README.md

---
license: cc-by-4.0
configs:
- config_name: affinity
  default: true
  data_files:
  - split: train
    path: data/affinity/data.csv
- config_name: p_ood_25
  data_dir: data/p_ood_25
- config_name: p_ood_28
  data_dir: data/p_ood_28
- config_name: p_ood_31
  data_dir: data/p_ood_31
- config_name: p_ood_33
  data_dir: data/p_ood_33
---

# InteractBind  

> A physically grounded, large-scale protein–ligand interaction dataset  
> for interpretable and interaction-aware binding prediction  

---

## Links

- Paper: [A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just Binding Likelihood?](https://arxiv.org/abs/2605.24045)
- Github: [ZhaohanM/InteractBind](https://github.com/ZhaohanM/InteractBind)

---

## Motivation  

Most existing protein–ligand binding datasets provide only coarse-grained supervision, such as binary labels or scalar affinity values. While effective for prediction, these signals compress complex molecular interaction processes into a single outcome, limiting interpretability and mechanistic understanding.

**InteractBind** addresses this limitation by explicitly modelling *non-covalent interaction patterns* derived from experimentally resolved protein–ligand complexes.  

It enables **token-level supervision**, bridging sequence-based representations with physically meaningful interaction structures.

---

## Dataset Overview  

InteractBind is constructed from high-quality experimentally resolved complexes and includes:

- Protein sequences (FASTA and structure-aware sequence)
- Ligand molecular representations (SMILES and SELFIES)
- Binding labels and affinity annotations
- Token-level non-covalent interaction maps  

The dataset is designed to support both **prediction accuracy** and **mechanistic interpretability**.

---
## Dataset

This repository provides benchmark CSVs with true residue-level interaction maps for PLI prediction evaluation.

| Dataset | Type | Example Use |
|----------|------|--------------|
| InteractBind (affinity) | Binding affinity splits | Evaluate in-domain |
| InteractBind-P-25%/28%/31%/33% OOD | Protein OOD splits | Evaluate novel protein generalisation |

## Files

The Hugging Face Dataset Viewer is configured to read the CSV subsets under `data/`:

- `affinity`: the full InteractBind affinity table.
- `p_ood_25`, `p_ood_28`, `p_ood_31`, `p_ood_33`: protein OOD benchmark subsets with `train`, `validation`, and `test` splits.

Each CSV includes seven residue-level binding-site fingerprint columns derived from the interaction maps:

- `Hydrogen bonding_binding_site`
- `Salt Bridges_binding_site`
- `π–π Stacking_binding_site`
- `Cation–π_binding_site`
- `Hydrophobic_binding_site`
- `Van der Waals_binding_site`
- `Overall_binding_site`

Each value is a binary list aligned to the protein FASTA sequence. For example, `[0,0,1,0]` marks the third residue as a binding-site residue. Negative protein-ligand pairs without contact-map entries are encoded as all-zero fingerprints.

## Supported Interaction Types  

Structured annotations are provided for major non-covalent interaction categories:

- Hydrogen bonds  
- Hydrophobic interactions  
- Salt bridges  
- π–π stacking  
- π–cation interactions  
- Van der Waals contacts  

Each interaction channel can be used independently or combined for multi-channel supervision.

---

## Key Features  

- **Physically grounded supervision**  
  Derived from experimentally resolved complexes rather than heuristic attention signals.  

- **Token-level interaction maps**  
  Enables fine-grained modelling of residue–atom interactions.  

- **Model-agnostic integration**  
  Compatible with sequence-based encoders (e.g., ESM, SELFormer, and other protein–ligand models).  

- **Interpretability support**  
  Facilitates binding residue identification and interaction pattern analysis.  

- **Scalable design**  
  Allows large-scale training without requiring full structural modelling during inference.  

---

## Research Applications  

InteractBind supports a broad range of research directions:

- Protein–ligand binding prediction  
- Binding site/pocket localisation 
- Interaction-aware representation learning  
- Mechanistic hypothesis generation  
- Drug discovery and virtual screening  
- Explainable AI for molecular modelling  

---

## Citation

If you use InteractBind in your research, please cite:

```bibtex
@misc{meng2026largescaleinteractbind,
  title = {A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just Binding Likelihood?},
  author = {Meng, Zhaohan and Bai, Zhen and Yuan, Ke and Ounis, Iadh and Meng, Zaiqiao and Xu, Hao and Loscalzo, Joseph},
  year = {2026},
  eprint = {2605.24045},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2605.24045}
}
```