(git:97501a3)
Loading...
Searching...
No Matches
topology_pdb.F
Go to the documentation of this file.
1!--------------------------------------------------------------------------------------------------!
2! CP2K: A general program to perform molecular dynamics simulations !
3! Copyright 2000-2025 CP2K developers group <https://cp2k.org> !
4! !
5! SPDX-License-Identifier: GPL-2.0-or-later !
6!--------------------------------------------------------------------------------------------------!
7
8! **************************************************************************************************
9!> \brief Handles PDB files
10!>
11!> PDB Format Description Version 2.2 from http://www.rcsb.org
12!> COLUMNS DATA TYPE FIELD DEFINITION
13!>
14!> 1 - 6 Record name "ATOM "
15!> 7 - 11 Integer serial Atom serial number.
16!> 13 - 16 Atom name Atom name.
17!> 17 Character altLoc Alternate location indicator.
18!> 18 - 20 Residue name resName Residue name.
19!> 22 Character chainID Chain identifier.
20!> 23 - 26 Integer resSeq Residue sequence number.
21!> 27 AChar iCode Code for insertion of residues.
22!> 31 - 38 Real(8.3) x Orthogonal coordinates for X in
23!> Angstroms.
24!> 39 - 46 Real(8.3) y Orthogonal coordinates for Y in
25!> Angstroms.
26!> 47 - 54 Real(8.3) z Orthogonal coordinates for Z in
27!> Angstroms.
28!> 55 - 60 Real(6.2) occupancy Occupancy.
29!> 61 - 66 Real(6.2) tempFactor Temperature factor.
30!> 73 - 76 LString(4) segID Segment identifier, left-justified.
31!> 77 - 78 LString(2) element Element symbol, right-justified.
32!> 79 - 80 LString(2) charge Charge on the atom.
33!>
34!> 81 - Real(*) Charge Ext. This last field is an extenstion to
35!> standard PDB to provide a full charge
36!> without limitation of digits.
37!>
38!> 1 - 6 Record name "CRYST1"
39!> 7 - 15 Real(9.3) a (Angstroms)
40!> 16 - 24 Real(9.3) b (Angstroms)
41!> 25 - 33 Real(9.3) c (Angstroms)
42!> 34 - 40 Real(7.2) alpha (degrees)
43!> 41 - 47 Real(7.2) beta (degrees)
44!> 48 - 54 Real(7.2) gamma (degrees)
45!> 56 - 66 LString Space group
46!> 67 - 70 Integer Z value
47! **************************************************************************************************
49 USE cell_types, ONLY: get_cell
50 USE cp2k_info, ONLY: compile_revision,&
63 USE cp_units, ONLY: cp_unit_to_cp2k
69 USE kinds, ONLY: default_path_length,&
71 dp
72 USE machine, ONLY: m_timestamp,&
76 USE physcon, ONLY: angstrom
78 USE string_table, ONLY: id2str,&
79 s2s,&
80 str2id
83#include "./base/base_uses.f90"
84
85 IMPLICIT NONE
86
87 CHARACTER(len=*), PARAMETER, PRIVATE :: moduleN = 'topology_pdb'
88
89 PRIVATE
91
92CONTAINS
93
94! **************************************************************************************************
95!> \brief ...
96!> \param topology ...
97!> \param para_env ...
98!> \param subsys_section ...
