Curriculum-guided multimodal representation learning enables generalizable prediction of nanomaterial-protein interactions

TL;DR

This paper introduces CuMMI, a curriculum-guided multimodal model that predicts nanomaterial-protein interactions with high accuracy and robustness across unseen data, leveraging a large dataset and multi-stage training.

Contribution

The study presents a novel, generalizable framework combining multimodal data and curriculum learning to improve nanomaterial-protein interaction prediction.

Findings

CuMMI achieves mean classification metrics over 0.75 across multiple validation tests.

The model effectively generalizes to unseen nanomaterials and proteins.

Fine-tuning with limited data enhances performance significantly.

Abstract

Nanomaterial-protein interactions (NPI) are pivotal to realizing the therapeutic and diagnostic potential of nanomaterials. Although AI promises to accelerate mechanistic understanding and enable rational nanomaterial design, robust generalization to unseen nanomaterials or proteins remains unresolved. Here, we present CuMMI (curriculum-guided multimodal interaction model), a generalizable, explainable, and transferable model designed to infer NPI across complex biological settings. CuMMI leverages a self-constructed million-scale NPI dataset and adopts a multi-stage curriculum centered on human plasma, with progressively broader biofluid exposure to enhance data coverage and generalizability. By integrating protein sequence, structure, and a text-encoded experimental context of 37 features, CuMMI captures complementary material-specific, biochemical, and environmental information. Sample-level quality weights are assigned to ensure full utilization of available data while mitigating low-confidence and sparsely recorded entries. Ablation studies highlight the most influential tabular features, clarifying their contribution to the prediction. Through rigorous external validation across independence-preserving temporal, nanomaterial-held-out, and protein-held-out evaluations, our framework consistently achieves good performance (mean of five classification metrics exceeding 0.75), highlighting its robustness and generalizability to unseen data. Furthermore, fine-tuning on independent gold-nanoparticle data and a held-out protein subset further delivers better performance than training from scratch with substantially fewer samples. Together, our approach enables generalizable and transferable NPI prediction and may accelerate in vitro research and applications of nanomaterials.