iMAP: integration of multiple single-cell datasets by adversarial paired transfer networks

Genome Biology

Xiliang Wang¹  Dongfang Wang²  Zemin Zhang³  Baolin Liu⁴  Lei Zhang⁵  Siyu Hou⁶ 

[1] Analytical Biosciences Limited, Beijing, China;BIOPIC and School of Life Sciences, Peking University, Beijing, China;BIOPIC and School of Life Sciences, Peking University, Beijing, China;Analytical Biosciences Limited, Beijing, China;Beijing Advanced Innovation Center for Genomics, Peking-Tsinghua Center for Life Sciences, Peking University, Beijing, China;BIOPIC and School of Life Sciences, Peking University, Beijing, China;Beijing Advanced Innovation Center for Genomics, Peking-Tsinghua Center for Life Sciences, Peking University, Beijing, China;Institute of Cancer Research, Shenzhen Bay Laboratory, Shenzhen, China;MOE Key Laboratory for Bioinformatics, BNRIST Bioinformatics Division, Department of Automation, Tsinghua University, Beijing, China;

关键词: scRNA-seq;    Data integration;    Deep learning;    GAN;   

DOI  :  10.1186/s13059-021-02280-8

来源: Springer

【 摘 要 】

The integration of single-cell RNA-sequencing datasets from multiple sources is critical for deciphering cell-to-cell heterogeneities and interactions in complex biological systems. We present a novel unsupervised batch effect removal framework, called iMAP, based on both deep autoencoders and generative adversarial networks. Compared with current methods, iMAP shows superior, robust, and scalable performance in terms of both reliably detecting the batch-specific cells and effectively mixing distributions of the batch-shared cell types. Applying iMAP to tumor microenvironment datasets from two platforms, Smart-seq2 and 10x Genomics, we find that iMAP can leverage the powers of both platforms to discover novel cell-cell interactions.

【 授权许可】

CC BY