MOTIVATION: Topologically associating domains (TADs) are fundamental building blocks of 3D genome. TAD-like domains in single cells are regarded as the underlying genesis of TADs discovered in bulk cells. Understanding the organization of TAD-like domains helps to get deeper insights into their regulatory functions. Unfortunately, it remains a challenge to identify TAD-like domains on single-cell Hi-C data due to its ultra-sparsity. RESULTS: We propose scKTLD, an in silico tool for the identification of TAD-like domains on single-cell Hi-C data. It takes Hi-C contact matrix as the adjacency matrix for a graph, embeds the graph structures into a low-dimensional space with the help of sparse matrix factorization followed by spectral propagation, and the TAD-like domains can be identified using a kernel-based changepoint detection in the embedding space. The results tell that our scKTLD is superior to the other methods on the sparse contact matrices, including downsampled bulk Hi-C data as well as simulated and experimental single-cell Hi-C data. Besides, we demonstrated the conservation of TAD-like domain boundaries at single-cell level apart from heterogeneity within and across cell types, and found that the boundaries with higher frequency across single cells are more enriched for architectural proteins and chromatin marks, and they preferentially occur at TAD boundaries in bulk cells, especially at those with higher hierarchical levels. AVAILABILITY AND IMPLEMENTATION: scKTLD is freely available at https://github.com/lhqxinghun/scKTLD.

Abstract Traditional knowledge distillation relies on high‐capacity teacher models to supervise the training of compact student networks. To avoid the computational resource costs associated with pretraining high‐capacity teacher models, teacher‐free online knowledge distillation methods have achieved satisfactory performance. Among these methods, feature fusion methods have effectively alleviated the limitations of training without the strong guidance of a powerful teacher model. However, existing feature fusion methods often focus primarily on end‐layer features, overlooking the efficient utilization of holistic knowledge loops and high‐level information within the network. In this article, we propose a new feature fusion‐based mutual learning method called Diversify Feature Enhancement and Fusion for Online Knowledge Distillation (DFEF). First, we enhance advanced semantic information by mapping multiple end‐of‐network features to obtain richer feature representations. Next, we design a self‐distillation module to strengthen knowledge interactions between the deep and shallow network layers. Additionally, we employ attention mechanisms to provide deeper and more diversified enhancements to the input feature maps of the self‐distillation module, allowing the entire network architecture to acquire a broader range of knowledge. Finally, we employ feature fusion to merge the enhanced features and generate a high‐performance virtual teacher to guide the training of the student model. Extensive evaluations on the CIFAR‐10, CIFAR‐100, and CINIC‐10 datasets demonstrate that our proposed method can significantly enhance performance compared to state‐of‐the‐art feature fusion‐based online knowledge distillation methods. Our code can be found at https://github.com/JSJ515-Group/DFEF-Liu .

MOTIVATION: The emerging single-cell Hi-C technology provides opportunities to study dynamics of chromosomal organization. How to construct a pseudotime path using single-cell Hi-C contact matrices to order cells along developmental trajectory is a challenging topic, since these matrices produced by the technology are inherently high dimensional and sparse, they suffer from noises and biases, and the topology of trajectory underlying them may be diverse. RESULTS: We present scHiCPTR, an unsupervised graph-based pipeline to infer pseudotime from single-cell Hi-C contact matrices. It provides a workflow consisting of imputation and embedding, graph construction, dual graph refinement, pseudotime calculation and result visualization. Beyond the few existing methods, scHiCPTR ties to optimize graph structure by two parallel procedures of graph pruning, which help reduce the spurious cell links resulted from noises and determine a global developmental directionality. Besides, it has an ability to handle developmental trajectories with multiple topologies, including linear, bifurcated and circular ones, and is competitive with methods developed for single-cell RNA-seq data. The comparative results tell that our scHiCPTR can achieve higher performance in pseudotime inference, and the inferred developmental trajectory exhibit a reasonable biological significance. AVAILABILITY AND IMPLEMENTATION: scHiCPTR is freely available at https://github.com/lhqxinghun/scHiCPTR. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.