File size: 10,107 Bytes
fdb5676 | 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 | """
Cross-Attention Denoiser for Image-conditioned RNA-seq Diffusion.
The denoiser takes:
- noisy RNA-seq embeddings (scGPT, 512-dim)
- imaging features (ViT-L, 5120-dim) as conditioning context
- diffusion timestep
And predicts the noise Ξ΅ added to the RNA-seq embeddings.
Architecture:
1. Project imaging features β model_dim, apply self-attention to create a
rich context representation.
2. Embed noisy RNA + sinusoidal time embedding β model_dim.
3. Multiple cross-attention transformer blocks where RNA queries attend to
imaging context.
4. Project back to RNA embedding space and predict noise.
"""
from __future__ import annotations
import torch
import torch.nn as nn
import torch.nn.functional as F
from models.model_utils import (
SinusoidalTimeEmbedding,
Mish,
FeedForward,
AdaLayerNorm,
)
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# Cross-Attention Block
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
class CrossAttentionBlock(nn.Module):
"""
Single cross-attention layer: RNA query attends to imaging context.
Uses adaptive layer norm for time-conditioning and pre-norm residual style.
"""
def __init__(self, dim: int, num_heads: int, time_dim: int, ff_mult: int = 4, dropout: float = 0.1):
super().__init__()
# Time-conditioned norms
self.norm_rna = AdaLayerNorm(dim, time_dim)
self.norm_ctx = nn.LayerNorm(dim)
self.norm_ff = AdaLayerNorm(dim, time_dim)
# Cross-attention: Q from RNA, K/V from imaging
self.cross_attn = nn.MultiheadAttention(
embed_dim=dim,
num_heads=num_heads,
dropout=dropout,
batch_first=True,
)
# Self-attention on RNA after cross-attention
self.self_attn_norm = AdaLayerNorm(dim, time_dim)
self.self_attn = nn.MultiheadAttention(
embed_dim=dim,
num_heads=num_heads,
dropout=dropout,
batch_first=True,
)
# Feedforward
self.ff = FeedForward(dim, mult=ff_mult, dropout=dropout)
def forward(
self,
rna: torch.Tensor, # (B, 1, D)
context: torch.Tensor, # (B, S, D) imaging context
time_emb: torch.Tensor, # (B, time_dim)
) -> torch.Tensor:
# Cross-attention
rna_normed = self.norm_rna(rna, time_emb)
ctx_normed = self.norm_ctx(context)
rna = rna + self.cross_attn(rna_normed, ctx_normed, ctx_normed, need_weights=False)[0]
# Self-attention (useful when we have multiple RNA tokens, but also adds
# a residual self-refinement step)
rna_normed = self.self_attn_norm(rna, time_emb)
rna = rna + self.self_attn(rna_normed, rna_normed, rna_normed, need_weights=False)[0]
# Feedforward
rna = rna + self.ff(self.norm_ff(rna, time_emb))
return rna
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# Imaging Context Encoder
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
class ImagingEncoder(nn.Module):
"""
Encodes a set of imaging cell features into context representations.
Uses a small self-attention stack to let imaging cells attend to each other
before being used as cross-attention context.
"""
def __init__(self, img_dim: int, model_dim: int, num_heads: int = 4, num_layers: int = 2, dropout: float = 0.1):
super().__init__()
self.proj = nn.Sequential(
nn.Linear(img_dim, model_dim),
Mish(),
nn.LayerNorm(model_dim),
nn.Dropout(dropout),
)
encoder_layer = nn.TransformerEncoderLayer(
d_model=model_dim,
nhead=num_heads,
dim_feedforward=model_dim * 4,
dropout=dropout,
activation="gelu",
batch_first=True,
norm_first=True,
)
self.encoder = nn.TransformerEncoder(encoder_layer, num_layers=num_layers)
def forward(self, img_features: torch.Tensor) -> torch.Tensor:
"""
Args:
img_features: (B, N, img_dim)
Returns:
(B, N, model_dim) context representations
"""
x = self.proj(img_features)
return self.encoder(x)
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# Full Denoiser
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
class Img2RNADenoiser(nn.Module):
"""
Noise prediction network for image-conditioned RNA-seq diffusion.
