Preprints

ProMeta: A meta-learning framework for robust disease diagnosis and prediction from plasma proteomics

Han Li*#, Haoteng Gu*, Lei Hu*, Zimo Zhang, Yongji Lv, Peng Gao, Johnathan Cooper-Knock, Yaosen Min#, Jianyang Zeng#, Sai Zhang# (* equal contribution, # corresponding author)

bioRxiv 2026

We developed ProMeta, a meta-learning framework designed for robust disease diagnosis and prediction using plasma proteomics data, effectively addressing the challenges of limited sample sizes through task-adaptive representation learning.

[Paper] [Code]

ProMeta: A meta-learning framework for robust disease diagnosis and prediction from plasma proteomics

Han Li*#, Haoteng Gu*, Lei Hu*, Zimo Zhang, Yongji Lv, Peng Gao, Johnathan Cooper-Knock, Yaosen Min#, Jianyang Zeng#, Sai Zhang# (* equal contribution, # corresponding author)

bioRxiv 2026

We developed ProMeta, a meta-learning framework designed for robust disease diagnosis and prediction using plasma proteomics data, effectively addressing the challenges of limited sample sizes through task-adaptive representation learning.

[Paper] [Code]

PRSNet-2: End-to-end genotype-to-phenotype prediction via hierarchical graph neural networks

Han Li*#, Zisen Shan*, Hongyu Fu*, Yiwei Du, Shuaishuai Gao, Peng Gao, Johnathan Cooper-Knock, Yaosen Min#, Xudong Xing#, Sai Zhang# (* equal contribution, # corresponding author)

bioRxiv 2025

We developed PRSNet-2, an end-to-end hierarchical graph neural network framework that integrates multi-scale biological priors to significantly enhance the accuracy and interpretability of complex trait prediction from raw genotype data.

[Paper] [Code]

PRSNet-2: End-to-end genotype-to-phenotype prediction via hierarchical graph neural networks

Han Li*#, Zisen Shan*, Hongyu Fu*, Yiwei Du, Shuaishuai Gao, Peng Gao, Johnathan Cooper-Knock, Yaosen Min#, Xudong Xing#, Sai Zhang# (* equal contribution, # corresponding author)

bioRxiv 2025

We developed PRSNet-2, an end-to-end hierarchical graph neural network framework that integrates multi-scale biological priors to significantly enhance the accuracy and interpretability of complex trait prediction from raw genotype data.

[Paper] [Code]

SpaTranslator: A deep generative framework for universal spatial multi-omics cross-modality translation

Hongyu Dong, Sheng Mao, Yukuan Liu, Tian Tian, Lihua Zhang, Juanshu Wu, Shichen Zhang, Peng Jiang, Danqing Yin, Xudong Xing#, Peizhuo Wang#, Han Li# (# corresponding author)

bioRxiv 2025

We developed SpaTranslator, a universal deep generative framework that enables high-fidelity cross-modality translation between spatial transcriptomics and other spatial omics, facilitating the integration and comprehension of spatially resolved molecular landscapes.

[Paper] [Code]

SpaTranslator: A deep generative framework for universal spatial multi-omics cross-modality translation

Hongyu Dong, Sheng Mao, Yukuan Liu, Tian Tian, Lihua Zhang, Juanshu Wu, Shichen Zhang, Peng Jiang, Danqing Yin, Xudong Xing#, Peizhuo Wang#, Han Li# (# corresponding author)

bioRxiv 2025

We developed SpaTranslator, a universal deep generative framework that enables high-fidelity cross-modality translation between spatial transcriptomics and other spatial omics, facilitating the integration and comprehension of spatially resolved molecular landscapes.

[Paper] [Code]

STARNet enables spatially resolved inference of gene regulatory networks from spatial multi-omics data

Lei Hu, Shichen Zhang, Xuting Zhang, Yihai Luo, Haoteng Gu, Peng Liu, Sheng Mao, Li Chen, Yuhao Xia, Minghao Yang, Sai Zhang, Yaosen Min, Han Li, Peizhuo Wang, Hongtao Yu, Jianyang Zeng

bioRxiv 2025

We developed STARNet, a computational framework that leverages spatial multi-omics data to infer spatially resolved gene regulatory networks, revealing the spatial heterogeneity of transcriptional regulation within complex tissues.

[Paper] [Code]

STARNet enables spatially resolved inference of gene regulatory networks from spatial multi-omics data

Lei Hu, Shichen Zhang, Xuting Zhang, Yihai Luo, Haoteng Gu, Peng Liu, Sheng Mao, Li Chen, Yuhao Xia, Minghao Yang, Sai Zhang, Yaosen Min, Han Li, Peizhuo Wang, Hongtao Yu, Jianyang Zeng

bioRxiv 2025

We developed STARNet, a computational framework that leverages spatial multi-omics data to infer spatially resolved gene regulatory networks, revealing the spatial heterogeneity of transcriptional regulation within complex tissues.

