Machine learning-based prediction of illness course in major depression: The relevance of risk factors.

Background: Major depressive disorder (MDD) comes along with an increased risk of recurrence and poor course of illness. Machine learning has recently shown promise in the prediction of mental illness, yet models aiming to predict MDD course are still rare and do not quantify the predictive value of established MDD recurrence risk factors.

Methods: We analyzed N = 571 MDD patients from the Marburg-Münster Affective Disorder Cohort Study (MACS).

Disentangling Sources of Momentum Fluctuations in Xe+Xe and Pb+Pb Collisions with the ATLAS Detector.

High-energy nuclear collisions create a quark-gluon plasma, whose initial condition and subsequent expansion vary from event to event, impacting the distribution of the eventwise average transverse momentum [P([p_{T}])]. Disentangling the contributions from fluctuations in the nuclear overlap size (geometrical component) and other sources at a fixed size (intrinsic component) remains a challenge. This problem is addressed by measuring the mean, variance, and skewness of P([p_{T}]) in ^{208}Pb+^{208}Pb and ^{129}Xe+^{129}Xe collisions at sqrt[s_{NN}]=5.

How Small Proteins Adjust the Metabolism of Cyanobacteria Under Stress: The Role of Small Proteins in Cyanobacterial Stress Responses.

Several recently discovered small proteins of less than 100 amino acids control important, but sometimes surprising, steps in the metabolism of cyanobacteria. There is mounting evidence that a large number of small protein genes have also been overlooked in the genome annotation of many other microorganisms. Although too short for enzymatic activity, their functional characterization has frequently revealed the involvement in processes such as signaling and sensing, interspecies communication, stress responses, metabolism, regulation of transcription and translation, and in the formation of multisubunit protein complexes.