Coverage for model_workflow/utils/constants.py: 99%

1from os import environ

2from shutil import which

4# CONSTANTS ---------------------------------------------------------------------------

6# Set a custom globals dict

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

8GLOBALS = {

9 # Set if symlinks are allowed

10 'no_symlinks': False,

11}

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

14GROMACS_EXECUTABLE_COMMON_NAMES = ['gmx', 'gmx_mpi']

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

16GROMACS_ENV = 'MWF_GMX'

17# Set the gromacs executable path

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

19GROMACS_EXECUTABLE = environ.get(GROMACS_ENV, None)

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

21if not GROMACS_EXECUTABLE:

22 for common_name in GROMACS_EXECUTABLE_COMMON_NAMES:

23 if which(common_name):

24 GROMACS_EXECUTABLE = common_name

25 break

26# If we do not find it then complain

27if not GROMACS_EXECUTABLE:

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

30# List typical text editor and their commands

31TEXT_EDITORS = {

32 'VIM': 'vim',

33 'GNU nano': 'nano',

34 'GNOME text editor': 'gedit',

35 'VScode': 'code',

36}

37# Keep only those editor which are already installed

38AVAILABLE_TEXT_EDITORS = { name: command for name, command in TEXT_EDITORS.items() if which(command) }

40# Set dates format

41DATE_STYLE = '%d-%m-%Y %H:%M:%S'

43# Database

44DEFAULT_API_URL = 'https://irb-dev.mddbr.eu/api/'

46# Selections

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

48ALL_ATOMS = 'all'

49PROTEIN_AND_NUCLEIC = 'protein or nucleic'

50PROTEIN_AND_NUCLEIC_BACKBONE = "(protein and name N CA C) or (nucleic and name P O5' O3' C5' C4' C3')"

52# Inputs file

53DEFAULT_INPUTS_FILENAME = 'inputs.yaml'

54ACCEPTED_INPUT_FILENAMES = [

55 DEFAULT_INPUTS_FILENAME, # The default

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

57 'inputs.json' # Legacy inputs file

58]

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

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

62DEFAULT_INPUT_VALUES = {

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

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

65 'mdref': 0,

66}

68# Expected MD inputs

69MD_DIRECTORY = 'mdir'

71# Input config file for the NASSA analysis

72DEFAULT_NASSA_CONFIG_FILENAME = 'nassa.json'

74# Markov State Model input filenames

75DEFAULT_POPULATIONS_FILENAME = 'populations.json'

76DEFAULT_TRANSITIONS_FILENAME = 'transitions.json'

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

79RAW_CHARGES_FILENAME = 'charges.txt'

80# Accepted topology formats for atomic charges mining

81ACCEPTED_TOPOLOGY_FORMATS = ['tpr', 'top', 'psf', 'prmtop', 'prm7']

83# Input files processing intermediate steps

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

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

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

88INCOMPLETE_PREFIX = 'incomplete_'

90CONVERTED = 'converted'

91CONVERTED_STRUCTURE = 'converted.pdb'

92CONVERTED_TRAJECTORY = 'converted.xtc'

94FILTERED = 'filtered'

95FILTERED_STRUCTURE = 'filtered.pdb'

96FILTERED_TRAJECTORY = 'filtered.xtc'

98IMAGED = 'imaged'

99IMAGED_STRUCTURE = 'imaged.pdb'

100IMAGED_TRAJECTORY = 'imaged.xtc'

101

102CORRECTED = 'corrected'

103CORRECTED_STRUCTURE = 'corrected.pdb'

104CORRECTED_TRAJECTORY = 'corrected.xtc'

105

106# Input and output core files

107STANDARD_TOPOLOGY_FILENAME = 'topology.json'

108STRUCTURE_FILENAME = 'structure.pdb'

109TRAJECTORY_FILENAME = 'trajectory.xtc'

110

111# Auxiliar files

112REGISTER_FILENAME = '.register.json'

113CACHE_FILENAME = '.mwf_cache.json'