99!> \par History
100!> TLAINO 05.2004 - Added the TER option to use different non-bonded molecules
101! **************************************************************************************************
102 SUBROUTINE read_coordinate_pdb(topology, para_env, subsys_section)
104 TYPE(mp_para_env_type), POINTER :: para_env
105 TYPE(section_vals_type), POINTER :: subsys_section
106
107 CHARACTER(len=*), PARAMETER :: routinen = 'read_coordinate_pdb'
108 INTEGER, PARAMETER :: nblock = 1000
109
110 CHARACTER(LEN=default_path_length) :: line
111 CHARACTER(LEN=default_string_length) :: record, root_mol_name, strtmp
112 INTEGER :: handle, id0, inum_mol, istat, iw, natom, &
113 newsize
114 LOGICAL :: my_end
115 REAL(kind=dp) :: pfactor
116 TYPE(atom_info_type), POINTER :: atom_info
117 TYPE(cp_logger_type), POINTER :: logger
118 TYPE(cp_parser_type) :: parser
119
120 NULLIFY (logger)
121 logger => cp_get_default_logger()
122 iw = cp_print_key_unit_nr(logger, subsys_section, "PRINT%TOPOLOGY_INFO/PDB_INFO", &
123 extension=".subsysLog")
124 CALL timeset(routinen, handle)
125
126 pfactor = section_get_rval(subsys_section, "TOPOLOGY%MEMORY_PROGRESSION_FACTOR")
127 atom_info => topology%atom_info
128 CALL reallocate(atom_info%id_molname, 1, nblock)
129 CALL reallocate(atom_info%id_resname, 1, nblock)
130 CALL reallocate(atom_info%resid, 1, nblock)
131 CALL reallocate(atom_info%id_atmname, 1, nblock)
132 CALL reallocate(atom_info%r, 1, 3, 1, nblock)
133 CALL reallocate(atom_info%atm_mass, 1, nblock)
134 CALL reallocate(atom_info%atm_charge, 1, nblock)
135 CALL reallocate(atom_info%occup, 1, nblock)
136 CALL reallocate(atom_info%beta, 1, nblock)
137 CALL reallocate(atom_info%id_element, 1, nblock)
138
139 IF (iw > 0) THEN
140 WRITE (unit=iw, fmt="(T2,A)") &
141 "BEGIN of PDB data read from file "//trim(topology%coord_file_name)
142 END IF
143
144 id0 = str2id(s2s(""))
145 topology%molname_generated = .false.
146
147 CALL parser_create(parser, topology%coord_file_name, para_env=para_env)
148
149 natom = 0
150 inum_mol = 1
151 WRITE (unit=root_mol_name, fmt='(A3,I0)') "MOL", inum_mol
152 DO
153 line = ""
154 CALL parser_get_next_line(parser, 1, at_end=my_end)
155 IF (my_end) EXIT
156 line = parser%input_line(1:default_path_length)
157 record = line(1:6)
158 record = trim(record)
159
160 IF ((record == "ATOM") .OR. (record == "HETATM")) THEN
161 natom = natom + 1
162 topology%natoms = natom
163 IF (natom > SIZE(atom_info%id_atmname)) THEN
164 newsize = int(pfactor*natom)
165 CALL reallocate(atom_info%id_molname, 1, newsize)
166 CALL reallocate(atom_info%id_resname, 1, newsize)
167 CALL reallocate(atom_info%resid, 1, newsize)
168 CALL reallocate(atom_info%id_atmname, 1, newsize)
169 CALL reallocate(atom_info%r, 1, 3, 1, newsize)
170 CALL reallocate(atom_info%atm_mass, 1, newsize)
171 CALL reallocate(atom_info%atm_charge, 1, newsize)
172 CALL reallocate(atom_info%occup, 1, newsize)
173 CALL reallocate(atom_info%beta, 1, newsize)
174 CALL reallocate(atom_info%id_element, 1, newsize)
175 END IF
176 END IF
177
178 SELECT CASE (record)
179 CASE ("ATOM", "HETATM")
180 READ (unit=line(13:16), fmt=*) strtmp
181 atom_info%id_atmname(natom) = str2id(s2s(strtmp))
182 READ (unit=line(18:20), fmt=*, iostat=istat) strtmp
183 IF (istat == 0) THEN
184 atom_info%id_resname(natom) = str2id(s2s(strtmp))
185 ELSE
186 atom_info%id_resname(natom) = id0
187 END IF
188 READ (unit=line(23:26), fmt=*, iostat=istat) atom_info%resid(natom)
189 READ (unit=line(31:38), fmt=*, iostat=istat) atom_info%r(1, natom)
190 READ (unit=line(39:46), fmt=*, iostat=istat) atom_info%r(2, natom)
191 READ (unit=line(47:54), fmt=*, iostat=istat) atom_info%r(3, natom)
192 READ (unit=line(55:60), fmt=*, iostat=istat) atom_info%occup(natom)
193 READ (unit=line(61:66), fmt=*, iostat=istat) atom_info%beta(natom)
194 READ (unit=line(73:76), fmt=*, iostat=istat) strtmp
195 IF (istat == 0) THEN
196 atom_info%id_molname(natom) = str2id(s2s(strtmp))
197 ELSE
198 atom_info%id_molname(natom) = str2id(s2s(root_mol_name))
199 topology%molname_generated = .true.
