ProtLink: Multispecies HGT for interactome prediction

GitHub Repository: straight-no-chaser/ProtLink

ProtLink combines frozen ESM-2 protein embeddings, species-specific interaction networks, and orthogroup relationships to predict human protein–protein interactions (PPIs). It provides a sequence only baseline and a heterogeneous graph transformer (HGT) pipeline, together with API for controlled graph ablations and held out protein evaluation.

The model uses a 3-layer, 4-head HGT encoder with an MLP link decoder. Protein features are derived from ESM-2 T33/650M using mean-pooled final layer residue embeddings. The model is evaluated on human–human PPI prediction, with non-human PPI and protein–orthogroup edges as graph context.

Load test

pip install -r requirements.txt
python inference.py --config config.json --weights model.safetensors

A successful run constructs the exact released HGT + MLP decoder and performs load_state_dict(..., strict=True).

Score an edge

inference.py expects the same heterogeneous graph schema used in training. Save the inference HeteroData object as inference_graph.pt, then run:

python inference.py --graph inference_graph.pt --edge 123 456

The two integers are protein node indices in that graph.

Deployment detail

HGT inference is graph-conditioned. The model weights alone do not contain the protein ESM-2 features, PPI context edges, or protein-to-orthogroup membership edges. Those must be reconstructed with the same indexing/schema as training.

Downloads last month
45
Safetensors
Model size
5M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support