Variational embedding of protein folding simulations using Gaussian mixture variational autoencoders

被引:13
|
作者
Ghorbani, Mahdi [1 ,2 ]
Prasad, Samarjeet [1 ]
Klauda, Jeffery B. [2 ]
Brooks, Bernard R. [1 ]
机构
[1] NHLBI, Lab Computat Biol, NIH, Bethesda, MD 20824 USA
[2] Univ Maryland, Dept Chem & Biomol Engn, College Pk, MD 20742 USA
来源
JOURNAL OF CHEMICAL PHYSICS | 2021年 / 155卷 / 19期
基金
美国国家科学基金会;
关键词
MARKOV STATE MODELS; MOLECULAR-DYNAMICS SIMULATIONS; TRP-CAGE; KINETICS;
D O I
10.1063/5.0069708
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
Conformational sampling of biomolecules using molecular dynamics simulations often produces a large amount of high dimensional data that makes it difficult to interpret using conventional analysis techniques. Dimensionality reduction methods are thus required to extract useful and relevant information. Here, we devise a machine learning method, Gaussian mixture variational autoencoder (GMVAE), that can simultaneously perform dimensionality reduction and clustering of biomolecular conformations in an unsupervised way. We show that GMVAE can learn a reduced representation of the free energy landscape of protein folding with highly separated clusters that correspond to the metastable states during folding. Since GMVAE uses a mixture of Gaussians as its prior, it can directly acknowledge the multi-basin nature of the protein folding free energy landscape. To make the model end-to-end differentiable, we use a Gumbel-softmax distribution. We test the model on three long-timescale protein folding trajectories and show that GMVAE embedding resembles the folding funnel with folded states down the funnel and unfolded states outside the funnel path. Additionally, we show that the latent space of GMVAE can be used for kinetic analysis and Markov state models built on this embedding produce folding and unfolding timescales that are in close agreement with other rigorous dynamical embeddings such as time independent component analysis.
引用
收藏
页数:11
相关论文
共 50 条
  • [31] Automated operational modal analysis using variational Gaussian mixture model
    Zeng, Jice
    Hu, Zhen
    ENGINEERING STRUCTURES, 2022, 273
  • [32] Blind Channel Equalization using Variational Autoencoders
    Caciularu, Avi
    Burshtein, David
    2018 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS (ICC WORKSHOPS), 2018,
  • [33] SRVAE: Super Resolution using Variational Autoencoders
    Heydari, A. Ali
    Mehmood, Asif
    PATTERN RECOGNITION AND TRACKING XXXI, 2020, 11400
  • [34] DoS and DDoS mitigation using Variational Autoencoders
    Bårli, Eirik Molde
    Yazidi, Anis
    Viedma, Enrique Herrera
    Haugerud, Hårek
    Computer Networks, 2021, 199
  • [35] Modelling urban networks using Variational Autoencoders
    Kempinska, Kira
    Murcio, Roberto
    APPLIED NETWORK SCIENCE, 2019, 4 (01)
  • [36] DoS and DDoS mitigation using Variational Autoencoders
    Barli, Eirik Molde
    Yazidi, Anis
    Viedma, Enrique Herrera
    Haugerud, Harek
    COMPUTER NETWORKS, 2021, 199
  • [37] Modeling and Transforming Speech using Variational Autoencoders
    Blaauw, Merlijn
    Bonada, Jordi
    17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 1770 - 1774
  • [38] Modelling urban networks using Variational Autoencoders
    Kira Kempinska
    Roberto Murcio
    Applied Network Science, 4
  • [39] Classification of Arcobacter species using variational autoencoders
    Patsekin, Valery
    On, Stephen
    Sturgis, Jennifer
    Bae, Euiwon
    Rajwa, Bartek
    Patsekin, Aleksandr
    Robinson, J. Paul
    SENSING FOR AGRICULTURE AND FOOD QUALITY AND SAFETY XI, 2019, 11016
  • [40] Link Activation Using Variational Graph Autoencoders
    Jamshidiha, Saeed
    Pourahmadi, Vahid
    Mohammadi, Abbas
    Bennis, Mehdi
    IEEE COMMUNICATIONS LETTERS, 2021, 25 (07) : 2358 - 2361