Detection of myocardial ischemia due to clinically asymptomatic coronary artery stenosis at rest using supervised artificial intelligence-enabled vectorcardiography - A five-fold cross validation of accuracy.

Background: Coronary artery disease (CAD) is a leading cause of death and disability. Conventional non-invasive diagnostic modalities for the detection of stable CAD at rest are subject to significant limitations: low sensitivity, and personal expertise. We aimed to develop a reliable and time-cost efficient screening tool for the detection of coronary ischemia using machine learning.

Retention of Coiled-Coil Dimer Formation in the Absence of Ion Pairing at Positions Flanking the Hydrophobic Core.

Hydrophobic interactions govern how proteins fold and interact with other molecules, but the impact of nearby polar functionality on the effective hydrophobicity of nonpolar surfaces remains unclear. Here we use a common protein quaternary structure motif, the parallel coiled-coil dimer, to ask whether the identity of basic residues (arginine vs lysine; guanidinium vs ammonium) arrayed along one side of the constituent α-helices influences the favorability of dimerization driven by burial of hydrophobic surface on the other side of each helix. Significant sequence redesign was necessary to achieve the desired juxtaposition of nonpolar and cationic functionality, because we needed to eliminate charged side chains from positions flanking the nonpolar helix surface.