Target-specific compound selectivity for multi-target drug discovery and repurposing.

Most drug molecules modulate multiple target proteins, leading either to therapeutic effects or unwanted side effects. Such target promiscuity partly contributes to high attrition rates and leads to wasted costs and time in the current drug discovery process, and makes the assessment of compound selectivity an important factor in drug development and repurposing efforts. Traditionally, selectivity of a compound is characterized in terms of its target activity profile (wide or narrow), which can be quantified using various statistical and information theoretic metrics. Even though the existing selectivity metrics are widely used for characterizing the overall selectivity of a compound, they fall short in quantifying how selective the compound is against a particular target protein (e.g., disease target of interest). We therefore extended the concept of compound selectivity towards target-specific selectivity, defined as the potency of a compound to bind to the particular protein in comparison to the other potential targets. We decompose the target-specific selectivity into two components: 1) the compound's potency against the target of interest (absolute potency), and 2) the compound's potency against the other targets (relative potency). The maximally selective compound-target pairs are then identified as a solution of a bi-objective optimization problem that simultaneously optimizes these two potency metrics. In computational experiments carried out using large-scale kinase inhibitor dataset, which represents a wide range of polypharmacological activities, we show how the optimization-based selectivity scoring offers a systematic approach to finding both potent and selective compounds against given kinase targets. Compared to the existing selectivity metrics, we show how the target-specific selectivity provides additional insights into the target selectivity and promiscuity of multi-targeting kinase inhibitors. Even though the selectivity score is shown to be relatively robust against both missing bioactivity values and the dataset size, we further developed a permutation-based procedure to calculate empirical p-values to assess the statistical significance of the observed selectivity of a compound-target pair in the given bioactivity dataset. We present several case studies that show how the target-specific selectivity can distinguish between highly selective and broadly-active kinase inhibitors, hence facilitating the discovery or repurposing of multi-targeting drugs.

Systematic review of computational methods for drug combination prediction.

Synergistic effects between drugs are rare and highly context-dependent and patient-specific. Hence, there is a need to develop novel approaches to stratify patients for optimal therapy regimens, especially in the context of personalized design of combinatorial treatments. Computational methods enable systematic in-silico screening of combination effects, and can thereby prioritize most potent combinations for further testing, among the massive number of potential combinations. To help researchers to choose a prediction method that best fits for various real-world applications, we carried out a systematic literature review of 117 computational methods developed to date for drug combination prediction, and classified the methods in terms of their combination prediction tasks and input data requirements. Most current methods focus on prediction or classification of combination synergy, and only a few methods consider the efficacy and potential toxicity of the combinations, which are the key determinants of therapeutic success of drug treatments. Furthermore, there is a need to further develop methods that enable dose-specific predictions of combination effects across multiple doses, which is important for clinical translation of the predictions, as well as model-based identification of biomarkers predictive of heterogeneous drug combination responses. Even if most of the computational methods reviewed focus on anticancer applications, many of the modelling approaches are also applicable to antiviral and other diseases or indications.

Modeling drug combination effects via latent tensor reconstruction.

MOTIVATION: Combination therapies have emerged as a powerful treatment modality to overcome drug resistance and improve treatment efficacy. However, the number of possible drug combinations increases very rapidly with the number of individual drugs in consideration, which makes the comprehensive experimental screening infeasible in practice. Machine-learning models offer time- and cost-efficient means to aid this process by prioritizing the most effective drug combinations for further pre-clinical and clinical validation. However, the complexity of the underlying interaction patterns across multiple drug doses and in different cellular contexts poses challenges to the predictive modeling of drug combination effects. RESULTS: We introduce comboLTR, highly time-efficient method for learning complex, non-linear target functions for describing the responses of therapeutic agent combinations in various doses and cancer cell-contexts. The method is based on a polynomial regression via powerful latent tensor reconstruction. It uses a combination of recommender system-style features indexing the data tensor of response values in different contexts, and chemical and multi-omics features as inputs. We demonstrate that comboLTR outperforms state-of-the-art methods in terms of predictive performance and running time, and produces highly accurate results even in the challenging and practical inference scenario where full dose-response matrices are predicted for completely new drug combinations with no available combination and monotherapy response measurements in any training cell line. AVAILABILITY AND IMPLEMENTATION: comboLTR code is available at https://github.com/aalto-ics-kepaco/ComboLTR. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Systematic mapping of cancer cell target dependencies using high-throughput drug screening in triple-negative breast cancer.

