Retention Time Prediction with Message-Passing Neural Networks

被引:20
|
作者
Osipenko, Sergey [1 ]
Nikolaev, Eugene [1 ]
Kostyukevich, Yury [1 ]
机构
[1] Skolkovo Inst Sci & Technol, Ctr Computat & Data Intens Sci & Engn, Nobel Str 3, Moscow 121205, Russia
关键词
retention time prediction; untargeted metabolomics; small molecules; message-passing neural networks; DIFFERENT GRADIENTS; FLOW-RATES; IDENTIFICATION; PERFORMANCE;
D O I
10.3390/separations9100291
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Retention time prediction, facilitated by advances in machine learning, has become a useful tool in untargeted LC-MS applications. State-of-the-art approaches include graph neural networks and 1D-convolutional neural networks that are trained on the METLIN small molecule retention time dataset (SMRT). These approaches demonstrate accurate predictions comparable with the experimental error for the training set. The weak point of retention time prediction approaches is the transfer of predictions to various systems. The accuracy of this step depends both on the method of mapping and on the accuracy of the general model trained on SMRT. Therefore, improvements to both parts of prediction workflows may lead to improved compound annotations. Here, we evaluate capabilities of message-passing neural networks (MPNN) that have demonstrated outstanding performance on many chemical tasks to accurately predict retention times. The model was initially trained on SMRT, providing mean and median absolute cross-validation errors of 32 and 16 s, respectively. The pretrained MPNN was further fine-tuned on five publicly available small reversed-phase retention sets in a transfer learning mode and demonstrated up to 30% improvement of prediction accuracy for these sets compared with the state-of-the-art methods. We demonstrated that filtering isomeric candidates by predicted retention with the thresholds obtained from ROC curves eliminates up to 50% of false identities.
引用
收藏
页数:9
相关论文
共 50 条
  • [31] A dynamic message-passing approach for social contagion in time-varying multiplex networks
    Su, Zhen
    Kurths, Juergen
    EPL, 2018, 123 (06)
  • [32] Graph neural architecture search with heterogeneous message-passing mechanisms
    Wang, Yili
    Chen, Jiamin
    Li, Qiutong
    He, Changlong
    Gao, Jianliang
    KNOWLEDGE AND INFORMATION SYSTEMS, 2024, 66 (07) : 4283 - 4308
  • [33] MORE ON MESSAGE-PASSING SILICON
    SCHWARTZ, DP
    COMPUTER DESIGN, 1986, 25 (06): : 18 - 18
  • [34] Rethinking Graph Neural Architecture Search from Message-passing
    Cai, Shaofei
    Li, Liang
    Deng, Jincan
    Zhang, Beichen
    Zha, Zheng-Jun
    Su, Li
    Huang, Qingming
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 6653 - 6662
  • [35] Combinators for Message-Passing in Haskell
    Brown, Neil C. C.
    PRACTICAL ASPECTS OF DECLARATIVE LANGUAGES, 2011, 6539 : 19 - 33
  • [36] msg: A message-passing library
    Roll, J
    Mandel, J
    ASTRONOMICAL DATA ANALYSIS SOFTWARE AND SYSTEMS X, 2001, 238 : 233 - 236
  • [37] EFFICIENT AND SCALABLE LOGICAL BUSSES FOR MESSAGE-PASSING INTERCONNECTION NETWORKS
    SCHEIDIG, H
    SCHNEIDER, MF
    SPURK, R
    LECTURE NOTES IN COMPUTER SCIENCE, 1991, 487 : 183 - 192
  • [38] An Efficient Message-Passing Algorithm for Optimizing Decentralized Detection Networks
    Kreidl, O. Patrick
    Willsky, Alan S.
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2010, 55 (03) : 563 - 578
  • [39] Structural Generalization in Autonomous Cyber Incident Response with Message-Passing Neural Networks and Reinforcement Learning
    Nyberg, Jakob
    Johnson, Pontus
    2024 IEEE INTERNATIONAL CONFERENCE ON CYBER SECURITY AND RESILIENCE, CSR, 2024, : 282 - 289
  • [40] Informed Lifting for Message-Passing
    Kersting, Kristian
    El Massaoudi, Youssef
    Ahmadi, Babak
    Hadiji, Fabian
    PROCEEDINGS OF THE TWENTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI-10), 2010, : 1181 - 1186