EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Complementary multi-modality molecular self-supervised learning via non-overlapping masking for property prediction

Ao Shen iD, Mingzhi Yuan iD, Yingfan Ma iD, Jie Du, Manning Wang iD

Briefings in Bioinformatics · 23.05.2024 · 25 (4)

DOI: 10.1093/bib/bbae256 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 27.05.2024. Verfasst von Ao Shen und 4 weiteren Autor:innen. Beteiligte Einrichtung: Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, 131 Dong'an Road, 200032, Shanghai, China. Hauptthemen laut MEDLINE: Supervised Machine Learning. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Innovation Plan of Shanghai Science and Technology Commission, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Self-supervised learning plays an important role in molecular representation learning because labeled molecular data are usually limited in many tasks, such as chemical property prediction and virtual screening. However, most existing molecular pre-training methods focus on one modality of molecular data, and the complementary information of two important modalities, SMILES and graph, is not fully explored. In this study, we propose an effective multi-modality self-supervised learning framework for molecular SMILES and graph. Specifically, SMILES data and graph data are first tokenized so that they can be processed by a unified Transformer-based backbone network, which is trained by a masked reconstruction strategy. In addition, we introduce a specialized non-overlapping masking strategy to encourage fine-grained interaction between these two modalities. Experimental results show that our framework achieves state-of-the-art performance in a series of molecular property prediction tasks, and a detailed ablation study demonstrates efficacy of the multi-modality framework and the masking strategy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Supervised Machine LearningAlgorithmsComputational Biology

Stichwörter der Autor:innen

molecular property predictionmolecular representationsmulti-modality self-supervised learning

Autor:innen und Institutionen

  • Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, 131 Dong'an Road, 200032, Shanghai, China.
  • Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University, 131 Dong'an Road, 200032, Shanghai, China.

ORCID-Profile: Ao Shen, Mingzhi Yuan, Yingfan Ma, Manning Wang

Förderung

  • Science and Technology Innovation Plan of Shanghai Science and Technology Commission
  • National Natural Science Foundation of China

Zitieren

APA

Shen, A., Yuan, M., Ma, Y., Du, J., & Wang, M. (2024). Complementary multi-modality molecular self-supervised learning via non-overlapping masking for property prediction. Briefings in Bioinformatics, 25(4). https://doi.org/10.1093/bib/bbae256

Vancouver

Shen A, Yuan M, Ma Y, Du J, Wang M. Complementary multi-modality molecular self-supervised learning via non-overlapping masking for property prediction. Briefings in Bioinformatics. 2024;25(4). doi:10.1093/bib/bbae256

BibTeX
@article{Shen2024,
  author = {Shen, Ao and Yuan, Mingzhi and Ma, Yingfan and Du, Jie and Wang, Manning},
  title = {Complementary multi-modality molecular self-supervised learning via non-overlapping masking for property prediction},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  volume = {25},
  number = {4},
  doi = {10.1093/bib/bbae256}
}
Kostenlos starten →