Bgoood/SpatialGT-MouseStroke-Sham

SpatialGT Finetuned Model - Mouse Stroke (Sham)

Model Description

This is the finetuned checkpoint of SpatialGT on mouse stroke Sham (control) spatial transcriptomics data.

This model is specifically finetuned for the mouse stroke perturbation simulation case study, trained on the Sham1-1 slice.

Model Details

• Base Model: SpatialGT Pretrained
• Finetuning Data: Mouse stroke Sham1-1 slice (Visium)
• Finetuning Strategy: Full finetuning (8 transformer layers unfrozen)
• Epochs: 100
• Learning Rate: 1e-4

Usage

import torch
from pretrain.model_spatialpt import SpatialNeighborTransformer
from pretrain.Config import Config

# Load configuration
config = Config()

# Initialize model
model = SpatialNeighborTransformer(config)

# Load finetuned weights
from safetensors.torch import load_file
state_dict = load_file("model.safetensors")
model.load_state_dict(state_dict)

model.eval()

Intended Use

This model is intended for:

• Reconstructing gene expression in mouse brain tissue
• Simulating perturbation effects in stroke-affected regions
• Comparative analysis with PT (stroke) model

Files

• model.safetensors: Model weights in safetensors format
• training_args.bin: Training arguments

Related Models

• SpatialGT-Pretrained: Base pretrained model
• SpatialGT-MouseStroke-PT: Finetuned on PT (stroke) slice

Citation

If you use this model, please cite our paper (details to be added upon publication).

License

MIT License