Contrastive Learning in Single-cell Multiomics Clustering

Contrastive Learning in Single-cell Multiomics Clustering
复制标题

单细胞多组学聚类中的对比学习

DOI:
10.1145/3584371.3613010
复制
发表时间:
2023
期刊:
ACM
影响因子:
--
通讯作者:
Nabavi, Sheida
Nabavi, Sheida
中科院分区:
--
文献类型:
--
作者:
Li, Bingjun;Nabavi, Sheida

文献摘要

参考文献

相似文献

单细胞多组学测序技术的最新进展为研究人员提供了新的机遇。然而,多组学数据的综合分析提出了新的挑战,特别是在细胞聚类方面,这是任何下游分析的关键步骤[5]。一个关键的挑战是融合过程中多模态组学特征的对齐。一种普遍采用的解决方案是通过实现不同组学特征的鉴别器来进行对抗性训练[1]。然而,判别器有几个影响现实世界性能的缺点[8]。在这项研究中,我们建议通过强制不同的潜在特征簇在同一空间中分离和紧凑,使用对比学习来实现更好的组学对齐。我们还旨在整合基因组学实体之间相互作用的先验知识,特别是基因调控网络(GRN),以实现更好的聚类。先前的研究已表明 GRN 在细胞类型分类中的重要作用 [3, 4]。据我们所知,不存在结合 GRN 的端到端聚类方法 [1]。
Recent advancements in single-cell multiomics sequencing technology present new opportunities for researchers. However, the integrative analysis of the multiomics data poses new challenges, especially in cell clustering, a crucial step for any downstream analysis [5]. A key challenge is the alignment of multimodal omic features during fusion. A commonly adopted solution is adversarial training by implementing a discriminator of different omic features [1]. However, discriminators have several drawbacks affecting real-world performance [8]. In this study, we propose to use contrastive learning for better omic alignment by forcing different clusters of latent features to be separable and compact in the same space. We also aim to incorporate prior knowledge of interactions across genomics entities, specifically the gene regulatory network (GRN) for better clustering. Prior studies have shown GRN's important role in cell type classification [3, 4]. To our best knowledge, no end-to-end clustering method that incorporates GRN exists [1].
用于预测和整合单细胞中 DNA、RNA 和蛋白质数据的沙箱
DOI: --
发表时间: 2021
期刊:
影响因子: --
作者:
Malte D. Luecken;Daniel B. Burkhardt;Robrecht Cannoodt;Christopher Lance;A. Agrawal;H. Aliee;A. Chen;Louise Deconinck;A. Detweiler;Alejandro A. Granados;Shelly Huynh;Laura Isacco;Y. Kim;B. D. Kumar;S. Kuppasani;H. Lickert;A. McGeever;Honey Mekonen;Joaquín Caceres;Melgarejo;Maurizio Morri;Michael Mueller;N. Neff;S. Paul;Bastian;Rieck;Kaylie Schneider;S. Steelman;Michael Sterr;D. Treacy;A. Tong;A. Villani;Guilin Wang;Jianrong Yan;Ce Zhang;A. Pisco;Smita;Krishnaswamy;Fabian J Theis;J. Bloom
通讯作者: J. Bloom
DOI: 10.1186/s12859-023-05622-4
发表时间: 2024-01-15
期刊: BMC bioinformatics
影响因子: 3
作者:
通讯作者: --