ComNet: A Multiview Deep Learning Model for Predicting Drug Combination Side Effects.

As combination therapy becomes more common in clinical applications, predicting adverse effects of combination medications is a challenging task. However, there are three limitations of the existing prediction models. First, they rely on a single view of the drug and cannot fully utilize multiview information, resulting in limited performance when capturing complex structures.

Nb O /RGO Nanocomposite Modified Separators with Robust Polysulfide Traps and Catalytic Centers for Boosting Performance of Lithium-Sulfur Batteries.

Lithium-sulfur batteries (LSBs) have shown great potential for application in high-density energy storage systems. However, the performance of LSBs is hindered by the shuttle effect and sluggish reaction kinetics of lithium polysulfides (LiPSs). Herein, heterostructual Nb O nanocrystals/reduced graphene oxide (Nb O /RGO) composites are introduced into LSBs through separator modification for boosting the electrochemical performance.

Global-scale computational analysis of genomic sequences reveals the recombination pattern and coevolution dynamics of cereal-infecting geminiviruses.

Genetic diversity and recombination patterns were evaluated for 229 isolates of Wheat dwarf virus (WDV), which are important cereal-infecting geminiviruses. Recombination hot spots were concentrated at the boundary of the genes encoding for the replication protein (Rep), the coat protein (cp) and the movement protein (mp), as well as inside Rep and cp and in the short intergenic regions (SIR). Phylogenomic analyses confirmed that the global population of WDV clustered into two groups according to their specific host: wheat and barley, and the crucial regions for the division of two groups were mp and the large intergenic regions (LIR).