We introduce IntFold, a controllable foundation model for general and specialized biomolecular structure prediction. Utilizing a high-performance custom attention kernel, IntFold achieves accuracy comparable to the state-of-the-art AlphaFold 3 on a comprehensive benchmark of diverse biomolecular structures, while also significantly outperforming other leading all-atom prediction approaches. The model's key innovation is its controllability, enabling downstream applications critical for drug screening and design. Through specialized adapters, it can be precisely guided to predict complex allosteric states, apply user-defined structural constraints, and estimate binding affinity. Furthermore, we present a training-free, similarity-based method for ranking predictions that improves success rates in a model-agnostic manner. This report details these advancements and shares insights from the training and development of this large-scale model.
@article{arxiv.2507.02025,
title = {IntFold: A Controllable Foundation Model for General and Specialized Biomolecular Structure Prediction},
author = {The IntFold Team and Leon Qiao and Wayne Bai and He Yan and Gary Liu and Nova Xi and Xiang Zhang and Siqi Sun},
journal= {arXiv preprint arXiv:2507.02025},
year = {2025}
}