Modeling CRISPR gene drives for suppression of invasive rodents using a supervised machine learning framework

Abstract

Invasive rodent populations pose a threat to biodiversity across the globe. When confronted with these invaders, native species that evolved independently are often defenseless. CRISPR gene drive systems could provide a solution to this problem by spreading transgenes among invaders that induce population collapse, and could be deployed even where traditional control methods are impractical or prohibitively expensive. Here, we develop a high-fidelity model of an island population of invasive rodents that includes three types of suppression gene drive systems. The individual-based model is spatially explicit, allows for overlapping generations and a fluctuating population size, and includes variables for drive fitness, efficiency, resistance allele formation rate, as well as a variety of ecological parameters. The computational burden of evaluating a model with such a high number of parameters presents a substantial barrier to a comprehensive understanding of its outcome space. We therefore accompany our population model with a meta-model that utilizes supervised machine learning to approximate the outcome space of the underlying model with a high degree of accuracy. This enables us to conduct an exhaustive inquiry of the population model, including variance-based sensitivity analyses using tens of millions of evaluations. Our results suggest that sufficiently capable gene drive systems have the potential to eliminate island populations of rodents under a wide range of demographic assumptions, though only if resistance can be kept to a minimal level. This study highlights the power of supervised machine learning to identify the key parameters and processes that determine the population dynamics of a complex evolutionary system.

Author summary

Invasive rodents can devastate biodiversity on small islands. This is because many types of plants and animals that evolved on such islands have no natural defense mechanisms against a rapidly spreading new invader. Gene drive is a promising new technology that, among other applications, may help control invasive rodent populations. A well-designed gene drive system could spread an engineered gene throughout a rodent population and eventually cause the population to collapse. We developed a detailed computational model of the release of a suppression gene drive into an island rat population and demonstrate that an efficient enough drive could indeed eradicate such a population within several years. To assist with a detailed analysis of our model, which involves various ecological and genetic parameters, we also developed a machine learning model to match the outcomes of the underlying population model. After sufficient training, this machine learning model is a close match to the underlying model, but runs thousands of times faster, thereby allowing for a much more detailed analysis of the behavior of the model. We believe that this new technique could be applied to the study of many other complex evolutionary systems.