Deep Reinforcement Learning for Modelling Protein Complexes
作者: Ziqi Gao, Tao Feng, Jiaxuan You, Chenyi Zi, Yan Zhou, Chen Zhang, Jia Li
分类: cs.CE, cs.LG
发布日期: 2024-03-11 (更新: 2024-05-07)
备注: International Conference on Learning Representations (ICLR 2024)
💡 一句话要点
提出GAPN以解决多链蛋白复合体建模的挑战
🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture)
关键词: 蛋白质复合体建模 深度强化学习 生成对抗网络 组合优化 生物信息学
📋 核心要点
- 现有的多链蛋白复合体建模方法在面对链数增加时,组合优化空间巨大,计算成本高,且模型在不同规模的蛋白复合体上泛化能力不足。
- 本文提出了一种生成对抗策略网络(GAPN),通过领域特定奖励和对抗损失,优化多链蛋白复合体的自动预测过程,提升搜索效率。
- 实验结果显示,GAPN在RMSD和TM-Score指标上均显著提高了准确性和效率,相较于领先的蛋白复合体建模软件有明显优势。
📝 摘要(中文)
AlphaFold可以用于单链和多链蛋白结构预测,但多链蛋白的结构预测在链数增加时变得极具挑战性。本文提出了一种基于无向无环连通图的多链蛋白复合体建模方法,利用生成对抗策略网络(GAPN)来应对组合优化空间巨大和蛋白复合体规模分布偏移的挑战。GAPN通过领域特定奖励和对抗损失优化,能够高效搜索组装空间并提升模型的全局感知能力。实验结果表明,GAPN在准确性和效率上均显著优于现有的蛋白复合体建模软件。
🔬 方法详解
问题定义:本文旨在解决多链蛋白复合体建模中的组合优化问题,现有方法在链数增加时计算成本高且泛化能力不足。
核心思路:提出GAPN,通过生成对抗学习和领域特定奖励,优化蛋白复合体的组装过程,提升模型的搜索效率和准确性。
技术框架:GAPN的整体架构包括节点表示(每条链作为节点)、边表示(组装动作作为边)、生成对抗网络结构和策略梯度优化模块。
关键创新:GAPN设计了对抗奖励函数,增强了模型的感知能力,使其能够同时关注特定复合体和全局组装规则,显著提高了模型的泛化能力。
关键设计:在GAPN中,采用了领域特定的奖励机制和对抗损失函数,通过策略梯度方法优化直接对接奖励,确保模型在不同规模的蛋白复合体上均能有效学习。
📊 实验亮点
实验结果表明,GAPN在RMSD和TM-Score指标上均显著优于现有的蛋白复合体建模软件,准确性和效率提升幅度达到XX%(具体数据待补充),展示了其在实际应用中的巨大潜力。
🎯 应用场景
该研究的潜在应用领域包括生物医药、药物设计和分子生物学等。通过提高多链蛋白复合体的建模精度,GAPN可以为新药研发和生物机制研究提供重要支持,推动相关领域的进步与发展。
📄 摘要(原文)
AlphaFold can be used for both single-chain and multi-chain protein structure prediction, while the latter becomes extremely challenging as the number of chains increases. In this work, by taking each chain as a node and assembly actions as edges, we show that an acyclic undirected connected graph can be used to predict the structure of multi-chain protein complexes (a.k.a., protein complex modelling, PCM). However, there are still two challenges: 1) The huge combinatorial optimization space of $N^{N-2}$ ($N$ is the number of chains) for the PCM problem can easily lead to high computational cost. 2) The scales of protein complexes exhibit distribution shift due to variance in chain numbers, which calls for the generalization in modelling complexes of various scales. To address these challenges, we propose GAPN, a Generative Adversarial Policy Network powered by domain-specific rewards and adversarial loss through policy gradient for automatic PCM prediction. Specifically, GAPN learns to efficiently search through the immense assembly space and optimize the direct docking reward through policy gradient. Importantly, we design an adversarial reward function to enhance the receptive field of our model. In this way, GAPN will simultaneously focus on a specific batch of complexes and the global assembly rules learned from complexes with varied chain numbers. Empirically, we have achieved both significant accuracy (measured by RMSD and TM-Score) and efficiency improvements compared to leading PCM softwares.