200 END IF
201 READ (unit=line(77:78), fmt=*, iostat=istat) strtmp
202 IF (istat == 0) THEN
203 atom_info%id_element(natom) = str2id(s2s(strtmp))
204 ELSE
205 atom_info%id_element(natom) = id0
206 END IF
207 atom_info%atm_mass(natom) = 0.0_dp
208 atom_info%atm_charge(natom) = -huge(0.0_dp)
209 IF (topology%charge_occup) atom_info%atm_charge(natom) = atom_info%occup(natom)
210 IF (topology%charge_beta) atom_info%atm_charge(natom) = atom_info%beta(natom)
211 IF (topology%charge_extended) THEN
212 READ (unit=line(81:), fmt=*, iostat=istat) atom_info%atm_charge(natom)
213 END IF
214
215 IF (atom_info%id_element(natom) == id0) THEN
216 ! Element is assigned on the basis of the atm_name
217 topology%aa_element = .true.
218 atom_info%id_element(natom) = atom_info%id_atmname(natom)
219 END IF
220
221 IF (iw > 0) THEN
222 WRITE (unit=iw, fmt="(A6,I5,T13,A4,T18,A3,T23,I4,T31,3F8.3,T73,A4,T77,A2)") &
223 record, natom, &
224 trim(id2str(atom_info%id_atmname(natom))), &
225 trim(id2str(atom_info%id_resname(natom))), &
226 atom_info%resid(natom), &
227 atom_info%r(1, natom), &
228 atom_info%r(2, natom), &
229 atom_info%r(3, natom), &
230 adjustl(trim(id2str(atom_info%id_molname(natom)))), &
231 adjustr(trim(id2str(atom_info%id_element(natom))))
232 END IF
233 atom_info%r(1, natom) = cp_unit_to_cp2k(atom_info%r(1, natom), "angstrom")
234 atom_info%r(2, natom) = cp_unit_to_cp2k(atom_info%r(2, natom), "angstrom")
235 atom_info%r(3, natom) = cp_unit_to_cp2k(atom_info%r(3, natom), "angstrom")
236 CASE ("TER")
237 inum_mol = inum_mol + 1
238 WRITE (unit=root_mol_name, fmt='(A3,I0)') "MOL", inum_mol
239 CASE ("REMARK")
240 IF (iw > 0) WRITE (unit=iw, fmt=*) trim(line)
241 CASE ("END")
242 EXIT
243 CASE DEFAULT
244 END SELECT
245 END DO
246 CALL parser_release(parser)
247
248 CALL reallocate(atom_info%id_molname, 1, natom)
249 CALL reallocate(atom_info%id_resname, 1, natom)
250 CALL reallocate(atom_info%resid, 1, natom)
251 CALL reallocate(atom_info%id_atmname, 1, natom)
252 CALL reallocate(atom_info%r, 1, 3, 1, natom)
253 CALL reallocate(atom_info%atm_mass, 1, natom)
254 CALL reallocate(atom_info%atm_charge, 1, natom)
255 CALL reallocate(atom_info%occup, 1, natom)
256 CALL reallocate(atom_info%beta, 1, natom)
257 CALL reallocate(atom_info%id_element, 1, natom)
258
259 IF (topology%conn_type /= do_conn_user) THEN
260 IF (.NOT. topology%para_res) atom_info%resid(:) = 1
261 END IF
262
263 IF (iw > 0) THEN
264 WRITE (unit=iw, fmt="(T2,A)") &
265 "END of PDB data read from file "//trim(topology%coord_file_name)
266 END IF
267
268 topology%natoms = natom
269 CALL cp_print_key_finished_output(iw, logger, subsys_section, &
270 "PRINT%TOPOLOGY_INFO/PDB_INFO")
271 CALL timestop(handle)
272
273 END SUBROUTINE read_coordinate_pdb
274
275! **************************************************************************************************
276!> \brief ...
