Transfer Learning Bayesian Optimization to Design Competitor DNA Molecules for Use in Diagnostic Assays
This work addresses the challenge of costly experimental optimization for biomolecular devices, making it more feasible for applications in diagnostics, though it appears incremental as it builds on existing transfer learning and Bayesian optimization methods.
The paper tackles the problem of optimizing biological sequences like DNA competitors for diagnostic assays, which typically requires many expensive lab experiments, by introducing a transfer learning Bayesian optimization workflow that reduces the total number of experiments needed, as demonstrated with data showing improved efficiency in single and penalized optimization tasks.
With the rise in engineered biomolecular devices, there is an increased need for tailor-made biological sequences. Often, many similar biological sequences need to be made for a specific application meaning numerous, sometimes prohibitively expensive, lab experiments are necessary for their optimization. This paper presents a transfer learning design of experiments workflow to make this development feasible. By combining a transfer learning surrogate model with Bayesian optimization, we show how the total number of experiments can be reduced by sharing information between optimization tasks. We demonstrate the reduction in the number of experiments using data from the development of DNA competitors for use in an amplification-based diagnostic assay. We use cross-validation to compare the predictive accuracy of different transfer learning models, and then compare the performance of the models for both single objective and penalized optimization tasks.