Coverage for mddb_workflow/utils/constants.py: 95%

1from os import environ

2from pathlib import Path

3from shutil import which

5# CONSTANTS ---------------------------------------------------------------------------

7# Set a custom globals dict

8# This way we can edit the value of a constant on runtime

9GLOBALS = {

10 # Set if symlinks are allowed

11 'no_symlinks': False,

12 # Set if colors are disabled for logging

13 'no_colors': False,

14}

16# Set the possible gromacs calls tried to find the gromacs executable in case it is not froced by the user

17GROMACS_EXECUTABLE_COMMON_NAMES = ['gmx', 'gmx_mpi']

18# Set the name of the environmental variable which is read by the workflow to know the gromacs path

19GROMACS_ENV = 'MWF_GMX'

20# Set the gromacs executable path

21# This may be forced by the user thorugh an enviornment variable

22GROMACS_EXECUTABLE = environ.get(GROMACS_ENV, None)

23# Otherwise we try with the known common gromacs executable names until we find an existing one

24if not GROMACS_EXECUTABLE:

25 for common_name in GROMACS_EXECUTABLE_COMMON_NAMES:

26 if which(common_name):

27 GROMACS_EXECUTABLE = common_name

28 break

29# If we do not find it then complain

30if not GROMACS_EXECUTABLE:

31 raise RuntimeError(f'Cannot find gromacs. Is gromacs installed? Set the env variable {GROMACS_ENV} as the gromacs executable path')

33# List typical text editor and their commands

34TEXT_EDITORS = {

35 'VIM': 'vim',

36 'GNU nano': 'nano',

37 'GNOME text editor': 'gedit',

38 'VScode': 'code',

39}

40# Keep only those editor which are already installed

41AVAILABLE_TEXT_EDITORS = { name: command for name, command in TEXT_EDITORS.items() if which(command) }

43# Set dates format

44DATE_STYLE = '%d-%m-%Y %H:%M:%S'

46# Database

47DEFAULT_API_URL = 'https://irb-dev.mddbr.eu/api/'

49# Selections

50# Set a standard selection for protein and nucleic acid backbones in vmd syntax

51ALL_ATOMS = 'all'

52PROTEIN_AND_NUCLEIC = 'protein or nucleic'

53PROTEIN_AND_NUCLEIC_BACKBONE = "(protein and name N CA C) or (nucleic and name P O5' O3' C5' C4' C3')"

55# Inputs file

56DEFAULT_INPUTS_FILENAME = 'inputs.yaml'

57ACCEPTED_INPUT_FILENAMES = [

58 DEFAULT_INPUTS_FILENAME, # The default

59 'inputs.yml', # Another extension of yaml files

60 'inputs.json' # Legacy inputs file

61]

63# Default input values used when the value is not specified

64# If an input field has no default value then it will be set as None

65DEFAULT_INPUT_VALUES = {

66 'license': 'This trajectory dataset is released under a Creative Commons Attribution 4.0 International Public License',

67 'linkcense': 'https://creativecommons.org/licenses/by/4.0/',

68 'mdref': 0,

69}

71# Resource files which are always part of the workflow

72RESOURCES_DIRECTORY_PATH = resources = str(Path(__file__).parent.parent / "resources")

73INPUTS_TEMPLATE_FILEPATH = f'{RESOURCES_DIRECTORY_PATH}/inputs_file_template.yml'

74NASSA_TEMPLATE_FILEPATH = f'{RESOURCES_DIRECTORY_PATH}/nassa_template.yml'

75GROMACS_CUSTOM_MASSES_FILEPATH = f'{RESOURCES_DIRECTORY_PATH}/atommass.dat'

76CMIP_INPUTS_CHECKONLY_SOURCE = f'{RESOURCES_DIRECTORY_PATH}/cmip_check.in'

77CMIP_INPUTS_SOURCE = f'{RESOURCES_DIRECTORY_PATH}/cmip.in'

78CMIP_VDW_SOURCE = f'{RESOURCES_DIRECTORY_PATH}/vdwprm'

79ENERGIES_DEBUG_SCRIPT_SOURCE = f'{RESOURCES_DIRECTORY_PATH}/get_energies_sum.py'

81# Expected MD inputs

82MD_DIRECTORY = 'mdir'

