict["in"]["input_frcmod_path"]
259 )
261 amber_params_list = []
262 if self.io_dict["in"]["input_params_path"] is not None:
263 if self.io_dict["in"]["input_params_path"].endswith(".zip"):
264 amber_params_list = fu.unzip_list(
265 self.stage_io_dict["in"]["input_params_path"],
266 dest_dir=self.tmp_folder,
267 out_log=self.out_log,
268 )
269 else:
270 amber_params_list.append(self.stage_io_dict["in"]["input_params_path"])
272 amber_prep_list = []
273 if self.io_dict["in"]["input_prep_path"] is not None:
274 if self.io_dict["in"]["input_prep_path"].endswith(".zip"):
275 amber_prep_list = fu.unzip_list(
276 self.stage_io_dict["in"]["input_prep_path"],
277 dest_dir=self.tmp_folder,
278 out_log=self.out_log,
279 )
280 else:
281 amber_prep_list.append(self.stage_io_dict["in"]["input_prep_path"])
283 leap_source_list = []
284 if self.io_dict["in"]["input_source_path"] is not None:
285 if self.io_dict["in"]["input_source_path"].endswith(".zip"):
286 leap_source_list = fu.unzip_list(
287 self.stage_io_dict["in"]["input_source_path"],
288 dest_dir=self.tmp_folder,
289 out_log=self.out_log,
290 )
291 else:
292 leap_source_list.append(self.stage_io_dict["in"]["input_source_path"])
294 with open(instructions_file, "w") as leapin:
295 # Forcefields loaded by default:
296 # Protein: ff14SB (PARM99 + frcmod.ff99SB + frcmod.parmbsc0 + OL3 for RNA)
297 # leapin.write("source leaprc.protein.ff14SB \n")
298 # DNA: parmBSC1 (ParmBSC1 (ff99 + bsc0 + bsc1) for DNA. Ivani et al. Nature Methods 13: 55, 2016)
299 # leapin.write("source leaprc.DNA.bsc1 \n")
300 # Ligands: GAFF (General Amber Force field, J. Comput. Chem. 2004 Jul 15;25(9):1157-74)
301 # leapin.write("source leaprc.gaff \n")
303 # Forcefields loaded from input forcefield property
304 for t in self.forcefield:
305 leapin.write("source {}\n".format(t))
307 # Additional Leap commands
308 for leap_commands in leap_source_list:
309 leapin.write("source " + leap_commands + "\n")
311 # Additional Amber parameters
312 for amber_params in amber_params_list:
313 leapin.write("loadamberparams " + amber_params + "\n")
315 # Additional Amber prep files
316 for amber_prep in amber_prep_list:
317 leapin.write("loadamberprep " + amber_prep + "\n")
319 # Ions libraries
320 leapin.write("loadOff atomic_ions.lib \n")
322 # Ligand(s) libraries (if any)
323 for amber_lib in ligands_lib_list:
324 leapin.write("loadOff " + amber_lib + "\n")
325 for amber_frcmod in ligands_frcmod_list:
326 leapin.write("loadamberparams " + amber_frcmod + "\n")
328 # Loading PDB file
329 leapin.write(
330 "mol = loadpdb " + self.stage_io_dict["in"]["input_pdb_path"] + " \n"
331 )
333 # Saving output PDB file, coordinates and topology
334 leapin.write(
335 "savepdb mol " + self.stage_io_dict["out"]["output_pdb_path"] + " \n"
336 )
337 leapin.write(
338 "saveAmberParm mol " + self.stage_io_dict["out"]["output_top_path"] + " " + self.stage_io_dict["out"]["output_crd_path"] + "\n"
339 )
340 leapin.write("quit \n")
342 # Command line
343 self.cmd = [self.binary_path, "-f", instructions_file_path]
345 # Run Biobb block
346 self.run_biobb()
348 # Copy files to host
349 self.copy_to_host()
351 # remove temporary folder(s)
352 self.tmp_files.extend([
353 # self.stage_io_dict.get("unique_dir", ""),
354 str(self.tmp_folder), "leap.log"
355 ])
356 self.remove_tmp_files()
358 self.check_arguments(output_files_created=True, raise_exception=False)
360 return self.return_code
363def leap_gen_top(
364 input_pdb_path: str,
365 output_pdb_path: str,
366 output_top_path: str,
367 output_crd_path: str,
