Lechuan Li

A network of bZIP transcription factors and inhibitors enforces differentially proliferative and cytotoxic states in T cells

This study identifies bZIP transcription factors and inhibitors that influence T-cell proliferation and cytotoxicity under exhaustion conditions.

Interpretable phenotype decoding from multi-condition sequencing data with ALPINE

ALPINE is a supervised NMF framework that disentangles technical and phenotypic factors in multi-condition sequencing data, improving condition-specific signal isolation and interpretability.

Benchmarking gene embeddings from sequence, expression, network, and text models for functional prediction tasks

This study benchmarks 38 gene embedding methods across three functional prediction tasks, finding literature-based embeddings perform best overall, while sequence-based models excel in genetic interactions.

ANDES: a novel best-match approach for enhancing gene set analysis in embedding spaces

ANDES enhances gene set analysis in embedding spaces by comparing gene sets and achieving state-of-the-art performance in enrichment analysis.

Joint embedding of biological networks for cross-species functional alignment

This paper introduces ETNA, a joint embedding method for cross-species functional alignment using biological networks and sequence orthologs, showing improved preservation of gene functional relationships.

The proto-oncogene DEK regulates neuronal excitability and tau accumulation in Alzheimer's disease vulnerable neurons

The paper identifies DEK as a driver of tau pathology in Alzheimer's disease vulnerable neurons using in silico modeling and experimental validation.