Maura John

SummaryPredicting complex traits from genotypic information is a major challenge in various biological domains. With easyPheno, we present a comprehensive Python framework enabling the rigorous training, comparison, and analysis of phenotype predictions for a variety of different models, ranging from common genomic selection approaches over classical machine learning and modern deep learning based techniques. Our framework is easy-to-use, also for non-programming-experts, and includes an automatic hyperparameter search using state-of-the-art Bayesian optimization. Moreover, easyPheno provides various benefits for bioinformaticians developing new prediction models. easyPheno enables to quickly integrate novel models and functionalities in a reliable framework and to benchmark against various integrated prediction models in a comparable setup. In addition, the framework allows the assessment of newly developed prediction models under pre-defined settings using simulated data. We provide a detailed documentation with various hands-on tutorials and videos explaining the usage of easyPheno to novice users.Availability and ImplementationeasyPheno is publicly available at https://github.com/grimmlab/easyPheno and can be easily installed as Python package via https://pypi.org/project/easypheno/ or using Docker.Supplementary informationA comprehensive documentation including various tutorials complemented with videos can be found at https://easypheno.readthedocs.io/. In addition, we provide examples of how to use easyPheno with real and simulated data in the Supplementary.

Motivation: Genome-wide Association Studies (GWAS) are an integral tool for studying the architecture ofcomplex genotype and phenotype relationships. Linear Mixed Models (LMMs) are commonly used to detectassociations between genetic markers and a trait of interest, while at the same time allowing to account for population structure and cryptic relatedness. Assumptions of LMMs include a normal distribution of theresiduals and that the genetic markers are independent and identically distributed - both assumptions are often violated in real data. Permutation-based methods can help to overcome some of these limitations and provide more realistic thresholds for the discovery of true associations. Still, in practice they are rarely implemented due to the high computational complexity.Results: We propose permGWAS, an efficient linear mixed model reformulation based on 4D-tensors that can provide permutation-based significance thresholds. We show that our method outperforms current state-of-the-art LMMs with respect to runtime and that permutation-based thresholds have a lower false discovery rates for skewed phenotypes compared to the commonly used Bonferroni threshold. Furthermore, using permGWAS we re-analyzed more than 500 Arabidopsis thaliana phenotypes with 100 permutations each in less than eight days on a single GPU. Our re-analyses suggest that applying a permutation-based threshold can improve and refine the interpretation of GWAS results.Availability: permGWAS is open-source and publicly available on GitHub for download: https://github.com/grimmlab/permGWAS

Genomic selection is an integral tool for breeders to accurately select plants directly from genotype data leading to faster and more resource-efficient breeding programs. Several prediction methods have been established in the last few years. These range from classical linear mixed models to complex non-linear machine learning approaches, such as Support Vector Regression, and modern deep learning-based architectures. Many of these methods have been extensively evaluated on different crop species with varying outcomes. In this work, our aim is to systematically compare twelve different phenotype prediction models, including basic genomic selection methods to more advanced deep learning-based techniques. More importantly, we assess the performance of these models on simulated phenotype data as well as on real-world data from Arabidopsis thaliana and two breeding datasets from soy and corn. The synthetic phenotypic data allows us to analyze all prediction models and especially the selected markers under controlled and predefined settings. We show that Bayes B and linear regression models with sparsity constraints perform best under different simulation settings with respect to explained variance. Further, we can confirm results from other studies that there is no superiority of more complex neural network-based architectures for phenotype prediction compared to well established methods. However, on real-world data, for which several prediction models yield comparable results with slight advantages for Elastic Net, this picture is less clear, suggesting that there is a lot of room for future research.