SS-Pro: a simplified siamese contrastive learning approach for protein surface representation

doi:10.1007/s11704-024-3806-9

Front. Comput. Sci.

2024, Vol. 18

Issue (5) : 185910 https://doi.org/10.1007/s11704-024-3806-9

Interdisciplinary

SS-Pro: a simplified siamese contrastive learning approach for protein surface representation

Ao SHEN^1,², Mingzhi YUAN^1,², Yingfan MA^1,², Manning WANG^1,²(

)

¹. Digital Medical Research Center, School of Basic Medical Science, Fudan University, Shanghai 200032, China
². Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Shanghai 200032, China

Download: PDF(339 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Corresponding Author(s): Manning WANG

Just Accepted Date: 08 May 2024 Issue Date: 05 June 2024

Cite this article:

Ao SHEN,Mingzhi YUAN,Yingfan MA, et al. SS-Pro: a simplified siamese contrastive learning approach for protein surface representation[J]. Front. Comput. Sci., 2024, 18(5): 185910.

URL:

https://academic.hep.com.cn/fcs/EN/10.1007/s11704-024-3806-9
https://academic.hep.com.cn/fcs/EN/Y2024/V18/I5/185910

Fig.1 The SS-Pro framework. (a) Contrastive pre-training using protein surface point cloud; (b) fine-tuning on downstream tasks using the pre-trained encoder

Tab.1 Protein surface binding site recognition results.

Fig.2 Visualization of ground-truth protein surface binding site (a) and the prediction of pre-trained dMaSIF network (b). The orange area represents the ground-truth binding site, and the green area represents binding sites predicted by pre-trained dMaSIF network

Tab.2 Protein-protein interaction prediction results.

1	C, Isert K, Atz G Schneider . Structure-based drug design with geometric deep learning. Current Opinion in Structural Biology, 2023, 79: 102548
2	P, Gainza F, Sverrisson F, Monti E, Rodolà D, Boscaini M M, Bronstein B E Correia . Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning. Nature Methods, 2020, 17(2): 184−192
3	F, Sverrisson J, Feydy B E, Correia M M Bronstein . Fast end-to-end learning on protein surfaces. In: Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021, 15267−15276
4	X, Chen K He . Exploring simple Siamese representation learning. In: Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021, 15745−15753
5	H M, Berman J, Westbrook Z, Feng G, Gilliland T N, Bhat H, Weissig I N, Shindyalov P E Bourne . The protein data bank. Nucleic Acids Research, 2000, 28(1): 235−242
6	M, Yuan A, Shen K, Fu J, Guan Y, Ma Q, Qiao M Wang . ProteinMAE: masked autoencoder for protein surface self-supervised learning. Bioinformatics, 2023, 39(12): btad724
7	A, Vaswani N, Shazeer N, Parmar J, Uszkoreit L, Jones A N, Gomez Ł, Kaiser I Polosukhin . Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 6000−6010
8	A V, Phan Nguyen M, Le Y L H, Nguyen L T Bui . DGCNN: A convolutional neural network over large-scale labeled graphs. Neural Networks, 2018, 108: 533−543
9	C R, Qi L, Yi H, Su L J Guibas . PointNet++: Deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 5105−5114

[1]

FCS-23806-OF-AS_suppl_1

Download

Viewed

Full text

Abstract

Cited

Shared

Discussed