Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Research findings on Machine Learning are discussed in a new report. According to news originating from Bonn, Germany, by NewsRx correspondents, research stated, “Molecular property predictions play a central role in computer-aided drug discovery. Although a variety of physicoc hemical (e.g., solubility or chemical reactivity) or physiological properties (e .g., metabolic stability or toxicity) can be predicted, biological activity is b y far the most frequently investigated compound feature.” Our news journalists obtained a quote from the research from the University of B onn, “Activity predictions are carried out in a qualitative (target-based activi ty, through compound classification) or quantitative (compound potency or studie s have evaluated and compared different machine learning methods for activity an d potency predictions, recently with a focus on deep learning. Regardless of the methods used, these studies generally rely on conventional benchmark settings. Recent work has shown that potency prediction benchmarks have severe general lim itations that have long been unnoticed but prevent a reliable assessment of diff erent methods and their relative performance.”
NETL
NSTL