… Deep networks can be used to model these interactions, … deep interpretability technique
named DeepLIFT to show that known diabetes genetic risk factors can be identified using deep …

… more interpretable if its decisions are easier for humans to understand. The terms interpretable
… In this dissertation, interpretable machine learning refers to gaining meaningful insights …

… deep learning framework to identify disease-associated genes (NETTAG). We leverage
non-coding GWAS … In summary, NETTAG offers a deep learning methodology that utilizes GWAS …

… evolve, our extended deep neural network approach emerges as a potent tool for researchers
seeking accurate and interpretable feature selection in the complex landscape of GWAS. …

… , deep Taylor-based explanation techniques (48) have not yet been applied in the field of
GWAS and … To make LRP applicable as an explanation method for GWAS data, we use a very …

… While genome-wide association studies (GWAS) have … Recent GWAS studies with increasingly
large sample sizes are … To illustrate, the latest GWAS for body height based on 700,000 …

… and interpretability of black-box models, including the motivations and goals of interpretability
research. We then give a brief survey of current interpretability techniques for deep …

… massive GWAS data … deep learning to effectively extract features from the GWAS data.
Therefore, we develop and apply the DNN survival model to build an accurate and interpretable …

… in interpretable deep-learning applications and the millions of individuals included in
genome-wide association studies (GWAS) (… Around these topics, GWAS consortia have formed …

… variants in a GWAS risk locus. Finally, we release the proposed deep learning model as a
… not readily interpretable as the linear counterparts. However, a common practice to interpret …