Work

An AI co-scientist and research observatory at KBase. It connects an agent to the BER data lakehouse through a set of reusable skills. Part of the BERIL project.

I built it and am its main contributor.

Predicting what a bacterium can do from its genome sequence.

I lead this work.

Interaction scores computed from pairs of genome-scale metabolic models, and a classifier that turns them into a predicted ecological outcome.

I work on CommScores with Andrew Freiburger and Chris Henry.

A genotype-to-phenotype data lakehouse at Oak Ridge, holding data from GPTgp, PMI and other projects behind one queryable model.

I worked on G2PAI.

A Nextflow pipeline for annotating bacterial genomes and predicting traits from them: quality control, then gene annotation, then several annotation tools run in parallel.

I built it.

A perspective on which computational kernels inside whole-cell simulation have scaling a quantum algorithm could improve, and which do not.

A perspective written with colleagues at Oak Ridge.

A workflow for working out which microbes tend to turn up together in a sample, and for comparing the methods that infer that.

I built MiCoNE with collaborators at Boston University and the Segrè lab.

Steering a microbial community in a bioreactor toward a target composition, learned by trial and error in simulation.

The last chapter of my PhD at Boston University.

A database of microbial interaction networks, with a web interface for browsing them.

Joint work with Zhenjun Hu, who designed the architecture, and Yan Wang, who implemented the platform with him.

A Python package for simulating biochemical systems where randomness matters: small molecule counts, noisy gene expression.

I wrote it with Srikiran Chandrasekaran.

A Nextflow framework for building sequencing-analysis pipelines, for bulk and single-cell RNA-seq.

An earlier project at Boston University that I contributed to.