Large-scale prediction and testing of drug activity on side-effect targets

Integrated QSAR and Adverse Outcome Pathway Analysis of Chemicals Released on 3D Printing Using Acrylonitrile Butadiene Styrene

Additive manufacturing commonly known as 3D printing has numerous applications in several domains including material and biomedical technologies and has emerged as a tool of capabilities by providing fast, highly customized, and cost-effective solutions. However, the impact of the printing materials and chemicals present in the printing fumes has raised concerns about their adverse potential affecting humans and the environment. Thus, it is necessary to understand the properties of the chemicals emitted during additive manufacturing for developing safe and biocompatible fibers having controlled emission of fumes including its sustainable usage. Therefore, in this study, we have developed a computational predictive risk-assessment framework on the comprehensive list of chemicals released during 3D printing using the acrylonitrile butadiene styrene (ABS) filament. Our results showed that the chemicals present in the fumes of the ABS-based fiber used in additive manufacturing have the potential to lead to various toxicity end points such as inhalation toxicity, oral toxicity, carcinogenicity, hepatotoxicity, and teratogenicity. Moreover, because of their absorption, distribution in the body, metabolism, and excretion properties, most of the chemicals exhibited a high absorption level in the intestine and the potential to cross the blood-brain barrier. Furthermore, pathway analysis revealed that signaling like alpha-adrenergic receptor signaling, heterotrimeric G-protein signaling, and Alzheimer's disease-amyloid secretase pathway are significantly overrepresented given the identified target proteins of these chemicals. These findings signify the adversities associated with 3D printing fumes and the necessity for the development of biodegradable and considerably safer fibers for 3D printing technology.

Artificial intelligence in drug discovery and development

Artificial intelligence-integrated drug discovery and development has accelerated the growth of the pharmaceutical sector, leading to a revolutionary change in the pharma industry. Here, we discuss areas of integration, tools, and techniques utilized in enforcing AI, ongoing challenges, and ways to overcome them.

Computational Approaches for De Novo Drug Design: Past, Present, and Future

Drug discovery is time- and resource-consuming. To this end, computational approaches that are applied in de novo drug design play an important role to improve the efficiency and decrease costs to develop novel drugs. Over several decades, a variety of methods have been proposed and applied in practice. Traditionally, drug design problems are always taken as combinational optimization in discrete chemical space. Hence optimization methods were exploited to search for new drug molecules to meet multiple objectives. With the accumulation of data and the development of machine learning methods, computational drug design methods have gradually shifted to a new paradigm. There has been particular interest in the potential application of deep learning methods to drug design. In this chapter, we will give a brief description of these two different de novo methods, compare their application scopes and discuss their possible development in the future.

Acoustically Mediated Controlled Drug Release and Targeted Therapy with Degradable 3D Porous Magnetic Microrobots

Microrobots for targeted drug delivery are of great interest due to their minimal invasiveness and wireless controllability. Here, a magnetically driven porous degradable microrobot (PDM) is reported that consists of a 3D printed helical soft polymeric chassis made of a poly(ethylene glycol) diacrylate and pentaerythritol triacrylate matrix containing magnetite nanoparticles and the anticancer drug 5-fluorouracil (5-FU). The encapsulated Fe₃ O₄ nanoparticles render the PDM a precise wireless magnetic actuation by means of rotating magnetic fields (RMFs). The increased surface area of the porous PDM facilitates the acoustically induced drug release due to a higher response to the acoustic energy. The drug release profile from the PDM can be selected on command from three different modes, referred to herein as natural, burst, and constant, by differentiating the ultrasound exposure condition. Finally, in vitro test results reveal different therapeutic results for each release mode. The observed great reduction of cancer cell viability in the burst- and constant-release modes confirms that ultrasound with the proposed PDM can enhance the therapeutic effect by increasing drug concentration and sonoporation.