368 input_lib_path: Optional[str] = None,
369 input_frcmod_path: Optional[str] = None,
370 input_params_path: Optional[str] = None,
371 input_prep_path: Optional[str] = None,
372 input_source_path: Optional[str] = None,
373 properties: Optional[dict] = None,
374 **kwargs,
375) -> int:
376 """Create :class:`LeapGenTop <leap.leap_gen_top.LeapGenTop>`leap.leap_gen_top.LeapGenTop class and
377 execute :meth:`launch() <leap.leap_gen_top.LeapGenTop.launch>` method"""
379 return LeapGenTop(
380 input_pdb_path=input_pdb_path,
381 input_lib_path=input_lib_path,
382 input_frcmod_path=input_frcmod_path,
383 input_params_path=input_params_path,
384 input_prep_path=input_prep_path,
385 input_source_path=input_source_path,
386 output_pdb_path=output_pdb_path,
387 output_top_path=output_top_path,
388 output_crd_path=output_crd_path,
389 properties=properties,
390 ).launch()
392 leap_gen_top.__doc__ = LeapGenTop.__doc__
395def main():
396 parser = argparse.ArgumentParser(
397 description="Generating a MD topology from a molecule structure using tLeap program from AmberTools MD package.",
398 formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999),
399 )
400 parser.add_argument("--config", required=False, help="Configuration file")
402 # Specific args
403 required_args = parser.add_argument_group("required arguments")
404 required_args.add_argument(
405 "--input_pdb_path",
406 required=True,
407 help="Input 3D structure PDB file. Accepted formats: pdb.",
408 )
409 required_args.add_argument(
410 "--input_lib_path",
411 required=False,
412 help="Input ligand library parameters file. Accepted formats: lib, zip.",
413 )
414 required_args.add_argument(
415 "--input_frcmod_path",
416 required=False,
417 help="Input ligand frcmod parameters file. Accepted formats: frcmod, zip.",
418 )
419 required_args.add_argument(
420 "--input_params_path",
421 required=False,
422 help="Additional leap parameter files to load with loadAmberParams Leap command. Accepted formats: leapin, in, txt, zip.",
423 )
424 required_args.add_argument(
425 "--input_prep_path",
426 required=False,
427 help="Additional leap parameter files to load with loadAmberPrep Leap command. Accepted formats: leapin, in, txt, zip.",
428 )
429 required_args.add_argument(
430 "--input_source_path",
431 required=False,
432 help="Additional leap command files to load with source Leap command. Accepted formats: leapin, in, txt, zip.",
433 )
434 required_args.add_argument(
435 "--output_pdb_path",
436 required=True,
437 help="Output 3D structure PDB file matching the topology file. Accepted formats: pdb.",
438 )
439 required_args.add_argument(
440 "--output_top_path",
441 required=True,
442 help="Output topology file (AMBER ParmTop). Accepted formats: top.",
443 )
444 required_args.add_argument(
445 "--output_crd_path",
446 required=True,
447 help="Output coordinates file (AMBER crd). Accepted formats: crd.",
448 )
450 args = parser.parse_args()
451 config = args.config if args.config else None
452 properties = settings.ConfReader(config=config).get_prop_dic()
454 # Specific call
455 leap_gen_top(
456 input_pdb_path=args.input_pdb_path,
457 input_lib_path=args.input_lib_path,
458 input_frcmod_path=args.input_frcmod_path,
459 input_params_path=args.input_params_path,
460 input_prep_path=args.input_prep_path,
461 input_source_path=args.input_source_path,
462 output_pdb_path=args.output_pdb_path,
463 output_top_path=args.output_top_path,
464 output_crd_path=args.output_crd_path,
465 properties=properties,
466 )
469if __name__ == "__main__":
470 main()