Mol-JEPA: 分子のためのマルチモーダル統合予測アーキテクチャ
Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules
分子構造や細胞表現型など複数のデータモダリティを潜在空間で予測することで、化学的に無効な拡張やモダリティ崩壊などの問題を解決する分子基盤モデルを提案した。
著者: Florian Rottach, Sebastian Schieferdecker, William Rudman, Randall Balestriero, Carsten Eickhoff
分類: cs.LG, cs.AI
原文アブストラクト
Despite recent advances in molecular foundation models, several limitations remain, such as chemically invalid augmentations, modality collapse, and incomplete representation of biochemical environments. To address these challenges, we present \textbf{Mol-JEPA}, a scalable framework for learning molecular world models. Rather than relying on suboptimal molecular perturbations, our model uses modality masking to exploit information from molecular structures, cellular phenotypes, binding affinities, ADMET profiles, quantum chemistry simulations and other drug discovery data. Across various benchmarks, we show that the representations learned by Mol-JEPA deliver strong performance, demonstrating the value of incorporating biochemical context through latent space prediction.