File size: 11,077 Bytes
a376829 | 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 | # Copyright 2025 Dhruv Nair. All rights reserved.
# Licensed under the Apache License, Version 2.0
"""
RF3 (RosettaFold3) Transformer model.
A diffusers-compatible wrapper around the foundry RF3 model components.
Reuses FeatureInitializer, Recycler, DiffusionModule, and DistogramHead
from ``rf3.model.*`` directly, adding only the ModelMixin/ConfigMixin
interface needed for diffusers ModularPipeline integration.
RF3 is structurally similar to RFD3 but adds a trunk recycler (48
pairformer blocks + MSA + templates) for sequence-conditioned folding.
"""
from dataclasses import dataclass
from typing import Optional
import torch
import torch.nn as nn
from diffusers.configuration_utils import ConfigMixin, register_to_config
from diffusers.models.modeling_utils import ModelMixin
from rf3.model.RF3_structure import DiffusionModule, DistogramHead, Recycler
from rf3.model.layers.pairformer_layers import FeatureInitializer
@dataclass
class RF3TransformerOutput:
"""Output class for RF3 transformer."""
xyz: torch.Tensor # [D, L, 3]
distogram: Optional[torch.Tensor] = None # [I, I, bins]
single: Optional[torch.Tensor] = None # [I, c_s]
pair: Optional[torch.Tensor] = None # [I, I, c_z]
trajectory_noisy: Optional[list] = None # list of [D, L, 3]
trajectory_denoised: Optional[list] = None # list of [D, L, 3]
class RF3TransformerModel(ModelMixin, ConfigMixin):
"""
Diffusers-compatible wrapper around the foundry RF3 model.
Wraps FeatureInitializer, Recycler, DiffusionModule, and DistogramHead
to provide a diffusers ModelMixin/ConfigMixin interface.
State dict keys match the foundry checkpoint format via the
``feature_initializer.*``, ``recycler.*``, ``diffusion_module.*``,
and ``distogram_head.*`` prefixes.
"""
config_name = "config.json"
_supports_gradient_checkpointing = True
@register_to_config
def __init__(
self,
c_s: int = 384,
c_z: int = 128,
c_atom: int = 128,
c_atompair: int = 16,
c_s_inputs: int = 449,
c_token: int = 768,
sigma_data: float = 16.0,
n_pairformer_blocks: int = 48,
n_diffusion_blocks: int = 24,
n_atom_encoder_blocks: int = 3,
n_atom_decoder_blocks: int = 3,
n_msa_blocks: int = 4,
n_template_blocks: int = 2,
n_head: int = 16,
n_pairformer_head: int = 16,
n_recycles: int = 10,
distogram_bins: int = 65,
p_drop: float = 0.25,
):
super().__init__()
# ── FeatureInitializer ──────────────────────────────────────────
self.feature_initializer = FeatureInitializer(
c_s=c_s,
c_z=c_z,
c_atom=c_atom,
c_atompair=c_atompair,
c_s_inputs=c_s_inputs,
input_feature_embedder={
"features": ["restype", "profile", "deletion_mean"],
"atom_attention_encoder": {
"c_token": c_s,
"c_atom_1d_features": 389,
"c_tokenpair": c_z,
"use_inv_dist_squared": True,
"atom_1d_features": [
"ref_pos", "ref_charge", "ref_mask",
"ref_element", "ref_atom_name_chars",
],
"atom_transformer": {
"n_queries": 32,
"n_keys": 128,
"diffusion_transformer": {
"n_block": 3,
"diffusion_transformer_block": {
"n_head": 4,
"no_residual_connection_between_attention_and_transition": True,
"kq_norm": True,
},
},
},
},
},
relative_position_encoding={"r_max": 32, "s_max": 2},
)
# ── Recycler (trunk) ───────────────────────────────────────────
self.recycler = Recycler(
c_s=c_s,
c_z=c_z,
n_pairformer_blocks=n_pairformer_blocks,
pairformer_block={
"p_drop": p_drop,
"triangle_multiplication": {"d_hidden": 128},
"triangle_attention": {"n_head": 4, "d_hidden": 32},
"attention_pair_bias": {"n_head": n_head},
},
template_embedder={
"n_block": n_template_blocks,
"raw_template_dim": 108,
"c": 64,
"p_drop": p_drop,
},
msa_module={
"n_block": n_msa_blocks,
"c_m": 64,
"p_drop_msa": 0.15,
