Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions.

Machine-learned ranking models have been developed for the prediction of substrate-specific cross-coupling reaction conditions. Data sets of published reactions were curated for Suzuki, Negishi, and C-N couplings, as well as Pauson-Khand reactions. String, descriptor, and graph encodings were tested as input representations, and models were trained to predict the set of conditions used in a reaction as a binary vector. Unique reagent dictionaries categorized by expert-crafted reaction roles were constructed for each data set, leading to context-aware predictions. We find that relational graph convolutional networks and gradient-boosting machines are very effective for this learning task, and we disclose a novel reaction-level graph attention operation in the top-performing model.

Sex-specific effects of sitting vs standing on upper body muscle activity during text typing.

Standing computer work is increasingly popular. However, despite the higher rates of computer work-related disorders in women, no studies have compared how standing work affects men and women. Twelve males and 12 females completed 90-min typing tasks in each posture while electromyography (EMG) data was recorded from eight muscles of the upper body. Results show that females had significantly higher EMG root-mean-squared (RMS) values in the anterior deltoid than males when seated, but higher EMG RMS in the medial trapezius than males when standing (SBC ≤ 0.05). In standing, they also had lower values than males in the erector spinae. Overall, standing elicited less activity in the upper trapezius, wrist extensors and erector spinae than sitting. Results suggest that the standing posture is generally less muscularly demanding than the seated one, although men and women's neck/shoulder musculature responds differently to the same task performed while seated or standing.