Tong Zhu

Reinforcement learning-driven unified generative framework for multi-objective RNA codon design

RNARL is a reinforcement learning framework for RNA codon design that generates high-performance sequences across multiple species and RNA types.

DeepSAP: Improved RNA-Seq Alignment by Integrating Transcriptome Guidance with Transformer-Based Splice Junction Scoring

DeepSAP improves RNA-seq alignment by combining transcriptome-guided alignment with a transformer-based model for splice junction scoring, achieving the highest F1 score on simulated datasets.

Time-resolved fluorescent proteins towards fluorescence microscopy in the temporal and spectral domains

This paper introduces time-resolved fluorescent proteins (TRFPs) that enable temporal-spectral resolved microscopy for multiplexed imaging and super-resolution in live cells.

Parabricks: GPU Accelerated Universal Pan-Instrument Genomics Analysis Software Suite

Parabricks accelerates genomic analysis using GPU acceleration, reducing processing time while maintaining accuracy across various sequencing modalities.

Accelerated somatic mutation calling for whole-genome and whole-exome sequencing data from heterogenous tumor samples

The paper introduces MuSE2.0, a tool that accelerates somatic mutation calling for whole-genome and whole-exome sequencing data from heterogeneous tumor samples, achieving significant speed improvements over existing methods.

Defective mechanosensory transduction of the new inner hair cells prevents hearing recover in the damaged cochlea

This study shows that newly regenerated inner hair cells in the cochlea lack functional mechanosensory transduction, preventing hearing recovery despite successful cell regeneration.

Tbx2 is essential for cochlear inner hair cell development and regeneration

This study identifies Tbx2 as essential for inner hair cell development and shows that its co-expression with Atoh1 can reprogram supporting cells into functional inner hair cells.