Towards Unified AI Drug Discovery with Multiple Knowledge Modalities

TL;DR

KEDD is a unified multimodal deep learning framework that integrates structured knowledge and unstructured biomedical literature to enhance AI-driven drug discovery, showing significant improvements over existing methods.

Contribution

It introduces KEDD, a novel end-to-end multimodal framework that effectively combines heterogeneous knowledge sources for improved drug discovery tasks.

Findings

Achieves significant performance improvements over state-of-the-art methods

Effectively handles missing modalities with multi-head sparse attention

Demonstrates potential in real-world pharmaceutical applications

Abstract

In recent years, AI models that mine intrinsic patterns from molecular structures and protein sequences have shown promise in accelerating drug discovery. However, these methods partly lag behind real-world pharmaceutical approaches of human experts that additionally grasp structured knowledge from knowledge bases and unstructured knowledge from biomedical literature. To bridge this gap, we propose KEDD, a unified, end-to-end, and multimodal deep learning framework that optimally incorporates both structured and unstructured knowledge for vast AI drug discovery tasks. The framework first extracts underlying characteristics from heterogeneous inputs, and then applies multimodal fusion for accurate prediction. To mitigate the problem of missing modalities, we leverage multi-head sparse attention and a modality masking mechanism to extract relevant information robustly. Benefiting from integrated knowledge, our framework achieves a deeper understanding of molecule entities, brings significant improvements over state-of-the-art methods on a wide range of tasks and benchmarks, and reveals its promising potential in assisting real-world drug discovery.