Maris Lapins

Proteochemometric modeling of HIV protease susceptibility

BackgroundA major obstacle in treatment of HIV is the ability of the virus to mutate rapidly into drug-resistant variants. A method for predicting the susceptibility of mutated HIV strains to antiviral agents would provide substantial clinical benefit as well as facilitate the development of new candidate drugs. Therefore, we used proteochemometrics to model the susceptibility of HIV to protease inhibitors in current use, utilizing descriptions of the physico-chemical properties of mutated HIV proteases and 3D structural property descriptions for the protease inhibitors. The descriptions were correlated to the susceptibility data of 828 unique HIV protease variants for seven protease inhibitors in current use; the data set comprised 4792 protease-inhibitor combinations.ResultsThe model provided excellent predictability (R2 = 0.92, Q2 = 0.87) and identified general and specific features of drug resistance. The models predictive ability was verified by external prediction in which the susceptibilities to each one of the seven inhibitors were omitted from the data set, one inhibitor at a time, and the data for the six remaining compounds were used to create new models. This analysis showed that the over all predictive ability for the omitted inhibitors was Q2inhibitors= 0.72.ConclusionOur results show that a proteochemometric approach can provide generalized susceptibility predictions for new inhibitors. Our proteochemometric model can directly analyze inhibitor-protease interactions and facilitate treatment selection based on viral genotype. The model is available for public use, and is located at HIV Drug Research Centre.

Kinome-wide interaction modelling using alignment-based and alignment-independent approaches for kinase description and linear and non-linear data analysis techniques

BackgroundProtein kinases play crucial roles in cell growth, differentiation, and apoptosis. Abnormal function of protein kinases can lead to many serious diseases, such as cancer. Kinase inhibitors have potential for treatment of these diseases. However, current inhibitors interact with a broad variety of kinases and interfere with multiple vital cellular processes, which causes toxic effects. Bioinformatics approaches that can predict inhibitor-kinase interactions from the chemical properties of the inhibitors and the kinase macromolecules might aid in design of more selective therapeutic agents, that show better efficacy and lower toxicity.ResultsWe applied proteochemometric modelling to correlate the properties of 317 wild-type and mutated kinases and 38 inhibitors (12,046 inhibitor-kinase combinations) to the respective combinations interaction dissociation constant (Kd). We compared six approaches for description of protein kinases and several linear and non-linear correlation methods. The best performing models encoded kinase sequences with amino acid physico-chemical z-scale descriptors and used support vector machines or partial least- squares projections to latent structures for the correlations. Modelling performance was estimated by double cross-validation. The best models showed high predictive ability; the squared correlation coefficient for new kinase-inhibitor pairs ranging P2 = 0.67-0.73; for new kinases it ranged P2kin = 0.65-0.70. Models could also separate interacting from non-interacting inhibitor-kinase pairs with high sensitivity and specificity; the areas under the ROC curves ranging AUC = 0.92-0.93. We also investigated the relationship between the number of protein kinases in the dataset and the modelling results. Using only 10% of all data still a valid model was obtained with P2 = 0.47, P2kin = 0.42 and AUC = 0.83.ConclusionsOur results strongly support the applicability of proteochemometrics for kinome-wide interaction modelling. Proteochemometrics might be used to speed-up identification and optimization of protein kinase targeted and multi-targeted inhibitors.

A Unified Proteochemometric Model for Prediction of Inhibition of Cytochrome P450 Isoforms

A unified proteochemometric (PCM) model for the prediction of the ability of drug-like chemicals to inhibit five major drug metabolizing CYP isoforms (i.e. CYP1A2, CYP2C9, CYP2C19, CYP2D6 and CYP3A4) was created and made publicly available under the Bioclipse Decision Support open source system at www.cyp450model.org. In regards to the proteochemometric modeling we represented the chemical compounds by molecular signature descriptors and the CYP-isoforms by alignment-independent description of composition and transition of amino acid properties of their protein primary sequences. The entire training dataset contained 63 391 interactions and the best PCM model was obtained using signature descriptors of height 1, 2 and 3 and inducing the model with a support vector machine. The model showed excellent predictive ability with internal AUC = 0.923 and an external AUC = 0.940, as evaluated on a large external dataset. The advantage of PCM models is their extensibility making it possible to extend our model for new CYP isoforms and polymorphic CYP forms. A key benefit of PCM is that all proteins are confined in one single model, which makes it generally more stable and predictive as compared with single target models. The inclusion of the model in Bioclipse Decision Support makes it possible to make virtual instantaneous predictions (∼100 ms per prediction) while interactively drawing or modifying chemical structures in the Bioclipse chemical structure editor.

