File size: 7,234 Bytes
c65e212 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 | """Minimal biological constants required by the local Boltz2 runtime.
The upstream project contains additional training-time curation tables. They
are intentionally excluded here because FastPLMs neither trains Boltz2 nor
uses upstream data-processing code. Keeping only runtime inputs makes this
module auditable and prevents parity-oracle data from becoming a package
dependency.
"""
from __future__ import annotations
def _index(values: list[str]) -> dict[str, int]:
return {value: index for index, value in enumerate(values)}
chain_types = ["PROTEIN", "DNA", "RNA", "NONPOLYMER"]
chain_type_ids = _index(chain_types)
canonical_tokens = [
"ALA",
"ARG",
"ASN",
"ASP",
"CYS",
"GLN",
"GLU",
"GLY",
"HIS",
"ILE",
"LEU",
"LYS",
"MET",
"PHE",
"PRO",
"SER",
"THR",
"TRP",
"TYR",
"VAL",
"UNK",
]
tokens = [
"<pad>",
"-",
*canonical_tokens,
"A",
"G",
"C",
"U",
"N",
"DA",
"DG",
"DC",
"DT",
"DN",
]
token_ids = _index(tokens)
num_tokens = len(tokens)
prot_letter_to_token = dict(
zip(
"ARNDCEQGHILKMFPSTWYV",
[
"ALA",
"ARG",
"ASN",
"ASP",
"CYS",
"GLU",
"GLN",
"GLY",
"HIS",
"ILE",
"LEU",
"LYS",
"MET",
"PHE",
"PRO",
"SER",
"THR",
"TRP",
"TYR",
"VAL",
],
strict=True,
)
)
prot_letter_to_token.update({letter: "UNK" for letter in "XJBZOU"} | {"-": "-"})
def _parse_atom_rows(rows: str) -> dict[str, list[str]]:
table: dict[str, list[str]] = {}
for row in rows.strip().splitlines():
residue, *atom_names = row.split()
table[residue] = atom_names
return table
ref_atoms = {"PAD": [], "-": []}
ref_atoms.update(
_parse_atom_rows(
"""
UNK N CA C O CB
ALA N CA C O CB
ARG N CA C O CB CG CD NE CZ NH1 NH2
ASN N CA C O CB CG OD1 ND2
ASP N CA C O CB CG OD1 OD2
CYS N CA C O CB SG
GLN N CA C O CB CG CD OE1 NE2
GLU N CA C O CB CG CD OE1 OE2
GLY N CA C O
HIS N CA C O CB CG ND1 CD2 CE1 NE2
ILE N CA C O CB CG1 CG2 CD1
LEU N CA C O CB CG CD1 CD2
LYS N CA C O CB CG CD CE NZ
MET N CA C O CB CG SD CE
PHE N CA C O CB CG CD1 CD2 CE1 CE2 CZ
PRO N CA C O CB CG CD
SER N CA C O CB OG
THR N CA C O CB OG1 CG2
TRP N CA C O CB CG CD1 CD2 NE1 CE2 CE3 CZ2 CZ3 CH2
TYR N CA C O CB CG CD1 CD2 CE1 CE2 CZ OH
VAL N CA C O CB CG1 CG2
"""
)
)
protein_backbone_atom_names = ["N", "CA", "C", "O"]
nucleic_backbone_atom_names = [
"P",
"OP1",
"OP2",
"O5'",
"C5'",
"C4'",
"O4'",
"C3'",
"O3'",
"C2'",
"O2'",
"C1'",
]
protein_backbone_atom_index = _index(protein_backbone_atom_names)
nucleic_backbone_atom_index = _index(nucleic_backbone_atom_names)
_rna_backbone = nucleic_backbone_atom_names
_dna_backbone = [atom for atom in _rna_backbone if atom != "O2'"]
ref_atoms.update(
{
"A": [*_rna_backbone, "N9", "C8", "N7", "C5", "C6", "N6", "N1", "C2", "N3", "C4"],