Args:
img_dim: input imaging feature dimension (5120)
rna_dim: RNA-seq embedding dimension (512)
model_dim: internal model dimension (1024)
num_heads: number of attention heads (8)
num_layers: number of cross-attention blocks (6)
time_dim: time embedding dimension (256)
ff_mult: feedforward multiplier (4)
dropout: dropout rate (0.1)
"""
def __init__(
self,
img_dim: int = 5120,
rna_dim: int = 512,
model_dim: int = 1024,
num_heads: int = 8,
num_layers: int = 6,
time_dim: int = 256,
ff_mult: int = 4,
dropout: float = 0.1,
):
super().__init__()
self.model_dim = model_dim
self.rna_dim = rna_dim
# ββ Time embedding ββββββββββββββββββββββββββββββββββββββββββββββββ
self.time_embed = nn.Sequential(
SinusoidalTimeEmbedding(time_dim),
nn.Linear(time_dim, time_dim * 4),
Mish(),
nn.Linear(time_dim * 4, time_dim),
)
# ββ Imaging encoder βββββββββββββββββββββββββββββββββββββββββββββββ
self.img_encoder = ImagingEncoder(
img_dim=img_dim,
model_dim=model_dim,
num_heads=min(num_heads, 4),
num_layers=2,
dropout=dropout,
)
# ββ RNA input projection ββββββββββββββββββββββββββββββββββββββββββ
self.rna_proj = nn.Sequential(
nn.Linear(rna_dim, model_dim),
Mish(),
nn.LayerNorm(model_dim),
)
# ββ Cross-attention transformer stack βββββββββββββββββββββββββββββ
self.layers = nn.ModuleList([
CrossAttentionBlock(
dim=model_dim,
num_heads=num_heads,
time_dim=time_dim,
ff_mult=ff_mult,
dropout=dropout,
)
for _ in range(num_layers)
])
# ββ Output projection: predict noise in RNA embedding space ββββββ
self.out_norm = nn.LayerNorm(model_dim)
self.out_proj = nn.Sequential(
nn.Linear(model_dim, model_dim),
Mish(),
nn.Linear(model_dim, rna_dim),
)
self._init_weights()
def _init_weights(self):
"""
Initialize weights for stable diffusion training.
Uses PyTorch defaults (kaiming) for all layers, with a small-scale
init on the very last linear so the model starts by predicting
near-zero noise while still allowing gradient flow.
"""
# Small (not zero) init for the final output linear
nn.init.normal_(self.out_proj[2].weight, std=1e-4)
nn.init.zeros_(self.out_proj[2].bias)
def forward(
self,
noisy_rna: torch.Tensor, # (B, rna_dim) β noisy scGPT embedding
img_features: torch.Tensor, # (B, N, img_dim) β imaging features
timestep: torch.Tensor, # (B,) β diffusion timestep
) -> torch.Tensor:
"""
Predict the noise component in the noisy RNA embedding.
Returns:
predicted_noise: (B, rna_dim)
"""
# Time embedding
t_emb = self.time_embed(timestep) # (B, time_dim)
# Encode imaging context
context = self.img_encoder(img_features) # (B, N, model_dim)
# Project noisy RNA and add as a single token
rna = self.rna_proj(noisy_rna).unsqueeze(1) # (B, 1, model_dim)
# Cross-attention layers
for layer in self.layers:
rna = layer(rna, context, t_emb)
# Output projection
rna = self.out_norm(rna.squeeze(1)) # (B, model_dim)
noise_pred = self.out_proj(rna) # (B, rna_dim)
return noise_pred
@torch.no_grad()
def count_parameters(self) -> dict:
"""Count trainable and total parameters."""
total = sum(p.numel() for p in self.parameters())
trainable = sum(p.numel() for p in self.parameters() if p.requires_grad)
return {"total": total, "trainable": trainable}
|