Nick Boyd

I'm a scientist with a background in optimization, AI, and structural biology.
I build measurement technologies and machine learning algorithms to understand and engineer biological systems.
At Atomic AI, I designed and trained ATOM-1, an RNA foundation model based on in-house chemical mapping datasets. Previously, as CTO of XGenomes, I developed algorithms and technologies for high-throughput DNA sequencing using localization microscopy.
During my PhD at Berkeley (with Ben Recht and Michael Jordan) and brief postdoc at the Broad Institute (with Aviv Regev) I built optimization algorithms for inverse problems, including the best performing algorithms for high-density super-resolution microscopy.
At Atomic AI, I designed and trained ATOM-1, an RNA foundation model based on in-house chemical mapping datasets. Previously, as CTO of XGenomes, I developed algorithms and technologies for high-throughput DNA sequencing using localization microscopy.
During my PhD at Berkeley (with Ben Recht and Michael Jordan) and brief postdoc at the Broad Institute (with Aviv Regev) I built optimization algorithms for inverse problems, including the best performing algorithms for high-density super-resolution microscopy.
select work
- boltz-binder-design
- ATOM-1: A Foundation Model for RNA Structure and Function Built on Chemical Mapping Data bioRxiv, 2023
- Sequencing by Emergence: Modeling and Estimation arXiv, 2021
- DeepLoco: fast 3D localization microscopy using neural networks BioRxiv, 2018
- The Alternating Descent Conditional Gradient Method for Sparse Inverse Problems SIAM Journal on Optimization, 2017
- Sets as Measures: Optimization and Machine LearningUC Berkeley, 2018
- Saturating Splines and Feature Selection JMLR, 2018
- Streaming Variational Bayes NeurIPS, 2013