An Integrated Machine Learning System to Computationally Screen Protein Databases for Protein Binding Peptide Ligands

Abstract

A fairly large set of protein interactions is mediated by families of peptide binding domains, such as Src homology 2 (SH2), SH3, PDZ, major histocompatibility complex, etc. To identify their ligands by experimental screening is not only labor-intensive but almost futile in screening low abundance species due to the suppression by high abundance species. An ideal way of studying protein-protein interactions is to use high throughput computational approaches to screen protein sequence databases to direct the validating experiments toward the most promising peptides. Predictors with only good cross-validation were not good enough to screen protein databases. In the current study we built integrated machine learning systems using three novel coding methods and screened the Swiss-Prot and GenBank TM protein databases for potential ligands of 10 SH3 and three PDZ domains. A large fraction of predictions has already been experimentally confirmed by other independent research groups, indicating a satisfying generalization capability for future applications in identifying protein interactions. Experimental screening for protein binding peptides is not only labor-intensive but almost futile in screening for low abundance binding species due to the suppression by high abundance species. A more plausible way of studying protein-protein interactions is by using high throughput computational predictions rather than experimental approaches to screen for interactions from protein sequence databases to direct the validating experiments toward the most promising peptides. A prediction can only be called successful when the overall efficiency and cost of computational prediction plus biological validation are much better than those of experimental screening. A fairly large set of protein interactions are mediated by families of peptide binding domains, such as SH2, 1 SH3, PDZ, MHC, etc. that act as receptors to accommodate, in their binding pockets, short peptides in an extended conformation (1, 2). We studied two common domainligand interactions mediated by SH3 domain and PDZ domain. SH3 domains selectively bind peptides of 8 -11 amino acids on their ligand proteins; PDZ domains bind 4 -8 amino acids in the C termini of their partners. Ligands of both PDZ and SH3 domains are of high diversity. Two good reviews provide detailed information on SH3 domain (3) and PDZ domain (4). Two major categories of methods have been developed to predict domain-ligand interactions. The first category is based on structure information as exemplified by the work on predicting MHC-specific epitopes with protein docking methods (5, 6). This type of method needs intensive computation and the prior knowledge of the three-dimensional structures of the bait proteins. Instead of using exact protein structures, Brannetti et al. (7) and Altuvia and Margalit (8) extracted ligandcontacting residues from the known domain-ligand complex structures to approximately represent domain interface structures of SH3 and MHC, respectively. The interactions of amino aci...

Characterization of Domain–Peptide Interaction Interface: A Case Study on the Amphiphysin-1 SH3 Domain

“…We investigated the performance of SVM using a balanced training data set. Following the procedure of Zhang et al, 13 we retrained an SVM classifier using a balanced data set of 41 binders and 41 randomly selected non-binders. The prediction accuracies for binders and non-binders are 90.2% and 85.4%, respectively.…”

“…Recently, machine learning algorithms, such as artificial neural network and support vector machine (SVM), were introduced to predict the SH3 domain binding peptides based on contact information. 12,13 Training these classifiers usually requires data for numerous SH3 domains because the number of possible combinations of contacts is huge. On the other hand, these methods are computationally efficient and can be used for quick proteome screening.…”

“…[10][11][12][13][14][15][16][17][18][19][20] For example, the SH3-SPOT method builds a positionspecific contact frequency matrix based on proteinpeptide contacts in a number of crystal structures of SH3/peptide and SH3/protein complexes. 11 The matrix was then used to calculate the probability of a peptide binding to a specific SH3 domain.…”

Characterization of Domain-Peptide Interaction Interface

“…Comparison with SH3-hunter-Among all the methods for predicting the binding specificity of SH3 domains (17)(18)(19) iSPOT and its improved version of SH3-hunter are publicly available (17,18). Sparks et al (10) studied interactions between 20 peptides and 13 SH3 domains among which Src, Yes, Abl, and Grb2 were modeled in our study.…”

Identification of Methyllysine Peptides Binding to Chromobox Protein Homolog 6 Chromodomain in the Human Proteome

“…Several computational methods related to domain-peptide interaction are available, but only on limited domains, such as SH2 (44), SH3 (45)(46)(47)(48)(49), and PDZ (50 -55). For all of these domains, enough interaction data have already been obtained to train a reasonably good machine learning model.…”