基于机器学习的天然产物基因组挖掘和生物活性预测。
Machine Learning-Enabled Genome Mining and Bioactivity Prediction of Natural Products.
机构信息
Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Urbana, Illinois 61801, United States.
Department of Chemical and Biomolecular Engineering, University of Illinois at Urbana-Champaign, Urbana, Illinois 61801, United States.
出版信息
ACS Synth Biol. 2023 Sep 15;12(9):2650-2662. doi: 10.1021/acssynbio.3c00234. Epub 2023 Aug 22.
Abstract
Natural products (NPs) produced by microorganisms and plants are a major source of drugs, herbicides, and fungicides. Thanks to recent advances in DNA sequencing, bioinformatics, and genome mining tools, a vast amount of data on NP biosynthesis has been generated over the years, which has been increasingly exploited to develop machine learning (ML) tools for NP discovery. In this review, we discuss the latest advances in developing and applying ML tools for exploring the potential NPs that can be encoded by genomic language and predicting the types of bioactivities of NPs. We also examine the technical challenges associated with the development and application of ML tools for NP research.
摘要
天然产物（NPs）由微生物和植物产生，是药物、除草剂和杀菌剂的主要来源。近年来，得益于 DNA 测序、生物信息学和基因组挖掘工具的进步，大量关于 NP 生物合成的相关数据被生成，这些数据被越来越多地用于开发用于 NP 发现的机器学习（ML）工具。在这篇综述中，我们讨论了开发和应用 ML 工具以探索可以用基因组语言编码的潜在 NP 并预测 NP 生物活性类型的最新进展。我们还研究了与 NP 研究的 ML 工具的开发和应用相关的技术挑战。
相似文献
1
Machine Learning-Enabled Genome Mining and Bioactivity Prediction of Natural Products.基于机器学习的天然产物基因组挖掘和生物活性预测。
ACS Synth Biol. 2023 Sep 15;12(9):2650-2662. doi: 10.1021/acssynbio.3c00234. Epub 2023 Aug 22.
2
The application potential of machine learning and genomics for understanding natural product diversity, chemistry, and therapeutic translatability.机器学习和基因组学在理解天然产物多样性、化学和治疗可转化性方面的应用潜力。
Nat Prod Rep. 2021 Jun 23;38(6):1100-1108. doi: 10.1039/d0np00055h.
3
Applications of machine learning in microbial natural product drug discovery.机器学习在微生物天然产物药物发现中的应用。
Expert Opin Drug Discov. 2023 Jul-Dec;18(11):1259-1272. doi: 10.1080/17460441.2023.2251400. Epub 2023 Aug 31.
4
Comprehensive curation and analysis of fungal biosynthetic gene clusters of published natural products.已发表天然产物的真菌生物合成基因簇的综合整理与分析
Fungal Genet Biol. 2016 Apr;89:18-28. doi: 10.1016/j.fgb.2016.01.012. Epub 2016 Jan 22.
5
Using natural products for drug discovery: the impact of the genomics era.利用天然产物进行药物研发：基因组学时代的影响。
Expert Opin Drug Discov. 2017 May;12(5):475-487. doi: 10.1080/17460441.2017.1303478. Epub 2017 Mar 14.
6
Mining for Microbial Gems: Integrating Proteomics in the Postgenomic Natural Product Discovery Pipeline.挖掘微生物瑰宝：将蛋白质组学整合到后基因组天然产物发现管道中。
Proteomics. 2018 Sep;18(18):e1700332. doi: 10.1002/pmic.201700332. Epub 2018 Jun 10.
7
Discovery of novel bioactive natural products driven by genome mining.基于基因组挖掘的新型生物活性天然产物的发现
Drug Discov Ther. 2018;12(6):318-328. doi: 10.5582/ddt.2018.01066.
8
Highlights of bioinformatic tools and methods for validating bioinformatics derived hypotheses for microbial natural products research.生物信息学工具和方法的亮点，用于验证微生物天然产物研究中基于生物信息学的假设。
Curr Opin Chem Biol. 2023 Oct;76:102367. doi: 10.1016/j.cbpa.2023.102367. Epub 2023 Jul 17.
9
Predicting biochemical and physiological effects of natural products from molecular structures using machine learning.利用机器学习从分子结构预测天然产物的生化和生理效应。
Nat Prod Rep. 2021 Nov 17;38(11):1954-1966. doi: 10.1039/d1np00016k.
10
A Machine Learning Bioinformatics Method to Predict Biological Activity from Biosynthetic Gene Clusters.一种基于机器学习的生物信息学方法，可从生物合成基因簇中预测生物活性。
J Chem Inf Model. 2021 Jun 28;61(6):2560-2571. doi: 10.1021/acs.jcim.0c01304. Epub 2021 May 27.
引用本文的文献
1
AmpHGT: expanding prediction of antimicrobial activity in peptides containing non-canonical amino acids using multi-view constrained heterogeneous graph transformer.AmpHGT：使用多视图约束异构图变换器扩展对含非标准氨基酸肽的抗菌活性预测
BMC Biol. 2025 Jul 1;23(1):184. doi: 10.1186/s12915-025-02253-4.
2
From data to discovery: leveraging big data in plant natural products biosynthesis research.从数据到发现：植物天然产物生物合成研究中大数据的利用
Plant J. 2025 Jun;122(6):e70288. doi: 10.1111/tpj.70288.
