{"title":"基于能量的抗体优化和增强筛选的主动学习","authors":"Kairi Furui, Masahito Ohue","doi":"arxiv-2409.10964","DOIUrl":null,"url":null,"abstract":"Accurate prediction and optimization of protein-protein binding affinity is\ncrucial for therapeutic antibody development. Although machine learning-based\nprediction methods $\\Delta\\Delta G$ are suitable for large-scale mutant\nscreening, they struggle to predict the effects of multiple mutations for\ntargets without existing binders. Energy function-based methods, though more\naccurate, are time consuming and not ideal for large-scale screening. To\naddress this, we propose an active learning workflow that efficiently trains a\ndeep learning model to learn energy functions for specific targets, combining\nthe advantages of both approaches. Our method integrates the RDE-Network deep\nlearning model with Rosetta's energy function-based Flex ddG to efficiently\nexplore mutants that bind to Flex ddG. In a case study targeting HER2-binding\nTrastuzumab mutants, our approach significantly improved the screening\nperformance over random selection and demonstrated the ability to identify\nmutants with better binding properties without experimental $\\Delta\\Delta G$\ndata. This workflow advances computational antibody design by combining machine\nlearning, physics-based computations, and active learning to achieve more\nefficient antibody development.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Active learning for energy-based antibody optimization and enhanced screening\",\"authors\":\"Kairi Furui, Masahito Ohue\",\"doi\":\"arxiv-2409.10964\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Accurate prediction and optimization of protein-protein binding affinity is\\ncrucial for therapeutic antibody development. Although machine learning-based\\nprediction methods $\\\\Delta\\\\Delta G$ are suitable for large-scale mutant\\nscreening, they struggle to predict the effects of multiple mutations for\\ntargets without existing binders. Energy function-based methods, though more\\naccurate, are time consuming and not ideal for large-scale screening. To\\naddress this, we propose an active learning workflow that efficiently trains a\\ndeep learning model to learn energy functions for specific targets, combining\\nthe advantages of both approaches. Our method integrates the RDE-Network deep\\nlearning model with Rosetta's energy function-based Flex ddG to efficiently\\nexplore mutants that bind to Flex ddG. In a case study targeting HER2-binding\\nTrastuzumab mutants, our approach significantly improved the screening\\nperformance over random selection and demonstrated the ability to identify\\nmutants with better binding properties without experimental $\\\\Delta\\\\Delta G$\\ndata. This workflow advances computational antibody design by combining machine\\nlearning, physics-based computations, and active learning to achieve more\\nefficient antibody development.\",\"PeriodicalId\":501266,\"journal\":{\"name\":\"arXiv - QuanBio - Quantitative Methods\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuanBio - Quantitative Methods\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.10964\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuanBio - Quantitative Methods","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.10964","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Active learning for energy-based antibody optimization and enhanced screening
Accurate prediction and optimization of protein-protein binding affinity is
crucial for therapeutic antibody development. Although machine learning-based
prediction methods $\Delta\Delta G$ are suitable for large-scale mutant
screening, they struggle to predict the effects of multiple mutations for
targets without existing binders. Energy function-based methods, though more
accurate, are time consuming and not ideal for large-scale screening. To
address this, we propose an active learning workflow that efficiently trains a
deep learning model to learn energy functions for specific targets, combining
the advantages of both approaches. Our method integrates the RDE-Network deep
learning model with Rosetta's energy function-based Flex ddG to efficiently
explore mutants that bind to Flex ddG. In a case study targeting HER2-binding
Trastuzumab mutants, our approach significantly improved the screening
performance over random selection and demonstrated the ability to identify
mutants with better binding properties without experimental $\Delta\Delta G$
data. This workflow advances computational antibody design by combining machine
learning, physics-based computations, and active learning to achieve more
efficient antibody development.