[Paper] [Code]

Dissecting the genetic complexity of myalgic encephalomyelitis/chronic fatigue syndrome via deep learning-powered genome analysis

Sai Zhang, Fereshteh Jahanbani, Varuna Chander, Martin Kjellberg, Menghui Liu, Katherine A. Glass, David S. Iu, Faraz Ahmed, Han Li, Rajan Douglas Maynard, Johnathan Cooper-Knock, Martin Jinye Zhang, Durga Thota, Michael Zeineh, Jennifer K. Grenier, Andrew Grimson, Maureen R. Hanson, Michael P. Snyder

medRxiv 2025

We employed deep learning-powered genome analysis to identify rare and common genetic variants associated with ME/CFS, providing new insights into the biological pathways and polygenic architecture underlying this complex disease.

[Paper]

Dissecting the genetic complexity of myalgic encephalomyelitis/chronic fatigue syndrome via deep learning-powered genome analysis

Sai Zhang, Fereshteh Jahanbani, Varuna Chander, Martin Kjellberg, Menghui Liu, Katherine A. Glass, David S. Iu, Faraz Ahmed, Han Li, Rajan Douglas Maynard, Johnathan Cooper-Knock, Martin Jinye Zhang, Durga Thota, Michael Zeineh, Jennifer K. Grenier, Andrew Grimson, Maureen R. Hanson, Michael P. Snyder

medRxiv 2025

We employed deep learning-powered genome analysis to identify rare and common genetic variants associated with ME/CFS, providing new insights into the biological pathways and polygenic architecture underlying this complex disease.

[Paper]

A multistage, multitask transformer-based framework for multi-disease diagnosis and prediction using personal proteomes

Han Li*#, Yongkang Li*, Yukuan Liu*, Johnathan Cooper-Knock, Peng Gao, Xiaotao Shen, Shengquan Chen#, Xudong Xing#, Sai Zhang# (* equal contribution, # corresponding author)

medRxiv 2025

We developed a multitask Transformer framework that leverages longitudinal personal proteomic profiles to achieve high-accuracy diagnosis and future risk prediction for multiple complex diseases simultaneously.

[Paper] [Code]

A multistage, multitask transformer-based framework for multi-disease diagnosis and prediction using personal proteomes

Han Li*#, Yongkang Li*, Yukuan Liu*, Johnathan Cooper-Knock, Peng Gao, Xiaotao Shen, Shengquan Chen#, Xudong Xing#, Sai Zhang# (* equal contribution, # corresponding author)

medRxiv 2025

We developed a multitask Transformer framework that leverages longitudinal personal proteomic profiles to achieve high-accuracy diagnosis and future risk prediction for multiple complex diseases simultaneously.

[Paper] [Code]

Pepgb: facilitating peptide drug discovery via graph neural networks

Yipin Lei, Xu Wang, Meng Fang, Han Li, Xiang Li, Jianyang Zeng# (# corresponding author)

arXiv 2024

We developed PepGB, a graph neural network-based framework designed to model peptide-protein interactions, significantly accelerating the virtual screening and optimization of therapeutic peptide candidates.

[Paper] [Code]

Pepgb: facilitating peptide drug discovery via graph neural networks

Yipin Lei, Xu Wang, Meng Fang, Han Li, Xiang Li, Jianyang Zeng# (# corresponding author)

arXiv 2024

We developed PepGB, a graph neural network-based framework designed to model peptide-protein interactions, significantly accelerating the virtual screening and optimization of therapeutic peptide candidates.

[Paper] [Code]

2025

Single-cell polygenic risk scores dissect cellular and molecular heterogeneity of complex human diseases

Sai Zhang, Hantao Shu, Jingtian Zhou, Jasper Rubin-Sigler, Xiaoyu Yang, Yuxi Liu, Johnathan Cooper-Knock, Emma Monte, Chenchen Zhu, Sharon Tu, Han Li, Mingming Tong, Joseph R. Ecker, Justin K. Ichida, Yin Shen, Jianyang Zeng, Philip S. Tsao, Michael P. Snyder

Nature Biotechnology 2025

We introduced a framework for calculating polygenic risk scores at the single-cell level, enabling the dissection of cell-type-specific genetic vulnerabilities and molecular heterogeneity across complex human diseases.

[Paper] [Code]

Single-cell polygenic risk scores dissect cellular and molecular heterogeneity of complex human diseases

Sai Zhang, Hantao Shu, Jingtian Zhou, Jasper Rubin-Sigler, Xiaoyu Yang, Yuxi Liu, Johnathan Cooper-Knock, Emma Monte, Chenchen Zhu, Sharon Tu, Han Li, Mingming Tong, Joseph R. Ecker, Justin K. Ichida, Yin Shen, Jianyang Zeng, Philip S. Tsao, Michael P. Snyder

Nature Biotechnology 2025

We introduced a framework for calculating polygenic risk scores at the single-cell level, enabling the dissection of cell-type-specific genetic vulnerabilities and molecular heterogeneity across complex human diseases.

