NbX: Machine Learning-Guided Re-Ranking of Nanobody-Antigen Binding Poses

被引:7
作者
Tam, Chunlai [1 ,2 ]
Kumar, Ashutosh [1 ]
Zhang, Kam Y. J. [1 ,2 ]
机构
[1] RIKEN, Lab Struct Bioinformat, Ctr Biosyst Dynam Res, 1-7-22 Suehiro, Yokohama, Kanagawa 2300045, Japan
[2] Univ Tokyo, Grad Sch Frontier Sci, Dept Computat Biol & Med Sci, Kashiwa, Chiba 2778561, Japan
基金
日本学术振兴会;
关键词
nanobody; single-domain antibody; antibody-antigen complex; pose prediction; AMINO-ACIDS; MOLECULAR-DYNAMICS; WEB SERVER; HOT-SPOTS; PROTEIN; DESCRIPTORS; ANTIBODY; SEQUENCE; PEPTIDE; SCALE;
D O I
10.3390/ph14100968
中图分类号
R914 [药物化学];
学科分类号
100701 ;
摘要
Modeling the binding pose of an antibody is a prerequisite to structure-based affinity maturation and design. Without knowing a reliable binding pose, the subsequent structural simulation is largely futile. In this study, we have developed a method of machine learning-guided re-ranking of antigen binding poses of nanobodies, the single-domain antibody which has drawn much interest recently in antibody drug development. We performed a large-scale self-docking experiment of nanobody-antigen complexes. By training a decision tree classifier through mapping a feature set consisting of energy, contact and interface property descriptors to a measure of their docking quality of the refined poses, significant improvement in the median ranking of native-like nanobody poses by was achieved eightfold compared with ClusPro and an established deep 3D CNN classifier of native protein-protein interaction. We further interpreted our model by identifying features that showed relatively important contributions to the prediction performance. This study demonstrated a useful method in improving our current ability in pose prediction of nanobodies.</p>
引用
收藏
页数:11
相关论文
共 57 条
  • [1] PyIgClassify: a database of antibody CDR structural classifications
    Adolf-Bryfogle, Jared
    Xu, Qifang
    North, Benjamin
    Lehmann, Andreas
    Dunbrack, Roland L., Jr.
    [J]. NUCLEIC ACIDS RESEARCH, 2015, 43 (D1) : D432 - D438
  • [2] Accurate refinement of docked protein complexes using evolutionary information and deep learning
    Akbal-Delibas, Bahar
    Farhoodi, Roshanak
    Pomplun, Marc
    Haspel, Nurit
    [J]. JOURNAL OF BIOINFORMATICS AND COMPUTATIONAL BIOLOGY, 2016, 14 (03)
  • [3] Structural and thermodynamic basis for the recognition of the substrate-binding cleft on hen egg lysozyme by a single-domain antibody
    Akiba, Hiroki
    Amura, Hiroko T.
    Kiyoshi, Masato
    Yanaka, Saeko
    Sugase, Kenji
    Aaveiro, Jose M. M. C.
    Tsumoto, Kouhei
    [J]. SCIENTIFIC REPORTS, 2019, 9 (1)
  • [4] proABC-2: PRediction of AntiBody contacts v2 and its application to information-driven docking
    Ambrosetti, Francesco
    Olsen, Tobias Hegelund
    Olimpieri, Pier Paolo
    Jimenez-Garcia, Brian
    Milanetti, Edoardo
    Marcatilli, Paolo
    Bonvin, Alexandre M. J. J.
    [J]. BIOINFORMATICS, 2020, 36 (20) : 5107 - 5108
  • [5] DockQ: A Quality Measure for Protein-Protein Docking Models
    Basu, Sankar
    Wallner, Bjorn
    [J]. PLOS ONE, 2016, 11 (08):
  • [6] Energy-based graph convolutional networks for scoring protein docking models
    Cao, Yue
    Shen, Yang
    [J]. PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2020, 88 (08) : 1091 - 1099
  • [7] Chen T.Q., 2016, KDD16 P 22 ACM, DOI DOI 10.1145/2939672.2939785
  • [8] Peptide studies by means of principal properties of amino acids derived from MIF descriptors
    Cruciani, G
    Baroni, M
    Carosati, E
    Clementi, M
    Valigi, R
    Clementi, S
    [J]. JOURNAL OF CHEMOMETRICS, 2004, 18 (3-4) : 146 - 155
  • [9] The backrub motion: How protein backbone shrugs when a sidechain dances
    Davis, IW
    Arendall, WB
    Richardson, DC
    Richardson, JS
    [J]. STRUCTURE, 2006, 14 (02) : 265 - 274
  • [10] Coupling Molecular Dynamics and Deep Learning to Mine Protein Conformational Space
    Degiacomi, Matteo T.
    [J]. STRUCTURE, 2019, 27 (06) : 1034 - +