84# Input config file for the NASSA analysis

85DEFAULT_NASSA_CONFIG_FILENAME = 'nassa.json'

87# Markov State Model input filenames

88DEFAULT_POPULATIONS_FILENAME = 'populations.json'

89DEFAULT_TRANSITIONS_FILENAME = 'transitions.json'

91# An old system for when original topology is very wrong and charges must be provided manually

92RAW_CHARGES_FILENAME = 'charges.txt'

93# Accepted topology formats for atomic charges mining

94ACCEPTED_TOPOLOGY_FORMATS = ['tpr', 'top', 'psf', 'prmtop', 'prm7']

96# Input files processing intermediate steps

97# We name differenlty every intermediate file and we never rename/overwrite any input or intermediate file

98# This allows us to know where we were in case the process was interrupted and not repeat steps on reset

99# Intermediate files are removed at the end of the process if it was successful

100

101INCOMPLETE_PREFIX = 'incomplete_'

102

103CONVERTED = 'converted'

104CONVERTED_STRUCTURE = 'converted.pdb'

105CONVERTED_TRAJECTORY = 'converted.xtc'

106

107FILTERED = 'filtered'

108FILTERED_STRUCTURE = 'filtered.pdb'

109FILTERED_TRAJECTORY = 'filtered.xtc'

110

111IMAGED = 'imaged'

112IMAGED_STRUCTURE = 'imaged.pdb'

113IMAGED_TRAJECTORY = 'imaged.xtc'

114

115CORRECTED = 'corrected'

116CORRECTED_STRUCTURE = 'corrected.pdb'

117CORRECTED_TRAJECTORY = 'corrected.xtc'

118

119# Output core files

120STANDARD_TOPOLOGY_FILENAME = 'topology.json'

121STRUCTURE_FILENAME = 'structure.pdb'

122TRAJECTORY_FILENAME = 'trajectory.xtc'

123

124# Auxiliar files

125REGISTER_FILENAME = '.register.json'

126CACHE_FILENAME = '.mwf_cache.json'

127

128# Files saving resorted bonds and charges when we have to resort atoms

129# Note that these files have priority when loading both bonds and charges

130RESORTED_CHARGES_FILENAME = 'resorted_charges.json'

131RESORTED_BONDS_FILENAME = 'resorted_bonds.json'

132

133# Set generated file names

134FIRST_FRAME_FILENAME = 'first_frame.pdb'

135AVERAGE_STRUCTURE_FILENAME = 'average.pdb'

136

137# Set the reference labels according to the reference file used

138REFERENCE_LABELS = {

139 FIRST_FRAME_FILENAME: 'firstframe',

140 AVERAGE_STRUCTURE_FILENAME: 'average'

141}

142

143# Set output files generated to be uploaded to the database

144

145# Set the PDB (Protein Data Bank) references filename

146PDB_REFERENCES_FILENAME = 'pdb_references.json'

147# Set the protein references filename

148PROTEIN_REFERENCES_FILENAME = 'protein_references.json'

149# Set the InChIKey references filename

150INCHIKEY_REFERENCES_FILENAME = 'inchikey_references.json'

151

152# Set the chains filename

153OUTPUT_CHAINS_FILENAME = 'chains.json'

154

155# Set the metadata filename

156OUTPUT_METADATA_FILENAME = 'metadata.json'

157

158# Set the screenshot filename

159OUTPUT_SCREENSHOT_FILENAME = 'mdf.screenshot.jpg'

160

161# Additional screenshot filenames

162OUTPUT_CLUSTER_SCREENSHOT_FILENAMES = 'mdf.clusters_*_screenshot_??.jpg'

163

164# Set analyses files to be generated

165OUTPUT_INTERACTIONS_FILENAME = 'mda.interactions.json'

166OUTPUT_RMSDS_FILENAME = 'mda.rmsds.json'

167OUTPUT_TMSCORES_FILENAME = 'mda.tmscores.json'

168OUTPUT_RMSF_FILENAME = 'mda.fluctuation.json'

169OUTPUT_RGYR_FILENAME = 'mda.rgyr.json'

170OUTPUT_PCA_FILENAME = 'mda.pca.json'

171OUTPUT_PCA_PROJECTION_PREFIX = 'mdt.pca_trajectory'

172OUTPUT_PCA_CONTACTS_FILENAME = 'mda.pca_contacts.json'