Linking the Resource Description Framework to cheminformatics and proteochemometrics.

BackgroundSemantic web technologies are finding their way into the life sciences. Ontologies and semantic markup have already been used for more than a decade in molecular sciences, but have not found widespread use yet. The semantic web technology Resource Description Framework (RDF) and related methods show to be sufficiently versatile to change that situation.ResultsThe work presented here focuses on linking RDF approaches to existing molecular chemometrics fields, including cheminformatics, QSAR modeling and proteochemometrics. Applications are presented that link RDF technologies to methods from statistics and cheminformatics, including data aggregation, visualization, chemical identification, and property prediction. They demonstrate how this can be done using various existing RDF standards and cheminformatics libraries. For example, we show how IC50 and Ki values are modeled for a number of biological targets using data from the ChEMBL database.ConclusionsWe have shown that existing RDF standards can suitably be integrated into existing molecular chemometrics methods. Platforms that unite these technologies, like Bioclipse, makes this even simpler and more transparent. Being able to create and share workflows that integrate data aggregation and analysis (visual and statistical) is beneficial to interoperability and reproducibility. The current work shows that RDF approaches are sufficiently powerful to support molecular chemometrics workflows.

Proteochemometric Modeling of Drug Resistance over the Mutational Space for Multiple HIV Protease Variants and Multiple Protease Inhibitors

The main therapeutic targets in HIV are its protease and reverse transcriptase. A major problem in treatment of HIV is the ability of the virus to develop drug resistance by accumulating mutations in its targets. Acquiring detailed understanding of the molecular mechanisms for the interactions of drugs with mutated variants of the HIV virus is mandatory to be able to design inhibitors that can evade the resistance. Here we have used proteochemometric modeling to simultaneously analyze the interactions of 21 protease inhibitors with 72 unique protease variants. Inhibition data (pK(i)) were correlated to descriptions of chemical and structural properties of the inhibitors and proteases. The proteochemometric model obtained showed excellent fit and predictive ability (R(2)=0.92, Q(2)=0.83, Q(2)(inh)=0.78) and provided quantitative assessments for the contribution of each mutation and their combinations to the decrease in inhibitor activity, both for the whole compounds series as well as for individual compounds. The model revealed the most deleterious mutations in the protease to be D30N, V32I, G48V, I50V, I54V, V82A, I84V, and L90M. The model was further used to identify molecular properties of chemical compounds that are important for their inhibition of multimutated protease variants. Our results give directions how to design novel improved inhibitors.

Design and evaluation of substrate-based octapeptide and non substrate-based tetrapeptide inhibitors of dengue virus NS2B-NS3 proteases.

A series of 45 peptide inhibitors was designed, synthesized, and evaluated against the NS2B-NS3 proteases of the four subtypes of dengue virus, DEN-1-4. The design was based on proteochemometric models for Michaelis (Km) and cleavage rate constants (kcat) of protease substrates. This led first to octapeptides showing submicromolar or low micromolar inhibitory activities on the four proteases. Stepwise removal of cationic substrate non-prime side residues and variations in the prime side sequence resulted finally in an uncharged tetrapeptide, WYCW-NH2, with inhibitory Ki values of 4.2, 4.8, 24.4, and 11.2 μM for the DEN-1-4 proteases, respectively. Analysis of the inhibition data by proteochemometric modeling suggested the possibility for different binding poses of the shortened peptides compared to the octapeptides, which was supported by results of docking of WYCW-NH2 into the X-ray structure of DEN-3 protease.

Proteochemometric modeling of the susceptibility of mutated variants of the HIV-1 virus to reverse transcriptase inhibitors.

