Graduate Researcher · Computational Biology

Kaiyu Nie

I frame RNA design as optimization and machine-learning problems, and build reproducible scientific software to solve them. Finishing my MASc at Concordia on RNA inverse folding.

Get in touch LinkedIn GitHub

◎ Montréal, QC, Canada ✓ Authorized to work in Canada · no sponsorship needed

Featured project

MASc thesis

A Modular Multi-Tool Evolutionary Framework for RNA Inverse Folding

CEC 2026 · Oral

A predictor-agnostic island-model evolutionary algorithm designed from scratch — population structure, fitness formulation, and mutation operators. A multi-oracle consensus fitness combines ViennaRNA and MXFold2 to make design robust under predictor uncertainty, reaching a 68% solve rate on the Eterna100 benchmark — comparable to published reinforcement-learning methods.

Python PyTorch ViennaRNA MXFold2 Evolutionary computation SLURM

Accepted and presented — K. Nie & N. Kharma, IEEE Congress on Evolutionary Computation (CEC 2026), part of IEEE WCCI 2026, Maastricht — oral presentation.

View repository →

Research

RNA design · evolutionary computation · machine learning for structured biomolecules

Currently

Extending the evolutionary framework to a larger oracle set, with oxDNA-based evaluation
Computational sequence design for wet-lab collaborators
Next paper in preparation

Toolkit

Languages & tooling

Python NumPy pandas Bash Git Linux

Machine learning

PyTorch CNN Transformer GNN Diffusion

Optimization

Evolutionary computation Benchmark design & evaluation

Computational RNA/DNA

ViennaRNA MXFold2 EternaFold IPknot BPfold oxDNA

HPC & reproducibility

Compute Canada SLURM multi-node jobs conda

Open to research / SWE roles

Let's talk.

kaiyu.work@icloud.com