SecNet tool and Set2018 data set Neural-network tool for prediction of secondary structure and data set of training, validation and testing (Test2018) sets. Supported on Unix / Mac.

Shapovalov MV, Dunbrack RL Jr., Vucetic S. Multifaceted analysis of training and testing convolutional neural networks for protein secondary structure prediction. bioRxiv preprint

BetaTurnLib18 & BetaTurnTool18 Library of 18 β turns and their Assignment Tool for mmCIF and PDB input. Supported on Unix / Mac / Windows.

Shapovalov MV, Vucetic S, Dunbrack RL Jr. A new clustering and nomenclature for beta turns derived from high-resolution protein structures.PLoS Comput Biol, 2019 Mar 7; 15(3) Paper

BioAssemblyModeler (BAM) Software for Homology Modeling of Protein Oligomers and Complexes (2014)

PDBfam: Accurate and complete Pfam assignments for the PDB (Bioinformatics, 2012)

ProtCID: The Protein Common Interface Database (Nucl. Acids Research, Jan 2011)

Neighbor-dependent Ramachandran distributions (PLOS Comp. Biol., Apr 2010)

Conformation-dependent library for backbone geometry in proteins (Structure, Oct 2009)

The Dunbrack group concentrates on research in computational structural biology, including homology modeling, fold recognition, molecular dynamics simulations, statistical analysis of the PDB, and bioinformatics. In developing these methods, we use modern methods of Bayesian statistics and extensive benchmarking. We are interested in applying comparative modeling to important problems in various areas of biology, especially in cancer research.