277!> \param file_unit ...
278!> \param topology ...
279!> \param subsys_section ...
280! **************************************************************************************************
281 SUBROUTINE write_coordinate_pdb(file_unit, topology, subsys_section)
282
283 INTEGER, INTENT(IN) :: file_unit
285 TYPE(section_vals_type), POINTER :: subsys_section
286
287 CHARACTER(len=*), PARAMETER :: routinen = 'write_coordinate_pdb'
288
289 CHARACTER(LEN=120) :: line
290 CHARACTER(LEN=default_path_length) :: record
291 CHARACTER(LEN=default_string_length) :: my_tag1, my_tag2, my_tag3, my_tag4
292 CHARACTER(LEN=timestamp_length) :: timestamp
293 INTEGER :: handle, i, id1, id2, idres, iw, natom
294 LOGICAL :: charge_beta, charge_extended, &
295 charge_occup, ldum
296 REAL(kind=dp) :: angle_alpha, angle_beta, angle_gamma
297 REAL(kind=dp), DIMENSION(3) :: abc
298 TYPE(atom_info_type), POINTER :: atom_info
299 TYPE(cp_logger_type), POINTER :: logger
300 TYPE(section_vals_type), POINTER :: print_key
301
302 NULLIFY (logger)
303 logger => cp_get_default_logger()
304 iw = cp_print_key_unit_nr(logger, subsys_section, "PRINT%TOPOLOGY_INFO/PDB_INFO", &
305 extension=".subsysLog")
306 print_key => section_vals_get_subs_vals(subsys_section, "TOPOLOGY%DUMP_PDB")
307 CALL timeset(routinen, handle)
308
309 CALL section_vals_val_get(print_key, "CHARGE_OCCUP", l_val=charge_occup)
310 CALL section_vals_val_get(print_key, "CHARGE_BETA", l_val=charge_beta)
311 CALL section_vals_val_get(print_key, "CHARGE_EXTENDED", l_val=charge_extended)
312 i = count((/charge_occup, charge_beta, charge_extended/))
313 IF (i > 1) &
314 cpabort("Either only CHARGE_OCCUP, CHARGE_BETA, or CHARGE_EXTENDED can be selected")
315
316 atom_info => topology%atom_info
317 record = cp_print_key_generate_filename(logger, print_key, &
318 extension=".pdb", &
319 my_local=.false.)
320
321 IF (iw > 0) WRITE (unit=iw, fmt=*) " Writing out PDB file ", trim(record)
322
323 ! Write file header
324 CALL m_timestamp(timestamp)
325 WRITE (unit=file_unit, fmt="(A6,T11,A)") &
326 "TITLE ", "PDB file created by "//trim(cp2k_version)//" (revision "//trim(compile_revision)//")", &
327 "AUTHOR", trim(r_user_name)//"@"//trim(r_host_name)//" "//timestamp(:19)
328 ! Write cell information
329 CALL get_cell(cell=topology%cell, alpha=angle_alpha, beta=angle_beta, gamma=angle_gamma, abc=abc)
330 WRITE (unit=file_unit, fmt="(A6,3F9.3,3F7.2)") &
331 "CRYST1", abc(1:3)*angstrom, angle_alpha, angle_beta, angle_gamma
332
333 natom = topology%natoms
334 idres = 0
335 id1 = 0
336 id2 = 0
337
338 DO i = 1, natom
339
340 IF (topology%para_res) THEN
341 idres = atom_info%resid(i)
342 ELSE
