Towards Unified AI Drug Discovery with Multiple Knowledge Modalities
This work addresses the gap in AI drug discovery by incorporating expert-like knowledge, potentially accelerating real-world pharmaceutical development, though it appears incremental as it builds on existing multimodal approaches.
The authors tackled the problem of AI drug discovery models lacking the structured and unstructured knowledge used by human experts, proposing KEDD, a unified multimodal framework that integrates these knowledge types, which achieved significant improvements over state-of-the-art methods across various tasks and benchmarks.
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.