A pair of artificial neural networks that each predict the propensity of a selected protein sequence to produce diffraction-quality crystals by current structural biology techniques. On blind test data XANNpred outperforms the other available algorithms XtalPred, PXS, OB-Score, and ParCrys. XANNpred also guides construct design by presenting graphs of predicted propensity for diffraction-quality crystals against residue sequence position.
School of Life Sciences Research, University of Dundee, Dow Street, Dundee, UK; Department of Computing Science, University of Glasgow, Glasgow, UK
XANNpred funding source(s)
UK Biotechnology and Biological Sciences Research Council (BBSRC) Structural Proteomics of Rational Targets initiative, Grant Number: BBS/B/14434; Wellcome Trust, Grant Number: WT083481 Royal Society of Edinburgh Scottish Government Fellowship co-funded by Marie Curie Actions