Abstract: Big data problems are becoming more prevalent for laboratory scientists who look to make clinical impact. A large part of this is due to increased computing power, in parallel with new technologies for high quality data generation. Both new and old techniques of artificial intelligence (AI) and machine learning (ML) can now help increase the success of translational studies in three areas: drug discovery, imaging, and genomic medicine. However, ML technologies do not come without their limitations and shortcomings. Current technical limitations and other limitations including governance, reproducibility, and interpretation will be discussed in this article. Overcoming these limitations will enable ML methods to be more powerful for discovery and reduce ambiguity within translational medicine, allowing data-informed decision-making to deliver the next generation of diagnostics and therapeutics to patients quicker, at lowered costs, and at scale.

Abstract: INTRODUCTION: Patients often take several different medications for multiple conditions concurrently. Therefore, when adverse drug events (ADEs) occur, it is necessary to consider the mechanisms responsible. Few approaches consider the mechanisms of ADEs, such as changes in physiological states. We proposed that the ontological framework for pharmacology and mechanism of action (pharmacodynamics) we developed could be used for this approach. However, the existing knowledge base contains little data on physiological chains (PCs). OBJECTIVE: We aimed to investigate a method for automatically generating missing PC from the viewpoint of anatomical structures. This study was conducted to determine dysuria-related adverse events more likely to occur during multidrug administration. METHODS: We adopted a systematic approach to determine drugs suspected to cause adverse events and incorporated existing data and data generated in our newly developed method into our ontological framework. The performance of automated data generation was evaluated using this newly developed system. Suspected drugs determined by the system were compared with those derived from adverse events databases. RESULTS: Of the 242 drugs involving suspected drug-induced urinary retention or dysuria, 26 suspected drugs were determined. Of these, five were drugs with side effects not listed in drug package inserts. The system derived potential mechanisms of action, PCs, and suspected drugs. CONCLUSION: Our method is novel in that it generates PC data from anatomical structural properties and could serve as a knowledge base for determining suspected drugs by potential mechanisms of action.

Abstract: Introduction: Results from recent studies have suggested a role for protease inhibitors in altering mechanisms involved in the initiation and proliferation of cancer cells. One such inhibitor, indinavir, may act as an anti-cancer agent by modulating the alpha-7-nicotinic acetylcholine receptor, which is a pro-carcinogenic protein that has been researched in conjunction with nicotine in lung cancer development. In our study, we compare indinavir's binding affinity towards alpha7-nAchR and MMP-2, another promoter of malignancy, to determine what extracellular effects the drug has before being internalized to inhibit HIV-1 protease. Methods: A computer program, PyRx, was used to compare indinavir's binding affinity with digital models for alpha7-nAchR, MMP-2 and HIV-1 protease, which were then compared to the results of in vitro binding assays for these targets. Results: PyRx testing predicted the highest binding affinity values for indinavir to MMP-2 (mean = 8.77 kcal/mol, S.D. = 0.29), followed by the alpha7-nAchR (mean = 8.53 kcal/mol, S.D. = 0.15) and HIV-1 protease (mean = 7.5 kcal/mol, S.D. = 0.44). In vitro, indinavir's mean percent inhibition of control values were 103.2 for HIV-1 protease, 5.3 for MMP-2, and 7.7 for the alpha7-nAchR. Conclusions: Binding affinity values for indinavir to MMP-2 and alpha7-nAchR were not significantly different. Using PyRx to predict affinity compared with in vitro testing did not yield comparable results. However, indinavir was shown to slightly inhibit both alpha7-nAchR and MMP-2, which may have ramifications in the drug's delivery to the intracellularly located HIV-1 protease.

Abstract: alpha-Branched amines are present in hundreds of pharmaceutical agents and clinical candidates and are important targets for synthesis. Here we show the convergent synthesis of alpha-branched amines from three readily accessible starting materials: aromatic C-H bond substrates, terminal alkenes, and aminating agents. This reaction proceeds by an intermolecular formation of C-C and C-N bonds at the sp (3) carbon branch site through an uncommon 1,1-alkene addition pathway. The reaction is carried out under mild conditions and has high functional group compatibility. Ethylene and propylene feedstock chemicals are effective alkene inputs with ethylene in particular providing for the one step synthesis of alpha-methyl branched amines, a motif prevalent in drug structures. The reaction is scalable, and 1% loading of an air stable dimeric rhodium precatalyst is effective for several different types of products. The use of chiral catalysts also enables the asymmetric synthesis of alpha-branched amines.

