iMAP: integration of multiple single-cell datasets by adversarial paired transfer networks
Autor: | Xiliang Wang, Siyu Hou, Lei Zhang, Zemin Zhang, Dongfang Wang, Baolin Liu |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
lcsh:QH426-470
Method Batch effect Biology computer.software_genre Machine learning scRNA-seq Leverage (statistics) Humans RNA-Seq lcsh:QH301-705.5 business.industry Sequence Analysis RNA Deep learning Computational Biology Reproducibility of Results Genomics GAN lcsh:Genetics ComputingMethodologies_PATTERNRECOGNITION lcsh:Biology (General) Organ Specificity Scalability Data integration Artificial intelligence Single-Cell Analysis business computer Algorithms |
Zdroj: | Genome Biology, Vol 22, Iss 1, Pp 1-24 (2021) Genome Biology |
Popis: | 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. Supplementary Information The online version contains supplementary material available at 10.1186/s13059-021-02280-8. |
Databáze: | OpenAIRE |
Externí odkaz: |