Improving clinical trial design using interpretable machine learning based prediction of early trial termination.

This study proposes using a machine learning pipeline to optimise clinical trial design. The goal is to predict early termination probability of clinical trials using machine learning modelling, and to understand feature contributions driving early termination. This will inform further suggestions to the study protocol to reduce the risk of wasted resources.

Regional insight into savanna hydrogeomorphology from termite mounds.

Global vegetation models predict the spread of woody vegetation in African savannas and grasslands under future climate scenarios, but they operate too broadly to consider hillslope-scale variations in tree-grass distribution. Topographically linked hydrology-soil-vegetation sequences, or catenas, underpin a variety of ecological processes in savannas, including responses to climate change. In this study, we explore the three-dimensional structure of hillslopes and vegetation, using high-resolution airborne LiDAR (Light Detection And Ranging), to understand the long-term effects of mean annual precipitation (MAP) on catena pattern.

Ectomycorrhizal fungal community structure across a bog-forest ecotone in southeastern Alaska.

We examined the ectomycorrhizal (ECM) fungal community across a bog-forest ecotone in southeastern Alaska. The bog and edge were both characterized by poorly drained Histosols and a continuous layer of Sphagnum species, ericaceous shrubs, Carex species, and shore pine [Pinus contorta Dougl. ex Loud.