Abstract: BACKGROUND AND PURPOSE: A second-generation antihistamine, terfenadine, is known to induce arrhythmia by blocking hERG channels. In this study, we have shown that terfenadine also inhibits the activity of G-protein-gated inwardly rectifying K(+) (GIRK) channels, which regulate the excitability of neurons and cardiomyocytes. To clarify the underlying mechanism(s), we examined the effects of several antihistamines on GIRK channels and identified the structural determinant for the inhibition. EXPERIMENTAL APPROACH: Electrophysiological recordings were made in Xenopus oocytes and rat atrial myocytes to analyse the effects of antihistamines on various GIRK subunits (Kir 3.x). Mutagenesis analyses identified the residues critical for inhibition by terfenadine and the regulation of ion selectivity. The potential docking site of terfenadine was analysed by molecular docking. KEY RESULTS: GIRK channels containing Kir 3.1 subunits heterologously expressed in oocytes and native GIRK channels in atrial myocytes were inhibited by terfenadine and other non-sedating antihistamines. In Kir 3.1 subunits, mutation of Phe137, located in the centre of the pore helix, to the corresponding Ser in Kir 3.2 subunits reduced the inhibition by terfenadine. Introduction of an amino acid with a large side chain in Kir 3.2 subunits at Ser148 increased the inhibition. When this residue was mutated to a non-polar amino acid, the channel became permeable to Na(+) . Phosphoinositide-mediated activity was also decreased by terfenadine. CONCLUSION AND IMPLICATIONS: The Phe137 residue in Kir 3.1 subunits is critical for inhibition by terfenadine. This study provides novel insights into the regulation of GIRK channels by the pore helix and information for drug design.

Abstract: Pathway analysis is widely used to gain mechanistic insights from high-throughput omics data. However, most existing methods do not consider signal integration represented by pathway topology, resulting in enrichment of convergent pathways when downstream genes are modulated. Incorporation of signal flow and integration in pathway analysis could rank the pathways based on modulation in key regulatory genes. This implementation can be facilitated for large-scale data by discrete state network modeling due to simplicity in parameterization. Here, we model cellular heterogeneity using discrete state dynamics and measure pathway activities in cross-sectional data. We introduce a new algorithm, Boolean Omics Network Invariant-Time Analysis (BONITA), for signal propagation, signal integration, and pathway analysis. Our signal propagation approach models heterogeneity in transcriptomic data as arising from intercellular heterogeneity rather than intracellular stochasticity, and propagates binary signals repeatedly across networks. Logic rules defining signal integration are inferred by genetic algorithm and are refined by local search. The rules determine the impact of each node in a pathway, which is used to score the probability of the pathway's modulation by chance. We have comprehensively tested BONITA for application to transcriptomics data from translational studies. Comparison with state-of-the-art pathway analysis methods shows that BONITA has higher sensitivity at lower levels of source node modulation and similar sensitivity at higher levels of source node modulation. Application of BONITA pathway analysis to previously validated RNA-sequencing studies identifies additional relevant pathways in in-vitro human cell line experiments and in-vivo infant studies. Additionally, BONITA successfully detected modulation of disease specific pathways when comparing relevant RNA-sequencing data with healthy controls. Most interestingly, the two highest impact score nodes identified by BONITA included known drug targets. Thus, BONITA is a powerful approach to prioritize not only pathways but also specific mechanistic role of genes compared to existing methods. BONITA is available at: https://github.com/thakar-lab/BONITA.

