Explainability and validity of statistical methods for genome-wide association studies: Extending Shapley-based explanation methods and adapting saddlepoint approximations
Doctoral thesis
Permanent lenke
https://hdl.handle.net/11250/2837438Utgivelsesdato
2022Metadata
Vis full innførselSamlinger
Består av
Paper 1: Johnsen, Pål V.; Bakke, Øyvind; Bjørnland, Thea; DeWan, Andrew Thomas; and Langaas Mette. Saddlepoint approximations in binary genome-wide association studies. 2021. Awaiting publication. arXiv: https://arxiv.org/abs/2110.04025Paper 2: Johnsen, Pål Vegard; Riemer-Sørensen, Signe; DeWan, Andrew Thomas; DeWan, Andrew; Cahill, Megan E.; Langaas, Mette. A new method for exploring gene–gene and gene–environment interactions in GWAS with tree ensemble methods and SHAP values. BMC Bioinformatics 2021 ;Volum 22.(1) s. 1-29
Paper 3: Johnsen, Pål V.; Strümke, Inga; Riemer-Sørensen, Signe; DeWan, Andrew Thomas and Langaas, Mette. Inferring feature importance with uncertainties in high-dimensional data 2021. Awaiting publication. arXiv: https://arxiv.org/abs/2109.00855