Mark Gerstein

TL;DR: An HMM formalism that explicitly uses 3D coordinates in its match states for protein structures is developed and implemented, which suggests that the described construct is quite useful for protein structure analysis.

TL;DR: Overall, the performance improves with more data points per locus, coupled with statistical scoring approaches that properly take advantage of this, where this larger number of data points arises from higher genomic tiling density and the use of replicate arrays and mismatches.

TL;DR: The article by O’Toole et al. in this issue of Proteins describes some of the features of these protein targets lists, the overlap between these worldwide efforts, and a first pass at the data mining that becomes possible by analyzing success and failure at various points along the structure production pipeline across thousands of protein targets.

TL;DR: The authors show sensitive information leakage is possible by analyzing functional genomics signal profiles, and develop an anonymization procedure for privacy protection.

TL;DR: The introduction of ThermoNet, a deep, 3D-convolutional neural network designed for structure-based prediction of ∆∆Gs upon point mutation, and the presence of homologous proteins in commonly used training and testing sets for ∆â�G prediction methods has likely influenced previous performance estimates are demonstrated.