Research

Research Interests

My research interests encompass high-dimensional data analysis and machine learning.

• High-dimensional data analysis: multiple testing, replicable inference, and dimension reduction, with applications in genotype data.
• Machine Learning: diffusion models, transformer, and synthetic data.

Publications and Preprints

• Wang, P., Lyu, P., Peddada, S., and Cao, H. (2025). Statistical analysis of correlated expression data from high-throughput experiments.
  Genetics, iyaf060.
• Bell, T.N., Kusi-Appiah, A.E., Tocci, V., Lyu, P., Zhu, L., Zhu, F., Van Winkle, D., Cao, H., Singh, M.S., and Lenhert, S. (2024). Scalable lipid droplet microarray fabrication, validation, and screening.
  Plos one, 19(7).
• Lyu, P., Li, Y., Wen, X., and Cao, H. (2023). JUMP: replicability analysis of high-throughput experiments with applications to spatial transcriptomic studies.
  Bioinformatics, 39(6).
• Lyu, P., Ma, Z., Zhang, L., and Zhang, A. (2025+). Bias-Corrected Data Synthesis for Imbalanced Learning.
• Lyu, P., Ma, Z., and Zhang, A. (2025+). Inference of diffusion models with imbalanced samples.
• Lyu, P., Zhang, X., and Cao, H. (2025+). Replicability analysis of high-dimensional data accounting for dependence. [arXiv].
• Wang, W., Chen, M., Luo, Y., and Lyu, P. (2025+). SFP-GNNformer: Global port fuel market dynamics and price volatility analysis based on spatiotemporal feature fusion.
• Lyu. P., Bell, T., Lenhert, S., and Cao, H. (2025+). Sample size calculation in cell culture - how many cells should I count?