114

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

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

117RESORTED_CHARGES_FILENAME = 'resorted_charges.json'

118RESORTED_BONDS_FILENAME = 'resorted_bonds.json'

119

120# Set generated file names

121FIRST_FRAME_FILENAME = 'first_frame.pdb'

122AVERAGE_STRUCTURE_FILENAME = 'average.pdb'

123

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

125REFERENCE_LABELS = {

126 FIRST_FRAME_FILENAME: 'firstframe',

127 AVERAGE_STRUCTURE_FILENAME: 'average'

128}

129

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

131

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

133PDB_REFERENCES_FILENAME = 'pdb_references.json'

134# Set the protein references filename

135PROTEIN_REFERENCES_FILENAME = 'protein_references.json'

136# Set the ligand references filename

137LIGAND_REFERENCES_FILENAME = 'ligand_references.json'

138# Set the Lipid references filename

139LIPID_REFERENCES_FILENAME = 'lipid_references.json'

140

141# Set the chains filename

142OUTPUT_CHAINS_FILENAME = 'chains.json'

143

144# Set the metadata filename

145OUTPUT_METADATA_FILENAME = 'metadata.json'

146

147# Set the screenshot filename

148OUTPUT_SCREENSHOT_FILENAME = 'mdf.screenshot.jpg'

149

150# Additional screenshot filenames

151OUTPUT_CLUSTER_SCREENSHOT_FILENAMES = 'mdf.clusters_*_screenshot_??.jpg'

152

153# Set analyses files to be generated

154OUTPUT_INTERACTIONS_FILENAME = 'mda.interactions.json'

155OUTPUT_RMSDS_FILENAME = 'mda.rmsds.json'

156OUTPUT_TMSCORES_FILENAME = 'mda.tmscores.json'

157OUTPUT_RMSF_FILENAME = 'mda.fluctuation.json'

158OUTPUT_RGYR_FILENAME = 'mda.rgyr.json'

159OUTPUT_PCA_FILENAME = 'mda.pca.json'

160OUTPUT_PCA_PROJECTION_PREFIX = 'mdt.pca_trajectory'

161OUTPUT_PCA_CONTACTS_FILENAME = 'mda.pca_contacts.json'

162OUTPUT_RMSD_PERRES_FILENAME = 'mda.rmsd_perres.json'

163OUTPUT_RMSD_PAIRWISE_FILENAME = 'mda.rmsd_pairwise.json'

164OUTPUT_CLUSTERS_FILENAME = 'mda.clusters.json'

165OUTPUT_DIST_PERRES_FILENAME = 'mda.dist_perres.json'

166OUTPUT_HBONDS_FILENAME = 'mda.hbonds.json'

167OUTPUT_SASA_FILENAME = 'mda.sasa.json'

168OUTPUT_ENERGIES_FILENAME = 'mda.energies.json'

169OUTPUT_DIHEDRAL_ENERGIES_FILENAME = 'mda.dihenergies.json'

170OUTPUT_POCKETS_FILENAME = 'mda.pockets.json'

171OUTPUT_POCKET_STRUCTURES_PREFIX = 'mdf.pocket' # WARNING: If this is changed then the pockets function must be updated as well

172OUTPUT_HELICAL_PARAMETERS_FILENAME = 'mda.helical.json'

173OUTPUT_MARKOV_FILENAME = 'mda.markov.json'

174MEMBRANE_MAPPING_FILENAME = 'mda.mem_map.json'

175OUTPUT_DENSITY_FILENAME = 'mda.density.json'

176OUTPUT_THICKNESS_FILENAME = 'mda.thickness.json'

177OUTPUT_APL_FILENAME = 'mda.apl.json'

178OUTPUT_LIPID_ORDER_FILENAME = 'mda.lipid_order.json'

179OUTPUT_LIPID_INTERACTIONS_FILENAME = 'mda.lipid_inter.json'

180

181# Set problematic signs for directory/folder names

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

183FORBIDDEN_DIRECTORY_CHARACTERS = ['.', ',', ';', ':', 'º', '/']

