Update README.md

README.md

@@ -1,3 +1,116 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+tags:
+  - graph-neural-networks
+  - histopathology
+  - self-supervised-learning
+  - pytorch-geometric
+  - graph-representation-learning
+datasets:
+  - graph-tcga-brca
+library_name: pytorch
+---
+
+# GrapHist: Graph Self-Supervised Learning for Histopathology
+
+This repository contains the pre-trained model from [GrapHist](https://github.com/ogutsevda/graphist). Pre-trained on the [graph-tcga-brca](https://huggingface.co/datasets/ogutsevda/graph-tcga-brca) dataset, it employs an **ACM-GIN** (Adaptive Channel Mixing Graph Isomorphism Network) encoder-decoder architecture with a masked node attribute prediction objective.
+
+<p align="center">
+  <img src="graphist.png" alt="GrapHist architecture" width="100%">
+</p>
+
+## Repository Structure
+
+```
+graphist/
+├── graphist.pt            # Pre-trained model checkpoint
+├── graphist.png           # Architecture overview
+├── models/
+│   ├── __init__.py        # build_model(args) factory
+│   ├── edcoder.py         # PreModel encoder-decoder wrapper
+│   ├── acm_gin.py         # ACM-GIN backbone (encoder/decoder)
+│   └── utils.py           # Activation and normalization helpers
+└── README.md
+```
+
+## Requirements
+
+```
+torch
+torch-geometric
+huggingface_hub
+```
+
+The model expects graphs in PyTorch Geometric format with `x`, `edge_index`, `edge_attr`, and `batch`.
+
+## Usage
+
+### 1. Clone the repository
+
+```python
+from huggingface_hub import snapshot_download
+
+repo_path = snapshot_download(repo_id="ogutsevda/graphist")
+```
+
+### 2. Build and load the model
+
+```python
+import sys, torch
+sys.path.insert(0, repo_path)
+
+from models import build_model
+
+class Args:
+    encoder = "acm_gin"
+    decoder = "acm_gin"
+    drop_edge_rate = 0.0
+    mask_rate = 0.5
+    replace_rate = 0.1
+    num_hidden = 512
+    num_layers = 5
+    num_heads = 4
+    num_out_heads = 1
+    residual = None
+    attn_drop = 0.1
+    in_drop = 0.2
+    norm = None
+    negative_slope = 0.2
+    batchnorm = False
+    activation = "prelu"
+    loss_fn = "sce"
+    alpha_l = 3
+    concat_hidden = True
+    num_features = 46
+    num_edge_features = 1
+
+args = Args()
+model = build_model(args)
+checkpoint = torch.load(f"{repo_path}/graphist.pt", weights_only=False)
+model.load_state_dict(checkpoint["model_state_dict"])
+model.eval()
+```
+
+### 3. Generate embeddings
+
+```python
+with torch.no_grad():
+    embeddings = model.embed(
+        batch.x, batch.edge_index, batch.edge_attr, batch.batch
+    )
+```
+
+## Acknowledgements
+
+The model architecture adapts code from [GraphMAE](https://github.com/THUDM/GraphMAE) and [ACM-GNN](https://github.com/SitaoLuan/ACM-GNN).
+
+## Citation
+
+```bibtex
+@article{graphist2025,
+  title     = {GrapHist: Graph Self-Supervised Learning for Histopathology},
+  author    = {TODO},
+  journal   = {TODO},
+  year      = {2025},
+}
+```