Weiguang Mao

The paper introduces mousiPLIER, a mouse pathway-level information extractor model trained on brain RNA-seq data, which reduces dimensionality and identifies aging-related latent variables.

The paper introduces NIFA, a probabilistic factor analysis model for scRNA-seq data that disentangles discrete cell-type identity and continuous pathway activity, outperforming existing methods in biological interpretation.

DataRemix is a normalization method that enhances biological signal detection in gene expression data by tuning hidden factors, outperforming existing methods without external knowledge.

PLIER improves pathway inference and cell proportion analysis in gene expression data, enhancing replicability and biological insight in trans-eQTL studies.

The paper shows that enhancer-promoter interaction prediction models can achieve competitive performance without capturing the underlying mechanism, highlighting issues with overfitting and cross-validation.

The paper develops an attention-based neural network to predict enhancer-promoter interactions using DNA sequences and identifies key transcription factor binding sites.