提出Hyformer模型，实现分子生成与性质预测的协同优化。
Synergistic Benefits of Joint Molecule Generation and Property Prediction
- 基于Transformer设计交替注意力机制，融合生成与预测功能。
- 在条件采样和分布外预测中表现优于单一任务模型。
- 适合药物研发中的新型抗菌肽发现场景。
联合建模数据样本及其属性的分布，可构建一个同时支持数据生成与属性预测的单一模型，带来超越纯生成或纯预测模型的协同优势。然而，联合模型的训练面临严峻的架构与优化挑战。本文提出Hyformer，一种基于Transformer的联合模型，通过交替注意力机制和联合预训练策略，成功融合生成与预测功能。实验表明，Hyformer在分子生成与属性预测上均实现了同步优化，并在条件采样、分布外属性预测及表征学习方面展现出显著协同优势。最后，在新抗菌肽发现的药物设计用例中验证了联合学习的实际价值。
原文摘要 · Abstract (English)
Modeling the joint distribution of data samples and their properties allows to construct a single model for both data generation and property prediction, with synergistic benefits reaching beyond purely generative or predictive models. However, training joint models presents daunting architectural and optimization challenges. Here, we propose Hyformer, a transformer-based joint model that successfully blends the generative and predictive functionalities, using an alternating attention mechanism and a joint pre-training scheme. We show that Hyformer is simultaneously optimized for molecule generation and property prediction, while exhibiting synergistic benefits in conditional sampling, out-of-distribution property prediction and representation learning. Finally, we demonstrate the benefits of joint learning in a drug design use case of discovering novel antimicrobial~peptides.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。