Background Reverse transcriptase is a major drug target in highly active antiretroviral therapy (HAART) against HIV, which typically comprises two nucleoside/nucleotide analog reverse transcriptase (RT) inhibitors (NRTIs) in combination with a non-nucleoside RT inhibitor or a protease inhibitor. Unfortunately, HIV is capable of escaping the therapy by mutating into drug-resistant variants. Computational models that correlate HIV drug susceptibilities to the virus genotype and to drug molecular properties might facilitate selection of improved combination treatment regimens. Methodology/Principal Findings We applied our earlier developed proteochemometric modeling technology to analyze HIV mutant susceptibility to the eight clinically approved NRTIs. The data set used covered 728 virus variants genotyped for 240 sequence residues of the DNA polymerase domain of the RT; 165 of these residues contained mutations; totally the data-set covered susceptibility data for 4,495 inhibitor-RT combinations. Inhibitors and RT sequences were represented numerically by 3D-structural and physicochemical property descriptors, respectively. The two sets of descriptors and their derived cross-terms were correlated to the susceptibility data by partial least-squares projections to latent structures. The model identified more than ten frequently occurring mutations, each conferring more than two-fold loss of susceptibility for one or several NRTIs. The most deleterious mutations were K65R, Q151M, M184V/I, and T215Y/F, each of them decreasing susceptibility to most of the NRTIs. The predictive ability of the model was estimated by cross-validation and by external predictions for new HIV variants; both procedures showed very high correlation between the predicted and actual susceptibility values (Q 2 = 0.89 and Q2ext = 0.86). The model is available at www.hivdrc.org as a free web service for the prediction of the susceptibility to any of the clinically used NRTIs for any HIV-1 mutant variant. Conclusions/Significance Our results give directions how to develop approaches for selection of genome-based optimum combination therapy for patients harboring mutated HIV variants.

Reductive amination products containing naphthalene and indole moieties bind to melanocortin receptors

Presumed pharmacophoric groups of melanocortin peptides (naphthalene, amino or guanidine, and indole moieties) were combined in mimetics molecules looking for their favorable location for activity at melanocortin (MC) receptors. Twenty-two compounds were prepared and tested. The best of these displayed micromolar affinities for the MC receptors.

Identification and analysis of functionally important amino acids in human purinergic 12 receptor using a Saccharomyces cerevisiae expression system

The purinergic 12 receptor (P2Y12) is a major drug target for anticoagulant therapies, but little is known about the regions involved in ligand binding and activation of this receptor. We generated four randomized P2Y12 libraries and investigated their ligand binding characteristics. P2Y12 was expressed in a Saccharomyces cerevisiae model system. Four libraries were generated with randomized amino acids at positions 181, 256, 265 and 280. Mutant variants were screened for functional activity in yeast using the natural P2Y12 ligand ADP. Activation results were investigated using quantitative structure–activity relationship (QSAR) models and ligand–receptor docking. We screened four positions in P2Y12 for functional activity by substitution with amino acids with diverse physiochemical properties. This analysis revealed that positions E181, R256 and R265 alter the functional activity of P2Y12 in a specific manner. QSAR models for E181 and R256 mutant libraries strongly supported the experimental data. All substitutions of amino acid K280 were completely inactive, highlighting the crucial role of this residue in P2Y12 function. Ligand–receptor docking revealed that K280 is likely to be a key element in the ligand‐binding pocket of P2Y12. The results of this study demonstrate that positions 181, 256, 265 and 280 of P2Y12 are important for the functional integrity of the receptor. Moreover, K280 appears to be a crucial feature of the P2Y12 ligand‐binding pocket. These results are important for rational design of novel antiplatelet agents.

Towards Proteome-Wide Interaction Models Using the Proteochemometrics Approach.

A proteochemometrics model was induced from all interaction data in the BindingDB database, comprizing in all 7078 protein‐ligand complexes with representatives from all major drug target categories. Proteins were represented by alignment‐independent sequence descriptors holding information on properties such as hydrophobicity, charge, and secondary structure. Ligands were represented by commonly used QSAR descriptors. The inhibition constant (pKi) values of protein‐ligand complexes were discretized into “high” and “low” interaction activity. Different machine‐learning techniques were used to induce models relating protein and ligand properties to the interaction activity. The best was decision trees, which gave an accuracy of 80 % and an area under the ROC curve of 0.81. The tree pointed to the protein and ligand properties, which are relevant for the interaction. As the approach does neither require alignments nor knowledge of protein 3D structures virtually all available protein‐ligand interaction data could be utilized, thus opening a way to completely general interaction models that may span entire proteomes.