While high-throughput drug screening offers possibilities to profile phenotypic responses of hundreds of compounds, elucidation of the cell context-specific mechanisms of drug action requires additional analyses. To that end, we developed a computational target deconvolution pipeline that identifies the key target dependencies based on collective drug response patterns in each cell line separately. The pipeline combines quantitative drug-cell line responses with drug-target interaction networks among both intended on- and potent off-targets to identify pharmaceutically actionable and selective therapeutic targets. To demonstrate its performance, the target deconvolution pipeline was applied to 310 small molecules tested on 20 genetically and phenotypically heterogeneous triple-negative breast cancer (TNBC) cell lines to identify cell line-specific target mechanisms in terms of cytotoxic and cytostatic drug target vulnerabilities. The functional essentiality of each protein target was quantified with a target addiction score (TAS), as a measure of dependency of the cell line on the therapeutic target. The target dependency profiling was shown to capture inhibitory information that is complementary to that obtained from the structure or sensitivity of the drugs. Comparison of the TAS profiles and gene essentiality scores from CRISPR-Cas9 knockout screens revealed that certain proteins with low gene essentiality showed high target addictions, suggesting that they might be functioning as protein groups, and therefore be resistant to single gene knock-out. The comparative analysis discovered protein groups of potential multi-target synthetic lethal interactions, for instance, among histone deacetylases (HDACs). Our integrated approach also recovered a number of well-established TNBC cell line-specific drivers and known TNBC therapeutic targets, such as HDACs and cyclin-dependent kinases (CDKs). The present work provides novel insights into druggable vulnerabilities for TNBC, and opportunities to identify multi-target synthetic lethal interactions for further studies.

In Silico Prediction of Blood-Brain Barrier Permeability of Compounds by Machine Learning and Resampling Methods.

The blood-brain barrier (BBB) as a part of absorption protects the central nervous system by separating the brain tissue from the bloodstream. In recent years, BBB permeability has become a critical issue in chemical ADMET prediction, but almost all models were built using imbalanced data sets, which caused a high false-positive rate. Therefore, we tried to solve the problem of biased data sets and built a reliable classification model with 2358 compounds. Machine learning and resampling methods were used simultaneously for the refinement of models with both 2 D molecular descriptors and molecular fingerprints to represent the chemicals. Through a series of evaluation, we realized that resampling methods such as Synthetic Minority Oversampling Technique (SMOTE) and SMOTE+edited nearest neighbor could effectively solve the problem of imbalanced data sets and that MACCS fingerprint combined with support vector machine performed the best. After the final construction of a consensus model, the overall accuracy rate was increased to 0.966 for the final external data set. Also, the accuracy rate of the model for the test set was 0.919, with an excellent balanced capacity of 0.925 (sensitivity) to predict BBB-positive compounds and of 0.899 (specificity) to predict BBB-negative compounds. Compared with other BBB classification models, our models reduced the rate of false positives and were more robust in prediction of BBB-positive as well as BBB-negative compounds, which would be quite helpful in early drug discovery.

A Computational Systems Pharmacology Approach to Investigate Molecular Mechanisms of Herbal Formula Tian-Ma-Gou-Teng-Yin for Treatment of Alzheimer's Disease.

Traditional Chinese medicine (TCM) is typically prescribed as formula to treat certain symptoms. A TCM formula contains hundreds of chemical components, which makes it complicated to elucidate the molecular mechanisms of TCM. Here, we proposed a computational systems pharmacology approach consisting of network link prediction, statistical analysis, and bioinformatics tools to investigate the molecular mechanisms of TCM formulae. Taking formula Tian-Ma-Gou-Teng-Yin as an example, which shows pharmacological effects on Alzheimer's disease (AD) and its mechanism is unclear, we first identified 494 formula components together with corresponding 178 known targets, and then predicted 364 potential targets for these components with our balanced substructure-drug-target network-based inference method. With Fisher's exact test and statistical analysis we identified 12 compounds to be most significantly related to AD. The target genes of these compounds were further enriched onto pathways involved in AD, such as neuroactive ligand-receptor interaction, serotonergic synapse, inflammatory mediator regulation of transient receptor potential channel and calcium signaling pathway. By regulating key target genes, such as ACHE, HTR2A, NOS2, and TRPA1, the formula could have neuroprotective and anti-neuroinflammatory effects against the progression of AD. Our approach provided a holistic perspective to study the relevance between TCM formulae and diseases, and implied possible pharmacological effects of TCM components.

