Synergistic Attention-Guided Cascaded Graph Diffusion Model for Complementarity Determining Region Synthesis.

IF 10.2 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE IEEE transactions on neural networks and learning systems Pub Date : 2024-11-05 DOI:10.1109/TNNLS.2024.3477248
Rongchao Zhang, Yu Huang, Yiwei Lou, Weiping Ding, Yongzhi Cao, Hanpin Wang
{"title":"Synergistic Attention-Guided Cascaded Graph Diffusion Model for Complementarity Determining Region Synthesis.","authors":"Rongchao Zhang, Yu Huang, Yiwei Lou, Weiping Ding, Yongzhi Cao, Hanpin Wang","doi":"10.1109/TNNLS.2024.3477248","DOIUrl":null,"url":null,"abstract":"<p><p>Complementarity determining region (CDR) is a specific region in antibody molecules that binds to antigens, where a small portion of residues undergoes particularly pronounced variations. Generating CDRs with high affinity and specificity is a pivotal milestone in accelerating drug development for daunting and unresolved diseases. However, existing approaches predominantly center on characterizing the attributes of residues through sequential generation models, thus falling short in effectively modeling the intricate spatial correlations among residues and frequently succumbing to the trap of generating sequences that exhibit a high degree of arbitrariness. In this article, we propose a novel synergistic attention-guided cascaded graph diffusion model, termed GraphCas, which offers a pathway for optimized generation of high-affinity CDRs. Our approach is the first cascaded-based graph diffusion model for CDR synthesis. Specifically, we design a graph propagation algorithm with a relation-aware synergistic attention mechanism, enabling the targeted acquisition of structural insights from diverse protein sequences and bolstering the global information representation of the graph by precisely localizing to long-range key residue sites. We design a cascaded conditional enhanced diffusion approach, providing the capability to incorporate additional control constraints into the input. Experimental results demonstrate that GraphCas can generate photo-realistic CDRs and achieve performance comparable to top-tier approaches. In particular, GraphCas reduces the RMSD by nearly 0.42 units in the H1 region and improves the ERRAT by 9.36% points in the L1 region.</p>","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":null,"pages":null},"PeriodicalIF":10.2000,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on neural networks and learning systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/TNNLS.2024.3477248","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Complementarity determining region (CDR) is a specific region in antibody molecules that binds to antigens, where a small portion of residues undergoes particularly pronounced variations. Generating CDRs with high affinity and specificity is a pivotal milestone in accelerating drug development for daunting and unresolved diseases. However, existing approaches predominantly center on characterizing the attributes of residues through sequential generation models, thus falling short in effectively modeling the intricate spatial correlations among residues and frequently succumbing to the trap of generating sequences that exhibit a high degree of arbitrariness. In this article, we propose a novel synergistic attention-guided cascaded graph diffusion model, termed GraphCas, which offers a pathway for optimized generation of high-affinity CDRs. Our approach is the first cascaded-based graph diffusion model for CDR synthesis. Specifically, we design a graph propagation algorithm with a relation-aware synergistic attention mechanism, enabling the targeted acquisition of structural insights from diverse protein sequences and bolstering the global information representation of the graph by precisely localizing to long-range key residue sites. We design a cascaded conditional enhanced diffusion approach, providing the capability to incorporate additional control constraints into the input. Experimental results demonstrate that GraphCas can generate photo-realistic CDRs and achieve performance comparable to top-tier approaches. In particular, GraphCas reduces the RMSD by nearly 0.42 units in the H1 region and improves the ERRAT by 9.36% points in the L1 region.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
用于互补性决定区域合成的协同注意引导级联图扩散模型
互补决定区(CDR)是抗体分子中与抗原结合的特定区域,其中一小部分残基会发生特别明显的变化。产生具有高亲和力和特异性的 CDR 是加快药物开发的一个重要里程碑,可用于治疗令人生畏和尚未解决的疾病。然而,现有的方法主要是通过顺序生成模型来描述残基的属性,因此无法有效地模拟残基之间错综复杂的空间相关性,而且经常陷入生成具有高度任意性的序列的陷阱。在本文中,我们提出了一种新颖的协同注意力引导级联图扩散模型,称为 GraphCas,它为优化生成高亲和性 CDR 提供了一条途径。我们的方法是首个用于 CDR 合成的基于级联的图扩散模型。具体来说,我们设计了一种具有关系感知协同关注机制的图传播算法,可以有针对性地从不同的蛋白质序列中获取结构见解,并通过精确定位长程关键残基位点来增强图的全局信息表示。我们设计了一种级联条件增强扩散方法,能够在输入中加入额外的控制约束。实验结果表明,GraphCas 可以生成逼真的 CDR,其性能可与顶级方法媲美。特别是,GraphCas 将 H1 区域的 RMSD 降低了近 0.42 个单位,并将 L1 区域的 ERRAT 提高了 9.36% 个百分点。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
IEEE transactions on neural networks and learning systems
IEEE transactions on neural networks and learning systems COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-COMPUTER SCIENCE, HARDWARE & ARCHITECTURE
CiteScore
23.80
自引率
9.60%
发文量
2102
审稿时长
3-8 weeks
期刊介绍: The focus of IEEE Transactions on Neural Networks and Learning Systems is to present scholarly articles discussing the theory, design, and applications of neural networks as well as other learning systems. The journal primarily highlights technical and scientific research in this domain.
期刊最新文献
Analysis of Discrete-Time Switched Linear Systems Under Logical Dynamic Switching. Multiview Representation Learning With One-to-Many Dynamic Relationships. Secure and Efficient Federated Learning Against Model Poisoning Attacks in Horizontal and Vertical Data Partitioning. SRCD: Semantic Reasoning With Compound Domains for Single-Domain Generalized Object Detection. Synergistic Attention-Guided Cascaded Graph Diffusion Model for Complementarity Determining Region Synthesis.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1