[Paper] [Code]

Modeling gene interactions in polygenic prediction via geometric deep learning

Han Li, Jianyang Zeng, Michael P. Snyder, Sai Zhang

Genome Research 2025

We developed PRS-Net, a geometric deep learning framework that captures complex gene-gene interactions through biological networks to improve the accuracy and interpretability of polygenic risk scores.

[Paper] [Code]

Modeling gene interactions in polygenic prediction via geometric deep learning

Han Li, Jianyang Zeng, Michael P. Snyder, Sai Zhang

Genome Research 2025

We developed PRS-Net, a geometric deep learning framework that captures complex gene-gene interactions through biological networks to improve the accuracy and interpretability of polygenic risk scores.

[Paper] [Code]

2024

Revolutionizing biomolecular structure determination with artificial intelligence

Han Li*, Yipin Lei*, Jianyang Zeng (* equal contribution)

National Science Review 2024

We review and envision how AI-driven methodologies are transforming biomolecular structure determination, providing high-resolution insights into complex biological machineries and dynamic molecular ensembles.

[Paper]

Revolutionizing biomolecular structure determination with artificial intelligence

Han Li*, Yipin Lei*, Jianyang Zeng (* equal contribution)

National Science Review 2024

We review and envision how AI-driven methodologies are transforming biomolecular structure determination, providing high-resolution insights into complex biological machineries and dynamic molecular ensembles.

[Paper]

From Static to Dynamic Structures: Improving Binding Affinity Prediction with Graph-Based Deep Learning

Yaosen Min, Ye Wei, Peizhuo Wang, Xiaoting Wang, Han Li, Nian Wu, Stefan Bauer, Shuxin Zheng, Yu Shi, Yingheng Wang, Ji Wu, Dan Zhao, Jianyang Zeng

Advanced Science 2024

We developed a graph-based deep learning approach to bridge the gap between static protein-ligand structures and their dynamic binding processes, significantly improving the accuracy of binding affinity predictions.

[Paper] [Code]

From Static to Dynamic Structures: Improving Binding Affinity Prediction with Graph-Based Deep Learning

Yaosen Min, Ye Wei, Peizhuo Wang, Xiaoting Wang, Han Li, Nian Wu, Stefan Bauer, Shuxin Zheng, Yu Shi, Yingheng Wang, Ji Wu, Dan Zhao, Jianyang Zeng

Advanced Science 2024

We developed a graph-based deep learning approach to bridge the gap between static protein-ligand structures and their dynamic binding processes, significantly improving the accuracy of binding affinity predictions.

[Paper] [Code]

PRSNet: Interpretable polygenic risk scores via geometric learning

Han Li, Jianyang Zeng, Michael P. Snyder, Sai Zhang

International Conference on Research in Computational Molecular Biology (RECOMB) 2024

We introduced PRS-net, a geometric deep learning framework that incorporates biological network topologies to enhance the accuracy and interpretability of polygenic risk scores across complex human traits.

[Paper] [Code]

PRSNet: Interpretable polygenic risk scores via geometric learning

Han Li, Jianyang Zeng, Michael P. Snyder, Sai Zhang

International Conference on Research in Computational Molecular Biology (RECOMB) 2024

We introduced PRS-net, a geometric deep learning framework that incorporates biological network topologies to enhance the accuracy and interpretability of polygenic risk scores across complex human traits.

[Paper] [Code]

2023

Deciphering driver regulators of cell fate decisions from single-cell transcriptomics data with CEFCON

Peizhuo Wang, Xiao Wen, Han Li, Peng Lang, Shuya Li, Yipin Lei, Hantao Shu, Lin Gao, Dan Zhao, Jianyang Zeng

Nature Communications 2023

We developed CEFCON, a computational framework that integrates cell-specific gene network flow with causality analysis to accurately identify key transcription factors driving cell fate transitions.

[Paper] [Code]

Deciphering driver regulators of cell fate decisions from single-cell transcriptomics data with CEFCON

Peizhuo Wang, Xiao Wen, Han Li, Peng Lang, Shuya Li, Yipin Lei, Hantao Shu, Lin Gao, Dan Zhao, Jianyang Zeng

Nature Communications 2023

We developed CEFCON, a computational framework that integrates cell-specific gene network flow with causality analysis to accurately identify key transcription factors driving cell fate transitions.