3
ElixirSeeker: A Machine Learning Framework Utilizing Fusion Molecular Fingerprints for the Discovery of Lifespan-Extending Compounds.长生不老药探索者：一种利用融合分子指纹发现延长寿命化合物的机器学习框架。
Aging Cell. 2025 Aug;24(8):e70116. doi: 10.1111/acel.70116. Epub 2025 May 26.
4
Advances in the biological production of sugar alcohols from biomass-derived xylose.从生物质衍生木糖生物生产糖醇的进展。
World J Microbiol Biotechnol. 2025 Mar 28;41(4):110. doi: 10.1007/s11274-025-04316-8.
5
Synthetic Biology in Natural Product Biosynthesis.天然产物生物合成中的合成生物学
Chem Rev. 2025 Apr 9;125(7):3814-3931. doi: 10.1021/acs.chemrev.4c00567. Epub 2025 Mar 21.
6
Microbial Technologies Enhanced by Artificial Intelligence for Healthcare Applications.用于医疗保健应用的人工智能增强微生物技术。
Microb Biotechnol. 2025 Mar;18(3):e70131. doi: 10.1111/1751-7915.70131.
7
Self-resistance-gene-guided, high-throughput automated genome mining of bioactive natural products from Streptomyces.基于自我抗性基因引导的链霉菌生物活性天然产物高通量自动化基因组挖掘
Cell Syst. 2025 Mar 19;16(3):101237. doi: 10.1016/j.cels.2025.101237. Epub 2025 Mar 11.
8
Enhancing rufomycin production by CRISPR/Cas9-based genome editing and promoter engineering in sp. MJM3502.通过基于CRISPR/Cas9的基因组编辑和启动子工程提高链霉菌MJM3502中鲁夫霉素的产量。
Synth Syst Biotechnol. 2025 Jan 17;10(2):421-432. doi: 10.1016/j.synbio.2025.01.002. eCollection 2025 Jun.
9
Exploring the secrets of marine microorganisms: Unveiling secondary metabolites through metagenomics.探索海洋微生物的奥秘：通过宏基因组学揭示次生代谢产物。
Microb Biotechnol. 2024 Aug;17(8):e14533. doi: 10.1111/1751-7915.14533.
10
Cutting-edge plant natural product pathway elucidation.前沿的植物天然产物途径阐明。
Curr Opin Biotechnol. 2024 Jun;87:103137. doi: 10.1016/j.copbio.2024.103137. Epub 2024 Apr 26.
本文引用的文献
1
Deep learning-guided discovery of an antibiotic targeting Acinetobacter baumannii.深度学习指导下针对鲍曼不动杆菌的抗生素的发现。
Nat Chem Biol. 2023 Nov;19(11):1342-1350. doi: 10.1038/s41589-023-01349-8. Epub 2023 May 25.
2
Deep self-supervised learning for biosynthetic gene cluster detection and product classification.深度自监督学习在生物合成基因簇检测和产物分类中的应用。
PLoS Comput Biol. 2023 May 23;19(5):e1011162. doi: 10.1371/journal.pcbi.1011162. eCollection 2023 May.
3
Enzyme function prediction using contrastive learning.使用对比学习进行酶功能预测。
Science. 2023 Mar 31;379(6639):1358-1363. doi: 10.1126/science.adf2465. Epub 2023 Mar 30.
4
Recent Progress in the Discovery and Design of Antimicrobial Peptides Using Traditional Machine Learning and Deep Learning.利用传统机器学习和深度学习发现与设计抗菌肽的最新进展
Antibiotics (Basel). 2022 Oct 21;11(10):1451. doi: 10.3390/antibiotics11101451.
5
A scalable platform to discover antimicrobials of ribosomal origin.一种可扩展的平台，用于发现核糖体来源的抗菌药物。
Nat Commun. 2022 Oct 17;13(1):6135. doi: 10.1038/s41467-022-33890-w.
6
InflamNat: web-based database and predictor of anti-inflammatory natural products.InflamNat：基于网络的抗炎天然产物数据库及预测工具。
J Cheminform. 2022 Jun 4;14(1):30. doi: 10.1186/s13321-022-00608-5.
7
Current progress and open challenges for applying deep learning across the biosciences.深度学习在整个生命科学中的应用现状及面临的开放性挑战。
Nat Commun. 2022 Apr 1;13(1):1728. doi: 10.1038/s41467-022-29268-7.
8
Strategies to access biosynthetic novelty in bacterial genomes for drug discovery.用于药物发现的细菌基因组中生物合成新颖性的获取策略。
Nat Rev Drug Discov. 2022 May;21(5):359-378. doi: 10.1038/s41573-022-00414-6. Epub 2022 Mar 16.
9
Natural product drug discovery in the artificial intelligence era.人工智能时代的天然产物药物发现
Chem Sci. 2021 Dec 13;13(6):1526-1546. doi: 10.1039/d1sc04471k. eCollection 2022 Feb 9.
10
Identification of antimicrobial peptides from the human gut microbiome using deep learning.利用深度学习从人类肠道微生物组中识别抗菌肽。
Nat Biotechnol. 2022 Jun;40(6):921-931. doi: 10.1038/s41587-022-01226-0. Epub 2022 Mar 3.
Zotero 插件