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
  • [1] Embracing Graph Neural Networks for Hardware Security (Invited Paper)
    Alrahis, Lilas
    Patnaik, Satwik
    Shafique, Muhammad
    Sinanoglu, Ozgur
    2022 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER AIDED DESIGN, ICCAD, 2022,
  • [2] Composite Graph Neural Networks for Molecular Property Prediction
    Bongini, Pietro
    Pancino, Niccolo
    Bendjeddou, Asma
    Scarselli, Franco
    Maggini, Marco
    Bianchini, Monica
    INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES, 2024, 25 (12)
  • [3] Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties
    Shui, Zeren
    Karypis, George
    20TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2020), 2020, : 492 - 500
  • [4] Evolving Molecular Graph Neural Networks with Hierarchical Evaluation Strategy
    Yuan, Yingfang
    Wang, Wenjun
    Li, Xin
    PROCEEDINGS OF THE 2024 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, GECCO 2024, 2024, : 1417 - 1425
  • [5] Graph neural networks for molecular and materials representation
    Wu, Xing
    Wang, Hongye
    Gong, Yifei
    Fan, Dong
    Ding, Peng
    Li, Qian
    Qian, Quan
    JOURNAL OF MATERIALS INFORMATICS, 2023, 3 (02):
  • [6] Property Prediction of Functional Organic Molecular Crystals with Graph Neural Networks
    O'Connor, Dana
    Buitrago, Paola A.
    PRACTICE AND EXPERIENCE IN ADVANCED RESEARCH COMPUTING 2024, PEARC 2024, 2024,
  • [7] Comparison of Atom Representations in Graph Neural Networks for Molecular Property Prediction
    Pocha, Agnieszka
    Dana, Tomasz
    Podlewska, Sabina
    Tabor, Jacek
    Maziarka, Lukasz
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [8] Semisupervised Graph Neural Networks for Graph Classification
    Xie, Yu
    Liang, Yanfeng
    Gong, Maoguo
    Qin, A. K.
    Ong, Yew-Soon
    He, Tiantian
    IEEE TRANSACTIONS ON CYBERNETICS, 2023, 53 (10) : 6222 - 6235
  • [9] Torsion Graph Neural Networks
    Shen, Cong
    Liu, Xiang
    Luo, Jiawei
    Xia, Kelin
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2025, 47 (04) : 2946 - 2956
  • [10] Molecular generative Graph Neural Networks for Drug Discovery
    Bongini, Pietro
    Bianchini, Monica
    Scarselli, Franco
    NEUROCOMPUTING, 2021, 450 : 242 - 252