Determining Effects of Non-synonymous SNPs on Protein-Protein Interactions using Supervised and Semi-supervised Learning

Abstract

Single nucleotide polymorphisms (SNPs) are among the most common types of genetic variation in complex genetic disorders. A growing number of studies link the functional role of SNPs with the networks and pathways mediated by the disease-associated genes. For example, many non-synonymous missense SNPs (nsSNPs) have been found near or inside the protein-protein interaction (PPI) interfaces. Determining whether such nsSNP will disrupt or preserve a PPI is a challenging task to address, both experimentally and computationally. Here, we present this task as three related classification problems, and develop a new computational method, called the SNP-IN tool (non-synonymous SNP INteraction effect predictor). Our method predicts the effects of nsSNPs on PPIs, given the interaction's structure. It leverages supervised and semi-supervised feature-based classifiers, including our new Random Forest self-learning protocol. The classifiers are trained based on a dataset of comprehensive mutagenesis studies for 151 PPI complexes, with experimentally determined binding affinities of the mutant and wild-type interactions. Three classification problems were considered: (1) a 2-class problem (strengthening/weakening PPI mutations), (2) another 2-class problem (mutations that disrupt/preserve a PPI), and (3) a 3-class classification (detrimental/neutral/beneficial mutation effects). In total, 11 different supervised and semi-supervised classifiers were trained and assessed resulting in a promising performance, with the weighted f-measure ranging from 0.87 for Problem 1 to 0.70 for the most challenging Problem 3. By integrating prediction results of the 2-class classifiers into the 3-class classifier, we further improved its performance for Problem 3. To demonstrate the utility of SNP-IN tool, it was applied to study the nsSNP-induced rewiring of two disease-centered networks. The accurate and balanced performance of SNP-IN tool makes it readily available to study the rewiring of large-scale protein-protein interaction networks, and can be useful for functional annotation of disease-associated SNPs. SNIP-IN tool is freely accessible as a web-server at http://korkinlab.org/snpintool/.

Docking features for predicting binding loss due to protein mutation

“…A recent study used SKEMPI mutants to train a classifier for nsSNPs that affect protein-interactions, using three classes -no effect, diminished binding, and enhanced binding [51]. However, the classifier did not define a class of "non-binders", as in the present study.…”

“…Such a classifier could aid in the development of more sophisticated free energy (∆G) scoring functions. There is preliminary evidence that disease-causing nsSNPs that alter protein interactions act through distinct mechanisms [51]. The functional insight that future tools such as the one in the present study might shed on interaction-altering human SNPs would prove invaluable to the current understanding of human genetic variation in disease.…”

Recent advances in automated protein design and its future challenges

“…Machine-learning-based scoring functions uses a variety of mostly supervised machine-learning algorithms [158,159], such as artificial neural networks [160], random forest [161–163], and support vector machine [164], to learn about a specific energetic or other structural or biological properties using a training set of protein structures. The resulting, trained, machine-learning-based function, can then be used to produce a scoring value associated with a predicted property: $$\begin{gathered} \mathbf{Input}:\text{Descriptors}\to \text{Trained}\text{Scoring}\text{Function}\to \mathbf{Output} \\ :\text{Scoring}\text{Value} \end{gathered}$$…”

SNPViz - Visualization of SNPs in proteins

“…A prominent example is the sickle-cell disease [2]. However, even though many non-synonymous SNPs are known, for the majority of them the corresponding structural change is still un-known [3]. In personalized medicine, whole exome sequencing can lead to the detection of several thousand SNPs per sample.…”