“Scalable learning of interpretable rules for the dynamic microbiome domain” from Venkata Suhas Maringanti, Vanni Bucci, Georg K. Gerber.
A new fully-differentiable model that learns human-interpretable rules operating on microbiome time-series data to classify host status .Our approach uses a novel 5-layer Neural Inductive Logic Programming (ILP)-type model with domain-specific microbiome and temporal attention mechanisms that outputs human-interpretable classification rules.