DAMpred: Recognizing Disease-Associated nsSNPs through Bayes-Guided Neural-Network Model Built on Low-Resolution Structure Prediction of Proteins and Protein–Protein Interactions

• Published in: Journal of molecular biology Vol. 431; no. 13; pp. 2449 - 2459
• Main Authors: Quan, Lijun, Wu, Hongjie, Lyu, Qiang, Zhang, Yang
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 14.06.2019
• Subjects: algorithms; Bayes-guided artificial neural network algorithm; control methods; data collection; genes; genetic disorders; human diseases; human health; humans; neural networks; non-synonymous single nucleotide polymorphisms; open reading frames; p53 protein; prediction; protein structure; protein structure prediction; protein-protein interactions; proteins; protein–protein interaction; single nucleotide polymorphism; BANN; non-synonymous single nucleotide polymorphisms; DAMpred; Bayes-guided artificial neural network algorithm; protein–protein interaction; DM; protein structure prediction; p53 protein; NM; Protein structure prediction; Non-synonymous single nucleotide polymorphisms; Protein–protein interaction
• ISSN: 0022-2836; 1089-8638; 1089-8638
• DOI: 10.1016/j.jmb.2019.02.017

Nearly one-third of non-synonymous single-nucleotide polymorphism (nsSNPs) are deleterious to human health, but recognition of the disease-associated mutations remains a significant unsolved problem. We proposed a new algorithm, DAMpred, to identify disease-causing nsSNPs through the coupling of evolutionary profiles with structure predictions of proteins and protein–protein interactions. The pipeline was trained by a novel Bayes-guided artificial neural network algorithm that incorporates posterior probabilities of distinct feature classifiers with the network training process. DAMpred was tested on a large-scale data set involving 10,635 nsSNPs from 2154 ORFs in the human genome and recognized disease-associated nsSNPs with an accuracy 0.80 and a Matthews correlation coefficient of 0.601, which is 9.1% higher than the best of other state-of-the-art methods. In the blind test on the TP53 gene, DAMpred correctly recognized the mutations causative of Li–Fraumeni-like syndrome with a Matthews correlation coefficient that is 27% higher than the control methods. The study demonstrates an efficient avenue to quantitatively model the association of nsSNPs with human diseases from low-resolution protein structure prediction, which should find important usefulness in diagnosis and treatment of genetic diseases. [Display omitted] •At least one-third of nsSNPs are deleterious, but recognition of them remains unsolved problem.•Hybrid approach combines pharmacophores with protein structure prediction.•Novel BANN method significantly increases model training efficiency.•Both webserver and standalone package are freely available to the community.•The method should find usefulness in diagnosis and treatment of genetic diseases.