Pharmacology-informed prediction of the risk posed to fish by mixtures of non-steroidal anti-inflammatory drugs (NSAIDs) in the environment

The presence of non-steroidal anti-inflammatory drugs (NSAIDs) in the aquatic environment has raised concern that chronic exposure to these compounds may cause adverse effects in wild fish populations. This potential scenario has led some stakeholders to advocate a stricter regulation of NSAIDs, especially diclofenac. Considering their global clinical importance for the management of pain and inflammation, any regulation that may affect patient access to NSAIDs will have considerable implications for public health. The current environmental risk assessment of NSAIDs is driven by the results of a limited number of standard toxicity tests and does not take into account mechanistic and pharmacological considerations. Here we present a pharmacology-informed framework that enables the prediction of the risk posed to fish by 25 different NSAIDs and their dynamic mixtures. Using network pharmacology approaches, we demonstrated that these 25 NSAIDs display a significant mechanistic promiscuity that could enhance the risk of target-mediated mixture effects near environmentally relevant concentrations. Integrating NSAIDs pharmacokinetic and pharmacodynamic features, we provide highly specific predictions of the adverse phenotypes associated with exposure to NSAIDs, and we developed a visual multi-scale model to guide the interpretation of the toxicological relevance of any given set of NSAIDs exposure data. Our analysis demonstrated a non-negligible risk posed to fish by NSAID mixtures in situations of high drug use and low dilution of waste-water treatment plant effluents. We anticipate that this predictive framework will support the future regulatory environmental risk assessment of NSAIDs and increase the effectiveness of ecopharmacovigilance strategies. Moreover, it can facilitate the prediction of the toxicological risk posed by mixtures via the implementation of mechanistic considerations and could be readily extended to other classes of chemicals.

New Associations between Drug-Induced Adverse Events in Animal Models and Humans Reveal Novel Candidate Safety Targets

To improve our ability to extrapolate preclinical toxicity to humans, there is a need to understand and quantify the concordance of adverse events (AEs) between animal models and clinical studies. In the present work, we discovered 3011 statistically significant associations between preclinical and clinical AEs caused by drugs reported in the PharmaPendium database of which 2952 were new associations between toxicities encoded by different Medical Dictionary for Regulatory Activities terms across species. To find plausible and testable candidate off-target drug activities for the derived associations, we investigated the genetic overlap between the genes linked to both a preclinical and a clinical AE and the protein targets found to interact with one or more drugs causing both AEs. We discuss three associations from the analysis in more detail for which novel candidate off-target drug activities could be identified, namely, the association of preclinical mutagenicity readouts with clinical teratospermia and ovarian failure, the association of preclinical reflexes abnormal with clinical poor-quality sleep, and the association of preclinical psychomotor hyperactivity with clinical drug withdrawal syndrome. Our analysis successfully identified a total of 77% of known safety targets currently tested in in vitro screening panels plus an additional 431 genes which were proposed for investigation as future safety targets for different clinical toxicities. This work provides new translational toxicity relationships beyond AE term-matching, the results of which can be used for risk profiling of future new chemical entities for clinical studies and for the development of future in vitro safety panels.

Drug-target-ADR Network and Possible Implications of Structural Variants in Adverse Events

Adverse drug reactions (ADRs) are of major concern in drug safety. However, due to the biological complexity of human systems, understanding the underlying mechanisms involved in development of ADRs remains a challenging task. Here, we applied network sciences to analyze a tripartite network between 1000 drugs, 1407 targets, and 6164 ADRs. It allowed us to suggest drug targets susceptible to be associated to ADRs and organs, based on the system organ class (SOC). Furthermore, a score was developed to determine the contribution of a set of proteins to ADRs. Finally, we identified proteins that might increase the susceptibility of genes to ADRs, on the basis of knowledge about genomic structural variation in genes encoding proteins targeted by drugs. Such analysis should pave the way to individualize drug therapy and precision medicine.