[Paper] [Code]

A knowledge-guided pre-training framework for improving molecular representation learning

Han Li, Ruotian Zhang, Yaosen Min, Dacheng Ma, Dan Zhao, Jianyang Zeng

Nature Communications 2023

We developed KPGT, a self-supervised learning framework that integrates molecular descriptors and structural knowledge to significantly enhance the accuracy and robustness of molecular representation learning.

[Paper] [Code]

A knowledge-guided pre-training framework for improving molecular representation learning

Han Li, Ruotian Zhang, Yaosen Min, Dacheng Ma, Dan Zhao, Jianyang Zeng

Nature Communications 2023

We developed KPGT, a self-supervised learning framework that integrates molecular descriptors and structural knowledge to significantly enhance the accuracy and robustness of molecular representation learning.

[Paper] [Code]

Improving comparative analyses of Hi-C data via contrastive self-supervised learning

Han Li, Xuan He, Lawrence Kurowski, Ruotian Zhang, Dan Zhao, Jianyang Zeng

Briefings in Bioinformatics 2023

We introduced a contrastive self-supervised learning framework to extract robust features from Hi-C contact maps, effectively enhancing the detection of differential chromatin interactions across biological conditions.

[Paper] [Code]

Improving comparative analyses of Hi-C data via contrastive self-supervised learning

Han Li, Xuan He, Lawrence Kurowski, Ruotian Zhang, Dan Zhao, Jianyang Zeng

Briefings in Bioinformatics 2023

We introduced a contrastive self-supervised learning framework to extract robust features from Hi-C contact maps, effectively enhancing the detection of differential chromatin interactions across biological conditions.

[Paper] [Code]

2022

Improving molecular property prediction through a task similarity enhanced transfer learning strategy

Han Li, Xinyi Zhao, Shuya Li, Fangping Wan, Dan Zhao, Jianyang Zeng

iScience 2022

We developed a transfer learning strategy that quantifies task similarity to identify optimal source data, significantly improving prediction performance on low-resource molecular property tasks.

[Paper] [Code]

Improving molecular property prediction through a task similarity enhanced transfer learning strategy

Han Li, Xinyi Zhao, Shuya Li, Fangping Wan, Dan Zhao, Jianyang Zeng

iScience 2022

We developed a transfer learning strategy that quantifies task similarity to identify optimal source data, significantly improving prediction performance on low-resource molecular property tasks.

[Paper] [Code]

KPGT: knowledge-guided pre-training of graph transformer for molecular property prediction

Han Li, Dan Zhao, Jianyang Zeng

Proceedings of the 28th ACM SIGKDD Conference (KDD) 2022

We proposed KPGT, a novel Graph Transformer framework that leverages large-scale unlabelled molecular data and structural knowledge through a self-supervised pre-training strategy to master molecular representations.

[Paper] [Code]

KPGT: knowledge-guided pre-training of graph transformer for molecular property prediction

Han Li, Dan Zhao, Jianyang Zeng

Proceedings of the 28th ACM SIGKDD Conference (KDD) 2022

We proposed KPGT, a novel Graph Transformer framework that leverages large-scale unlabelled molecular data and structural knowledge through a self-supervised pre-training strategy to master molecular representations.

[Paper] [Code]

2021

Modeling gene regulatory networks using neural network architectures

Hantao Shu, Jingtian Zhou, Qiuyu Lian, Han Li, Dan Zhao, Jianyang Zeng, Jianzhu Ma

Nature Computational Science 2021

We introduced an interpretable neural network framework to infer gene regulatory networks, bridging the gap between deep learning's predictive power and the mechanistic understanding of transcriptional regulation.

[Paper] [Code]

Modeling gene regulatory networks using neural network architectures

Hantao Shu, Jingtian Zhou, Qiuyu Lian, Han Li, Dan Zhao, Jianyang Zeng, Jianzhu Ma

Nature Computational Science 2021

We introduced an interpretable neural network framework to infer gene regulatory networks, bridging the gap between deep learning's predictive power and the mechanistic understanding of transcriptional regulation.

[Paper] [Code]

MoTSE: an interpretable task similarity estimator for small molecular property prediction tasks

Han Li, Xinyi Zhao, Shuya Li, Fangping Wan, Dan Zhao, Jianyang Zeng

International Conference on Research in Computational Molecular Biology (RECOMB) 2021

We proposed MoTSE, a framework to estimate task similarity by comparing neural network hidden representations, effectively guiding transfer learning for molecular property prediction with limited data.

[Paper] [Code]

MoTSE: an interpretable task similarity estimator for small molecular property prediction tasks

Han Li, Xinyi Zhao, Shuya Li, Fangping Wan, Dan Zhao, Jianyang Zeng

International Conference on Research in Computational Molecular Biology (RECOMB) 2021

We proposed MoTSE, a framework to estimate task similarity by comparing neural network hidden representations, effectively guiding transfer learning for molecular property prediction with limited data.

[Paper] [Code]