Xiangchun Li

OmniNA: A foundation model for nucleotide sequences

OmniNA is a foundation model for nucleotide sequences trained on diverse species data, achieving performance across 17 tasks and offering insights into mutation effects on DNA/RNA processing.

Reformer: Deep learning model for characterizing protein-RNA interactions from sequence at single-base resolution

Reformer predicts protein-RNA binding affinity from sequence with single-base resolution, showing high accuracy and discovering novel binding motifs.

Scalable batch-correction method for integrating large-scale single-cell transcriptomes

This paper introduces a scalable batch-correction method for integrating large-scale single-cell transcriptomes and shows it matches state-of-the-art performance on 18 million cells from the Human Cell Atlas.

Generative pretraining from large-scale transcriptomes: Implications for single-cell deciphering and clinical translation

The paper introduces tGPT, a generative model for integrating large-scale single-cell transcriptomes, showing its effectiveness in clustering, trajectory inference, and linking gene patterns to clinical outcomes.

A universal approach for integrating super large-scale single-cell transcriptomes by exploring gene rankings

The paper introduces iSEEEK, a method for integrating large-scale single-cell transcriptomes using gene rankings, showing good clustering and transferability across datasets.

The landscape of somatic mutation in sporadic Chinese colorectal cancer

This study identifies novel somatic mutations and altered mutation frequencies in Chinese colorectal cancer patients using whole exome sequencing, highlighting differences from TCGA data.