Cheminformatics in Natural Product-based Drug Discovery

This review seeks to provide a timely survey of the scope and limitations of cheminformatics methods in natural product-based drug discovery. Following an overview of data resources of chemical, biological and structural information on natural products, we discuss, among other aspects, in silico methods for (i) data curation and natural products dereplication, (ii) analysis, visualization, navigation and comparison of the chemical space, (iii) quantification of natural product-likeness, (iv) prediction of the bioactivities (virtual screening, target prediction), ADME and safety profiles (toxicity) of natural products, (v) natural products-inspired de novo design and (vi) prediction of natural products prone to cause interference with biological assays. Among the many methods discussed are rule-based, similarity-based, shape-based, pharmacophore-based and network-based approaches, docking and machine learning methods.

Adding Stochastic Negative Examples into Machine Learning Improves Molecular Bioactivity Prediction

Multitask deep neural networks learn to predict ligand-target binding by example, yet public pharmacological data sets are sparse, imbalanced, and approximate. We constructed two hold-out benchmarks to approximate temporal and drug-screening test scenarios, whose characteristics differ from a random split of conventional training data sets. We developed a pharmacological data set augmentation procedure, Stochastic Negative Addition (SNA), which randomly assigns untested molecule-target pairs as transient negative examples during training. Under the SNA procedure, drug-screening benchmark performance increases from R² = 0.1926 ± 0.0186 to 0.4269 ± 0.0272 (122%). This gain was accompanied by a modest decrease in the temporal benchmark (13%). SNA increases in drug-screening performance were consistent for classification and regression tasks and outperformed y-randomized controls. Our results highlight where data and feature uncertainty may be problematic and how leveraging uncertainty into training improves predictions of drug-target relationships.

Analysis of Biological Screening Compounds with Single- or Multi-Target Activity via Diagnostic Machine Learning

Predicting compounds with single- and multi-target activity and exploring origins of compound specificity and promiscuity is of high interest for chemical biology and drug discovery. We present a large-scale analysis of compound promiscuity including two major components. First, high-confidence datasets of compounds with multi- and corresponding single-target activity were extracted from biological screening data. Positive and negative assay results were taken into account and data completeness was ensured. Second, these datasets were investigated using diagnostic machine learning to systematically distinguish between compounds with multi- and single-target activity. Models built on the basis of chemical structure consistently produced meaningful predictions. These findings provided evidence for the presence of structural features differentiating promiscuous and non-promiscuous compounds. Machine learning under varying conditions using modified datasets revealed a strong influence of nearest neighbor relationship on the predictions. Many multi-target compounds were found to be more similar to other multi-target compounds than single-target compounds and vice versa, which resulted in consistently accurate predictions. The results of our study confirm the presence of structural relationships that differentiate promiscuous and non-promiscuous compounds.

Virtual screening and drug repurposing experiments to identify potential novel selective MAO-B inhibitors for Parkinson's disease treatment

The main study's purpose is to detect novel natural products (NPs) that are potentially selective MAO-B inhibitors and, additionally, to computationally reposition the marketed drugs with a new therapeutic role for Parkinson's disease. To reach the goals, 3D similarity search, docking, ADMETox, and drug repurposing approaches were employed. Thus, an unbiased benchmarking dataset was built including selective and nonselective inhibitors for MAO-B compliant with both ligand- and structure-based virtual screening approaches. A retrospective and prospective mining scenario was applied to SPECS NP and DrugBank databases to detect novel scaffolds with potential benefits for Parkinson's disease patients. Out of the three best selected natural products, cardamomin showed excellently predicted drug-like properties, superior pharmacological profile, and specific interactions with MAO-B active site, indicating a potential selectivity over MAO-B. Two marketed drugs, fenamisal and monobenzone, were proposed as promising candidates repurposed for Parkinson's disease. The application of shape, physicochemical, and electrostatic similarity searches protocol emerged as a plausible solution to explore MAO-B inhibitors selectivity. This protocol might serve as a rewarding tool in early drug discovery and can be extended to other protein targets.

