SCREEN: predicting single-cell gene expression perturbation responses via optimal transport

doi:10.1007/s11704-024-31014-9

Front. Comput. Sci.

2024, Vol. 18

Issue (3) : 183909 https://doi.org/10.1007/s11704-024-31014-9

Interdisciplinary

SCREEN: predicting single-cell gene expression perturbation responses via optimal transport

Haixin WANG¹, Yunhan WANG², Qun JIANG³, Yan ZHANG¹(

), Shengquan CHEN⁴(

)

¹. Cadre Medical Department, The 1st Clinical Center, Chinese PLA General Hospital, Beijing 100853, China
². School of Statistics, Renmin University of China, Beijing 100872, China
³. Ministry of Education Key Laboratory of Bioinformatics, Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University, Beijing 100084, China
⁴. School of Mathematical Sciences and LPMC, Nankai University, Tianjin 300071, China

Download: PDF(3748 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Corresponding Author(s): Yan ZHANG,Shengquan CHEN

Issue Date: 18 March 2024

Cite this article:

Haixin WANG,Yunhan WANG,Qun JIANG, et al. SCREEN: predicting single-cell gene expression perturbation responses via optimal transport[J]. Front. Comput. Sci., 2024, 18(3): 183909.

URL:

https://academic.hep.com.cn/fcs/EN/10.1007/s11704-024-31014-9
https://academic.hep.com.cn/fcs/EN/Y2024/V18/I3/183909

Fig.1 The architecture of SCREEN and experiment results. (a) The graphical illustration of SCREEN model; (b) performance of different methods on various datasets evaluated by maximum mean discrepancy (MMD) and Wasserstein distance; (c) performance of different methods on various datasets evaluated by the number of common genes between the two sets of differentially expressed genes (DEGs) derived from true and predicted responses, respectively; (d) gene ontology enrichment results of the DEGs between unperturbed and real perturbed dendritic cells (left) and the DEGs between unperturbed and SCREEN-predicted perturbed dendritic cells (right); (e) robustness of different methods to data noise/sparsity; (f) robustness of different methods to number of cell types; (g) robustness of different methods to cell type imbalance

1	M, Lotfollahi F A, Wolf F J Theis . scGen predicts single-cell perturbation responses. Nature Methods, 2019, 16( 8): 715–721
2	Y, Ji M, Lotfollahi F A, Wolf F J Theis . Machine learning for perturbational single-cell omics. Cell Systems, 2021, 12( 6): 522–537
3	X, Wei J, Dong F Wang . scPreGAN, a deep generative model for predicting the response of single-cell expression to perturbation. Bioinformatics, 2022, 38( 13): 3377–3384
4	K, He X, Chen S, Xie Y, Li P, Dollár R Girshick . Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022, 15979–15988
5	A V, Makkuva A, Taghvaei J D, Lee S Oh . Optimal transport mapping via input convex neural networks. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 619
6	H M, Kang M, Subramaniam S, Targ M, Nguyen L, Maliskova E, McCarthy E, Wan S, Wong L, Byrnes C M, Lanata R E, Gate S, Mostafavi A, Marson N, Zaitlen L A, Criswell C J Ye . Multiplexed droplet single-cell RNA-sequencing using natural genetic variation. Nature Biotechnology, 2018, 36( 1): 89–94
7	A L, Haber M, Biton N, Rogel R H, Herbst K, Shekhar C, Smillie G, Burgin T M, Delorey M R, Howitt Y, Katz I, Tirosh S, Beyaz D, Dionne M, Zhang R, Raychowdhury W S, Garrett O, Rozenblatt-Rosen H N, Shi O, Yilmaz R J, Xavier A Regev . A single-cell survey of the small intestinal epithelium. Nature, 2017, 551( 7680): 333–339
8	T D, Green S, Peidli C, Shen T, Gross J, Min S, Garda J P, Taylor-King D S, Marks A, Luna N, Blüthgen C Sander . scPerturb: information resource for harmonized single-cell perturbation data. In: Proceedings of the 6th Conference on Neural Information Processing Systems. 2022
9	S, Chen R, Wang W, Long R Jiang . ASTER: accurately estimating the number of cell types in single-cell chromatin accessibility data. Bioinformatics, 2023, 39( 1): btac842
10	J, Wang H, Tao H, Li X, Bo H Chen . 3D genomic organization in cancers. Quantitative Biology, 2023, 11( 2): 109–121
11	Z, Gao X, Chen Z, Li X, Cui Q, Jiang K, Li S, Chen R Jiang . scEpiTools: a database to comprehensively interrogate analytic tools for single-cell epigenomic data. Journal of Genetics and Genomics, 2023, doi: 10.1016/j.jgg.2023.09.011
12	S, Chen K, Hua H, Cui R Jiang . VPAC: variational projection for accurate clustering of single-cell transcriptomic data. BMC Bioinformatics, 2019, 20: 139-151

[1]		Download
[2]		Download

Viewed

Full text

Abstract

Cited

Shared

Discussed