scI2CL: Effectively Integrating Single-cell Multi-omics by Intra- and Inter-omics Contrastive Learning

2025-08-22

AI Summary

This study addresses the challenges of modeling cell–cell interaction patterns and resolving cellular heterogeneity in single-cell multi-omics data. We propose a cross-modal integration framework based on intra-group and inter-group contrastive learning. Our method employs self-supervised contrastive learning to jointly learn unified cell embeddings, achieve cross-modal alignment, and integrate multi-dimensional omics data—including transcriptomic and epigenomic profiles. To our knowledge, it is the first method to accurately reconstruct the complete hematopoietic differentiation trajectory from hematopoietic stem cells to memory B cells on real data and to identify a novel monocyte subpopulation. Evaluated on four benchmark datasets, our approach significantly outperforms eight state-of-the-art methods—particularly in CD4⁺ T cell subpopulation deconvolution, clustering accuracy, cell-type identification, and pseudotemporal ordering. The framework establishes a scalable, robust computational paradigm for multi-omics-driven dissection of dynamic cellular processes.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Single-cell multi-omics data contain huge information of cellular states, and analyzing these data can reveal valuable insights into cellular heterogeneity, diseases, and biological processes. However, as cell differentiation & development is a continuous and dynamic process, it remains challenging to computationally model and infer cell interaction patterns based on single-cell multi-omics data. This paper presents scI2CL, a new single-cell multi-omics fusion framework based on intra- and inter-omics contrastive learning, to learn comprehensive and discriminative cellular representations from complementary multi-omics data for various downstream tasks. Extensive experiments of four downstream tasks validate the effectiveness of scI2CL and its superiority over existing peers. Concretely, in cell clustering, scI2CL surpasses eight state-of-the-art methods on four widely-used real-world datasets. In cell subtyping, scI2CL effectively distinguishes three latent monocyte cell subpopulations, which are not discovered by existing methods. Simultaneously, scI2CL is the only method that correctly constructs the cell developmental trajectory from hematopoietic stem and progenitor cells to Memory B cells. In addition, scI2CL resolves the misclassification of cell types between two subpopulations of CD4+ T cells, while existing methods fail to precisely distinguish the mixed cells. In summary, scI2CL can accurately characterize cross-omics relationships among cells, thus effectively fuses multi-omics data and learns discriminative cellular representations to support various downstream analysis tasks.

Problem

• Integrating single-cell multi-omics data through contrastive learning
• Modeling continuous cell differentiation and interaction patterns
• Learning discriminative cellular representations for downstream tasks

Innovation

• Intra- and inter-omics contrastive learning framework
• Learns comprehensive discriminative cellular representations
• Effectively fuses single-cell multi-omics data