Targeting Beta-Blocker Drug-Drug Interactions with Fibrinogen Blood Plasma Protein: A Computational and Experimental Study

In this work, one of the most prevalent polypharmacology drug–drug interaction events that occurs between two widely used beta-blocker drugs—i.e., acebutolol and propranolol—with the most abundant blood plasma fibrinogen protein was evaluated. Towards that end, molecular docking and Density Functional Theory (DFT) calculations were used as complementary tools. A fibrinogen crystallographic validation for the three best ranked binding-sites shows 100% of conformationally favored residues with total absence of restricted flexibility. From those three sites, results on both the binding-site druggability and ligand transport analysis-based free energy trajectories pointed out the most preferred biophysical environment site for drug–drug interactions. Furthermore, the total affinity for the stabilization of the drug–drug complexes was mostly influenced by steric energy contributions, based mainly on multiple hydrophobic contacts with critical residues (THR22: P and SER50: Q) in such best-ranked site. Additionally, the DFT calculations revealed that the beta-blocker drug–drug complexes have a spontaneous thermodynamic stabilization following the same affinity order obtained in the docking simulations, without covalent-bond formation between both interacting beta-blockers in the best-ranked site. Lastly, experimental ultrasound density and velocity measurements were performed and allowed us to validate and corroborate the computational obtained results.

Systematic Data Analysis and Diagnostic Machine Learning Reveal Differences between Compounds with Single- and Multitarget Activity

Small molecules with multitarget activity are capable of triggering polypharmacological effects and are of high interest in drug discovery. Compared to single-target compounds, promiscuity also affects drug distribution and pharmacodynamics and alters ADMET characteristics. Features distinguishing between compounds with single- and multitarget activity are currently only little understood. On the basis of systematic data analysis, we have assembled large sets of promiscuous compounds with activity against related or functionally distinct targets and the corresponding compounds with single-target activity. Machine learning predicted promiscuous compounds with surprisingly high accuracy. Molecular similarity analysis combined with control calculations under varying conditions revealed that accurate predictions were largely determined by structural nearest-neighbor relationships between compounds from different classes. We also found that large proportions of promiscuous compounds with activity against related or unrelated targets and corresponding single-target compounds formed analog series with distinct chemical space coverage, which further rationalized the predictions. Moreover, compounds with activity against proteins from functionally distinct classes were often active against unique targets that were not covered by other promiscuous compounds. The results of our analysis revealed that nearest-neighbor effects determined the prediction of promiscuous compounds and that preferential partitioning of compounds with single- and multitarget activity into structurally distinct analog series was responsible for such effects, hence providing a rationale for the presence of different structure-promiscuity relationships.

New small-molecule compound Hu-17 inhibits estrogen biosynthesis by aromatase in human ovarian granulosa cancer cells

Estrogen-dependent cancers (breast, endometrial, and ovarian) are among the leading causes of morbidity and mortality in women worldwide. Aromatase is the main enzyme that catalyzes the biosynthesis of estrogen, which drives proliferation, and antiestrogens can inhibit the growth of these estrogen-dependent cancers. Hu-17, an aromatase inhibitor, is a novel small-molecule compound that suppresses viability of and promotes apoptosis in ovarian cancer cells. Therefore, this study aimed to predict targets of Hu-17 and assess its intracellular signaling in ovarian cancer cells. Using the Similarity Ensemble Approach software to predict the potential mechanism of Hu-17 and combining phospho-proteome arrays with western blot analysis, we observed that Hu-17 could inhibit the ERK pathway, resulting in reduced estrogen synthesis in KGN cells, a cell line derived from a patient with invasive ovarian granulosa cell carcinoma. Hu-17 reduced the expression of CYP19A1 mRNA, responsible for producing aromatase, by suppressing the phosphorylation of cAMP response element binding-1. Hu-17 also accelerated aromatase protein degradation but had no effect on aromatase activity. Therefore, Hu-17 could serve as a potential treatment for estrogen-dependent cancers albeit further investigation is warranted.

