MSAGPT:通过 MSA 生成式预训练神经提示蛋白质结构预测
MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training
AI总结:
本文提出 MSAGPT,通过 MSA 生成式预训练、二维进化位置编码及 AlphaFold2 反馈优化,在低同源信息场景生成虚拟 MSA 并提升蛋白质结构预测性能。
摘要:
多序列比对(Multiple Sequence Alignment,MSA)在揭示蛋白质家族的进化轨迹方面发挥着关键作用。对于缺乏足够同源信息以构建高质量 MSA 的蛋白质序列,蛋白质结构预测的准确性通常会受到损害。尽管已有多种方法被提出用于在这些条件下生成虚拟 MSA,但它们要么无法全面捕捉 MSA 内部复杂的共进化模式,要么需要来自外部 oracle 模型的指导。在此,我们提出 MSAGPT,这是一种在低 MSA 场景下通过 MSA 生成式预训练来提示蛋白质结构预测的新方法。MSAGPT 采用一种简单而有效的二维进化位置编码方案来建模复杂的进化模式。得益于此,其灵活的一维 MSA 解码框架支持零样本或少样本学习。此外,我们证明,利用来自 AlphaFold2 的反馈,可以通过拒绝微调(Rejective Fine-tuning,RFT)和来自 AF2 反馈的强化学习(Reinforcement Learning from AF2 Feedback,RLAF)进一步增强模型能力。大量实验证实了 MSAGPT 在生成可信虚拟 MSA 以提升结构预测准确性方面的有效性。其迁移学习能力也凸显了它在促进其他蛋白质任务方面的巨大潜力。
英文摘要:
Multiple Sequence Alignment (MSA) plays a pivotal role in unveiling the evolutionary trajectories of protein families. The accuracy of protein structure predictions is often compromised for protein sequences that lack sufficient homologous information to construct high quality MSA. Although various methods have been proposed to generate virtual MSA under these conditions, they fall short in comprehensively capturing the intricate coevolutionary patterns within MSA or require guidance from external oracle models. Here we introduce MSAGPT, a novel approach to prompt protein structure predictions via MSA generative pretraining in the low MSA regime. MSAGPT employs a simple yet effective 2D evolutionary positional encoding scheme to model complex evolutionary patterns. Endowed by this, its flexible 1D MSA decoding framework facilitates zero or few shot learning. Moreover, we demonstrate that leveraging the feedback from AlphaFold2 can further enhance the model capacity via Rejective Fine tuning (RFT) and Reinforcement Learning from AF2 Feedback (RLAF). Extensive experiments confirm the efficacy of MSAGPT in generating faithful virtual MSA to enhance the structure prediction accuracy. The transfer learning capabilities also highlight its great potential for facilitating other protein tasks.
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。