利用深度学习模型，我们能在多大程度上解读蛋白质进化？
How deep can we decipher protein evolution with deep learning models.
作者信息
Fu Xiaozhi
机构信息
Department of Life Sciences, Chalmers University of Technology, Kemivägen 10, SE-412 96 Gothenburg, Sweden.
出版信息
Patterns (N Y). 2024 Aug 9;5(8):101043. doi: 10.1016/j.patter.2024.101043.
Abstract
Evolutionary-based machine learning models have emerged as a fascinating approach to mapping the landscape for protein evolution. Lian et al. demonstrated that evolution-based deep generative models, specifically variational autoencoders, can organize SH3 homologs in a hierarchical latent space, effectively distinguishing the specific Sho1 domains.
摘要
基于进化的机器学习模型已成为一种描绘蛋白质进化图景的迷人方法。Lian等人证明，基于进化的深度生成模型，特别是变分自编码器，可以在分层潜在空间中组织SH3同源物，有效区分特定的Sho1结构域。
相似文献
1
How deep can we decipher protein evolution with deep learning models.利用深度学习模型，我们能在多大程度上解读蛋白质进化？
Patterns (N Y). 2024 Aug 9;5(8):101043. doi: 10.1016/j.patter.2024.101043.
2
Deep-learning-based design of synthetic orthologs of SH3 signaling domains.基于深度学习的 SH3 信号结构域合成同源物的设计。
Cell Syst. 2024 Aug 21;15(8):725-737.e7. doi: 10.1016/j.cels.2024.07.005. Epub 2024 Aug 5.
3
Interpretable Machine Learning Models for Molecular Design of Tyrosine Kinase Inhibitors Using Variational Autoencoders and Perturbation-Based Approach of Chemical Space Exploration.基于变分自动编码器和基于扰动的化学空间探索方法的酪氨酸激酶抑制剂分子设计可解释机器学习模型。
Int J Mol Sci. 2022 Sep 24;23(19):11262. doi: 10.3390/ijms231911262.
4
Optimizing Few-Shot Learning Based on Variational Autoencoders.基于变分自编码器优化少样本学习。
Entropy (Basel). 2021 Oct 24;23(11):1390. doi: 10.3390/e23111390.
5
An Overview of Variational Autoencoders for Source Separation, Finance, and Bio-Signal Applications.用于源分离、金融和生物信号应用的变分自编码器概述。
Entropy (Basel). 2021 Dec 28;24(1):55. doi: 10.3390/e24010055.
6
An Overview of Deep Generative Models in Functional and Evolutionary Genomics.深度生成模型在功能和进化基因组学中的概述。
Annu Rev Biomed Data Sci. 2023 Aug 10;6:173-189. doi: 10.1146/annurev-biodatasci-020722-115651. Epub 2023 May 3.
7
ProtWave-VAE: Integrating Autoregressive Sampling with Latent-Based Inference for Data-Driven Protein Design.ProtWave-VAE：用于数据驱动蛋白质设计的基于潜在信息的推断与自回归采样的整合。
ACS Synth Biol. 2023 Dec 15;12(12):3544-3561. doi: 10.1021/acssynbio.3c00261. Epub 2023 Nov 21.
8
Latent generative landscapes as maps of functional diversity in protein sequence space.潜在生成景观作为蛋白质序列空间中功能多样性的图谱。
Nat Commun. 2023 Apr 19;14(1):2222. doi: 10.1038/s41467-023-37958-z.
9
Learning Hierarchical Variational Autoencoders With Mutual Information Maximization for Autoregressive Sequence Modeling.通过互信息最大化学习用于自回归序列建模的分层变分自编码器
IEEE Trans Pattern Anal Mach Intell. 2023 Feb;45(2):1949-1962. doi: 10.1109/TPAMI.2022.3160509. Epub 2023 Jan 6.
10
Comparative Study of Deep Generative Models on Chemical Space Coverage.化学空间覆盖的深度生成模型比较研究。
J Chem Inf Model. 2021 Jun 28;61(6):2572-2581. doi: 10.1021/acs.jcim.0c01328. Epub 2021 May 20.
本文引用的文献
1
Deep-learning-based design of synthetic orthologs of SH3 signaling domains.基于深度学习的 SH3 信号结构域合成同源物的设计。
Cell Syst. 2024 Aug 21;15(8):725-737.e7. doi: 10.1016/j.cels.2024.07.005. Epub 2024 Aug 5.
2
Clustering predicted structures at the scale of the known protein universe.对已知蛋白质宇宙尺度的预测结构进行聚类。
Nature. 2023 Oct;622(7983):637-645. doi: 10.1038/s41586-023-06510-w. Epub 2023 Sep 13.
3
Latent generative landscapes as maps of functional diversity in protein sequence space.潜在生成景观作为蛋白质序列空间中功能多样性的图谱。
Nat Commun. 2023 Apr 19;14(1):2222. doi: 10.1038/s41467-023-37958-z.
4
Machine learning for evolutionary-based and physics-inspired protein design: Current and future synergies.基于机器学习的进化和物理启发的蛋白质设计：当前和未来的协同作用。
Curr Opin Struct Biol. 2023 Jun;80:102571. doi: 10.1016/j.sbi.2023.102571. Epub 2023 Mar 21.
5
Sourcing thermotolerant poly(ethylene terephthalate) hydrolase scaffolds from natural diversity.从自然多样性中筛选耐热聚对苯二甲酸乙二醇酯水解酶支架。
Nat Commun. 2022 Dec 21;13(1):7850. doi: 10.1038/s41467-022-35237-x.
6
Ig-VAE: Generative modeling of protein structure by direct 3D coordinate generation.Ig-VAE：通过直接 3D 坐标生成对蛋白质结构进行生成式建模。
PLoS Comput Biol. 2022 Jun 27;18(6):e1010271. doi: 10.1371/journal.pcbi.1010271. eCollection 2022 Jun.
7
Learning the protein language: Evolution, structure, and function.学习蛋白质语言：进化、结构和功能。
Cell Syst. 2021 Jun 16;12(6):654-669.e3. doi: 10.1016/j.cels.2021.05.017.
8
Deciphering protein evolution and fitness landscapes with latent space models.利用潜在空间模型破解蛋白质进化和适应度景观。
Nat Commun. 2019 Dec 10;10(1):5644. doi: 10.1038/s41467-019-13633-0.
9
Advances and Applications in the Quest for Orthologs.同源基因的探索、发展与应用。
Mol Biol Evol. 2019 Oct 1;36(10):2157-2164. doi: 10.1093/molbev/msz150.
Zotero 插件