Tianhao Wu

scMaize provides a maize-specific foundation model and integrated single-cell atlas, showing improved classification and cross-species generalizability with functional priors.

The paper introduces dropTotal, a method for single-cell total RNA-seq that detects both coding and non-coding transcripts, and applies it to human glioma nuclei to uncover ncRNA-driven regulatory landscapes.

ASOCompass predicts ASO activity by integrating sequence, chemistry, and biological context, achieving higher correlation than baselines across diverse conditions.

HalluCodon designs species-specific coding sequences using multimodal language models trained on plant omics data, generating codons that match host-specific usage and support high expression.

Surf2Spot predicts protein-protein and nanobody-antigen interaction hotspots using a deep learning model that integrates sequence, structure, and surface properties, improving performance over existing methods.