173OUTPUT_RMSD_PERRES_FILENAME = 'mda.rmsd_perres.json'

174OUTPUT_RMSD_PAIRWISE_FILENAME = 'mda.rmsd_pairwise.json'

175OUTPUT_CLUSTERS_FILENAME = 'mda.clusters.json'

176OUTPUT_DIST_PERRES_FILENAME = 'mda.dist_perres.json'

177OUTPUT_HBONDS_FILENAME = 'mda.hbonds.json'

178OUTPUT_SASA_FILENAME = 'mda.sasa.json'

179OUTPUT_ENERGIES_FILENAME = 'mda.energies.json'

180OUTPUT_DIHEDRAL_ENERGIES_FILENAME = 'mda.dihenergies.json'

181OUTPUT_POCKETS_FILENAME = 'mda.pockets.json'

182OUTPUT_POCKET_STRUCTURES_PREFIX = 'mdf.pocket' # WARNING: If this is changed then the pockets function must be updated as well

183OUTPUT_HELICAL_PARAMETERS_FILENAME = 'mda.helical.json'

184OUTPUT_MARKOV_FILENAME = 'mda.markov.json'

185OUTPUT_PROVENANCE_FILENAME = 'mda.provenance.json'

186MEMBRANE_MAPPING_FILENAME = 'mda.mem_map.json'

187OUTPUT_DENSITY_FILENAME = 'mda.density.json'

188OUTPUT_THICKNESS_FILENAME = 'mda.thickness.json'

189OUTPUT_APL_FILENAME = 'mda.apl.json'

190OUTPUT_LIPID_ORDER_FILENAME = 'mda.lipid_order.json'

191OUTPUT_LIPID_INTERACTIONS_FILENAME = 'mda.lipid_inter.json'

192OUTPUT_CHANNELS_FILENAME = 'mda.channels.json'

193

194# Set problematic signs for directory/folder names

195# º is forbidden since paths including this characters are not readable by MDtraj

196FORBIDDEN_DIRECTORY_CHARACTERS = ['.', ',', ';', ':', 'º', '/']

197

198# Default parameters

199DEFAULT_RMSD_CUTOFF = 9

200DEFAULT_INTERACTION_CUTOFF = 0.1

201

202# Set register cache flags

203SNAPSHOTS_FLAG = 'snapshots'

204PDB_TO_PUBCHEM = 'pdb2pubchem'

205

206# Set the different test and warning flags

207MISSING_BONDS_FLAG = 'nobonds'

208STABLE_BONDS_FLAG = 'stabonds'

209COHERENT_BONDS_FLAG = 'cohbonds'

210TRAJECTORY_INTEGRITY_FLAG = 'intrajrity'

211CORRECT_ELEMENTS = 'elements'

212REFERENCE_SEQUENCE_FLAG = 'refseq'

213STABLE_INTERACTIONS_FLAG = 'interact'

214LIGANDS_MATCH_FLAG = 'ligands'

215CHAINS_ANALYSIS = 'chains'

216FAITH_BYPASS = 'faith'

217

218# State all the available checkings, which may be trusted

219AVAILABLE_CHECKINGS = [ STABLE_BONDS_FLAG, COHERENT_BONDS_FLAG, TRAJECTORY_INTEGRITY_FLAG ]

220# State all critical process failures, which are to be lethal for the workflow unless mercy is given

221AVAILABLE_FAILURES = AVAILABLE_CHECKINGS + [ CORRECT_ELEMENTS, REFERENCE_SEQUENCE_FLAG, STABLE_INTERACTIONS_FLAG, LIGANDS_MATCH_FLAG, CHAINS_ANALYSIS ]

222

223# Set which tests are to be run when some input files are modified

224STRUCTURE_TESTS = [STABLE_BONDS_FLAG, COHERENT_BONDS_FLAG]

225TRAJECTORY_TESTS = [STABLE_BONDS_FLAG, TRAJECTORY_INTEGRITY_FLAG]

226TOPOLOGY_TESTS = [STABLE_BONDS_FLAG, COHERENT_BONDS_FLAG]

227

228# Terminal colors

229# https://stackoverflow.com/questions/287871/how-do-i-print-colored-text-to-the-terminal

230if not GLOBALS['no_colors']:

