File size: 11,798 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 | """
PhenoSeq inference pipeline.
Self-contained entry point for generating scGPT RNA-seq embeddings from
ViT-L microscopy imaging features using a pretrained diffusion model.
Quick start
-----------
>>> import numpy as np
>>> from pipeline import PhenoSeqPipeline
>>>
>>> # Load from a local directory (or a HuggingFace repo id)
>>> pipe = PhenoSeqPipeline.from_pretrained(".")
>>>
>>> # img_features: (n_cells, n_imaging_cells, 5120) — raw ViT-L embeddings
>>> # img_norm is loaded automatically from img_norm.npz when present
>>> rna = pipe(img_features) # → np.ndarray (n_cells, 512)
Input format
------------
img_features : np.ndarray or torch.Tensor
Shape (B, N, 5120) where
B = number of target RNA cells to generate
N = number of imaging cells per well (default 16)
Features should be raw (unnormalized) ViT-L embeddings when img_norm
is available, or pre-normalized when img_norm is None.
Output format
-------------
np.ndarray of shape (B, 512) — scGPT embedding space predictions,
un-normalized back to the original scGPT scale.
"""
from __future__ import annotations
import logging
import os
from pathlib import Path
from typing import Optional, Union
import numpy as np
import torch
import yaml
logger = logging.getLogger(__name__)
# ──────────────────────────────────────────────────────────────────────────────
# Pipeline
# ──────────────────────────────────────────────────────────────────────────────
class PhenoSeqPipeline:
"""
Wraps the trained PhenoSeq diffusion model for single-cell RNA prediction.
Parameters
----------
diffusion : GaussianDiffusion
Loaded diffusion model (weights applied, eval mode).
img_norm : dict with 'mean' and 'std' arrays of shape (5120,), optional
Imaging normalisation statistics computed from the training split.
If None, input features are assumed to be pre-normalized.
device : str or torch.device
Device for inference ('cuda', 'cpu', etc.).
ddim_steps : int
Number of DDIM denoising steps (50 is a good default; 0 = full DDPM).
"""
def __init__(
self,
diffusion,
img_norm: Optional[dict] = None,
device: Union[str, torch.device] = "cpu",
ddim_steps: int = 50,
):
self.diffusion = diffusion
self.img_norm = img_norm
self.device = torch.device(device)
self.ddim_steps = ddim_steps
self.diffusion.to(self.device).eval()
# ── Factory ───────────────────────────────────────────────────────────
@classmethod
def from_pretrained(
cls,
model_dir: Union[str, Path] = ".",
checkpoint_name: str = "best_model.pt",
img_norm_name: str = "img_norm.npz",
device: Optional[Union[str, torch.device]] = None,
ddim_steps: int = 50,
use_ema: bool = True,
) -> "PhenoSeqPipeline":
"""
Load a pipeline from a local directory or HuggingFace Hub repo.
Parameters
----------
model_dir : str or Path
Local path or HuggingFace Hub repo id containing the checkpoint.
checkpoint_name : str
Filename of the PyTorch checkpoint inside model_dir.
img_norm_name : str
Filename of the imaging normalisation stats (.npz with 'mean', 'std').
If the file is not found, img_norm is set to None and a warning is logged.
device : str, torch.device, or None
Target device; auto-selects CUDA when available if None.
ddim_steps : int
DDIM sampling steps.
use_ema : bool
Prefer EMA weights when available in the checkpoint (recommended).
