Yihang Xiao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yihang Xiao has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Jiajie Peng
AI for Science Interdisciplinary Research Center, School of Computer Science, Northwestern Polytechnical University, Xi’an, China
3 shared publications Changxiao Yang
1 shared publicationFei Ni
College of Intelligence and Computing, Tianjin University
1 shared publication- Jianye Hao
College of Intelligence and Computing, Tianjin University
1 shared publication Jintian Luo
AI for Science Interdisciplinary Research Center, School of Computer Science, Northwestern Polytechnical University
1 shared publicationJinyi Liu
College of Intelligence and Computing, Tianjin University
1 shared publication
Latest Publications
- Open Access
- 2 November 2026
- Published by Springer Nature in Nature Communications
Building a pre-trained model for single-cell multi-omics analysis beyond highly variable feature selection
Single-cell multi-omics technologies enable simultaneous measurement of transcriptomic, epigenomic, and proteomic modalities in individual cells, offering a unique opportunity to dissect cellular identity and regulation. The heterogeneity of multi-omics data, together with the wide range of downstream analytical tasks, underscores the need for a versatile computational framework for integrative analysis. However, current multi-omics analysis approaches typically rely on task-specific training and highly variable feature selection, which can hinder effective knowledge transfer across datasets and discard biologically informative signals. Here, we present scPMMI, a pre-trained multimodal model for integrative analysis of single-cell multi-omics data. By grouping features into patches according to genomic coordinates, scPMMI processes tens of thousands of features per cell with reduced reliance on prior feature selection, thereby preserving more complete biological information. Our results demonstrate that scPMMI learns biologically coherent cell representations by jointly modeling multi-omics data. Through further transfer learning, the model can be readily adapted to achieve superior performance across diverse downstream tasks, including multi-omics integration, cell type annotation, protein abundance prediction, transcriptomic enhancement, and trajectory reconstruction.
- 2 November 2026
- Published by Springer Nature in Nature Communications
Open AccessBuilding a pre-trained model for single-cell multi-omics analysis beyond highly variable feature selection
Single-cell multi-omics technologies enable simultaneous measurement of transcriptomic, epigenomic, and proteomic modalities in individual cells, offering a unique opportunity to dissect cellular identity and regulation. The heterogeneity of multi-omics data, together with the wide range of downstream analytical tasks, underscores the need for a versatile computational framework for integrative analysis. However, current multi-omics analysis approaches typically rely on task-specific training and highly variable feature selection, which can hinder effective knowledge transfer across datasets and discard biologically informative signals. Here, we present scPMMI, a pre-trained multimodal model for integrative analysis of single-cell multi-omics data. By grouping features into patches according to genomic coordinates, scPMMI processes tens of thousands of features per cell with reduced reliance on prior feature selection, thereby preserving more complete biological information. Our results demonstrate that scPMMI learns biologically coherent cell representations by jointly modeling multi-omics data. Through further transfer learning, the model can be readily adapted to achieve superior performance across diverse downstream tasks, including multi-omics integration, cell type annotation, protein abundance prediction, transcriptomic enhancement, and trajectory reconstruction.
- Open Access
Compositional Brain Age Profiles Reveal Disease-Related Neuroimaging Patterns Beyond the Brain Age Gap
The brain age gap (BAG)—the difference between the predicted and chronological age—does not describe the imaging patterns underlying such deviation. To characterize these patterns, we developed a semantic-guided mixture-of-experts model using multimodal imaging-derived phenotypes and their metadata. Global and local expert outputs were combined to predict age and retained as an individualized composition profile. An evaluation in 37,894 UK Biobank participants used separate reference and clinical cohorts, with a test mean absolute error of 2.784–2.811 years. Participants with nearly identical standardized BAGs had different profiles, indicating imaging heterogeneity at similar levels of age deviation. Adding the profile to a baseline of age, standardized BAG, sex, and imaging center improved discrimination in four disease contrasts. The area under the receiver operating characteristic curve (AUC) increased by 0.018–0.060, with gains persisting after matching by age and standardized BAG. Higher AUC point estimates than equal-dimensional controls suggested that adding dimensions alone did not explain the gains. Combining the age-trained profile with unsupervised principal components improved discrimination further, suggesting complementary imaging information. These findings support composition profiles for examining disease-related imaging differences beyond overall brain age deviation.