231 GREEN_HEADER = '\033[92m'

232 CYAN_HEADER = '\033[96m'

233 BLUE_HEADER = '\033[94m'

234 YELLOW_HEADER = '\033[93m'

235 RED_HEADER = '\033[91m'

236 GREY_HEADER = '\033[90m'

237 COLOR_END = '\033[0m'

238else:

239 GREEN_HEADER = ''

240 CYAN_HEADER = ''

241 BLUE_HEADER = ''

242 YELLOW_HEADER = ''

243 RED_HEADER = ''

244 GREY_HEADER = ''

245 COLOR_END = ''

246

247# Set a dictionary to parse an internal raw name to a pretty human firendly name

248NICE_NAMES = {

249 STABLE_BONDS_FLAG: 'Stable bonds test',

250 COHERENT_BONDS_FLAG: 'Coherent bonds test',

251 TRAJECTORY_INTEGRITY_FLAG: 'Trajectory integrity test',

252 CORRECT_ELEMENTS: 'Correct elements',

253 REFERENCE_SEQUENCE_FLAG: 'Reference sequence match',

254 STABLE_INTERACTIONS_FLAG: 'Interactions are stable',

255 LIGANDS_MATCH_FLAG: 'Ligands matched residues',

256 CHAINS_ANALYSIS: 'Chains analysis'

257}

258

259# Set the "standard" file format of every possible file extension

260# Note that some formats have different possible extension (e.g. nc, cdf, netcdf)

261EXTENSION_FORMATS = {

262 # Topologies

263 'tpr': 'tpr',

264 'top': 'top',

265 'psf': 'psf',

266 'prmtop': 'prmtop',

267 'parm7': 'prmtop',

268 'prm7': 'prmtop',

269 'txt': 'txt', # charges.txt

270 # Structures

271 'pdb': 'pdb',

272 'gro': 'gro',

273 'cif': 'cif',

274 # Trajectories

275 'xtc': 'xtc',

276 'trr': 'trr',

277 'dcd': 'dcd',

278 'nc': 'nc',

279 'cdf': 'nc',

280 'netcdf': 'nc',

281 'crd': 'crd',

282 'mdcrd': 'crd',

283 'trj': 'crd',

284 # Restart files (may be used as single frame trajectories)

285 'rst7': 'rst7',

286 # Other

287 'json': 'json',

288 'yaml': 'yaml',

289 'yml': 'yaml',

290 'npy': 'npy',

291 'in': 'txt',

292 'h5': 'h5',

293 'jpg': 'jpg',

294 'jpeg': 'jpg',

295}

296

297# Topology and trajectory file formats supported by PyTraj

298PYTRAJ_SUPPORTED_FORMATS = set([

299 # Topologies

300 'prmtop', 'top', 'psf', 'pdb'

301 # Trajectories

302 'nc', 'crd', 'dcd', 'trr', 'xtc'

303])

304

305# From GitHub:

306# ParmFormatDict = {

307# "AMBERPARM": AMBERPARM,

308# "PDBFILE": PDBFILEPARM,

309# "MOL2FILE": MOL2FILEPARM,

310# "CHARMMPSF": CHARMMPSF,

311# "CIFFILE": CIFFILE,

312# "GMXTOP": GMXTOP,

313# "SDFFILE": SDFFILE,

314# "TINKER": TINKERPARM,

315# "UNKNOWN_PARM": UNKNOWN_PARM,

316# }

317

318# Set some flags requeired to write files with pytraj

319PYTRAJ_PARM_FORMAT = {

320 'prmtop': 'AMBERPARM',

321 'psf': 'CHARMMPSF',

322 'top': 'GMXTOP',

323 'pdb': 'PDBFILE'

324}

325

326# Elements supported while correcting atom elements

327# DANI: Ba was found in PDB 1J6S

328# DANI: Lu was found in PDB 1DUH

329# DANI: U was found in PDB 2GIC

330# DANI: V was found in PDB 2P7E

331# DANI: Tb was found in PDB 359D

332# DANI: Ag was found in PDB 5AY2

333# DANI: Rb was found in PDB 3GGK

334

335# Set elements which are always "bonded"

336SUPPORTED_POLYMER_ELEMENTS = set([ 'C', 'N', 'O', 'H', 'P', 'S', 'D' ])

