Deep learning (DL) is a branch of machine learning (ML) capable of extracting high-level features from raw inputs in multiple stages. Compared to traditional ML, DL models have provided significant improvements across a range of domains and applications. Single-cell (SC) omics are often high-dimensional, sparse, and complex, making DL techniques ideal for analyzing and processing such data. We examine DL applications in a variety of single-cell omics (genomics, transcriptomics, proteomics, metabolomics and multi-omics integration) and address whether DL techniques will prove to be advantageous or if the SC omics domain poses unique challenges. Through a systematic literature review, we have found that DL has not yet revolutionized or addressed the most pressing challenges of the SC omics field. However, using DL models for single-cell omics has shown promising results (in many cases outperforming the previous state-of-the-art models) but lacking the needed biological interpretability in many cases. Although such developments have generally been gradual, recent advances reveal that DL methods can offer valuable resources in fast-tracking and advancing research in SC.Abstract Figure

Motivation Single-cell RNA sequencing (scRNAseq) technologies allow for measurements of gene expression at a single-cell resolution. This provides researchers with a tremendous advantage for detecting heterogeneity, delineating cellular maps or identifying rare subpopulations. However, a critical complication remains: the low number of single-cell observations due to limitations by rarity of subpopulation, tissue degradation or cost. This absence of sufficient data may cause inaccuracy or irreproducibility of downstream analysis. In this work, we present ACTIVA (Automated Cell-Type-informed Introspective Variational Autoencoder): a novel framework for generating realistic synthetic data using a single-stream adversarial variational autoencoder conditioned with cell-type information. Within a single framework, ACTIVA can enlarge existing datasets and generate specific subpopulations on demand, as opposed to two separate models (such as scGAN and cscGAN). Data generation and augmentation with ACTIVA can enhance scRNAseq pipelines and analysis, such as benchmarking new algorithms, studying the accuracy of classifiers and detecting marker genes. ACTIVA will facilitate analysis of smaller datasets, potentially reducing the number of patients and animals necessary in initial studies. Results We train and evaluate models on multiple public scRNAseq datasets. In comparison to GAN-based models (scGAN and cscGAN), we demonstrate that ACTIVA generates cells that are more realistic and harder for classifiers to identify as synthetic which also have better pair-wise correlation between genes. Data augmentation with ACTIVA significantly improves classification of rare subtypes (more than 45% improvement compared to not augmenting and 4% better than cscGAN) all while reducing run-time by an order of magnitude in comparison to both models. Availability of data and code The codes and datasets are hosted on Zenodo (https://doi.org/10.5281/zenodo.5879639). Tutorials are available at https://github.com/SindiLab/ACTIVA. Supplementary information Supplementary material is available online.

Multiple sclerosis (MS) is a chronic demyelinating disease of the central nervous system (CNS) that is characterized by inflammation which typically results in significant impairment in most patients. Immune checkpoints act as co-stimulatory and co-inhibitory molecules and play a fundamental role in keeping the equilibrium of the immune system. Cytotoxic T-lymphocyte antigen-4 (CTLA-4) and Programmed death-ligand 1 (PD-L1), as inhibitory immune checkpoints, participate in terminating the development of numerous autoimmune diseases, including MS. We assessed the CTLA-4 and PD-L1 gene expression in the different cell types of peripheral blood mononuclear cells of MS patients using single-cell RNA-seq data. Additionally, this study outlines how CTLA-4 and PD-L1 expression was altered in the PBMC samples of relapsing-remitting multiple sclerosis (RRMS) patients compared to the healthy group. Finally, it investigates the impact of various MS-related treatments in the CTLA-4 and PD-L1 expression to restrain autoreactive T cells and stop the development of MS autoimmunity.