Finding New Molecular Targets of Familiar Natural Products Using In Silico Target Prediction

Natural products comprise a rich reservoir for innovative drug leads and are a constant source of bioactive compounds. To find pharmacological targets for new or already known natural products using modern computer-aided methods is a current endeavor in drug discovery. Nature's treasures, however, could be used more effectively. Yet, reliable pipelines for the large-scale target prediction of natural products are still rare. We developed an in silico workflow consisting of four independent, stand-alone target prediction tools and evaluated its performance on dihydrochalcones (DHCs)-a well-known class of natural products. Thereby, we revealed four previously unreported protein targets for DHCs, namely 5-lipoxygenase, cyclooxygenase-1, 17β-hydroxysteroid dehydrogenase 3, and aldo-keto reductase 1C3. Moreover, we provide a thorough strategy on how to perform computational target predictions and guidance on using the respective tools.

Computational/in silico methods in drug target and lead prediction

Drug-like compounds are most of the time denied approval and use owing to the unexpected clinical side effects and cross-reactivity observed during clinical trials. These unexpected outcomes resulting in significant increase in attrition rate centralizes on the selected drug targets. These targets may be disease candidate proteins or genes, biological pathways, disease-associated microRNAs, disease-related biomarkers, abnormal molecular phenotypes, crucial nodes of biological network or molecular functions. This is generally linked to several factors, including incomplete knowledge on the drug targets and unpredicted pharmacokinetic expressions upon target interaction or off-target effects. A method used to identify targets, especially for polygenic diseases, is essential and constitutes a major bottleneck in drug development with the fundamental stage being the identification and validation of drug targets of interest for further downstream processes. Thus, various computational methods have been developed to complement experimental approaches in drug discovery. Here, we present an overview of various computational methods and tools applied in predicting or validating drug targets and drug-like molecules. We provide an overview on their advantages and compare these methods to identify effective methods which likely lead to optimal results. We also explore major sources of drug failure considering the challenges and opportunities involved. This review might guide researchers on selecting the most efficient approach or technique during the computational drug discovery process.

The activities of drug inactive ingredients on biological targets

Excipients, considered "inactive ingredients," are a major component of formulated drugs and play key roles in their pharmacokinetics. Despite their pervasiveness, whether they are active on any targets has not been systematically explored. We computed the likelihood that approved excipients would bind to molecular targets. Testing in vitro revealed 25 excipient activities, ranging from low-nanomolar to high-micromolar concentration. Another 109 activities were identified by testing against clinical safety targets. In cellular models, five excipients had fingerprints predictive of system-level toxicity. Exposures of seven excipients were investigated, and in certain populations, two of these may reach levels of in vitro target potency, including brain and gut exposure of thimerosal and its major metabolite, which had dopamine D3 receptor dissociation constant K _d values of 320 and 210 nM, respectively. Although most excipients deserve their status as inert, many approved excipients may directly modulate physiologically relevant targets.

A hybrid ensemble-based technique for predicting drug-target interactions

Drug-target interaction is the intercommunication between chemical drugs and target proteins to produce any kind of change in the human body. The laboratory experiments conducted to recognize these potential intercommunications are costly and tedious. Various computational methods have been established recently, including the chemogenomic approach for identifying drug-target intercommunication, that integrates the chemical data of the drugs and the genomic properties of the proteins for identifying the interactions between them. This paper proposes a novel technique based on hybrid ensemble to predict drug target interactions. Hybrid ensembles introduce diversity in classification that helps to improve the performance of prediction. The proposed method has been evaluated by comparing the technique with state-of-the-art methods on two different databases under three cross-validation settings. The comparison clearly shows that the technique produced significant improvement in the interaction prediction.

Machine learning guided association of adverse drug reactions with in vitro target-based pharmacology

BACKGROUND

Adverse drug reactions (ADRs) are one of the leading causes of morbidity and mortality in health care. Understanding which drug targets are linked to ADRs can lead to the development of safer medicines.

