Guiding Mineralization Co-Culture Discovery Using Bayesian Optimization

Abstract

Many disciplines rely on testing combinations of compounds, materials, proteins, or bacterial species to drive scientific discovery. It is timeconsuming and expensive to determine experimentally, via trial-and-error or random selection approaches, which of the many possible combinations will lead to desirable outcomes. Hence, there is a pressing need for more rational and efficient experimental design approaches to reduce experimental effort. In this work, we demonstrate the potential of machine learning methods for the in silico selection of promising co-culture combinations in the application of bioaugmentation. We use the example of pollutant removal in drinking water treatment plants, which can be achieved using co-cultures of a specialized pollutant degrader with combinations of bacterial isolates. To reduce the experimental effort needed to discover high-performing combinations, we propose a data-driven experimental design. Based on a dataset of mineralization performance for all pairs of 13 bacterial species co-cultured with MSH1, we built a Gaussian process regression model to predict the Gompertz mineralization parameters of the co-cultures of two and three species, based on the single-strain parameters. We subsequently used this model in a Bayesian optimization scheme to suggest potentially high-performing combinations of bacteria. We achieved good performance with this approach, both for predicting mineralization parameters and for selecting effective co-cultures, despite the limited dataset. As a novel application of Bayesian optimization in bioremediation, this experimental design approach has promising applications for highlighting co-culture combinations for in vitro testing in various settings, to lessen the experimental burden and perform more targeted screenings.

Interspecies Interactions of the 2,6-Dichlorobenzamide Degrading Aminobacter sp. MSH1 with Resident Sand Filter Bacteria: Indications for Mutual Cooperative Interactions That Improve BAM Mineralization Activity

“…Future research using both top-down and bottom-up approaches can demonstrate whether the concept that uses residents as helpers for bioaugmentation as outlined above, is feasible in practice and additionally uncover (i) the underlying fundamental mechanisms including the molecular processes, the role of resources and niche availability, and the role of the resident community diversity, as well as (ii) the constraints for successful bioaugmentation such as the required propagule numbers and relative abundances of MSH1 and the benefactor for inoculation. The availability of the SFI collection that has been interrogated in this study regarding interactions with MSH1, of suitable model environments and of predictive models to reduce experimental efforts, will be the important asset for the bottom-up approach, whereas inventive meta-omics will be pivotal for a top-down approach. , Overall, such ecological studies will contribute to an improved understanding of the biotic factors and ecological mechanisms determining a particular strain’s invasive potential and a community’s resistance to invasion, a key requirement for managing bioaugmentation efforts and microbial invasion processes …”

“…Functionality was related to MSH1 cell density and to the individual fitness of the SFIs, and for selected combinations, the cell densities of the SFIs were examined to understand the interactions from the perspective of the SFIs. Some results of this work were used and reported previously for developing mathematical models of the invasion process, where the focus was on analysis and discussion of the predictive modeling methodologies and performances rather than an ecologically focused interpretation and discussion as in this paper. , …”

“…Some results of this work were used and reported previously for developing mathematical models of the invasion process, where the focus was on analysis and discussion of the predictive modeling methodologies and performances rather than an ecologically focused interpretation and discussion as in this paper. 40,41 ■ MATERIALS AND METHODS Bacterial Strains. A variant of Aminobacter sp.…”

Open-endedness in synthetic biology: a route to continual innovation for biological design

“…Finally, Bayesian Optimization [134] has recently gained popularity in synthetic biology [37,120,85,114] and might offer a possible route to open-endedness. A machine learning surrogate model, such as a Gaussian Process or Random Forest, is used to grade the entities based on a so-called acquisition function.…”