Bayesian Optimization for Crop Genetics with Scalable Probabilistic Models

Ruhana Azam, Sang T. Truong, samuel bonfim fernandes, Andrew D.B. Leakey, Alexander Lipka, Mohammed El-Kebir, Sanmi Koyejo

Keywords: bayesian optimization; genomic selection

Abstract: An overarching goal of crop improvement is to select plants with desirable traits so that crops can provide sufficient food and nutrients for humanity in the face of climate change. To achieve such a goal, crop breeders utilize genomic prediction, in which that genome-wide DNA marker information is used to predict breeding values for desirable traits . Genomic prediction is complemented by advancements in high-throughput phenotyping, in robots and drones collect orders of magnitude higher amounts of trait information than in the past. Although such data are abundant and easy to collect, identifying the most biologically meaningful traits for use in genomic prediction is expensive. Bayesian optimization (BO) is a strong cost-effective solution to identify such meaningful traits. In this work, we quantified the performance of BO with a collection of acquisition function and surrogate models for identifying good proxies, in a set of +4 million proxies. We found that BO achieves comparable sample efficiency to random search while requiring significantly less computation. Despite traditional BO and random search techniques performing sufficiently well, both search techniques fail to leverage information from related tasks. To this end, we propose a pre-trained model as a transfer learning method. Using this benchmark, we conduct an extensive empirical study and demonstrate promising results on the transfer learning effect, highlighting a core design principle for developing more parsimonious optimization algorithms for crop improvement.

Submission Number: 8