JLJunwei Liu

Junwei Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Junwei Liu has a total of 45 co-authors. Here are the top co-authors by number of shared publications:

  • Yixue Li

    Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai 200031, China

    13 shared publications
  • Feng-Ao Wang

    Key Laboratory of Systems Health Science of Zhejiang Province, School of Life Science, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, China

    4 shared publications
  • Ruikun He

    BYHEALTH Institute of Nutrition & Health, Guangzhou, China

    4 shared publications
  • Ruikun He

    BYHEALTH Institute of Nutrition & Health, Guangzhou 510663, China

    4 shared publications
  • Chenxin Yi

    Guangzhou National Laboratory , No. 9 XingDaoHuanBei Road, Guangzhou International Bio Island, Guangzhou 510005 Guangdong Province

    3 shared publications
  • Chenxin Yi

    Guangzhou National Laboratory, Guangzhou, China

    3 shared publications

Latest Publications

  • Open Access

    Quantum-boosted deep generative learning unveils the energy-landscape of single cell omics

    by Feng-Ao Wang, Shaobo Chen, Yao Xuan, Junwei Liu, Qi Gao, Hongdong Zhu, Junjie Hou, Lixin Yuan, Weizhi Ji, Yongchang Chen, et al.

  • Open Access

    TSTScope Unifies Single‐Cell Multi‐Omics to Identify Functional T Cell States Predictive of Immunotherapy Response

    by Shiwei Cao, Jinyu Cheng, Feng‐Ao Wang, Chenxin Yi, Jiajun Chen, Keyue Wang, Lulu Liu, Junwei Liu, Yixue Li

    Immune checkpoint blockade (ICB) can produce durable responses in cancer, but reliable predictors of benefit are still lacking. CD8 + tumor‐specific T cells (TSTs) are essential for ICB efficacy, yet it remains unclear which functional states of these cells are associated with therapeutic benefit. To address this, we developed TSTScope, an interpretable deep learning framework that integrates single‐cell transcriptomic and T‐cell receptor sequencing data to generate unified representations of CD8 + T‐cell identity. By applying TSTScope to non‐small cell lung cancer (NSCLC) datasets, we characterized the gene programs defining tumor specificity and computationally inferred a population of potential TSTs (pTSTs). Our analyses show that clinical response is associated with the functional state of these cells rather than their abundance alone. We derived the major pathological response (MPR) score, a metric capturing this functional potential. In an independent validation cohort, the MPR score was associated with pathological response and recurrence‐free survival and provided complementary information to selected response‐associated biomarkers. Collectively, TSTScope identifies a distinct functional state of tumor‐specific T cells linked to ICB response, providing an interpretable framework for studying receptor‐linked T‐cell function in immunotherapy cohorts.

  • Open Access

    Exploring phenotype-related single-cells through attention-enhanced representation learning

    by Qinhua Wu, Junxiang Ding, Ruikun He, Lijian Hui, Junwei Liu, Yixue Li

    Atlas-level single-cell investigations elucidate disease pathogenesis and progression. Accurate interpretation of phenotype-related single-cell data necess


  • Open Access

    Harnessing multi-omics and machine learning for predicting immune checkpoint blockade responses: Advances, challenges, and future directions

    by Shiwei Cao, Junwei Liu, Yixue Li

    Immune checkpoint blockade (ICB) therapies have revolutionized cancer treatment, showing success across various cancer types. However, there is variability in response rates among different cancers and individual patients. This highlights the critical need for precise patient stratification. Machine Learning and Deep Learning models are increasingly utilized to predict ICB responses by integrating multi-omics data, such as clinical, genomic, radiomic, and transcriptomic information. This review outlines the key methodologies of these predictive models. It underscores their role in enhancing response prediction. We delve into the advanced mechanisms of ICB response and discuss the biological foundations that inform these models. This demonstrates how basic research informs clinical application. We aim to offer comprehensive insights into how artificial intelligence can optimize patient stratification for ICB therapy.


  • Open Access

    Benchmarking deep learning methods for biologically conserved single-cell integration

    by Chenxin Yi, Jinyu Cheng, Jiajun Chen, Wanquan Liu, Junwei Liu, Yixue Li

    Advancements in single-cell RNA sequencing have enabled the analysis of millions of cells, but integrating such data across samples and methods while mitigating batch effects remains challenging. Deep learning approaches address this by learning biologically conserved gene expression representations, yet systematic benchmarking of loss functions and integration performance is lacking. We evaluate 16 integration methods using a unified variational autoencoder framework, incorporating batch and cell-type information. Results reveal limitations in the single-cell integration benchmarking index (scIB) for preserving intra-cell-type information. To address this, we introduce a correlation-based loss function and enhance benchmarking metrics to better capture biological conservation. Using cell annotations from lung and breast atlases, our approach improves biological signal preservation. We propose a refined integration framework, scIB-E, and metrics that provide deeper insights into the integration process and offer guidance for advanced developments in integrating increasingly complex single-cell data. This benchmark highlights the potential of deep learning-based approaches for single-cell data integration, emphasizing the importance of biologically informed metrics and improved benchmarking strategies.


