BACKGROUND: HIV-1 targets human cells expressing both the CD4 receptor, which binds the viral envelope glycoprotein gp120, as well as either the CCR5 (R5) or CXCR4 (X4) co-receptors, which interact primarily with the third hypervariable loop (V3 loop) of gp120. Determination of HIV-1 affinity for either the R5 or X4 co-receptor on host cells facilitates the inclusion of co-receptor antagonists as a part of patient treatment strategies. A dataset of 1193 distinct gp120 V3 loop peptide sequences (989 R5-utilizing, 204 X4-capable) is utilized to train predictive classifiers based on implementations of random forest, support vector machine, boosted decision tree, and neural network machine learning algorithms. An in silico mutagenesis procedure employing multibody statistical potentials, computational geometry, and threading of variant V3 sequences onto an experimental structure, is used to generate a feature vector representation for each variant whose components measure environmental perturbations at corresponding structural positions. RESULTS: Classifier performance is evaluated based on stratified 10-fold cross-validation, stratified dataset splits (2/3 training, 1/3 validation), and leave-one-out cross-validation. Best reported values of sensitivity (85%), specificity (100%), and precision (98%) for predicting X4-capable HIV-1 virus, overall accuracy (97%), Matthew's correlation coefficient (89%), balanced error rate (0.08), and ROC area (0.97) all reach critical thresholds, suggesting that the models outperform six other state-of-the-art methods and come closer to competing with phenotype assays. CONCLUSIONS: The trained classifiers provide instantaneous and reliable predictions regarding HIV-1 co-receptor usage, requiring only translated V3 loop genotypes as input. Furthermore, the novelty of these computational mutagenesis based predictor attributes distinguishes the models as orthogonal and complementary to previous methods that utilize sequence, structure, and/or evolutionary information. The classifiers are available online at http://proteins.gmu.edu/automute.

A computational mutagenesis methodology utilizing a four-body, knowledge-based, statistical contact potential is applied toward quantifying sequence-structure compatibility changes in bacteriophage T4 lysozyme upon single amino acid replacements. We show that these scalar scores correlate with experimentally measured stability changes to the protein due to the mutations. For each mutant, the approach also generates a vector of environmental perturbations occurring at every position in the protein. Implementation of the random forest algorithm, utilizing 521 experimental T4 lysozyme mutants each represented by its respective perturbation vector, correctly classifies mutants based on the direction of stability change with 88% cross-validation accuracy and 0.70 Matthew's correlation coefficient while achieving 0.91 area under the receiver operating characteristic curve. Learning curves are presented and reveal the dependence of training set size on model performance. The trained random forest model is used to infer stability changes for all remaining unexplored T4 lysozyme mutants.

A computational mutagenesis methodology utilizing a four-body, knowledge-based, statistical contact potential is applied toward globally quantifying relative structural changes (residual scores) in bacteriophage f1 gene V protein (GVP) due to single amino acid residue substitutions. We show that these residual scores correlate well with experimentally measured relative changes in protein function caused by the mutations. For each mutant, the approach also yields local measures of environmental perturbation occurring at every residue position (residual profile) in the protein. Implementation of the random forest algorithm, utilizing experimental GVP mutants whose feature vector components include environmental changes at the mutated position and at six nearest neighbors, correctly classifies mutants based on function with up to 72% accuracy while achieving 0.77 area under the receiver operating characteristic curve and a 0.42 correlation coefficient. An optimally trained random forest model is subsequently used to infer function for all remaining unexplored GVP mutants.

