Biology subjects

Treloar, N. J.

Publications and source records attributed to Treloar, N. J..

4 recordsLinked to original sources

bioRxiv2026

Learning the Language of the Microbiome with Transformers

Self-supervised pretraining has become central to biological machine learning, yet microbiome data remains comparatively underexplored in terms of both modeling approaches and evaluation frameworks. To address this gap, we present Atlas, a pretraining dataset of 539,308 microbiome datapoints from the MGnify database. Using Atlas, we train the Waypoint family of microbiome foundation models: a series of GPT-2 style causal language models ranging from 6M to 170M parameters. We also introduce Compass, a curated benchmark of eight predictive tasks spanning biome classification, drug-microbiome interactions, drug degradation, and infant gut development. Using this benchmark, we compare the performance of Waypoint models against classical baselines and the existing MGM foundation model. Our results show that pretraining leads to consistent and significant improvements in downstream task performance, that both dataset scale and tokenization strategy impact model quality, that pretraining is essential for achieving favorable scaling behavior and that representations learned during pretraining generalise between microbiome domains. Furthermore, pretrained transformer models begin to reliably outperform classical methods once training data exceeds roughly 10,000 examples - a threshold that is attainable for modern microbiome studies. Finally, we demonstrate that the Waypoint models achieve state-of-the-art performance among microbiome foundation models. Overall, our work highlights the importance of large-scale self-supervised pretraining in this domain and establishes Atlas, Compass, and the Waypoint models as valuable resources for the research community in this emerging field.

bioinformatics↗

bioRxiv2023

Emergent digital bio-computation through spatial diffusion and engineered bacteria

Building computationally capable biological systems has long been an aim of synthetic biology. The potential utility of biocomputing devices ranges from biosafety and environmental applications to diagnosis and personalised medicine. Here we present work for the design of bacterial computers which use spatial patterning to process information. Our computers are composed of bacterial colonies which, inspired by patterning in embryo development, receive information in the form of diffusible morphogen-like signals. A computation is encoded by the physical locations of the input sources of morphogen and the output receiver colonies. We demonstrate, mathematically and with engineered Escherichia coli, the simple digital logic capability of single bacterial colonies and show how additional colonies are required to build complex functions. Inspired by electronic design automation, an algorithm for designing optimal spatial circuits computing two-level digital functions is presented. This enhances the capability of our system to complex digital functions without increasing the biological complexity. We extend our experimental system to incorporate biosensing colonies as morphogen sources, demonstrating how a diagnostic device might be constructed. Our approach will open up new ways to perform biological computation, with applications in bioengineering, biomaterials and biosensing. Ultimately, these computational bacterial communities will help us explore information processing in natural biological systems.

synthetic biology↗

bioRxiv2022

Deep Reinforcement Learning for Optimal Experimental Design in Biology

The field of optimal experimental design uses mathematical techniques to determine experiments that are maximally informative from a given experimental setup. Here we apply a technique from artificial intelligence--reinforcement learning--to the optimal experimental design task of maximizing confidence in estimates of model parameter values. We show that a reinforcement learning approach performs favourably in comparison with a one-step ahead optimisation algorithm and a model predictive controller for the inference of bacterial growth parameters in a simulated chemostat. Further, we demonstrate the ability of reinforcement learning to train over a distribution of parameters, indicating that this approach is robust to parametric uncertainty. 1 Author summaryBiological systems are often complex and typically exhibit non-linear behaviour, making accurate model parametrisation difficult. Optimal experimental design tools help address this problem by identifying experiments that are predicted to provide maximally accurate parameter estimates. In this work we use reinforcement learning, an artificial intelligence method, to determine such experiments. Our simulation studies show that this approach allows uncertainty in model parameterisation to be directly incorporated into the search for optimal experiments, opening a practical avenue for training an experimental controller without confident knowledge of the systems parameter values. We present this method as complementary to existing optimisation approaches and we anticipate that artificial intelligence has a fundamental role to play in the future of optimal experimental design.

synthetic biology↗

bioRxiv2018

Deep reinforcement learning for the control of bacterial populations in bioreactors

Multi-species microbial communities are widespread in natural ecosystems. When employed for biomanufacturing, engineered synthetic communities have shown increased productivity (in comparison with pure cultures) and allow for the reduction of metabolic load by compartmentalising bioprocesses between multiple sub-populations. Despite these benefits, co-cultures are rarely used in practice because control over the constituent species of an assembled community has proven challenging. Here we demonstrate, in silico, the efficacy of an approach from artificial intelligence - reinforcement learning - in the control of co-cultures within continuous bioreactors. We confirm that feedback via reinforcement learning can be used to maintain populations at target levels, and that model-free performance with bang-bang control can outperform traditional proportional integral controller with continuous control, when faced with infrequent sampling. Further, we demonstrate that a satisfactory control policy can be learned in one twenty-four hour experiment, by running five bioreactors in parallel. Finally, we show that reinforcement learning can directly optimise the output of a co-culture bioprocess. Overall, reinforcement learning is a promising technique for the control of microbial communities.

synthetic biology↗