Castrense Savojardo1,2, Piero Fariselli3, Pier Luigi Martelli1,2, Rita Casadio1,2. 1. Biocomputing Group, Department of Biological, Geological and Environmental Sciences (BiGeA), University of Bologna, Bologna, Italy. 2. CIG, Interdepartmental Center «Luigi Galvani» for Integrated Studies of Bioinformatics, Biophysics and Biocomplexity, University of Bologna, Bologna, Italy. 3. Department of Comparative Biomedicine and Food Science (BCA), University of Padova, Padova, Italy.
Abstract
MOTIVATION: The identification of protein-protein interaction (PPI) sites is an important step towards the characterization of protein functional integration in the cell complexity. Experimental methods are costly and time-consuming and computational tools for predicting PPI sites can fill the gaps of PPI present knowledge. RESULTS: We present ISPRED4, an improved structure-based predictor of PPI sites on unbound monomer surfaces. ISPRED4 relies on machine-learning methods and it incorporates features extracted from protein sequence and structure. Cross-validation experiments are carried out on a new dataset that includes 151 high-resolution protein complexes and indicate that ISPRED4 achieves a per-residue Matthew Correlation Coefficient of 0.48 and an overall accuracy of 0.85. Benchmarking results show that ISPRED4 is one of the top-performing PPI site predictors developed so far. CONTACT: gigi@biocomp.unibo.it. AVAILABILITY AND IMPLEMENTATION: ISPRED4 and datasets used in this study are available at http://ispred4.biocomp.unibo.it .
MOTIVATION: The identification of protein-protein interaction (PPI) sites is an important step towards the characterization of protein functional integration in the cell complexity. Experimental methods are costly and time-consuming and computational tools for predicting PPI sites can fill the gaps of PPI present knowledge. RESULTS: We present ISPRED4, an improved structure-based predictor of PPI sites on unbound monomer surfaces. ISPRED4 relies on machine-learning methods and it incorporates features extracted from protein sequence and structure. Cross-validation experiments are carried out on a new dataset that includes 151 high-resolution protein complexes and indicate that ISPRED4 achieves a per-residue Matthew Correlation Coefficient of 0.48 and an overall accuracy of 0.85. Benchmarking results show that ISPRED4 is one of the top-performing PPI site predictors developed so far. CONTACT: gigi@biocomp.unibo.it. AVAILABILITY AND IMPLEMENTATION: ISPRED4 and datasets used in this study are available at http://ispred4.biocomp.unibo.it .
Authors: M Walder; E Edelstein; M Carroll; S Lazarev; J E Fajardo; A Fiser; R Viswanathan Journal: BMC Bioinformatics Date: 2022-07-25 Impact factor: 3.307