Single-cell RNA sequencing (scRNA-seq) has provided unprecedented insights for life science research. In scRNA-seq data analysis, clustering is a crucial step that lays the foundation for downstream tasks. However, the high dimensionality and sparsity of scRNA-seq data lead to suboptimal representations learned by existing methods, thereby limiting clustering performance. To address these issues, we propose scDGCL, a novel dual-level and graph-constrained contrastive learning method for scRNA-seq data clustering. Specifically, we first design Dual-level Contrastive Learning (DCL), which optimizes cell representations by simultaneously considering similarities and disparities at both cell and cluster levels. Then, we design Graph-constrained Contrastive Learning (GCL), which aligns the DCL-derived representations with the graph's relational priors, further enhancing cell representations. To systematically evaluate scDGCL, we perform experiments on 12 real datasets and 8 simulated datasets. Comparing scDGCL with 17 representative clustering methods, the results demonstrate it's superiority in scRNA-seq data clustering. Ablation experiments and hyperparameter experiments are performed to verify the effectiveness of each component and the overall robustness of our method. Marker gene expression and cell trajectory inference analysis verify the biological plausibility of our method from a biological perspective.

Shengxiang Gao, Fang Nan, Yongbing Zhang, Yuxin Huang, Kaiwen Tan, Zhengtao Yu. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Clustering is a crucial step in single-cell RNA sequencing (scRNA-seq) data analysis, facilitating the discovery of new cell types and the grouping of similar cells. Recently, graph convolutional networks (GCNs) have gained prominence in scRNA-seq data clustering because they effectively learn cell representations by capturing the relationship between cells. However, GCNs are sensitive to noise in scRNA-seq data and are prone to over-smoothing, resulting in the loss of cell-specific information. To overcome these challenges, we propose sigRGCN, a robust residual graph convolutional network for scRNA-seq data clustering. Specifically, we first construct a disturbed cell graph by injecting noise into a cell graph constructed from scRNA-seq data. Then, we design a graph structure optimization graph convolutional network to eliminate the impact of noise in the disturbed cell graph. It significantly improves the robustness of the proposed model in real scRNA-seq data clustering tasks. After that, we utilize a $L$-layers residual graph convolutional network to alleviate the over-smoothing problem. It allows our model to effectively capture higher-order relationships between cells, leading to better cell representations. Finally, we employ a self-supervised manner to optimize our model. The experimental results on nine real scRNA-seq datasets show that our proposed model demonstrates competitive performance in real clustering tasks.

The interaction between SNPs plays a key role in revealing the genetic mechanisms of complex diseases. However, as the order of SNP interactions increases, the number of SNP combinations increases exponentially, presenting a serious combinatorial explosion problem. Although swarm intelligence algorithms can alleviate the combinatorial explosion problem by optimizing search paths and have been widely used in SNP interaction detection, the performance of swarm intelligence algorithms is greatly affected by initialization and search direction. To mitigate these issues, we propose a high-order SNP interaction detection algorithm based on hierarchical clustering and multitask harmony search (abbreviated as HCMHS). In harmony memory initialization, considering that similar SNPs are more likely to form pathogenic combinations, hierarchical clustering is first used to cluster SNPs into different clusters, and then based on these clusters, harmony memory is initialized. In harmony search, considering the correlation between different orders of SNP interactions, the search directions for SNPs of various orders are optimized through a multi-task framework. To verify the performance of HCMHS, we carried out experiments on 58 simulated datasets and one real dataset, and HCMHS achieved the best results compared to nine advanced algorithms. The code of HCMHS is available at https://github.com/huoluan17-tian/HCMHS.

Clustering plays a crucial role in analyzing scRNA-seq data and has been widely used in studying cellular distribution over the past few years. However, the high dimensionality and complexity of scRNA-seq data pose significant challenges to achieving accurate clustering from a singular perspective. To address these challenges, we propose a novel approach, called multi-level multi-view network based on structural consistency contrastive learning (scMMN), for scRNA-seq data clustering. Firstly, the proposed method constructs shallow views through the $k$-nearest neighbor ($k$NN) and diffusion mapping (DM) algorithms, and then deep views are generated by utilizing the graph Laplacian filters. These deep multi-view data serve as the input for representation learning. To improve the clustering performance of scRNA-seq data, contrastive learning is introduced to enhance the discrimination ability of our network. Specifically, we construct a group contrastive loss for representation features and a structural consistency contrastive loss for structural relationships. Extensive experiments on eight real scRNA-seq datasets show that the proposed method outperforms other state-of-the-art methods in scRNA-seq data clustering tasks. Our source code has already been available at https://github.com/szq0816/scMMN.

The development of omics data and biomedical images has greatly advanced the progress of precision medicine in diagnosis, treatment, and prognosis. The fusion of omics and imaging data, i.e., omics-imaging fusion, offers a new strategy for understanding complex diseases. However, due to a variety of issues such as the limited number of samples, high dimensionality of features, and heterogeneity of different data types, efficiently learning complementary or associated discriminative fusion information from omics and imaging data remains a challenge. Recently, numerous machine learning methods have been proposed to alleviate these problems. In this review, from the perspective of fusion levels and fusion methods, we first provide an overview of preprocessing and feature extraction methods for omics and imaging data, and comprehensively analyze and summarize the basic forms and variations of commonly used and newly emerging fusion methods, along with their advantages, disadvantages and the applicable scope. We then describe public datasets and compare experimental results of various fusion methods on the ADNI and TCGA datasets. Finally, we discuss future prospects and highlight remaining challenges in the field.

Multi-modal neural machine translation (MNMT) aims to improve textual level machine translation performance in the presence of text-related images. Most of the previous works on MNMT focus on multi-modal fusion methods with full visual features. However, text and its corresponding image may not match exactly, visual noise is generally inevitable. The irrelevant image regions may mislead or distract the textual attention and cause model performance degradation. This paper proposes a noise-robust multi-modal interactive fusion approach with cross-modal relation-aware mask mechanism for MNMT. A text-image relation-aware attention module is constructed through the cross-modal interaction mask mechanism, and visual features are extracted based on the text-image interaction mask knowledge. Then a noise-robust multi-modal adaptive fusion approach is presented by fusion the relevant visual and textual features for machine translation. We validate our method on the Multi30K dataset. The experimental results show the superiority of our proposed model, and achieve the state-of-the-art scores in all En-De, En-Fr and En-Cs translation tasks.

The curse of dimensionality, which is caused by high-dimensionality and low-sample-size, is a major challenge in gene expression data analysis. However, the real situation is even worse: labelling data is laborious and time-consuming, so only a small part of the limited samples will be labelled. Having such few labelled samples further increases the difficulty of training deep learning models. Interpretability is an important requirement in biomedicine. Many existing deep learning methods are trying to provide interpretability, but rarely apply to gene expression data. Recent semi-supervised graph convolution network methods try to address these problems by smoothing the label information over a graph. However, to the best of our knowledge, these methods only utilize graphs in either the feature space or sample space, which restrict their performance. We propose a transductive semi-supervised representation learning method called a hierarchical graph convolution network (HiGCN) to aggregate the information of gene expression data in both feature and sample spaces. HiGCN first utilizes external knowledge to construct a feature graph and a similarity kernel to construct a sample graph. Then, two spatial-based GCNs are used to aggregate information on these graphs. To validate the model's performance, synthetic and real datasets are provided to lend empirical support. Compared with two recent models and three traditional models, HiGCN learns better representations of gene expression data, and these representations improve the performance of downstream tasks, especially when the model is trained on a few labelled samples. Important features can be extracted from our model to provide reliable interpretability.