Be aware of overfitting by hyperparameter optimization!

Hyperparameter optimization is very frequently employed in machine learning. However, an optimization of a large space of parameters could result in overfitting of models. In recent studies on solubility prediction the authors collected seven thermodynamic and kinetic solubility datasets from different data sources.

Relationships between trunk muscle activation and thoraco-lumbar kinematics in non-specific chronic low back pain subgroups during a forward bending task.

Background: Trunk muscle activity and thoraco-lumbar kinematics can discriminate between non-specific chronic low back pain (NSCLBP) subgroups and healthy controls. However, research commonly focuses on lumbar kinematics, with limited understanding of relationships between kinematics and muscle activity across clinical subgroups. Similarly, the thoracic spine, whilst intuitively associated with NSCLBP, has received less attention and potential relationships between spinal regions and muscle activity requires exploration.

Factors associated with the outcomes of a novel virtual reality therapy for military veterans with PTSD: Theory development using a mixed methods analysis.

Background: Multi-modular motion-assisted memory desensitization and reconsolidation therapy (3MDR) is a new psychological intervention for people with post-traumatic stress disorder (PTSD). 3MDR is immersive, delivered in a virtual reality environment, and emphasises engagement, recollection and reprocessing.

Objective: Through a theory-driven examination of data relating to 10 out of 42 UK military veterans taking part in a trial of 3MDR, the principal objective was to explore the complex interrelationships between people, interventions and context and to investigate how factors within these domains interacted in specific outcome typologies.

The psychophysiological response during post-traumatic stress disorder treatment with modular motion-assisted memory desensitisation and reconsolidation (3MDR).

: Psychophysiological changes are part of post-traumatic stress disorder (PTSD) symptomatology and can signal emotional engagement during psychological treatment. : The aim of this study was to explore psychophysiological responses during multi-modular motion-assisted memory desensitization and reconsolidation (3MDR) therapy. Increased self-reported distress, substantially increased heart rate (HR) and breathing rate (BR) were expected at the start of therapy and predicted to improve over time.

GEN: highly efficient SMILES explorer using autodidactic generative examination networks.

Recurrent neural networks have been widely used to generate millions of de novo molecules in defined chemical spaces. Reported deep generative models are exclusively based on LSTM and/or GRU units and frequently trained using canonical SMILES. In this study, we introduce Generative Examination Networks (GEN) as a new approach to train deep generative networks for SMILES generation.