184

185# Default parameters

186DEFAULT_RMSD_CUTOFF = 9

187DEFAULT_INTERACTION_CUTOFF = 0.1

188

189# Set register cache flags

190SNAPSHOTS_FLAG = 'snapshots'

191PDB_TO_PUBCHEM = 'pdb2pubchem'

192NOT_MATCHED_LIGANDS = 'notmatchedligands'

193

194# Set the different test flags

195STABLE_BONDS_FLAG = 'stabonds'

196COHERENT_BONDS_FLAG = 'cohbonds'

197TRAJECTORY_INTEGRITY_FLAG = 'intrajrity'

198CORRECT_ELEMENTS = 'elements'

199REFERENCE_SEQUENCE_FLAG = 'refseq'

200STABLE_INTERACTIONS_FLAG = 'interact'

201LIGANDS_MATCH_FLAG = 'ligands'

202CHAINS_ANALYSIS = 'chains'

203

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

205AVAILABLE_CHECKINGS = [ STABLE_BONDS_FLAG, COHERENT_BONDS_FLAG, TRAJECTORY_INTEGRITY_FLAG ]

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

207AVAILABLE_FAILURES = AVAILABLE_CHECKINGS + [ CORRECT_ELEMENTS, REFERENCE_SEQUENCE_FLAG, STABLE_INTERACTIONS_FLAG, LIGANDS_MATCH_FLAG, CHAINS_ANALYSIS ]

208

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

210STRUCTURE_TESTS = [STABLE_BONDS_FLAG, COHERENT_BONDS_FLAG]

211TRAJECTORY_TESTS = [STABLE_BONDS_FLAG, TRAJECTORY_INTEGRITY_FLAG]

212TOPOLOGY_TESTS = [STABLE_BONDS_FLAG, COHERENT_BONDS_FLAG]

213

214# Terminal colors

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

216GREEN_HEADER = '\033[92m'

217CYAN_HEADER = '\033[96m'

218BLUE_HEADER = '\033[94m'

219YELLOW_HEADER = '\033[93m'

220RED_HEADER = '\033[91m'

221GREY_HEADER = '\033[90m'

222COLOR_END = '\033[0m'

223

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

225NICE_NAMES = {

226 STABLE_BONDS_FLAG: 'Stable bonds test',

227 COHERENT_BONDS_FLAG: 'Coherent bonds test',

228 TRAJECTORY_INTEGRITY_FLAG: 'Trajectory integrity test',

229 CORRECT_ELEMENTS: 'Correct elements',

230 REFERENCE_SEQUENCE_FLAG: 'Reference sequence match',

231 STABLE_INTERACTIONS_FLAG: 'Interactions are stable',

232 LIGANDS_MATCH_FLAG : 'Ligands matched residues',

233 CHAINS_ANALYSIS: 'Chains analysis'

234}

235

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

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

238EXTENSION_FORMATS = {

239 # Topologies

240 'tpr': 'tpr',

241 'top': 'top',

242 'psf': 'psf',

243 'prmtop': 'prmtop',

244 'parm7': 'prmtop',

245 'prm7': 'prmtop',

246 'txt': 'txt', # charges.txt

247 # Structures

248 'pdb': 'pdb',

249 'gro': 'gro',

250 'cif': 'cif',

251 # Trajectories

252 'xtc': 'xtc',

253 'trr': 'trr',

254 'dcd': 'dcd',

255 'nc': 'nc',

256 'cdf': 'nc',

257 'netcdf': 'nc',

258 'crd': 'crd',

259 'mdcrd': 'crd',

260 'trj': 'crd',

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

262 'rst7': 'rst7',

263 # Other

264 'json': 'json',

265 'yaml': 'yaml',

266 'yml': 'yaml',

267 'npy': 'npy',

268 'in': 'txt',

269 'h5': 'h5'

270}

271

272# Topology and trajectory file formats supported by PyTraj

273PYTRAJ_SUPPORTED_FORMATS = set([

274 # Topologies

275 'prmtop', 'top', 'psf', 'pdb'

