Neythen J. Treloar

Learning the Language of the Microbiome with Transformers

The paper introduces Atlas, a microbiome dataset, and Waypoint, a series of transformer-based models, showing improvements in downstream tasks through pretraining.

Emergent digital bio-computation through spatial diffusion and engineered bacteria

This paper designs bacterial computers using spatial diffusion and engineered Escherichia coli to perform digital logic operations and complex computations.

Conflict during learning reconfigures the neural representation of positive valence and approach behaviour

The paper investigates how conflicting positive and negative experiences are represented in the neural circuit of C. elegans during learning, showing that valence is flexibly encoded across neurons rather than in a single class.

Deep Reinforcement Learning for Optimal Experimental Design in Biology

This paper applies reinforcement learning to optimal experimental design in biology, showing it outperforms existing methods in bacterial growth parameter inference under parametric uncertainty.

Deep reinforcement learning for the control of microbial co-cultures in bioreactors

This paper demonstrates the use of reinforcement learning to control microbial co-cultures in bioreactors, showing improved performance over traditional methods.