{"title":"酶序列优化通过Gromov-Wasserstein自动编码器集成MSA技术。","authors":"Xuze Wang, Yangyang Li, Xiancong Hou, Hao Liu","doi":"10.1080/14756366.2025.2524742","DOIUrl":null,"url":null,"abstract":"<p><p>Enzyme sequence design has always been a challenging task, particularly in optimising key properties such as enzyme solubility, stability, and activity. This study proposes an innovative approach by utilising a variational autoencoder (VAE) model integrated with the Gromov-Wasserstein (GW) distance for enzyme sequence optimisation. The GWAE model improves representation learning by using the GW distance, thereby generating functional variants with desired characteristics. We also introduce an innovative enzyme dataset construction method that incorporates multiple sequence alignment (MSA) techniques to address sequence length discrepancies, enhancing the accuracy of the optimisation process. Experimental results show that the GWAE model outperforms the traditional VAE on multiple metrics. The generated enzyme sequences demonstrate superior solubility, stability, and hydrophobicity. Additionally, by integrating AlphaFold3 for structural prediction, we verify the structural stability of the generated sequences, further enhancing their practical applicability.</p>","PeriodicalId":15769,"journal":{"name":"Journal of Enzyme Inhibition and Medicinal Chemistry","volume":"40 1","pages":"2524742"},"PeriodicalIF":5.4000,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12231317/pdf/","citationCount":"0","resultStr":"{\"title\":\"Enzyme sequence optimisation via Gromov-Wasserstein Autoencoders integrating MSA techniques.\",\"authors\":\"Xuze Wang, Yangyang Li, Xiancong Hou, Hao Liu\",\"doi\":\"10.1080/14756366.2025.2524742\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Enzyme sequence design has always been a challenging task, particularly in optimising key properties such as enzyme solubility, stability, and activity. This study proposes an innovative approach by utilising a variational autoencoder (VAE) model integrated with the Gromov-Wasserstein (GW) distance for enzyme sequence optimisation. The GWAE model improves representation learning by using the GW distance, thereby generating functional variants with desired characteristics. We also introduce an innovative enzyme dataset construction method that incorporates multiple sequence alignment (MSA) techniques to address sequence length discrepancies, enhancing the accuracy of the optimisation process. Experimental results show that the GWAE model outperforms the traditional VAE on multiple metrics. The generated enzyme sequences demonstrate superior solubility, stability, and hydrophobicity. Additionally, by integrating AlphaFold3 for structural prediction, we verify the structural stability of the generated sequences, further enhancing their practical applicability.</p>\",\"PeriodicalId\":15769,\"journal\":{\"name\":\"Journal of Enzyme Inhibition and Medicinal Chemistry\",\"volume\":\"40 1\",\"pages\":\"2524742\"},\"PeriodicalIF\":5.4000,\"publicationDate\":\"2025-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12231317/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Enzyme Inhibition and Medicinal Chemistry\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1080/14756366.2025.2524742\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/7/3 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"BIOCHEMISTRY & MOLECULAR BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Enzyme Inhibition and Medicinal Chemistry","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1080/14756366.2025.2524742","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/7/3 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}
Enzyme sequence optimisation via Gromov-Wasserstein Autoencoders integrating MSA techniques.
Enzyme sequence design has always been a challenging task, particularly in optimising key properties such as enzyme solubility, stability, and activity. This study proposes an innovative approach by utilising a variational autoencoder (VAE) model integrated with the Gromov-Wasserstein (GW) distance for enzyme sequence optimisation. The GWAE model improves representation learning by using the GW distance, thereby generating functional variants with desired characteristics. We also introduce an innovative enzyme dataset construction method that incorporates multiple sequence alignment (MSA) techniques to address sequence length discrepancies, enhancing the accuracy of the optimisation process. Experimental results show that the GWAE model outperforms the traditional VAE on multiple metrics. The generated enzyme sequences demonstrate superior solubility, stability, and hydrophobicity. Additionally, by integrating AlphaFold3 for structural prediction, we verify the structural stability of the generated sequences, further enhancing their practical applicability.
期刊介绍:
Journal of Enzyme Inhibition and Medicinal Chemistry publishes open access research on enzyme inhibitors, inhibitory processes, and agonist/antagonist receptor interactions in the development of medicinal and anti-cancer agents.
Journal of Enzyme Inhibition and Medicinal Chemistry aims to provide an international and interdisciplinary platform for the latest findings in enzyme inhibition research.
The journal’s focus includes current developments in:
Enzymology;
Cell biology;
Chemical biology;
Microbiology;
Physiology;
Pharmacology leading to drug design;
Molecular recognition processes;
Distribution and metabolism of biologically active compounds.