Modeling cellular dynamics over time is fundamental to understanding biological development and disease progression. Single-cell RNA sequencing (scRNA-seq) enables the high-resolution profiling of gene expression heterogeneity and the reconstruction of developmental trajectories. However, time-series scRNA-seq data present significant challenges due to the lack of temporal alignment inherent to destructive sampling and the limited ability of current models to capture dynamic expression patterns or extrapolate to future cell states. To address these issues, we propose scDiformer, a difference-aware Transformer framework developed for forecasting gene expression at future time points. scDiformer infers temporal couplings between cells at consecutive time points using optimal transport, enabling fine-grained trajectory modeling at the single-cell level. It further captures transcriptional dynamics by lever-aging expression-difference embeddings, which guide attention toward evolving gene expression trends. Additionally, we design a training strategy aligned with the target prediction objectives to enhance generalization under temporal shifts. Experiments on multiple real-world time-series scRNA-seq datasets demonstrate that scDiformer consistently outperforms existing methods in terms of Wasserstein distance and Pearson correlation. This framework offers a powerful tool for cell fate inference and provides valuable insights for studies in developmental biology and disease mechanisms.

Single-cell sequencing technology provides deep insights into gene activity at the individual cell level, facilitating the study of gene regulatory mechanisms. However, observed gene expression are often influenced by confounding factors such as batch effects, perturbations, and spatial position, which obscure the true gene regulatory network that governs the cell’s intrinsic state. To address these challenges, we propose scConCRL, a novel conditionally causal representation learning framework designed to extract the true gene regulatory relationships independent of confounding information. By considering both fine-grained molecular gene variables and coarse-grained latent domain variables, scConCRL not only uncovers the intrinsic biological signals but also models the complex relationships between these variables. This dual function enables the separation of genuine cellular states from domain information, providing valuable insights for downstream analyses and biological discovery. We demonstrate the effectiveness of our model on multi-domain datasets from different platforms and perturbation conditions, showing its ability to accurately disentangle confounding influences and discover novel gene relationships. Extensive comparisons across various scenarios illustrate the superior performance of scConCRL in several tasks compared to existing methods.

Understanding the intricate regulatory relationships among genes is crucial for comprehending the development, differentiation, and cellular response in living systems. Consequently, inferring gene regulatory networks (GRNs) based on observed data has gained significant attention as a fundamental goal in biological applications. The proliferation and diversification of available data present both opportunities and challenges in accurately inferring GRNs. Deep learning, a highly successful technique in various domains, holds promise in aiding GRN inference. Several GRN inference methods employing deep learning models have been proposed; however, the selection of an appropriate method remains a challenge for life scientists. In this survey, we provide a comprehensive analysis of 12 GRN inference methods that leverage deep learning models. We trace the evolution of these major methods and categorize them based on the types of applicable data. We delve into the core concepts and specific steps of each method, offering a detailed evaluation of their effectiveness and scalability across different scenarios. These insights enable us to make informed recommendations. Moreover, we explore the challenges faced by GRN inference methods utilizing deep learning and discuss future directions, providing valuable suggestions for the advancement of data scientists in this field.

Since single-cell RNA sequencing (scRNA-seq) has revolutionized the study of cellular dynamics, the construction of gene relationships based on dynamic information has attracted much attention. However, the sparsity and dropout events inherent in scRNA-seq data present challenges for downstream analysis like Gene Regulatory Network (GRN) inference. Existing data imputation methods have yielded good results beneficial for cell clustering, but it does not adequately consider gene expression dynamics. To address this, we introduce GROD, a novel deep learning approach that simultaneously infers GRN and imputes scRNA-seq data from a temporal perspective. GROD consists of three key components: an encoder, a graph learner, and a decoder. Experimental results demonstrate that GROD outperforms existing methods in both GRN inference and data imputation tasks, providing superior accuracy in capturing gene regulatory relationships and accurately imputing missing values. By integrating these two tasks, GROD enables more accurate downstream analysis and facilitates deeper insights into cellular dynamics.

MOTIVATION: Rapid developments of single-cell RNA sequencing technologies allow study of responses to external perturbations at individual cell level. However, in many cases, it is hard to collect the perturbed cells, such as knowing the response of a cell type to the drug before actual medication to a patient. Prediction in silicon could alleviate the problem and save cost. Although several tools have been developed, their prediction accuracy leaves much room for improvement. RESULTS: In this article, we propose scPreGAN (Single-Cell data Prediction base on GAN), a deep generative model for predicting the response of single-cell expression to perturbation. ScPreGAN integrates autoencoder and generative adversarial network, the former is to extract common information of the unperturbed data and the perturbed data, the latter is to predict the perturbed data. Experiments on three real datasets show that scPreGAN outperforms three state-of-the-art methods, which can capture the complicated distribution of cell expression and generate the prediction data with the same expression abundance as the real data. AVAILABILITY AND IMPLEMENTATION: The implementation of scPreGAN is available via https://github.com/JaneJiayiDong/scPreGAN. To reproduce the results of this article, please visit https://github.com/JaneJiayiDong/scPreGAN-reproducibility. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: With the development of modern sequencing technology, hundreds of thousands of single-cell RNA-sequencing (scRNA-seq) profiles allow to explore the heterogeneity in the cell level, but it faces the challenges of high dimensions and high sparsity. Dimensionality reduction is essential for downstream analysis, such as clustering to identify cell subpopulations. Usually, dimensionality reduction follows unsupervised approach. RESULTS: In this paper, we introduce a semi-supervised dimensionality reduction method named scSemiAE, which is based on an autoencoder model. It transfers the information contained in available datasets with cell subpopulation labels to guide the search of better low-dimensional representations, which can ease further analysis. CONCLUSIONS: Experiments on five public datasets show that, scSemiAE outperforms both unsupervised and semi-supervised baselines whether the transferred information embodied in the number of labeled cells and labeled cell subpopulations is much or less.