343 IF ((id1 /= atom_info%map_mol_num(i)) .OR. (id2 /= atom_info%map_mol_typ(i))) THEN
344 idres = idres + 1
345 id1 = atom_info%map_mol_num(i)
346 id2 = atom_info%map_mol_typ(i)
347 END IF
348 END IF
349
350 line = ""
351 my_tag1 = id2str(atom_info%id_atmname(i)); ldum = qmmm_ff_precond_only_qm(my_tag1)
352 my_tag2 = id2str(atom_info%id_resname(i)); ldum = qmmm_ff_precond_only_qm(my_tag2)
353 my_tag3 = id2str(atom_info%id_molname(i)); ldum = qmmm_ff_precond_only_qm(my_tag3)
354 my_tag4 = id2str(atom_info%id_element(i)); ldum = qmmm_ff_precond_only_qm(my_tag4)
355
356 WRITE (unit=line(1:6), fmt="(A6)") "ATOM "
357 WRITE (unit=line(7:11), fmt="(I5)") modulo(i, 100000)
358 WRITE (unit=line(13:16), fmt="(A4)") adjustl(my_tag1(1:4))
359 WRITE (unit=line(18:20), fmt="(A3)") trim(my_tag2)
360 WRITE (unit=line(23:26), fmt="(I4)") modulo(idres, 10000)
361 WRITE (unit=line(31:54), fmt="(3F8.3)") atom_info%r(1:3, i)*angstrom
362 IF (ASSOCIATED(atom_info%occup)) THEN
363 WRITE (unit=line(55:60), fmt="(F6.2)") atom_info%occup(i)
364 ELSE
365 WRITE (unit=line(55:60), fmt="(F6.2)") 0.0_dp
366 END IF
367 IF (ASSOCIATED(atom_info%beta)) THEN
368 WRITE (unit=line(61:66), fmt="(F6.2)") atom_info%beta(i)
369 ELSE
370 WRITE (unit=line(61:66), fmt="(F6.2)") 0.0_dp
371 END IF
372 IF (ASSOCIATED(atom_info%atm_charge)) THEN
373 IF (any((/charge_occup, charge_beta, charge_extended/)) .AND. &
374 (atom_info%atm_charge(i) == -huge(0.0_dp))) &
375 cpabort("No atomic charges found yet (after the topology setup)")
376 IF (charge_occup) THEN
377 WRITE (unit=line(55:60), fmt="(F6.2)") atom_info%atm_charge(i)
378 ELSE IF (charge_beta) THEN
379 WRITE (unit=line(61:66), fmt="(F6.2)") atom_info%atm_charge(i)
380 ELSE IF (charge_extended) THEN
381 WRITE (unit=line(81:), fmt="(F20.16)") atom_info%atm_charge(i)
382 ELSE
383 ! Write no atomic charge
384 END IF
385 END IF
386 WRITE (unit=line(73:76), fmt="(A4)") adjustl(my_tag3)
387 WRITE (unit=line(77:78), fmt="(A2)") trim(my_tag4)
388 WRITE (unit=file_unit, fmt="(A)") trim(line)
389 END DO
390 WRITE (unit=file_unit, fmt="(A3)") "END"
391
392 IF (iw > 0) WRITE (unit=iw, fmt=*) " Exiting "//routinen
393
394 CALL cp_print_key_finished_output(iw, logger, subsys_section, &
395 "PRINT%TOPOLOGY_INFO/PDB_INFO")
396
397 CALL timestop(handle)
398
399 END SUBROUTINE write_coordinate_pdb
400
401END MODULE topology_pdb
static GRID_HOST_DEVICE int modulo(int a, int m)
Equivalent of Fortran's MODULO, which always return a positive number. https://gcc....
Handles all functions related to the CELL.
Definition cell_types.F:15
subroutine, public get_cell(cell, alpha, beta, gamma, deth, orthorhombic, abc, periodic, h, h_inv, symmetry_id, tag)
Get informations about a simulation cell.
