Senior Deep Learning Scientist, Illumina AI Lab
I build machine learning for genomics — sequence-to-function models, genome annotation, and DNA language models.
I am a Senior Deep Learning Scientist at the Illumina AI Lab. I earned my Ph.D. in Computer Science from the Center for Computational Biology, Johns Hopkins University (August 2025), advised by Steven Salzberg and Mihaela Pertea. My research focuses on AI for genomics — sequence-to-function modeling, genome annotation, and DNA language models. I hold a B.S. in Electrical Engineering from National Taiwan University and exchanged in my final year at the Australian National University.
What I work on
Gene expression
Shorkie is a masked-DNA language model pretrained on 165 fungal genomes and fine-tuned on high-resolution yeast transcription-factor induction time-course RNA-seq data to predict dynamic expression patterns.
RNA splicing
A dilated residual convolutional neural network that decodes RNA splicing, alternative splicing, and the impact of genetic variants on cryptic splicing — released as Splam and OpenSpliceAI.
Genome annotation
Graph-based methods that combine fragmented DNA and protein alignments to assemble more accurate genome annotations, implemented in the LiftOn annotation lift-over tool.
Genome assembly
Han1: the first gapless, reference-quality, fully annotated Southern Han Chinese genome, assembled from PacBio HiFi and Oxford Nanopore long reads using T2T-CHM13 as a guide.
Selected work
“Build what you need, use what you build.”
Background
Experience
Education
Writing
LiftOn 2.0 rebuilds our DNA-plus-protein genome-annotation lift-over tool for whole-genome scale: lower memory, fewer crashes, broader feature recovery, and a safer merge — validated on six whole-genome end-to-end lift-overs from same-species to mammal-to-fish.
Read postThe story behind Shorkie — a fungal DNA language model that learns the regulatory grammar of budding yeast and predicts how its genes turn on and off over time.
Read postUpdates
I give an invited talk in the Machine Learning in Genomics session at ProbGen 2026 at UC Berkeley. The talk is titled “Predicting dynamic expression patterns in budding yeast with a fungal DNA language model.”
The OpenSpliceAI version of record is published in eLife. The GitHub repository and documentation are available.
Our Shorkie preprint describing a fungal DNA language model for predicting RNA-seq coverage from DNA sequence in S. cerevisiae is available on bioRxiv.
My public dissertation talk, “Decoding the Language of Genomes: Bridging Sequences and Function through Deep Learning,” is scheduled for August 25, 2025.
I defend my Ph.D. dissertation at Johns Hopkins University on August 25, 2025, advised by Steven Salzberg and Mihaela Pertea.
I'm always glad to talk about computational genomics, machine learning, or mentoring research projects. Reach out anytime.