  • Open Access

    scTFBridge: a disentangled deep generative model informed by TF-motif binding for gene regulation inference in single-cell multi-omics

    by Feng-Ao Wang, Chenxin Yi, Jiajun Chen, Ruikun He, Junwei Liu, Yixue Li

    The interplay between transcription factors (TFs) and regulatory elements (REs) drives gene transcription, forming gene regulatory networks (GRNs). Advances in single-cell technologies now enable simultaneous measurement of RNA expression and chromatin accessibility, offering unprecedented opportunities for GRN inference at single-cell resolution. However, heterogeneity across omics layers complicates regulatory feature extraction. We present scTFBridge, a multi-omics deep generative model for GRN inference. scTFBridge disentangles latent spaces into shared and specific components across omics layers. By integrating TF-motif binding knowledge, scTFBridge aligns shared embeddings with specific TF regulatory activities, enhancing biological interpretability. Using explainability methods, scTFBridge computes regulatory scores for REs and TFs, enabling robust GRN inference. Our results further demonstrate that scTFBridge can identify cell-type-specific susceptibility genes and distinct regulatory programs, providing insights into gene regulation mechanisms at the single-cell level.


  • Open Access

    scTFBridge: A Disentangled Deep Generative Model Informed by TF-Motif Binding for Gene Regulation Inference in Single-Cell Multi-Omics

    by Junwei Liu, Feng-Ao Wang, Ruikun He, Yixue Li

    The interplay between transcription factors (TFs) and regulatory elements (REs) drives gene transcription, forming gene regulatory networks (GRNs). Advances in single-cell technologies now enable simultaneous measurement of RNA expression and chromatin accessibility, offering unprecedented opportunities for GRN inference at single-cell resolution. However, heterogeneity across omics layers complicates regulatory feature extraction. We present scTFBridge, a multi-omics deep generative model for GRN inference. scTFBridge disentangles latent spaces into shared and specific components across omics layers. By integrating TF-motif binding knowledge, scTFBridge aligns shared embeddings with specific TF regulatory activities, enhancing biological interpretability. Using explainability methods, scTFBridge computes regulatory scores for REs and TFs, enabling robust GRN inference. It consistently outperformed baseline methods in both cis- and trans-regulation inference tasks. Our results demonstrate that scTFBridge can uncover cell-type-specific susceptibility genes and distinct regulatory programs, offering new insights into gene regulation mechanisms at single-cell resolution.

  • Open Access

    Interpretable Multimodal Fusion Model for Bridged Histology and Genomics Survival Prediction in Pan‐Cancer

    by Feng Gao, Junxiang Ding, Baowen Gai, Du Cai, Chuling Hu, Feng‐Ao Wang, Ruikun He, Junwei Liu, Yixue Li, Xiao‐Jian Wu

    Understanding the prognosis of cancer patients is crucial for enabling precise diagnosis and treatment by clinical practitioners. Multimodal fusion models based on artificial intelligence (AI) offer a comprehensive depiction of the tumor heterogeneity landscape, facilitating more accurate predictions of cancer patient prognosis. However, in the real‐world, the lack of complete multimodal data from patients often hinders the practical clinical utility of such models. To address this limitation, an interpretable bridged multimodal fusion model is developed that combines histopathology, genomics, and transcriptomics. This model assists clinical practitioners in achieving more precise prognosis predictions, particularly when patients lack corresponding molecular features. The predictive capabilities of the model are validated across 12 cancer types, achieving optimal performance in both complete and missing modalities. The work highlights the promise of developing a clinically applicable medical multimodal fusion model. This not only aids in reducing the healthcare burden on cancer patients but also provides improved assistance for clinical practitioners in precise diagnosis and treatment.


  • Top Cited Papers
    Open Access

    Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis

    by Junwei Liu, Xiaoping Cen, Chenxin Yi, Feng-Ao Wang, Junxiang Ding, Jinyu Cheng, Qinhua Wu, Baowen Gai, Yiwen Zhou, Ruikun He, et al.

    The rapid development of biological and medical examination methods has vastly expanded personal biomedical information, including molecular, cellular, image, and electronic health record datasets. Integrating this wealth of information enables precise disease diagnosis, biomarker identification, and treatment design in clinical settings. Artificial intelligence (AI) techniques, particularly deep learning models, have been extensively employed in biomedical applications, demonstrating increased precision, efficiency, and generalization. The success of the large language and vision models further significantly extends their biomedical applications. However, challenges remain in learning these multimodal biomedical datasets, such as data privacy, fusion, and model interpretation. In this review, we provide a comprehensive overview of various biomedical data modalities, multimodal representation learning methods, and the applications of AI in biomedical data integrative analysis. Additionally, we discuss the challenges in applying these deep learning methods and how to better integrate them into biomedical scenarios. We then propose future directions for adapting deep learning methods with model pretraining and knowledge integration to advance biomedical research and benefit their clinical applications.


  • Open Access

    scTFBridge: A Disentangled Deep Generative Model Informed by TF-Motif Binding for Gene Regulation Inference in Single-Cell Multi-Omics

    by Feng-Ao Wang, Ruikun He, Junwei Liu, Yixue Li

    The interplay between transcription factors (TFs) and regulatory elements (REs) drives gene transcription, forming gene regulatory networks (GRNs). Advances in single-cell technologies now enable simultaneous measurement of RNA expression and chromatin accessibility, offering unprecedented opportunities for GRN inference at single-cell resolution. However, heterogeneity across omics layers complicates regulatory feature extraction. We present scTFBridge, a multi-omics deep generative model for GRN inference. scTFBridge disentangles latent spaces into shared and specific components across omics layers. By integrating TF-motif binding knowledge, scTFBridge aligns shared embeddings with specific TF regulatory activities, enhancing biological interpretability. Using explainability methods, scTFBridge computes regulatory scores for REs and TFs, enabling robust GRN inference. It consistently outperformed baseline methods in both cis- and trans-regulation inference tasks. Our results demonstrate that scTFBridge can uncover cell-type-specific susceptibility genes and distinct regulatory programs, offering new insights into gene regulation mechanisms at single-cell resolution.