In Silico Prediction of Compounds Binding to Human Plasma Proteins by QSAR Models.

Plasma protein binding (PPB) is a significant pharmacokinetic property of compounds in drug discovery and design. Due to the high cost and time-consuming nature of experimental assays, in silico approaches have been developed to assess the binding profiles of chemicals. However, because of unambiguity and the lack of uniform experimental data, most available predictive models are far from satisfactory. In this study, an elaborately curated training set containing 967 diverse pharmaceuticals with plasma-protein-bound fractions (fb ) was used to construct quantitative structure-activity relationship (QSAR) models by six machine learning algorithms with 26 molecular descriptors. Furthermore, we combined all of the individual learners to yield consensus prediction, marginally improving the accuracy of the consensus model. The model performance was estimated by tenfold cross validation and three external validation sets comprising 242 pharmaceutical, 397 industrial, and 231 newly designed chemicals, respectively. The models showed excellent performance for the entire test set, with mean absolute error (MAE) ranging from 0.126 to 0.178, demonstrating that our models could be used by a chemist when drawing a molecular structure from scratch. Meanwhile, structural descriptors contributing significantly to the predictive power of the models were related to the binding mechanisms, and the trend in terms of their effects on PPB can serve as guidance for the structural modification of chemicals. The applicability domain was also defined to distinguish favorable predictions from unfavorable predictions.

Discovery of novel propargylamine-modified 4-aminoalkyl imidazole substituted pyrimidinylthiourea derivatives as multifunctional agents for the treatment of Alzheimer's disease.

A series of novel propargylamine-modified pyrimidinylthiourea derivatives (1-3) were designed and synthesized as multifunctional agents for Alzheimer's disease (AD) therapy, and their potential was evaluated through various biological experiments. Among these derivatives, compound 1b displayed good selective inhibitory activity against AChE (vs BuChE, IC50 = 0.324 µM, SI > 123) and MAO-B (vs MAO-A, IC50 = 1.427 µM, SI > 35). Molecular docking study showed that the pyrimidinylthiourea moiety of 1b could bind to the catalytic active site (CAS) of AChE, and the propargylamine moiety interacted directly with the flavin adenine dinucleotide (FAD) of MAO-B. Moreover, 1b demonstrated mild antioxidant ability, good copper chelating property, effective inhibitory activity against Cu2+-induced Aß1-42 aggregation, moderate neuroprotection, low cytotoxicity, and appropriate blood-brain barrier (BBB) permeability in vitro and was capable of ameliorating scopolamine-induced cognitive impairment in mice. These results indicated that 1b has the potential to be a multifunctional candidate for the treatment of Alzheimer's disease.

Quantitative and systems pharmacology 2. In silico polypharmacology of G protein-coupled receptor ligands via network-based approaches.

G protein-coupled receptors (GPCRs) are the largest super family with more than 800 membrane receptors. Currently, over 30% of the approved drugs target human GPCRs. However, only approximately 30 human GPCRs have been resolved three-dimensional crystal structures, which limits traditional structure-based drug discovery. Recent advances in network-based systems pharmacology approaches have demonstrated powerful strategies for identifying new targets of GPCR ligands. In this study, we proposed a network-based systems pharmacology framework for comprehensive identification of new drug-target interactions on GPCRs. Specifically, we reconstructed both global and local drug-target interaction networks for human GPCRs. Network analysis on the known drug-target networks showed rational strategies for designing new GPCR ligands and evaluating side effects of the approved GPCR drugs. We further built global and local network-based models for predicting new targets of the known GPCR ligands. The area under the receiver operating characteristic curve of more than 0.96 was obtained for the best network-based models in cross validation. In case studies, we identified that several network-predicted GPCR off-targets (e.g. ADRA2A, ADRA2C and CHRM2) were associated with cardiovascular complications (e.g. bradycardia and palpitations) of the approved GPCR drugs via an integrative analysis of drug-target and off-target-adverse drug event networks. Importantly, we experimentally validated that two newly predicted compounds, AM966 and Ki16425, showed high binding affinities on prostaglandin E2 receptor EP4 subtype with IC50=2.67µM and 6.34µM, respectively. In summary, this study offers powerful network-based tools for identifying polypharmacology of GPCR ligands in drug discovery and development.