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

Samuel E. Champer, Nathan Oakes, Ronin Sharma, Pablo Garcia Diaz, Jackson Champer, Philipp W Messer* (Corresponding Author)

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

13 Citations (Scopus)
11 Downloads (Pure)


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 meta13 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.
Original languageEnglish
Article numbere1009660
Number of pages37
JournalPLoS Computational Biology
Issue number12
Early online date21 Dec 2021
Publication statusPublished - 29 Dec 2021

Bibliographical note

Funding: This study was supported by funding from New Zealand’s Predator Free 2050 program under Predator Free 2050 Ltd. award SS/05/01 to PWM, and from National Institutes of Health award R01GM127418 to PWM. PG-D received funding from the New Zealand BioHeritage National Science Challenge (contract 1617-28-033 A to Manaaki Whenua – Landcare Research) and from Natural Environment Research Council grant NE/S011641/1 under the Newton Latam programme. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Data Availability Statement

Data and Model Availability The data generated for this paper, the population model, and the GP models are available at Among the available files is a Jupyter notebook that loads pre-trained GP models and which can be used to generate heatmap graphs such as those presented in this paper. A series of animated heatmap plots wherein three parameters are varied at a time is also available in the GitHub repo. The SLiM simulation software used in the project is available at


Dive into the research topics of 'Modeling CRISPR gene drives for suppression of invasive rodents using a supervised machine learning framework'. Together they form a unique fingerprint.

Cite this