276 # Trajectories

277 'nc', 'crd', 'dcd', 'trr', 'xtc'

278])

279

280# From GitHub:

281# ParmFormatDict = {

282# "AMBERPARM": AMBERPARM,

283# "PDBFILE": PDBFILEPARM,

284# "MOL2FILE": MOL2FILEPARM,

285# "CHARMMPSF": CHARMMPSF,

286# "CIFFILE": CIFFILE,

287# "GMXTOP": GMXTOP,

288# "SDFFILE": SDFFILE,

289# "TINKER": TINKERPARM,

290# "UNKNOWN_PARM": UNKNOWN_PARM,

291# }

292

293# Set some flags requeired to write files with pytraj

294PYTRAJ_PARM_FORMAT = {

295 'prmtop': 'AMBERPARM',

296 'psf': 'CHARMMPSF',

297 'top': 'GMXTOP',

298 'pdb': 'PDBFILE'

299}

300

301# Elements supported while correcting atom elements

302# DANI: Ba was found in PDB 1J6S

303# DANI: Lu was found in PDB 1DUH

304# DANI: U was found in PDB 2GIC

305# DANI: V was found in PDB 2P7E

306# DANI: Tb was found in PDB 359D

307# DANI: Ag was found in PDB 5AY2

308# DANI: Rb was found in PDB 3GGK

309

310# Set elements which are always "bonded"

311SUPPORTED_POLYMER_ELEMENTS = set([ 'C', 'N', 'O', 'H', 'P', 'S' ])

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

313SUPPORTED_COORDINATED_ELEMENTS = set([ 'Zn', 'Fe', 'Mn', 'Co', 'Lu', 'U', 'V', 'Al', 'Ba', 'Be', 'F' ])

314# Set elements which are always "alone"

315SUPPORTED_ION_ELEMENTS = set([ 'K', 'Cl', 'Na', 'Mg', 'Br', 'I', 'Ca', 'Tb', 'Ag', 'Tl', 'Rb' ])

