RDb2C2: an improved method to identify the residue-residue pairing in β strands

Background Despite the great advance of protein structure prediction, accurate prediction of the structures of mainly beta proteins is still highly challenging, but could be assisted by the knowledge of residue-residue pairing in beta strands. Previously, we proposed a ridge-detection-based algorithm RDb(2)C that adopted a multi-stage random forest framework to predict the beta-beta pairing given the amino acid sequence of a protein. Results In this work, we developed a second version of this algorithm, RDb(2)C2, by employing the residual neural network to further enhance the prediction accuracy. In the benchmark test, this new algorithm improves the F1-score by > 10 percentage points, reaching impressively high values of similar to 72% and similar to 73% in the BetaSheet916 and BetaSheet1452 sets, respectively. Conclusion Our new method promotes the prediction accuracy of beta-beta pairing to a new level and the prediction results could better assist the structure modeling of mainly beta proteins. We prepared an online server of RDb(2)C2 at .