Protein design
Interpretable generation and ranking across interfaces, sequences, and fitness landscapes.
Research
Connecting molecular mechanism and design through computation
My work explores AI for drug discovery through protein and peptide modeling, alongside computational evaluation of RNA and antisense oligonucleotides (ASOs), with an emphasis on rigorous, reproducible analysis.
RNA structure
Computational links among sequence, three-dimensional structure, dynamics, and regulation.
Molecular machine learning
Testing whether models answer real scientific questions under rigorous data boundaries.
Project experience
Research projects and collaborations
CGB3002: peptide design for blood–brain barrier delivery
ChainGen Biopharma · Independently led computational design
Independently designed peptide sequences and assessed their structures using multiple deep-learning approaches. CGB3002 has since entered Phase I clinical development for Alzheimer's disease; my contribution was to the earlier computational design stage. Sequences and unpublished design details remain confidential.
AI-assisted peptide substrate design for rapid SERS sensing
Co-first author (second-listed) | Computational substrate design
Led machine-learning-assisted sequence and structure design of MMP-2-cleavable peptide substrates to support matched dual-enzyme kinetics and rapid detection. The designed substrates were incorporated into the team’s dual-enzyme SERS sensing array, evaluated for intraoperative chemical mapping of epileptic foci, linking computational molecular design with diagnostic research.
Binding-affinity prediction for cytokine receptor interfaces
Independent computational project
Used deep learning to predict binding free-energy effects across single-residue saturation substitutions at a cytokine receptor complex interface involving the IL-2 receptor alpha chain.
Computational design of peptide substrates for palmitoyltransferase
Independent computational project
Applied deep-learning methods to peptide sequence redesign and computational substrate design.
Peptide binder design around an ATP1A3 phosphorylation site
Independently led computational design
Conducted computational peptide binder design focused on the S643 phosphorylation site of the sodium/potassium-transporting ATPase alpha-3 subunit (ATP1A3).
Ongoing research
Method development, driven by questions
SSDE: RNA candidate discovery through iterative learning
Self-Sustained Discovery Engine · End-to-end computational lead
Developing a discovery workflow that identifies RNA structural candidates from large collections of natural sequences when experimentally resolved structures are scarce. Responsible for data curation, model development and training, computational evaluation, candidate analysis, and delivery. The project has progressed to experimental validation.
Reliability and cross-source generalization of RNA design models
Evaluation framework · Interim findings established
Built a framework integrating multiple models and structural evidence for functional RNA evaluation, with data provenance checks, cross-source comparisons, and retrospective evaluation under a fixed budget. Interim findings show that ensemble gains depend on the data source, additional models do not consistently improve ranking, and structural plausibility cannot substitute for evidence of function.
Antisense oligonucleotide activity prediction and benchmarking
Machine learning for nucleic acid therapeutics · Initial benchmarks completed
Curated approximately 150,000 public records and benchmarked sequence and chemical features against RNA language-model representations. Used evaluation splits that separate targets, data sources, and similar sequences. Completed multi-seed benchmarks and ablation studies to characterize calibration shifts and limits to generalization under distribution shift.