Definition cell_types.F:195
some minimal info about CP2K, including its version and license
Definition cp2k_info.F:16
character(len=default_string_length), public r_host_name
Definition cp2k_info.F:68
character(len= *), parameter, public compile_revision
Definition cp2k_info.F:39
character(len= *), parameter, public cp2k_version
Definition cp2k_info.F:43
character(len=default_string_length), public r_user_name
Definition cp2k_info.F:68
various routines to log and control the output. The idea is that decisions about where to log should ...
type(cp_logger_type) function, pointer, public cp_get_default_logger()
returns the default logger
routines to handle the output, The idea is to remove the decision of wheter to output and what to out...
integer function, public cp_print_key_unit_nr(logger, basis_section, print_key_path, extension, middle_name, local, log_filename, ignore_should_output, file_form, file_position, file_action, file_status, do_backup, on_file, is_new_file, mpi_io, fout)
...
character(len=default_path_length) function, public cp_print_key_generate_filename(logger, print_key, middle_name, extension, my_local)
Utility function that returns a unit number to write the print key. Might open a file with a unique f...
subroutine, public cp_print_key_finished_output(unit_nr, logger, basis_section, print_key_path, local, ignore_should_output, on_file, mpi_io)
should be called after you finish working with a unit obtained with cp_print_key_unit_nr,...
Utility routines to read data from files. Kept as close as possible to the old parser because.
subroutine, public parser_get_next_line(parser, nline, at_end)
Read the next input line and broadcast the input information. Skip (nline-1) lines and skip also all ...
Utility routines to read data from files. Kept as close as possible to the old parser because.
subroutine, public parser_release(parser)
releases the parser
subroutine, public parser_create(parser, file_name, unit_nr, para_env, end_section_label, separator_chars, comment_char, continuation_char, quote_char, section_char, parse_white_lines, initial_variables, apply_preprocessing)
Start a parser run. Initial variables allow to @SET stuff before opening the file.
unit conversion facility
Definition cp_units.F:30
real(kind=dp) function, public cp_unit_to_cp2k(value, unit_str, defaults, power)
converts to the internal cp2k units to the given unit
Definition cp_units.F:1149
Calculation of the incomplete Gamma function F_n(t) for multi-center integrals over Cartesian Gaussia...
Definition gamma.F:15
collects all constants needed in input so that they can be used without circular dependencies
integer, parameter, public do_conn_user
objects that represent the structure of input sections and the data contained in an input section
real(kind=dp) function, public section_get_rval(section_vals, keyword_name)
...
recursive type(section_vals_type) function, pointer, public section_vals_get_subs_vals(section_vals, subsection_name, i_rep_section, can_return_null)
returns the values of the requested subsection
subroutine, public section_vals_val_get(section_vals, keyword_name, i_rep_section, i_rep_val, n_rep_val, val, l_val, i_val, r_val, c_val, l_vals, i_vals, r_vals, c_vals, explicit)
returns the requested value
Defines the basic variable types.
Definition kinds.F:23
integer, parameter, public dp
Definition kinds.F:34
integer, parameter, public default_string_length
Definition kinds.F:57
integer, parameter, public default_path_length
Definition kinds.F:58
Machine interface based on Fortran 2003 and POSIX.
Definition machine.F:17
integer, parameter, public timestamp_length
Definition machine.F:53
subroutine, public m_timestamp(timestamp)
Returns a human readable timestamp.
Definition machine.F:380
Utility routines for the memory handling.
Interface to the message passing library MPI.
Definition of physical constants:
Definition physcon.F:68
real(kind=dp), parameter, public angstrom
Definition physcon.F:144
logical function, public qmmm_ff_precond_only_qm(id1, id2, id3, id4, is_link)
This function handles the atom names and modifies the "_QM_" prefix, in order to find the parameters ...
generates a unique id number for a string (str2id) that can be used two compare two strings....
character(len=default_string_length) function, public s2s(str)
converts a string in a string of default_string_length
integer function, public str2id(str)
returns a unique id for a given string, and stores the string for later retrieval using the id.
character(len=default_string_length) function, public id2str(id)
returns the string associated with a given id
Handles PDB files.
subroutine, public write_coordinate_pdb(file_unit, topology, subsys_section)
...
subroutine, public read_coordinate_pdb(topology, para_env, subsys_section)
...
Control for reading in different topologies and coordinates.
Definition topology.F:13
type of a logger, at the moment it contains just a print level starting at which level it should be l...
stores all the informations relevant to an mpi environment