Skip to main content
Search

University of Leicester

2 related articles

Subscribe to updates
  1. A new check for cryo-EM assemblies reads only interfaces: DPI-score skips the density map and reaches AUC 0.99 on PowerFit fits

    Model validation for cryo-EM assemblies has relied on density-fit metrics, leaving the quality of protein-protein interfaces without a direct check. DPI-score uses only the raw 3D coordinates of interface atoms, placed on a dynamically scaled voxel grid and passed to a 3D convolutional network, and reaches 87.53% validation accuracy in cross-validation. On PowerFit rigid-body fits its ROC-AUC is 0.99, above 0.46 for DeepRank-GNN-ESM and 0.54 for PI-score; on CASP15 and CASP16 the gap narrows, and on CASP16 PI-score scores higher.

  2. JAMA Cardiology

    Coronary inflammation read from noncontrast CT: a fat attenuation index score sharpens risk in people with zero calcium

    Coronary inflammation could previously be measured only on contrast-enhanced coronary CT angiography, while routine calcium scoring uses low-dose noncontrast CT. A deep-learning pipeline trained and externally validated in a multicenter cohort computes a pericoronary fat attenuation index (FAI) score from noncontrast CT; the score performed comparably to the contrast-based FAI and further separated cardiovascular death and major adverse cardiovascular events among people with a calcium score of zero.

You’re all caught up