"""
model_dir = Path(model_dir)
# ── Resolve from HuggingFace Hub if path doesn't exist locally ────
if not model_dir.exists():
try:
from huggingface_hub import snapshot_download
model_dir = Path(snapshot_download(str(model_dir)))
logger.info(f"Downloaded from HuggingFace Hub → {model_dir}")
except Exception as exc:
raise FileNotFoundError(
f"Directory '{model_dir}' not found locally and Hub download failed: {exc}"
) from exc
if device is None:
device = "cuda" if torch.cuda.is_available() else "cpu"
device = torch.device(device)
# ── Load checkpoint ───────────────────────────────────────────────
ckpt_path = model_dir / checkpoint_name
if not ckpt_path.exists():
raise FileNotFoundError(f"Checkpoint not found: {ckpt_path}")
logger.info(f"Loading checkpoint from {ckpt_path}")
ckpt = torch.load(ckpt_path, map_location="cpu", weights_only=False)
# ── Build model from embedded config ──────────────────────────────
cfg = ckpt.get("config", {})
mc = ckpt.get("model_cfg", cfg.get("model", {}))
dc = cfg.get("diffusion", {})
from models.denoiser import Img2RNADenoiser
from models.diffusion import GaussianDiffusion
# RNA normalisation is stored in the checkpoint
rna_norm_raw = ckpt.get("rna_norm")
rna_norm = (
{"mean": np.array(rna_norm_raw["mean"]), "std": np.array(rna_norm_raw["std"])}
if rna_norm_raw is not None else None
)
denoiser = Img2RNADenoiser(
img_dim = mc.get("img_dim", 5120),
rna_dim = mc.get("rna_dim", 512),
model_dim = mc.get("model_dim", 1024),
num_heads = mc.get("num_heads", 8),
num_layers= mc.get("num_layers", 6),
time_dim = mc.get("time_dim", 256),
ff_mult = mc.get("ff_mult", 4),
dropout = 0.0,
)
diffusion = GaussianDiffusion(
denoiser = denoiser,
num_steps = dc.get("num_steps", 1000),
schedule = dc.get("schedule", "cosine"),
beta_start = dc.get("beta_start", 1e-4),
beta_end = dc.get("beta_end", 0.02),
rna_norm = rna_norm,
)
# ── Load weights ──────────────────────────────────────────────────
ema_state = ckpt.get("ema_state_dict")
if use_ema and ema_state is not None:
logger.info("Loading EMA weights")
diffusion.denoiser.load_state_dict(
{k.removeprefix("denoiser."): v for k, v in ema_state.items()},
strict=False,
)
else:
if use_ema and ema_state is None:
logger.warning("EMA weights not found; using standard model weights")
diffusion.load_state_dict(ckpt["model_state_dict"], strict=True)
n_params = sum(p.numel() for p in denoiser.parameters())
logger.info(f"Model loaded ({n_params:,} parameters) on {device}")
# ── Imaging normalisation stats ───────────────────────────────────
img_norm = None
norm_path = model_dir / img_norm_name
if norm_path.exists():
data = np.load(norm_path)
img_norm = {"mean": data["mean"], "std": data["std"]}
logger.info(f"Loaded imaging normalisation stats from {norm_path}")
else:
logger.warning(
f"{img_norm_name} not found in {model_dir}. "
"Pass pre-normalized imaging features, or provide img_norm manually. "
"See save_img_norm.py to generate this file from your training data."
)
return cls(diffusion, img_norm=img_norm, device=device, ddim_steps=ddim_steps) # type: ignore[return-value]
# ── Inference ─────────────────────────────────────────────────────────
@torch.no_grad()
def __call__(
self,
img_features: Union[np.ndarray, torch.Tensor],
batch_size: int = 256,
ddim_steps: Optional[int] = None,
) -> np.ndarray:
"""
Generate scGPT RNA-seq embeddings from imaging features.
Parameters
----------
img_features : array-like, shape (B, N, 5120) or (N, 5120)
ViT-L imaging embeddings. When img_norm is available these should
be raw (unnormalized); otherwise provide pre-normalized features.
If 2D (N, 5120), a batch dimension is added automatically.
batch_size : int
Number of cells processed per forward pass.
ddim_steps : int, optional
Override the pipeline's default DDIM steps for this call.
Pass 0 to use full DDPM sampling (slower, ~1000 steps).
Returns
-------
np.ndarray of shape (B, 512)
Predicted scGPT-space RNA embeddings in the original (denormalized) scale.
"""
steps = ddim_steps if ddim_steps is not None else self.ddim_steps
# Coerce to numpy then torch
if isinstance(img_features, torch.Tensor):
img_np = img_features.cpu().float().numpy()
else:
img_np = np.asarray(img_features, dtype=np.float32)
# Add batch dim if single sample
if img_np.ndim == 2:
img_np = img_np[np.newaxis]
if img_np.ndim != 3 or img_np.shape[-1] != 5120:
raise ValueError(
f"Expected img_features shape (B, N, 5120), got {img_np.shape}"
)
# Normalize imaging features if stats are available
if self.img_norm is not None:
mean = self.img_norm["mean"].astype(np.float32) # (5120,)
std = self.img_norm["std"].astype(np.float32) # (5120,)
img_np = (img_np - mean) / std
# Batch inference
all_preds: list[np.ndarray] = []
for start in range(0, len(img_np), batch_size):
chunk = torch.from_numpy(img_np[start : start + batch_size]).to(self.device)
if steps > 0:
preds = self.diffusion.sample_ddim(
img_features = chunk,
num_inference_steps = steps,
eta = 0.0,
)
else:
preds = self.diffusion.sample(chunk)
all_preds.append(preds.cpu().float().numpy())
return np.concatenate(all_preds, axis=0) # (B, 512)
# ── Convenience ───────────────────────────────────────────────────────
@property
def rna_dim(self) -> int:
return self.diffusion.denoiser.rna_dim
def __repr__(self) -> str:
d = self.diffusion.denoiser
return (
f"PhenoSeqPipeline("
f"rna_dim={d.rna_dim}, "
f"model_dim={d.model_dim}, num_layers={len(d.layers)}, "
f"ddim_steps={self.ddim_steps}, device={self.device})"
)
|