"p_drop_pair": p_drop,
"msa_subsample_embedder": {
"num_sequences": 1024,
"dim_raw_msa": 34,
"c_s_inputs": c_s_inputs,
"c_msa_embed": 64,
},
"outer_product": {
"c_msa_embed": 64,
"c_outer_product": 32,
"c_out": c_z,
},
"msa_pair_weighted_averaging": {
"n_heads": 8,
"c_weighted_average": 32,
"c_msa_embed": 64,
"c_z": c_z,
"separate_gate_for_every_channel": True,
},
"msa_transition": {"n": 4, "c": 64},
"triangle_multiplication_outgoing": {
"d_pair": c_z, "d_hidden": 128, "bias": True,
},
"triangle_multiplication_incoming": {
"d_pair": c_z, "d_hidden": 128, "bias": True,
},
"triangle_attention_starting": {
"d_pair": c_z, "n_head": 4, "d_hidden": 32, "p_drop": 0.0,
},
"triangle_attention_ending": {
"d_pair": c_z, "n_head": 4, "d_hidden": 32, "p_drop": 0.0,
},
"pair_transition": {"n": 4, "c": c_z},
},
)
# ── DiffusionModule ────────────────────────────────────────────
self.diffusion_module = DiffusionModule(
sigma_data=sigma_data,
c_atom=c_atom,
c_atompair=c_atompair,
c_token=c_token,
c_s=c_s,
c_z=c_z,
diffusion_conditioning={
"c_s_inputs": c_s_inputs,
"c_t_embed": 256,
"relative_position_encoding": {"r_max": 32, "s_max": 2},
},
atom_attention_encoder={
"c_tokenpair": c_z,
"c_atom_1d_features": 389,
"use_inv_dist_squared": True,
"atom_1d_features": [
"ref_pos", "ref_charge", "ref_mask",
"ref_element", "ref_atom_name_chars",
],
"atom_transformer": {
"n_queries": 32,
"n_keys": 128,
"diffusion_transformer": {
"n_block": n_atom_encoder_blocks,
"diffusion_transformer_block": {
"n_head": 4,
"no_residual_connection_between_attention_and_transition": True,
"kq_norm": True,
},
},
},
"broadcast_trunk_feats_on_1dim_old": False,
"use_chiral_features": True,
"no_grad_on_chiral_center": False,
},
diffusion_transformer={
"n_block": n_diffusion_blocks,
"diffusion_transformer_block": {
"n_head": n_head,
"no_residual_connection_between_attention_and_transition": True,
"kq_norm": True,
},
},
atom_attention_decoder={
"atom_transformer": {
"n_queries": 32,
"n_keys": 128,
"diffusion_transformer": {
"n_block": n_atom_decoder_blocks,
"diffusion_transformer_block": {
"n_head": 4,
"no_residual_connection_between_attention_and_transition": True,
"kq_norm": True,
},
},
},
},
)
# ── DistogramHead ──────────────────────────────────────────────
self.distogram_head = DistogramHead(c_z=c_z, bins=distogram_bins)
self._n_recycles = n_recycles
def forward(
self,
f: dict,
n_recycles: Optional[int] = None,
diffusion_batch_size: int = 1,
coord_atom_lvl_to_be_noised: Optional[torch.Tensor] = None,
) -> RF3TransformerOutput:
"""
Forward pass: recycling trunk → diffusion sampling.
Args:
f: Feature dictionary (sequence, MSA, templates, atom features).
n_recycles: Number of recycling iterations (default: config value).
diffusion_batch_size: Number of diffusion samples.
coord_atom_lvl_to_be_noised: Initial coordinates for partial diffusion.
Returns:
RF3TransformerOutput with predicted coordinates and distogram.
"""
n_recycles = n_recycles or self._n_recycles
# Pre-recycle: initialize features
initialized = self.feature_initializer(f)
S_inputs_I = initialized["S_inputs_I"]
S_I = initialized.get("S_init_I", initialized.get("S_I"))
Z_II = initialized.get("Z_init_II", initialized.get("Z_II"))
# Recycling trunk
for i in range(n_recycles):
ctx = torch.no_grad() if i < n_recycles - 1 else torch.enable_grad()
with ctx:
recycled = self.recycler(
S_I=S_I,
Z_II=Z_II,
S_inputs_I=S_inputs_I,
f=f,
)
S_I = recycled["S_I"]
Z_II = recycled["Z_II"]
# Distogram prediction
distogram = self.distogram_head(Z_II)
return RF3TransformerOutput(
xyz=torch.zeros(1), # placeholder — filled by sampler in denoise step
distogram=distogram,
single=S_I,
pair=Z_II,
)
|