ChiENN: Embracing Molecular Chirality with Graph Neural Networks

被引:1
作者
Gainski, Piotr [1 ]
Koziarski, Michal [2 ,3 ]
Tabor, Jacek [1 ]
Smieja, Marek [1 ]
机构
[1] Jagiellonian Univ, Fac Math & Comp Sci, Krakow, Poland
[2] Mila Quebec Inst, Montreal, PQ, Canada
[3] Univ Montreal, Montreal, PQ, Canada
来源
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: RESEARCH TRACK, ECML PKDD 2023, PT III | 2023年 / 14171卷
关键词
Graph Neural Networks; GNN; Message-passing; Chirality; Molecular Property Prediction;
D O I
10.1007/978-3-031-43418-1_3
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Graph Neural Networks (GNNs) play a fundamental role in many deep learning problems, in particular in cheminformatics. However, typical GNNs cannot capture the concept of chirality, which means they do not distinguish between the 3D graph of a chemical compound and its mirror image (enantiomer). The ability to distinguish between enantiomers is important especially in drug discovery because enantiomers can have very distinct biochemical properties. In this paper, we propose a theoretically justified message-passing scheme, which makes GNNs sensitive to the order of node neighbors. We apply that general concept in the context of molecular chirality to construct Chiral Edge Neural Network (ChiENN) layer which can be appended to any GNN model to enable chirality-awareness. Our experiments show that adding ChiENN layers to a GNN outperforms current state-of-the-art methods in chiral-sensitive molecular property prediction tasks.
引用
收藏
页码:36 / 52
页数:17
相关论文
共 50 条
  • [31] Survey on Graph Neural Networks
    Gkarmpounis, Georgios
    Vranis, Christos
    Vretos, Nicholas
    Daras, Petros
    IEEE ACCESS, 2024, 12 : 128816 - 128832
  • [32] Stochastic Graph Neural Networks
    Gao, Zhan
    Isufi, Elvin
    Ribeiro, Alejandro
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2021, 69 : 4428 - 4443
  • [33] Beyond graph neural networks with lifted relational neural networks
    Gustav Šourek
    Filip Železný
    Ondřej Kuželka
    Machine Learning, 2021, 110 : 1695 - 1738
  • [34] Beyond graph neural networks with lifted relational neural networks
    Sourek, Gustav
    Zelezny, Filip
    Kuzelka, Ondrej
    MACHINE LEARNING, 2021, 110 (07) : 1695 - 1738
  • [35] Clenshaw Graph Neural Networks
    Guo, Yuhe
    Wei, Zhewei
    PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, 2023, : 614 - 625
  • [36] AGGREGATION GRAPH NEURAL NETWORKS
    Gama, Fernando
    Marques, Antonio G.
    Ribeiro, Alejandro
    Leus, Geert
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 4943 - 4947
  • [37] Graph Neural Networks for Intelligent Transportation Systems: A Survey
    Rahmani, Saeed
    Baghbani, Asiye
    Bouguila, Nizar
    Patterson, Zachary
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2023, 24 (08) : 8846 - 8885
  • [38] Concept Graph Neural Networks for Surgical Video Understanding
    Ban, Yutong
    Eckhoff, Jennifer A.
    Ward, Thomas M.
    Hashimoto, Daniel A.
    Meireles, Ozanan R.
    Rus, Daniela
    Rosman, Guy
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2024, 43 (01) : 264 - 274
  • [39] Inference in Probabilistic Graphical Models by Graph Neural Networks
    Yoon, KiJung
    Liao, Renjie
    Xiong, Yuwen
    Zhang, Lisa
    Fetaya, Ethan
    Urtasun, Raquel
    Zemel, Richard
    Pitkow, Xaq
    CONFERENCE RECORD OF THE 2019 FIFTY-THIRD ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, 2019, : 868 - 875
  • [40] Graph Neural Networks for Wireless Networks: Graph Representation, Architecture and Evaluation
    Lu, Yang
    Li, Yuhang
    Zhang, Ruichen
    Chen, Wei
    Ai, Bo
    Niyato, Dusit
    IEEE WIRELESS COMMUNICATIONS, 2025, 32 (01) : 150 - 156