ProNA2020 predicts protein-DNA, protein-RNA, and protein-protein binding proteins and residues from sequence.

TitleProNA2020 predicts protein-DNA, protein-RNA, and protein-protein binding proteins and residues from sequence.
Publication TypeJournal Article
Year of Publication2020
AuthorsQiu, J, Bernhofer, M, Heinzinger, M, Kemper, S, Norambuena, T, Melo, F, Rost, B
JournalJ Mol Biol
Date Published2020 03 27
KeywordsAnimals, Binding Sites, Computational Biology, DNA, Eukaryota, Humans, Machine Learning, Neural Networks, Computer, Nucleic Acid Conformation, Prokaryotic Cells, Protein Binding, Protein Conformation, Proteins, RNA, Sequence Analysis, Protein, Software

The intricate details of how proteins bind to proteins, DNA, and RNA are crucial for the understanding of almost all biological processes. Disease-causing sequence variants often affect binding residues. Here, we described a new, comprehensive system of in silico methods that take only protein sequence as input to predict binding of protein to DNA, RNA, and other proteins. Firstly, we needed to develop several new methods to predict whether or not proteins bind (per-protein prediction). Secondly, we developed independent methods that predict which residues bind (per-residue). Not requiring three-dimensional information, the system can predict the actual binding residue. The system combined homology-based inference with machine learning and motif-based profile-kernel approaches with word-based (ProtVec) solutions to machine learning protein level predictions. This achieved an overall non-exclusive three-state accuracy of 77% ± 1% (±one standard error) corresponding to a 1.8 fold improvement over random (best classification for protein-protein with F1 = 91 ± 0.8%). Standard neural networks for per-residue binding residue predictions appeared best for DNA-binding (Q2 = 81 ± 0.9%) followed by RNA-binding (Q2 = 80 ± 1%) and worst for protein-protein binding (Q2 = 69 ± 0.8%). The new method, dubbed ProNA2020, is available as code through github ( and through PredictProtein (

PubMed ID32142788