Open AccessCompositional Brain Age Profiles Reveal Disease-Related Neuroimaging Patterns Beyond the Brain Age Gap
The brain age gap (BAG)—the difference between the predicted and chronological age—does not describe the imaging patterns underlying such deviation. To characterize these patterns, we developed a semantic-guided mixture-of-experts model using multimodal imaging-derived phenotypes and their metadata. Global and local expert outputs were combined to predict age and retained as an individualized composition profile. An evaluation in 37,894 UK Biobank participants used separate reference and clinical cohorts, with a test mean absolute error of 2.784–2.811 years. Participants with nearly identical standardized BAGs had different profiles, indicating imaging heterogeneity at similar levels of age deviation. Adding the profile to a baseline of age, standardized BAG, sex, and imaging center improved discrimination in four disease contrasts. The area under the receiver operating characteristic curve (AUC) increased by 0.018–0.060, with gains persisting after matching by age and standardized BAG. Higher AUC point estimates than equal-dimensional controls suggested that adding dimensions alone did not explain the gains. Combining the age-trained profile with unsupervised principal components improved discrimination further, suggesting complementary imaging information. These findings support composition profiles for examining disease-related imaging differences beyond overall brain age deviation.
- Open Access
CellAgent: LLM-Driven Multi-Agent Framework for Natural Language-Based Single-Cell Analysis
Single-cell RNA sequencing (scRNA-seq) and spatial transcriptomics (ST) data analysis are pivotal for advancing biological research, enabling precise characterization of cellular heterogeneity. However, existing analysis approaches require extensive manual programming and tool manipulation, posing significant challenges for researchers. To address this, we introduce CellAgent, an autonomous, LLM-driven approach that performs end-to-end scRNA-seq and spatial transcriptomics data analysis through natural language interactions. CellAgent employs a multi-agent hierarchical decision-making framework, simulating a “deep-thinking” workflow to ensure that each analytical step remains consistent with the overall task objective. To further enhance its capabilities, we developed sc-Omni, a high-performance, expert-curated toolkit that consolidates essential tools for scRNA-seq and spatial transcriptomics analysis. Additionally, we introduce a self-reflective optimization mechanism, enabling automated, iterative refinement of results through specialized evaluation methods, effectively replacing traditional manual assessments. Benchmarking against human experts demonstrates that CellAgent achieves approximately 60% improvement in efficiency across multiple downstream applications. In terms of accuracy, it maintains performance comparable to existing approaches while preserving natural language interactions. By translating natural language interactions into optimized analytical workflows, CellAgent establishes a scalable paradigm for LLM-driven scientific discovery, bridging the gap between experimental biologists and complex data analytics. This framework minimizes reliance on manual coding and exhaustive deliberation, ushering in the era of the “AI Agent for Science.”
Open AccessCellAgent: LLM-Driven Multi-Agent Framework for Natural Language-Based Single-Cell Analysis
Single-cell RNA sequencing (scRNA-seq) and spatial transcriptomics (ST) data analysis are pivotal for advancing biological research, enabling precise characterization of cellular heterogeneity. However, existing analysis approaches require extensive manual programming and tool manipulation, posing significant challenges for researchers. To address this, we introduce CellAgent, an autonomous, LLM-driven approach that performs end-to-end scRNA-seq and spatial transcriptomics data analysis through natural language interactions. CellAgent employs a multi-agent hierarchical decision-making framework, simulating a “deep-thinking” workflow to ensure that each analytical step remains consistent with the overall task objective. To further enhance its capabilities, we developed sc-Omni, a high-performance, expert-curated toolkit that consolidates essential tools for scRNA-seq and spatial transcriptomics analysis. Additionally, we introduce a self-reflective optimization mechanism, enabling automated, iterative refinement of results through specialized evaluation methods, effectively replacing traditional manual assessments. Benchmarking against human experts demonstrates that CellAgent achieves approximately 60% improvement in efficiency across multiple downstream applications. In terms of accuracy, it maintains performance comparable to existing approaches while preserving natural language interactions. By translating natural language interactions into optimized analytical workflows, CellAgent establishes a scalable paradigm for LLM-driven scientific discovery, bridging the gap between experimental biologists and complex data analytics. This framework minimizes reliance on manual coding and exhaustive deliberation, ushering in the era of the “AI Agent for Science.”