316SUPPORTED_ELEMENTS = {

317 *SUPPORTED_POLYMER_ELEMENTS,

318 *SUPPORTED_COORDINATED_ELEMENTS,

319 *SUPPORTED_ION_ELEMENTS

320}

321

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

323# Amino acids

324PROTEIN_RESIDUE_NAME_LETTERS = {

325 'ALA':'A',

326 'ALAN':'A',

327 'ALAC':'A',

328 'ARG':'R',

329 'ARGN':'R',

330 'ARGC':'R',

331 'ASN':'N',

332 'ASNN':'N',

333 'ASNC':'N',

334 'ASP':'D',

335 'ASPN':'D',

336 'ASPC':'D',

337 'CYS':'C',

338 'CYSN':'C',

339 'CYSC':'C',

340 'CYH':'C',

341 'CSH':'C',

342 'CSS':'C',

343 'CYX':'C',

344 'CYP':'C',

345 'GLN':'Q',

346 'GLNN':'Q',

347 'GLNC':'Q',

348 'GLU':'E',

349 'GLUN':'E',

350 'GLUC':'E',

351 'GLUP':'E',

352 'GLY':'G',

353 'GLYN':'G',

354 'GLYC':'G',

355 'HIS':'H',

356 'HISN':'H',

357 'HISC':'H',

358 'HID':'H',

359 'HIE':'H',

360 'HIP':'H',

361 'HSD':'H',

362 'HSE':'H',

363 'ILE':'I',

364 'ILEN':'I',

365 'ILEC':'I',

366 'ILU':'I',

367 'LEU':'L',

368 'LEUN':'L',

369 'LEUC':'L',

370 'LYS':'K',

371 'LYSN':'K',

372 'LYSC':'K',

373 'MET':'M',

374 'METN':'M',

375 'METC':'M',

376 'PHE':'F',

377 'PHEN':'F',

378 'PHEC':'F',

379 'PRO':'P',

380 'PRON':'P',

381 'PROC':'P',

382 'PRØ':'P',

383 'PR0':'P',

384 'PRZ':'P',

385 'SER':'S',

386 'SERN':'S',

387 'SERC':'S',

388 'THR':'T',

389 'THRN':'T',

390 'THRC':'R',

391 'TRP':'W',

392 'TRPN':'W',

393 'TRPC':'W',

394 'TRY':'W',

395 'TYR':'Y',

396 'TYRN':'Y',

397 'TYRC':'Y',

398 'VAL':'V',

399 'VALN':'V',

400 'VALC':'V',

401}

402# Nucleotides

403DNA_RESIDUE_NAME_LETTERS = {

404 'DA': 'A',

405 'T': 'T',

406 'T3': 'T',

407 'T5': 'T',

408 'DT': 'T',

409 'DC': 'C',

410 'DG': 'G',

411 'DA3': 'A',

412 'DA5': 'A',

413 'DT3': 'T',

414 'DT5': 'T',

415 'DC3': 'C',

416 'DC5': 'C',

417 'DG3': 'G',

418 'DG5': 'G',

419}

420RNA_RESIDUE_NAME_LETTERS = {

421 'RA': 'A',

422 'U': 'U',

423 'U3': 'U',

424 'U5': 'U',

425 'RU': 'U',

426 'RC': 'C',

427 'RG': 'G',

428 'RA3': 'A',

429 'RA5': 'A',

430 'RU3': 'U',

431 'RU5': 'U',

432 'RC3': 'C',

433 'RC5': 'C',

434 'RG3': 'G',

435 'RG5': 'G',

436}

437NUCLEIC_RESIDUE_NAME_LETTERS = {

438 **DNA_RESIDUE_NAME_LETTERS,

439 **RNA_RESIDUE_NAME_LETTERS,

440 'A': 'A',

441 'A3': 'A',

442 'A5': 'A',

443 'C': 'C',

444 'C3': 'C',

445 'C5': 'C',

446 'G': 'G',

447 'G3': 'G',

448 'G5': 'G',

449}

450# All of them together

451RESIDUE_NAME_LETTERS = { **PROTEIN_RESIDUE_NAME_LETTERS, **NUCLEIC_RESIDUE_NAME_LETTERS }

452

453# Lipid common residue names

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

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

456FATTY_RESIDUE_NAMES = {

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

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

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

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

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

462}

463STEROID_RESIDUE_NAMES = { "CHL", "CHL1", "CHOL", "DCHOL" }

464

465# Set typical residue names to guess what residues are

466STANDARD_SOLVENT_RESIDUE_NAMES = {'SOL', 'WAT', 'HOH', 'TIP', 'TP3', 'SWM4'}

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

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

469STANDARD_COUNTER_CATION_ATOM_NAMES = {'K', 'NA', 'SOD', 'POT'}

470STANDARD_COUNTER_ANION_ATOM_NAMES = {'CL', 'CLA'}

471STANDARD_COUNTER_ION_ATOM_NAMES = STANDARD_COUNTER_CATION_ATOM_NAMES.union(STANDARD_COUNTER_ANION_ATOM_NAMES)

472STANDARD_DUMMY_ATOM_NAMES = {'MW'}

473DUMMY_ATOM_ELEMENT = 'Dm'

474CG_ATOM_ELEMENT = 'Cg'

475

476# Topology flags

477

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

479NO_REFERABLE_FLAG = 'noref'

480

481# Set a flag to represent a not found reference

482NOT_FOUND_FLAG = 'notfound'

483

484# Reference id formats

485PDB_ID_FORMAT = r'^[1-9]{1}[a-zA-Z0-9]{3}$'

486

487# Available analysis for NASSA

488NASSA_ANALYSES_LIST = [ 'bconf', 'coordist', 'bpcorr', 'crdcorr', 'stiff' ]

489

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

491NASSA_ANALYSES_CANALS = {

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

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

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

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

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

497}