Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: Deep mixed model for marginal epistasis detection and population stratification correction in genome-wide association studies

Fig. 1

The structure of Deep Mixed Model (DMM), which consists two components: 1) the red component is a convolutional neural network with a large kernel size that scans over the SNP sequence to detect the population-level effect; and 2) the blue component is an LSTM with a vanilla network attached to the input that identifies the genetic variants associated with the phenotype

Back to article page