Combining Group Contribution Method and Semisupervised Learning to Build Machine Learning Models for Predicting Hydroxyl Radical Rate Constants of Water Contaminants.

Machine learning is an effective tool for predicting reaction rate constants for many organic compounds with the hydroxyl radical (HO). Previously reported models have achieved relatively good performance, but due to scarce data (<1400 records), the applicability domain (AD) has been significantly limited. To address this limitation, we curated a much larger experimental data set (Primary data set), which contains 2358 kinetic records.

A nociceptive amygdala-striatal pathway for chronic pain aversion.

The basolateral amygdala (BLA) is essential for assigning positive or negative valence to sensory stimuli. Noxious stimuli that cause pain are encoded by an ensemble of ceptive BLA projection neurons (BLA ensemble). However, the role of the BLA ensemble in mediating behavior changes and the molecular signatures and downstream targets distinguishing this ensemble remain poorly understood.