CleavPredict: A Platform for Reasoning about Matrix Metalloproteinases Proteolytic Events

Abstract

CleavPredict (http://cleavpredict.sanfordburnham.org) is a Web server for substrate cleavage prediction for matrix metalloproteinases (MMPs). It is intended as a computational platform aiding the scientific community in reasoning about proteolytic events. CleavPredict offers in silico prediction of cleavage sites specific for 11 human MMPs. The prediction method employs the MMP specific position weight matrices (PWMs) derived from statistical analysis of high-throughput phage display experimental results. To augment the substrate cleavage prediction process, CleavPredict provides information about the structural features of potential cleavage sites that influence proteolysis. These include: secondary structure, disordered regions, transmembrane domains, and solvent accessibility. The server also provides information about subcellular location, co-localization, and co-expression of proteinase and potential substrates, along with experimentally determined positions of single nucleotide polymorphism (SNP), and posttranslational modification (PTM) sites in substrates. All this information will provide the user with perspectives in reasoning about proteolytic events. CleavPredict is freely accessible, and there is no login required.

Fig 1. Distribution of PWM scores for peptide substrates of MMP-2 from Schilling et al. [66].

Red line—distribution of PWM score values for experimentally identified cleaved peptide bonds, black line—distribution of scores for all other peptide bonds. Red—dashed line represents distribution of scores for set of cleaved peptide bonds corrected by replacing poorly scored peptide bonds by those that have their scores above the threshold and were located in the vicinity of experimentally predicted positions. The separation between the cleavage site scores and the scores for other peptide bonds was subject to Kolmogorov-Smirnov test yielding D = 0.60 and D = 0.66 for red and red-dashed distributions, respectively, when tested against the black one.

Fig 2. Distribution of PWM scores for peptide substrates of MMP-2 and MMP-9 from Prudova et al. [65].

Red and black lines are distributions of PWM score values for experimentally identified cleaved peptide bonds and for all other peptide bonds, respectively. For both MMP-2 and MMP-9 the Kolmogorov-Smirnov test yields D = 0.60.

Fig 3. ROC curves for prediction cleavage sites in proteins collected in CutDB for MMP-2, MMP-3, MMP-8, MMP-9 and MMP-14.

Fig 4. Workflow of the CleavPredict Web server.

Top: the types of input queries; middle: the first tier of the output data; bottom: the second tier of the results obtained using a Uniprot id as for the input protein substrate. Blast program and mapping is used for determining the Uniprot id.

Fig 5. Snapshots of the result pages.

As an example the prediction of the cleavage positions in Q15848 protein for MMP2 enzyme is demonstrated. This section contains information about signal peptide prediction, subcellular location, co-expression and co-localization information, known cleavages in CutDB, data on experimentally identified SNPs and PTMs, congregated into tables.