MOTIVATION: Accurate predictive models for the impact of single amino acid substitutions on protein stability provide insight into protein structure and function. Such models are also valuable for the design and engineering of new proteins. Previously described methods have utilized properties of protein sequence or structure to predict the free energy change of mutants due to thermal (DeltaDeltaG) and denaturant (DeltaDeltaG(H2O)) denaturations, as well as mutant thermal stability (DeltaT(m)), through the application of either computational energy-based approaches or machine learning techniques. However, accuracy associated with applying these methods separately is frequently far from optimal. RESULTS: We detail a computational mutagenesis technique based on a four-body, knowledge-based, statistical contact potential. For any mutation due to a single amino acid replacement in a protein, the method provides an empirical normalized measure of the ensuing environmental perturbation occurring at every residue position. A feature vector is generated for the mutant by considering perturbations at the mutated position and it's ordered six nearest neighbors in the 3-dimensional (3D) protein structure. These predictors of stability change are evaluated by applying machine learning tools to large training sets of mutants derived from diverse proteins that have been experimentally studied and described. Predictive models based on our combined approach are either comparable to, or in many cases significantly outperform, previously published results. AVAILABILITY: A web server with supporting documentation is available at http://proteins.gmu.edu/automute.

Phenotypic tests are useful for measuring the degree of resistance of HIV-1 protease mutants to commercially available inhibitors. However, these tests are expensive and time-consuming, and phenotyping has been performed on only a fraction of the nearly 400 distinct patient-derived protease mutants. We employed a computational mutagenesis methodology, incorporating both sequence and structure information, to generate a feature vector representation for each of the isolated protease mutants. Training sets were prepared for seven protease inhibitors, each consisting of protease mutants with known phenotypes. Four machine-learning algorithms were implemented, and random forest performed best at distinguishing between sensitive/resistant mutants based on area under the ROC curve (0.81 -0.92). Trained models were used to make predictions about recently assayed protease mutants and displayed 83% agreement with the experimental data. The results suggest that susceptibility of unassayed protease mutants to each inhibitor can be reliably predicted.

MOTIVATION: An important area of research in biochemistry and molecular biology focuses on characterization of enzyme mutants. However, synthesis and analysis of experimental mutants is time consuming and expensive. We describe a machine-learning approach for inferring the activity levels of all unexplored single point mutants of an enzyme, based on a training set of such mutants with experimentally measured activity. RESULTS: Based on a Delaunay tessellation-derived four-body statistical potential function, a perturbation vector measuring environmental changes relative to wild type (wt) at every residue position uniquely characterizes each enzyme mutant for model development and prediction. First, a measure of model performance utilizing area (AUC) under the receiver operating characteristic (ROC) curve surpasses 0.83 and 0.77 for data sets of experimental HIV-1 protease and T4 lysozyme mutants, respectively. Additionally, a novel method is introduced for evaluating statistical significance associated with the number of correct test set predictions obtained from a trained model. Third, 100 stratified random splits of the protease and T4 lysozyme mutant data sets into training and test sets achieve 77.0% and 80.8% mean accuracy, respectively. Next, protease and T4 lysozyme models trained with experimental mutants are used to predict activity levels for all remaining mutants; a subsequent search for publications reporting on dozens of these test mutants reveals that experimental results are matched by 79% and 86% of predictions, respectively. Finally, learning curves for each mutant enzyme system indicate the influence of training set size on model performance. AVAILABILITY: Prediction databases at http://proteins.gmu.edu/automute/

The sequence-conformation-structure database for amino acid residues contains information on 114 828 individual residues derived from the spatial structures of 473 high-quality non-homologous proteins. The information in the database is obtained using a variety of different methods and can be used in various protein modeling applications.

Rapid growth of protein structures database in recent years requires an effective approach for objective comparison and classification of deposited protein structures. We describe a novel method for structure comparison and classification based on the alignment of one-dimensional structure profiles. These profiles are obtained by calculating the OCCO pseudodihedral angles (formed by O-C-C-O atoms of carbonyl groups of consecutive amino acid residues) from protein three-dimensional coordinates. These angle measurements are then converted into a 24 letter alphabet, and the protein structures are represented by sequences of letter from this alphabet. The BioSCAN parallel computer, designed for primary sequence alignment, is used to rapidly align and classify these one-dimensional structure profiles. We have developed and implemented weighted scoring matrix to identify structural classes based on commonly found structural motifs. The results of our experiments are in good agreement with the traditional protein structure classification schemes. One-dimensional structure profiles significantly improve efficiency of structure comparison and classification.