{"title":"DIProT:基于深度学习的交互式工具包,用于高效和有效的蛋白质设计","authors":"Jieling He , Wenxu Wu , Xiaowo Wang","doi":"10.1016/j.synbio.2024.01.011","DOIUrl":null,"url":null,"abstract":"<div><p>The protein inverse folding problem, designing amino acid sequences that fold into desired protein structures, is a critical challenge in biological sciences. Despite numerous data-driven and knowledge-driven methods, there remains a need for a user-friendly toolkit that effectively integrates these approaches for in-silico protein design. In this paper, we present DIProT, an interactive protein design toolkit. DIProT leverages a non-autoregressive deep generative model to solve the inverse folding problem, combined with a protein structure prediction model. This integration allows users to incorporate prior knowledge into the design process, evaluate designs in silico, and form a virtual design loop with human feedback. Our inverse folding model demonstrates competitive performance in terms of effectiveness and efficiency on TS50 and CATH4.2 datasets, with promising sequence recovery and inference time. Case studies further illustrate how DIProT can facilitate user-guided protein design.</p></div>","PeriodicalId":22148,"journal":{"name":"Synthetic and Systems Biotechnology","volume":null,"pages":null},"PeriodicalIF":4.4000,"publicationDate":"2024-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2405805X24000115/pdfft?md5=5b3ed4052e1bca3e811b5172802c4dcb&pid=1-s2.0-S2405805X24000115-main.pdf","citationCount":"0","resultStr":"{\"title\":\"DIProT: A deep learning based interactive toolkit for efficient and effective Protein design\",\"authors\":\"Jieling He , Wenxu Wu , Xiaowo Wang\",\"doi\":\"10.1016/j.synbio.2024.01.011\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The protein inverse folding problem, designing amino acid sequences that fold into desired protein structures, is a critical challenge in biological sciences. Despite numerous data-driven and knowledge-driven methods, there remains a need for a user-friendly toolkit that effectively integrates these approaches for in-silico protein design. In this paper, we present DIProT, an interactive protein design toolkit. DIProT leverages a non-autoregressive deep generative model to solve the inverse folding problem, combined with a protein structure prediction model. This integration allows users to incorporate prior knowledge into the design process, evaluate designs in silico, and form a virtual design loop with human feedback. Our inverse folding model demonstrates competitive performance in terms of effectiveness and efficiency on TS50 and CATH4.2 datasets, with promising sequence recovery and inference time. Case studies further illustrate how DIProT can facilitate user-guided protein design.</p></div>\",\"PeriodicalId\":22148,\"journal\":{\"name\":\"Synthetic and Systems Biotechnology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.4000,\"publicationDate\":\"2024-02-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2405805X24000115/pdfft?md5=5b3ed4052e1bca3e811b5172802c4dcb&pid=1-s2.0-S2405805X24000115-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Synthetic and Systems Biotechnology\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2405805X24000115\",\"RegionNum\":2,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"BIOTECHNOLOGY & APPLIED MICROBIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Synthetic and Systems Biotechnology","FirstCategoryId":"99","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2405805X24000115","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOTECHNOLOGY & APPLIED MICROBIOLOGY","Score":null,"Total":0}
DIProT: A deep learning based interactive toolkit for efficient and effective Protein design
The protein inverse folding problem, designing amino acid sequences that fold into desired protein structures, is a critical challenge in biological sciences. Despite numerous data-driven and knowledge-driven methods, there remains a need for a user-friendly toolkit that effectively integrates these approaches for in-silico protein design. In this paper, we present DIProT, an interactive protein design toolkit. DIProT leverages a non-autoregressive deep generative model to solve the inverse folding problem, combined with a protein structure prediction model. This integration allows users to incorporate prior knowledge into the design process, evaluate designs in silico, and form a virtual design loop with human feedback. Our inverse folding model demonstrates competitive performance in terms of effectiveness and efficiency on TS50 and CATH4.2 datasets, with promising sequence recovery and inference time. Case studies further illustrate how DIProT can facilitate user-guided protein design.
期刊介绍:
Synthetic and Systems Biotechnology aims to promote the communication of original research in synthetic and systems biology, with strong emphasis on applications towards biotechnology. This journal is a quarterly peer-reviewed journal led by Editor-in-Chief Lixin Zhang. The journal publishes high-quality research; focusing on integrative approaches to enable the understanding and design of biological systems, and research to develop the application of systems and synthetic biology to natural systems. This journal will publish Articles, Short notes, Methods, Mini Reviews, Commentary and Conference reviews.