Discovery of ongoing selective sweeps withinAnophelesmosquito populations using deep learning

Abstract

Identification of partial sweeps, which include both hard and soft sweeps that have not currently reached fixation, provides crucial information about ongoing evolutionary responses. To this end, we introduce a deep learning approach that uses a convolutional neural network for image processing, which is trained with coalescent simulations incorporating population-specific history, to discover selective sweeps from population genomic data. This approach distinguishes between completed versus partial sweeps, hard versus soft sweeps, and regions directly affected by selection versus those merely linked to nearby selective sweeps. We perform several simulation experiments under various demographic scenarios to demonstrate the performance of our deep learning classifier partialS/HIC, which exhibits unprecedented resolution for detecting partial sweeps. We also apply our method to whole genomes from eight mosquito populations sampled across sub-Saharan Africa by the Anopheles gambiae 1000 Genomes Consortium, elucidating both continent-wide patterns as well as sweeps unique to specific geographic regions. These populations have experienced intense insecticide exposure over the past two decades, and we observe a strong overrepresentation of sweeps at insecticide resistance loci. Our analysis thus provides a catalog of candidate adaptive loci that may aid mosquito control efforts. More broadly, the success of our supervised machine learning approach introduces a powerful method to distinguish between completed and partial sweeps, as well as between hard and soft sweeps, under a variety of demographic scenarios. As whole-genome data rapidly accumulate for a greater diversity of organisms, partialS/HIC addresses an increasing demand for useful selection scan tools that can track in-progress evolutionary dynamics. Author Summary Recent successful efforts to reduce malaria transmission are in danger of collapse due to evolving insecticide resistance in the mosquito vector Anopheles gambiae. We aim to understand the genetic basis of current adaptation to vector control efforts by deploying a novel method that can classify multiple categories of selective sweeps from population genomic data. In recent years, there has been great progress made in the identification of completed selective sweeps through the use of supervised machine learning (SML), but SML techniques have rarely been applied to partial or ongoing selective sweeps. Partial sweeps represent an important facet of evolution as they reflect present-day selection and thus may give insight into future dynamics. However, the genomic impact left by partial sweeps is more subtle than that left by completed sweeps, making such signatures more difficult to detect. To this end, we extend a recent SML method to partial sweep inference and apply it to elucidate ongoing selective sweeps from Anopheles population genomic samples.

Inference of selective sweep parameters through supervised learning

“…This could bias our method towards inferring sweep scenarios from the training data of fixed sweeps that maintained the highest levels of diversity, which should be RNM soft sweeps with weak selection. Our results confirm the previous findings of Xue et al (2021) that models trained on fixed sweeps are not robust when applied to partial sweeps.…”

“…Importantly, due to the flexibility provided by simulations, which can explore large regions of parameter space and be designed to represent any particular organism and locus of interest, supervised machine learning could provide a powerful approach for making sweep inferences for a variety of organisms and scenarios. Indeed, several implementations of supervised machine learning for sweep inferences have already been successfully demonstrated in recent years (Flagel et al, 2019; Kern & Schrider, 2018; Lin et al, 2011; Mughal & DeGiorgio, 2019; Pavlidis et al, 2010; Pybus et al, 2015; Ronen et al, 2013; Schrider & Kern, 2016; Sheehan & Song, 2016; Sugden et al, 2018; Torada et al, 2019; Xue et al, 2021). By their nature of learning by example from diverse training data, these methods are naturally capable of learning patterns across individual sweeps with highly stochastic signatures and across a variety of analysis hyperparameters such as window size.…”

Deep learning for population size history inference: design, comparison and combination with approximate Bayesian computation

“…First, multilayer perceptron (MLP) were used to process large sets of summary statistics and to predict jointly selective sweeps and simple demographic changes (Sheehan and Song, 2016), or to disentangle between multiple scenarios of archaic introgression thanks to an additional ABC step (Lorente-Galdos et al, 2019, Mondal et al, 2019). A second type of ANN, convolutional neural networks (CNN), were then applied to summary statistics computed over 5Kb genomic regions in order to predict selective sweeps (Xue et al, 2019). A considerable shift occurred when several studies applied ANN directly on genomic data instead of using summary statistic.…”

On the Inapplicability of Supervised Machine Learning to Studying the Driving Forces of Evolution

“…Such studies have been ballyhooed as "sophisticated," "cutting-edge," "robust," and "valuable," and it has been argued that they "make a strong case for the idea that machine learning methods could be useful for addressing diverse questions in molecular evolution" [5]. The method has since been applied to various other organisms [e.g., 6,7,8].…”