"G": [*_rna_backbone, "N9", "C8", "N7", "C5", "C6", "O6", "N1", "C2", "N2", "N3", "C4"],
"C": [*_rna_backbone, "N1", "C2", "O2", "N3", "C4", "N4", "C5", "C6"],
"U": [*_rna_backbone, "N1", "C2", "O2", "N3", "C4", "O4", "C5", "C6"],
"N": list(_rna_backbone),
"DA": [*_dna_backbone, "N9", "C8", "N7", "C5", "C6", "N6", "N1", "C2", "N3", "C4"],
"DG": [*_dna_backbone, "N9", "C8", "N7", "C5", "C6", "O6", "N1", "C2", "N2", "N3", "C4"],
"DC": [*_dna_backbone, "N1", "C2", "O2", "N3", "C4", "N4", "C5", "C6"],
"DT": [*_dna_backbone, "N1", "C2", "O2", "N3", "C4", "O4", "C5", "C7", "C6"],
"DN": list(_dna_backbone),
}
)
_protein_tokens = ["UNK", *canonical_tokens[:-1]]
_nucleic_tokens = ["A", "G", "C", "U", "N", "DA", "DG", "DC", "DT", "DN"]
res_to_center_atom = {
**dict.fromkeys(_protein_tokens, "CA"),
**dict.fromkeys(_nucleic_tokens, "C1'"),
}
res_to_disto_atom = {
**dict.fromkeys(_protein_tokens, "CB"),
"GLY": "CA",
"A": "C4",
"G": "C4",
"C": "C2",
"U": "C2",
"N": "C1'",
"DA": "C4",
"DG": "C4",
"DC": "C2",
"DT": "C2",
"DN": "C1'",
}
num_elements = 128
bond_types = ["OTHER", "SINGLE", "DOUBLE", "TRIPLE", "AROMATIC", "COVALENT"]
contact_conditioning_info = {
"UNSPECIFIED": 0,
"UNSELECTED": 1,
"POCKET>BINDER": 2,
"BINDER>POCKET": 3,
"CONTACT": 4,
}
chunk_size_threshold = 384
_method_groups = {
0: ("MD",),
1: ("X-RAY DIFFRACTION",),
2: ("ELECTRON MICROSCOPY",),
3: ("SOLUTION NMR",),
4: (
"SOLID-STATE NMR",
"NEUTRON DIFFRACTION",
"ELECTRON CRYSTALLOGRAPHY",
"FIBER DIFFRACTION",
"POWDER DIFFRACTION",
"INFRARED SPECTROSCOPY",
"FLUORESCENCE TRANSFER",
"EPR",
"THEORETICAL MODEL",
"SOLUTION SCATTERING",
"OTHER",
),
5: ("AFDB",),
6: ("BOLTZ-1",),
7: ("FUTURE1",),
8: ("FUTURE2",),
9: ("FUTURE3",),
10: ("FUTURE4",),
11: ("FUTURE5",),
}
method_types_ids = {
method.lower(): identifier
for identifier, methods in _method_groups.items()
for method in methods
}
num_method_types = len(_method_groups)
vdw_radii = [
float(radius)
for radius in [
"1.2",
"1.4",
"2.2",
"1.9",
"1.8",
"1.7",
"1.6",
"1.55",
"1.5",
"1.54",
"2.4",
"2.2",
"2.1",
"2.1",
"1.95",
"1.8",
"1.8",
"1.88",
"2.8",
"2.4",
"2.3",
"2.15",
"2.05",
"2.05",
"2.05",
"2.05",
"2.0",
"2.0",
"2.0",
"2.1",
"2.1",
"2.1",
"2.05",
"1.9",
"1.9",
"2.02",
"2.9",
"2.55",
"2.4",
"2.3",
"2.15",
"2.1",
"2.05",
"2.05",
"2.0",
"2.05",
"2.1",
"2.2",
"2.2",
"2.25",
"2.2",
"2.1",
"2.1",
"2.16",
"3.0",
"2.7",
"2.5",
"2.48",
"2.47",
"2.45",
"2.43",
"2.42",
"2.4",
"2.38",
"2.37",
"2.35",
"2.33",
"2.32",
"2.3",
"2.28",
"2.27",
"2.25",
"2.2",
"2.1",
"2.05",
"2.0",
"2.0",
"2.05",
"2.1",
"2.05",
"2.2",
"2.3",
"2.3",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.4",
"2.0",
"2.3",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
"2.0",
]
]
|