Graph Neural Networks Pretraining Through Inherent Supervision for Molecular Property Prediction

被引:4
|
作者
Benjamin, Roy [1 ]
Singer, Uriel [2 ]
Radinsky, Kira [1 ]
机构
[1] Technion Israel Inst Technol, Haifa, Israel
[2] Meta AI Res, Tel Aviv, Israel
关键词
Drug Discovery; ML for Healthcare; Molecular Property Prediction;
D O I
10.1145/3511808.3557085
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recent global events have emphasized the importance of accelerating the drug discovery process. A way to deal with the issue is to use machine learning to increase the rate at which drugs are made available to the public. However, chemical labeled data for real-world applications is extremely scarce making traditional approaches less effective. A fruitful course of action for this challenge is to pretrain a model using related tasks with large enough datasets, with the next step being finetuning it for the desired task. This is challenging as creating these datasets requires labeled data or expert knowledge. To aid in solving this pressing issue, we introduce MISU - Molecular Inherent SUpervision, a unique method for pretraining graph neural networks for molecular property prediction. Our method leapfrogs past the need for labeled data or any expert knowledge by introducing three innovative components that utilize inherent properties of molecular graphs to induce information extraction at different scales, from the local neighborhood of an atom to substructures in the entire molecule. Our empirical results for six chemical-property-prediction tasks show that our method reaches state-of-the-art results compared to numerous baselines.
引用
收藏
页码:2903 / 2912
页数:10
相关论文
共 50 条
  • [1] Composite Graph Neural Networks for Molecular Property Prediction
    Bongini, Pietro
    Pancino, Niccolo
    Bendjeddou, Asma
    Scarselli, Franco
    Maggini, Marco
    Bianchini, Monica
    [J]. INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES, 2024, 25 (12)
  • [2] Property Prediction of Functional Organic Molecular Crystals with Graph Neural Networks
    O'Connor, Dana
    Buitrago, Paola A.
    [J]. PRACTICE AND EXPERIENCE IN ADVANCED RESEARCH COMPUTING 2024, PEARC 2024, 2024,
  • [3] Quantitative evaluation of explainable graph neural networks for molecular property prediction
    Rao, Jiahua
    Zheng, Shuangjia
    Lu, Yutong
    Yang, Yuedong
    [J]. PATTERNS, 2022, 3 (12):
  • [4] Comparison of Atom Representations in Graph Neural Networks for Molecular Property Prediction
    Pocha, Agnieszka
    Dana, Tomasz
    Podlewska, Sabina
    Tabor, Jacek
    Maziarka, Lukasz
    [J]. 2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [5] Cross-dependent graph neural networks for molecular property prediction
    Ma, Hehuan
    Bian, Yatao
    Rong, Yu
    Huang, Wenbing
    Xu, Tingyang
    Xie, Weiyang
    Ye, Geyan
    Huang, Junzhou
    [J]. BIOINFORMATICS, 2022, 38 (07) : 2003 - 2009
  • [6] Physical pooling functions in graph neural networks for molecular property prediction
    Schweidtmann, Artur M.
    Rittig, Jan G.
    Weber, Jana M.
    Grohe, Martin
    Dahmen, Manuel
    Leonhard, Kai
    Mitsos, Alexander
    [J]. COMPUTERS & CHEMICAL ENGINEERING, 2023, 172
  • [7] InvarNet: Molecular property prediction via rotation invariant graph neural networks
    Chen, Danyan
    Duan, Gaoxiang
    Miao, Dengbao
    Zheng, Xiaoying
    Zhu, Yongxin
    [J]. Machine Learning with Applications, 2024, 18
  • [8] Extended study on atomic featurization in graph neural networks for molecular property prediction
    Agnieszka Wojtuch
    Tomasz Danel
    Sabina Podlewska
    Łukasz Maziarka
    [J]. Journal of Cheminformatics, 15
  • [9] Advanced graph and sequence neural networks for molecular property prediction and drug discovery
    Wang, Zhengyang
    Liu, Meng
    Luo, Youzhi
    Xu, Zhao
    Xie, Yaochen
    Wang, Limei
    Cai, Lei
    Qi, Qi
    Yuan, Zhuoning
    Yang, Tianbao
    Ji, Shuiwang
    [J]. BIOINFORMATICS, 2022, 38 (09) : 2579 - 2586
  • [10] Extended study on atomic featurization in graph neural networks for molecular property prediction
    Wojtuch, Agnieszka
    Danel, Tomasz
    Podlewska, Sabina
    Maziarka, Lukasz
    [J]. JOURNAL OF CHEMINFORMATICS, 2023, 15 (01)