Several papers have been published where non-linear machine learning algorithms, e.g. artificial neural networks, support vector machines and decision trees, have been used to model the specificity of the HIV-1 protease and extract specificity rules. We show that the dataset used in these studies is linearly separable and that it is a misuse of nonlinear classifiers to apply them to this problem. The best solution on this dataset is achieved using a linear classifier like the simple perceptron or the linear support vector machine, and it is straightforward to extract rules from these linear models. We identify key residues in peptides that are efficiently cleaved by the HIV-1 protease and list the most prominent rules, relating them to experimental results for the HIV-1 protease. Motivation: Understanding HIV-1 protease specificity is important when designing HIV inhibitors and several different machine learning algorithms have been applied to the problem. However, little progress has been made in understanding the specificity because nonlinear and overly complex models have been used. Results: We show that the problem is much easier than what has previously been reported and that linear classifiers like the simple perceptron or linear support vector machines are at least as good predictors as nonlinear algorithms. We also show how sets of specificity rules can be generated from the resulting linear classifiers.

Rapidly developing viral resistance to licensed human immunodeficiency virus type 1 (HIV-1) protease inhibitors is an increasing problem in the treatment of HIV-infected individuals and AIDS patients. A rational design of more effective protease inhibitors and discovery of potential biological substrates for the HIV-1 protease require accurate models for protease cleavage specificity. In this study, several popular bioinformatic machine learning methods, including support vector machines and artificial neural networks, were used to analyze the specificity of the HIV-1 protease. A new, extensive data set (746 peptides that have been experimentally tested for cleavage by the HIV-1 protease) was compiled, and the data were used to construct different classifiers that predicted whether the protease would cleave a given peptide substrate or not. The best predictor was a nonlinear predictor using two physicochemical parameters (hydrophobicity, or alternatively polarity, and size) for the amino acids, indicating that these properties are the key features recognized by the HIV-1 protease. The present in silico study provides new and important insights into the workings of the HIV-1 protease at the molecular level, supporting the recent hypothesis that the protease primarily recognizes a conformation rather than a specific amino acid sequence. Furthermore, we demonstrate that the presence of 1 to 2 lysine residues near the cleavage site of octameric peptide substrates seems to prevent cleavage efficiently, suggesting that this positively charged amino acid plays an important role in hindering the activity of the HIV-1 protease.

Peptide binding to HLA molecules is a critical step in induction and regulation of T-cell mediated immune responses. Because of combinatorial complexity of immune responses, systematic studies require combination of computational methods and experimentation. Most of available computational predictions are based on discriminating binders from non-binders based on use of suitable prediction thresholds. We compared four state-of-the-art binding affinity prediction models and found that nonlinear models show better performance than linear models. A comprehensive analysis of HLA binders (A*0101, A*0201, A*0301, A*1101, A*2402, B*0702, B*0801 and B*1501) showed that non-linear predictors predict peptide binding affinity with high accuracy. The analysis of known T-cell epitopes of survivin and known HIV T-cell epitopes showed lack of correlation between binding affinity and immunogenicity of HLA-presented peptides. T-cell epitopes, therefore, can not be directly determined from binding affinities by simple selection of the highest affinity binders.

HIV-1 protease has a broad and complex substrate specificity, which hitherto has escaped a simple comprehensive definition. This, and the relatively high mutation rate of the retroviral protease, makes it challenging to design effective protease inhibitors. Several attempts have been made during the last two decades to elucidate the enigmatic cleavage specificity of HIV-1 protease and to predict cleavage of novel substrates using bioinformatic analysis methods. This review describes the methods that have been utilized to date to address this important problem and the results achieved. The data sets used are also reviewed and important aspects of these are highlighted.