Integration of heterogeneous single-cell datasets generated by different laboratories, across tissue locations, time and conditions can provide comprehensive insights into the cellular states and expression programs that cannot be obtained from individual datasets. To integrate such datasets for the comprehensive understanding of biological systems, Dr. Hamim Zafar‘s lab at Indian Institute of Technology Kanpur developed scDREAMER, a deep generative framework that allows for the unsupervised and supervised integration of single-cell datasets. The unsupervised version of scDREAMER utilizes an adversarial variational autoencoder, and a batch classifier neural network for learning the batch-invariant low-dimensional cellular embeddings. The supervised version, scDREAMER-Sup, employs an additional variational autoencoder and a cell-type classifier neural network to utilize available cell-type annotations for a semi-supervised or supervised inference of low-dimensional cellular representations. scDREAMER was evaluated on a diverse set of integration tasks on datasets consisting of up to 1 million cells and 147 batches, where it outperformed 11 state-of-the-art unsupervised and supervised integration methods respectively in batch-correction and conservation of biological variation. scDREAMER-Sup also performed superior to all other methods in predicting the cell type labels for the cells missing annotations. scDREAMER was also faster compared to certain other deep learning methods. This coupled with higher accuracy of scDREAMER particularly makes it an important data integration method as the deep learning-based methods enable the inference of latent cellular embeddings as well as corrected expression profiles which are required for several downstream applications such as trajectory inference or differential expression analysis.
Shree, Ajita, Musale Krushna Pavan, and Hamim Zafar. “scDREAMER for atlas-level integration of single-cell datasets using deep generative model paired with adversarial classifier.” Nature Communications 14, no. 1 (2023): 7781. [article]