Heng Huang

The paper uses machine learning to predict autopsy-confirmed neuropathology from clinical, neuroimaging, and CSF biomarkers, finding that different modalities best predict specific pathologies.

This study improves modeling of amyloid-β spread in Alzheimer's Disease using a gene-modulated network diffusion framework, showing better performance in correlation and replicability across cohorts.

This study compares deep learning methods to predict cognitive decline using brain MRI and clinical data over two years, showing the value of integrating image and tabular data.

CodonTranslator is a Transformer-based model for codon optimization across species, achieving better codon usage and stability than existing methods.

This paper introduces instantaneous frequency as a biomarker for dynamic brain networks, showing it can distinguish clinical and demographic groups in neurodegenerative conditions.

The paper uses tiled whole genome sequence data to identify genetic signatures associated with Alzheimer's disease using machine learning methods.

This study identifies genetic subtypes of Alzheimer's Disease using cell-based gene networks and polygenic risk scores, then repositions existing drugs for AD treatment.

This paper introduces scRNAkinetics, a method to estimate RNA kinetics parameters from scRNA-seq data using biological priors, showing accurate inference on simulated datasets and validation with existing studies.

This paper introduces a watermarking framework for protein sequences generated by deep learning models to enhance biosecurity while preserving performance and accessibility.

This paper introduces RADO, a doublet detection algorithm for single-cell sequencing data that maximizes the area under the precision-recall curve, outperforming existing methods on multiple datasets.

SECANT improves clustering and annotation of single-cell multi-omics data by integrating surface protein and RNA information with biology-guided semi-supervised learning.

This paper introduces TransformerST, a Transformer-based model for spatial transcriptomics analysis without single-cell references, achieving high-resolution tissue clustering and gene expression prediction.

BREM-SC is a Bayesian model that jointly clusters single-cell transcriptomic and proteomic data, improving accuracy and quantifying clustering uncertainty.

This paper introduces an interpretable deep learning model to detect Alzheimer's disease by analyzing longitudinal neuroimaging data from the ADNI cohort.