337# Set elements which may be found both "bonded" or "alone"

338SUPPORTED_COORDINATED_ELEMENTS = set([ 'Zn', 'Fe', 'Mn', 'Co', 'Lu', 'U', 'V', 'Al', 'Ba', 'Be', 'F', 'Te' ])

339# Set elements which are always "alone"

340SUPPORTED_ION_ELEMENTS = set([ 'K', 'Cl', 'Na', 'Mg', 'Br', 'I', 'Ca', 'Tb', 'Ag', 'Tl', 'Rb' ])

341SUPPORTED_ELEMENTS = {

342 *SUPPORTED_POLYMER_ELEMENTS,

343 *SUPPORTED_COORDINATED_ELEMENTS,

344 *SUPPORTED_ION_ELEMENTS

345}

346

347# Set a dictionaries with all residue names and their equivalent letters

348# Amino acids

349PROTEIN_RESIDUE_NAME_LETTERS = {

350 'ALA':'A',

351 'ALAN':'A',

352 'ALAC':'A',

353 'ARG':'R',

354 'ARGN':'R',

355 'ARGC':'R',

356 'ASN':'N',

357 'ASNN':'N',

358 'ASNC':'N',

359 'ASP':'D',

360 'ASPN':'D',

361 'ASPC':'D',

362 'CYS':'C',

363 'CYSN':'C',

364 'CYSC':'C',

365 'CYH':'C',

366 'CSH':'C',

367 'CSS':'C',

368 'CYX':'C',

369 'CYP':'C',

370 'GLN':'Q',

371 'GLNN':'Q',

372 'GLNC':'Q',

373 'GLU':'E',

374 'GLUN':'E',

375 'GLUC':'E',

376 'GLUP':'E',

377 'GLY':'G',

378 'GLYN':'G',

379 'GLYC':'G',

380 'HIS':'H',

381 'HISN':'H',

382 'HISC':'H',

383 'HID':'H',

384 'HIE':'H',

385 'HIP':'H',

386 'HSD':'H',

387 'HSE':'H',

388 'ILE':'I',

389 'ILEN':'I',

390 'ILEC':'I',

391 'ILU':'I',

392 'LEU':'L',

393 'LEUN':'L',

394 'LEUC':'L',

395 'LYS':'K',

396 'LYSN':'K',

397 'LYSC':'K',

398 'MET':'M',

399 'METN':'M',

400 'METC':'M',

401 'PHE':'F',

402 'PHEN':'F',

403 'PHEC':'F',

404 'PRO':'P',

405 'PRON':'P',

406 'PROC':'P',

407 'PRØ':'P',

408 'PR0':'P',

409 'PRZ':'P',

410 'SER':'S',

411 'SERN':'S',

412 'SERC':'S',

413 'THR':'T',

414 'THRN':'T',

415 'THRC':'R',

416 'TRP':'W',

417 'TRPN':'W',

418 'TRPC':'W',

419 'TRY':'W',

420 'TYR':'Y',

421 'TYRN':'Y',

422 'TYRC':'Y',

423 'VAL':'V',

424 'VALN':'V',

425 'VALC':'V',

426}

427# Nucleotides

428DNA_RESIDUE_NAME_LETTERS = {

429 'DA': 'A',

430 'T': 'T',

431 'T3': 'T',

432 'T5': 'T',

433 'DT': 'T',

434 'DC': 'C',

435 'DG': 'G',

436 'DA3': 'A',

437 'DA5': 'A',

438 'DT3': 'T',

439 'DT5': 'T',

440 'DC3': 'C',

441 'DC5': 'C',

442 'DG3': 'G',

443 'DG5': 'G',

444}

445RNA_RESIDUE_NAME_LETTERS = {

446 'RA': 'A',

447 'U': 'U',

448 'U3': 'U',

449 'U5': 'U',

450 'RU': 'U',

451 'RC': 'C',

452 'RG': 'G',

453 'RA3': 'A',

454 'RA5': 'A',

455 'RU3': 'U',

456 'RU5': 'U',

457 'RC3': 'C',

458 'RC5': 'C',

459 'RG3': 'G',

460 'RG5': 'G',

461}

462NUCLEIC_RESIDUE_NAME_LETTERS = {

463 **DNA_RESIDUE_NAME_LETTERS,

464 **RNA_RESIDUE_NAME_LETTERS,

465 'A': 'A',

466 'A3': 'A',

467 'A5': 'A',

468 'C': 'C',

469 'C3': 'C',

470 'C5': 'C',

471 'G': 'G',

472 'G3': 'G',

473 'G5': 'G',

