A million-scale dataset and generalizable foundation model for nanomaterial-protein interactions
This work addresses the challenge of understanding nanomaterial-protein interactions for applications in medicine and environmental science, representing a significant but incremental advance through dataset scaling and multimodal modeling.
The authors tackled the problem of predicting nanomaterial-protein interactions, which is hindered by limited datasets and poor model generalizability, by creating NanoPro-3M, a dataset with over 3.2 million samples and 37,000 unique proteins, and developing NanoProFormer, a foundational model that significantly outperforms single-modality approaches and enables zero-shot inference and fine-tuning for various downstream tasks.
Unlocking the potential of nanomaterials in medicine and environmental science hinges on understanding their interactions with proteins, a complex decision space where AI is poised to make a transformative impact. However, progress has been hindered by limited datasets and the restricted generalizability of existing models. Here, we propose NanoPro-3M, the largest nanomaterial-protein interaction dataset to date, comprising over 3.2 million samples and 37,000 unique proteins. Leveraging this, we present NanoProFormer, a foundational model that predicts nanomaterial-protein affinities through multimodal representation learning, demonstrating strong generalization, handling missing features, and unseen nanomaterials or proteins. We show that multimodal modeling significantly outperforms single-modality approaches and identifies key determinants of corona formation. Furthermore, we demonstrate its applicability to a range of downstream tasks through zero-shot inference and fine-tuning. Together, this work establishes a solid foundation for high-performance and generalized prediction of nanomaterial-protein interaction endpoints, reducing experimental reliance and accelerating various in vitro applications.