Abstract: The ability to predict the skin sensitization potential of small organic molecules is of high importance to the development and safe application of cosmetics, drugs and pesticides. One of the most widely accepted methods for predicting this hazard is the local lymph node assay (LLNA). The goal of this work was to develop in silico models for the prediction of the skin sensitization potential of small molecules that go beyond the state of the art, with larger LLNA data sets and, most importantly, a robust and intuitive definition of the applicability domain, paired with additional indicators of the reliability of predictions. We explored a large variety of molecular descriptors and fingerprints in combination with random forest and support vector machine classifiers. The most suitable models were tested on holdout data, on which they yielded competitive performance (Matthews correlation coefficients up to 0.52; accuracies up to 0.76; areas under the receiver operating characteristic curves up to 0.83). The most favorable models are available via a public web service that, in addition to predictions, provides assessments of the applicability domain and indicators of the reliability of the individual predictions.

Abstract: Recent years have seen an increase in the availability of pharmacogenomic databases such as Genomics of Drug Sensitivity in Cancer (GDSC) and Cancer Cell Line Encyclopedia (CCLE) that provide genomic and functional characterization information for multiple cell lines. Studies have alluded to the fact that specific characterizations may be inconsistent between different databases. Analysis of the potential discrepancies in the different databases is highly significant, as these sources are frequently used to analyze and validate methodologies for personalized cancer therapies. In this article, we review the recent developments in investigating the correspondence between different pharmacogenomics databases and discuss the potential factors that require attention when incorporating these sources in any modeling analysis. Furthermore, we explored the consistency among these databases using copulas that can capture nonlinear dependencies between two sets of data.

Abstract: The identification of interactions between drugs/compounds and their targets is crucial for the development of new drugs. In vitro screening experiments (i.e. bioassays) are frequently used for this purpose; however, experimental approaches are insufficient to explore novel drug-target interactions, mainly because of feasibility problems, as they are labour intensive, costly and time consuming. A computational field known as 'virtual screening' (VS) has emerged in the past decades to aid experimental drug discovery studies by statistically estimating unknown bio-interactions between compounds and biological targets. These methods use the physico-chemical and structural properties of compounds and/or target proteins along with the experimentally verified bio-interaction information to generate predictive models. Lately, sophisticated machine learning techniques are applied in VS to elevate the predictive performance. The objective of this study is to examine and discuss the recent applications of machine learning techniques in VS, including deep learning, which became highly popular after giving rise to epochal developments in the fields of computer vision and natural language processing. The past 3 years have witnessed an unprecedented amount of research studies considering the application of deep learning in biomedicine, including computational drug discovery. In this review, we first describe the main instruments of VS methods, including compound and protein features (i.e. representations and descriptors), frequently used libraries and toolkits for VS, bioactivity databases and gold-standard data sets for system training and benchmarking. We subsequently review recent VS studies with a strong emphasis on deep learning applications. Finally, we discuss the present state of the field, including the current challenges and suggest future directions. We believe that this survey will provide insight to the researchers working in the field of computational drug discovery in terms of comprehending and developing novel bio-prediction methods.

Abstract: Identification of primary targets associated with phenotypes can facilitate exploration of the underlying molecular mechanisms of compounds and optimization of the structures of promising drugs. However, the literature reports limited effort to identify the target major isoform of a single known target gene. The majority of genes generate multiple transcripts that are translated into proteins that may carry out distinct and even opposing biological functions through alternative splicing. In addition, isoform expression is dynamic and varies depending on the developmental stage and cell type. To identify target major isoforms, we integrated a breast cancer type-specific isoform coexpression network with gene perturbation signatures in the MCF7 cell line in the Connectivity Map database using the 'shortest path' drug target prioritization method. We used a leukemia cancer network and differential expression data for drugs in the HL-60 cell line to test the robustness of the detection algorithm for target major isoforms. We further analyzed the properties of target major isoforms for each multi-isoform gene using pharmacogenomic datasets, proteomic data and the principal isoforms defined by the APPRIS and STRING datasets. Then, we tested our predictions for the most promising target major protein isoforms of DNMT1, MGEA5 and P4HB4 based on expression data and topological features in the coexpression network. Interestingly, these isoforms are not annotated as principal isoforms in APPRIS. Lastly, we tested the affinity of the target major isoform of MGEA5 for streptozocin through in silico docking. Our findings will pave the way for more effective and targeted therapies via studies of drug targets at the isoform level.