474}

475# All of them together

476RESIDUE_NAME_LETTERS = { **PROTEIN_RESIDUE_NAME_LETTERS, **NUCLEIC_RESIDUE_NAME_LETTERS }

477

478# Lipid common residue names

479# Source: https://github.com/NMRLipids/Databank/blob/main/Scripts/DatabankLib/settings/molecules.py#L10

480# Meanings: https://github.com/NMRLipids/Databank/blob/48fdf2c4149d0db8900ce08b0e74dc1836dcfab3/Scripts/BuildDatabank/docs/source/moleculesAndMapping.md?plain=1#L50

481FATTY_RESIDUE_NAMES = {

482 "POPC", "POPG", "POPS", "POPE", "PYPC", "PAzePCprot", "PAzePCdeprot", "DMPC",

483 "DPPC", "DPPE", "DPPG", "DEPC", "DRPC", "DYPC", "DLPC", "DLIPC", "DOG", "DOPC",

484 "DOPE", "DDOPC", "DOPS", "DSPC", "DAPC", "DMTAP", "SDG", "SDPE", "SOPC", "POPI",

485 "SAPI", "SAPI24", "SAPI25", "SLPI", "CER", "CER180", "DHMDMAB", "SLiPC", "SM16",

486 "SM18", "TOCL", "TLCL_0H", "TMCL", "GM1", "DPPGK", "GB3", "BOG"

487}

488STEROID_RESIDUE_NAMES = { "CHL", "CHL1", "CHOL", "DCHOL" }

489LIPIDS_RESIDUE_NAMES = FATTY_RESIDUE_NAMES.union(STEROID_RESIDUE_NAMES)

490

491# Set typical residue names to guess what residues are

492STANDARD_SOLVENT_RESIDUE_NAMES = {'SOL', 'WAT', 'HOH', 'TIP', 'TP3', 'SWM4', 'W'}

493# WARNING: Note that standard names also include + and - symbols

494# Use functions such as Structure.select_counter_ions instead of checking if the set includes a name

495STANDARD_COUNTER_CATION_ATOM_NAMES = {'K', 'NA', 'SOD', 'POT'}

496STANDARD_COUNTER_ANION_ATOM_NAMES = {'CL', 'CLA'}

497STANDARD_COUNTER_ION_ATOM_NAMES = STANDARD_COUNTER_CATION_ATOM_NAMES.union(STANDARD_COUNTER_ANION_ATOM_NAMES)

498STANDARD_DUMMY_ATOM_NAMES = {'MW'}

499DUMMY_ATOM_ELEMENT = 'Dm'

500CG_ATOM_ELEMENT = 'Cg'

501

502# Topology flags

503

504# Set a flag to represent a protein which is not referable (e.g. antibodies, synthetic constructs)

505NO_REFERABLE_FLAG = 'noref'

506

507# Set a flag to represent a not found reference

508NOT_FOUND_FLAG = 'notfound'

509

510# Reference id formats

511PDB_ID_FORMAT = r'^[1-9]{1}[a-zA-Z0-9]{3}$'

512

513# Available analysis for NASSA

514NASSA_ANALYSES_LIST = [ 'bconf', 'coordist', 'bpcorr', 'crdcorr', 'stiff' ]

515

516# Set the correponding canals archives (.ser) for each NASSA analysis

517NASSA_ANALYSES_CANALS = {

518 #'bconf': ['epsilC', 'epsilW', 'zetaC', 'zetaW'],

519 'coordist': ['shift', 'slide', 'rise', 'tilt', 'roll', 'twist','chiW', 'chiC'],

520 'bpcorr': ['shift', 'slide', 'rise', 'tilt', 'roll', 'twist'],

521 #'crdcorr': ['shift', 'slide', 'rise', 'tilt', 'roll', 'twist'],

522 'stiff': ['stretch', 'shear', 'buckle', 'stagger', 'propel', 'opening', 'chiW', 'chiC']

523}

Coverage for mddb_workflow / utils / constants.py: 95%

159 statements