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.

Invasive rodent populations pose a threat to biodiversity across the globe. When confronted with these new 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. Such systems might 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 and allows for overlapping generations and a fluctuating population size. Our model 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, but only if resistance can be kept to a minimal level. This study highlights the power of supervised machine learning for identifying the key parameters and processes that determine the population dynamics of a complex evolutionary system.

Allergies are complex conditions involving both environmental and genetic factors. The genetic basis underlying allergic disease is investigated through genetic association studies. Genome-wide association studies (GWAS) leverage sequenced data to identify genetic mutations, such as single-nucleotide polymorphisms (SNPs), associated with phenotypes of interest. Machine learning can be used to analyze large datasets and generate predictive models. In this study, several classification models were created to predict the significance level of SNPs associated with allergies. Summary statistics were obtained from the GWAS Catalog and combined from several studies. Biological features such as chromosomal location, base pair location, effect allele, and odds ratio were used to train the models. The models ranged from simple linear regressions to multi-layer neural networks. The final models reached accuracies of 80% and reflect the features that have the largest impact on a SNP’s association level.

No abstract