看向另一边：通过负数据设计'积极'分子的分子任务算术
Look the Other Way: Designing 'Positive' Molecules with Negative Data via Task Arithmetic
AI总结：
通过负数据训练模型学习属性方向，生成多样且成功的分子设计，为de novo分子设计提供高效迁移学习方法。
摘要：
desirable properties 的分子稀缺性是生成分子设计的固有瓶颈。为绕过这一障碍，我们提出分子任务算术：在多样且丰富的负例上训练模型，以学习'属性方向'——无需访问任何正例数据，并通过向相反属性方向移动模型来生成正例分子。在33个设计实验中分析，涉及不同的分子实体（小分子、蛋白质）、模型架构和规模，分子任务算术生成的分子设计在多样性与成功率上均优于基于正例分子训练的模型。此外，我们还利用分子任务算术在双目标和少样本设计任务中。我们发现分子任务算术能够一致地增加设计的多样性，同时保持良好的设计属性，如与蛋白质的良好对接分数。其简单性、数据效率和性能使其有潜力成为de novo分子设计的事实迁移学习策略。
英文摘要：
The scarcity of molecules with desirable properties (i.e., `positive' molecules) is an inherent bottleneck for generative molecule design. To sidestep such obstacle, here we propose molecular task arithmetic: training a model on diverse and abundant negative examples to learn 'property directions' - without accessing any positively labeled data - and moving models in the opposite property directions to generate positive molecules. When analyzed on 33 design experiments with distinct molecular entities (small molecules, proteins), model architectures, and scales, molecular task arithmetic generated more diverse and successful designs than models trained on positive molecules in general. Moreover, we employed molecular task arithmetic in dual-objective and few-shot design tasks. We find that molecular task arithmetic can consistently increase the diversity of designs while maintaining desirable complex design properties, such as good docking scores to a protein. With its simplicity, data efficiency, and performance, molecular task arithmetic bears the potential to become the de facto transfer learning strategy for de novo molecule design.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