METHODS

Here, we analyse in vitro secondary pharmacology of common (off) targets for 2134 marketed drugs. To associate these drugs with human ADRs, we utilized FDA Adverse Event Reports and developed random forest models that predict ADR occurrences from in vitro pharmacological profiles.

FINDINGS

By evaluating Gini importance scores of model features, we identify 221 target-ADR associations, which co-occur in PubMed abstracts to a greater extent than expected by chance. Amongst these are established relations, such as the association of in vitro hERG binding with cardiac arrhythmias, which further validate our machine learning approach. Evidence on bile acid metabolism supports our identification of associations between the Bile Salt Export Pump and renal, thyroid, lipid metabolism, respiratory tract and central nervous system disorders. Unexpectedly, our model suggests PDE3 is associated with 40 ADRs.

INTERPRETATION

These associations provide a comprehensive resource to support drug development and human biology studies.

FUNDING

This study was not supported by any formal funding bodies.

Utilizing drug-target-event relationships to unveil safety patterns in pharmacovigilance

INTRODUCTION

Signal detection is the most pivotal activity of signal management to guarantee that drugs maintain a positive risk-benefit ratio during their lifetime on the market. Signal detection is based on the systematic evaluation of available data sources, which have recently been extended in order to improve timely and comprehensive signal detection of drug safety problems.

AREAS COVERED

In recent years, attempts have been made to incorporate pharmacological data for the prediction of safety signals. Previous studies have shown that data on the pharmacological targets of drugs are predictive of post-marketing adverse events. However, current approaches limit such predictions to adverse events expected from the interaction of a drug with the main pharmacological target and do not take off-target interactions into consideration.

EXPERT OPINION

The authors propose the application of predictive modeling techniques utilizing pharmacological data from public databases for predicting drug-target-event relationships deriving from main- and off-target binding and from which potential safety signals can be deduced. Additionally, they provide an operative procedure for the identification of clinically relevant subgroups for predicted safety signals.

QSAR-derived affinity fingerprints (part 2): modeling performance for potency prediction

Affinity fingerprints report the activity of small molecules across a set of assays, and thus permit to gather information about the bioactivities of structurally dissimilar compounds, where models based on chemical structure alone are often limited, and model complex biological endpoints, such as human toxicity and in vitro cancer cell line sensitivity. Here, we propose to model in vitro compound activity using computationally predicted bioactivity profiles as compound descriptors. To this aim, we apply and validate a framework for the calculation of QSAR-derived affinity fingerprints (QAFFP) using a set of 1360 QSAR models generated using K_i, K_d, IC₅₀ and EC₅₀ data from ChEMBL database. QAFFP thus represent a method to encode and relate compounds on the basis of their similarity in bioactivity space. To benchmark the predictive power of QAFFP we assembled IC₅₀ data from ChEMBL database for 18 diverse cancer cell lines widely used in preclinical drug discovery, and 25 diverse protein target data sets. This study complements part 1 where the performance of QAFFP in similarity searching, scaffold hopping, and bioactivity classification is evaluated. Despite being inherently noisy, we show that using QAFFP as descriptors leads to errors in prediction on the test set in the ~ 0.65-0.95 pIC₅₀ units range, which are comparable to the estimated uncertainty of bioactivity data in ChEMBL (0.76-1.00 pIC₅₀ units). We find that the predictive power of QAFFP is slightly worse than that of Morgan2 fingerprints and 1D and 2D physicochemical descriptors, with an effect size in the 0.02-0.08 pIC₅₀ units range. Including QSAR models with low predictive power in the generation of QAFFP does not lead to improved predictive power. Given that the QSAR models we used to compute the QAFFP were selected on the basis of data availability alone, we anticipate better modeling results for QAFFP generated using more diverse and biologically meaningful targets. Data sets and Python code are publicly available at https://github.com/isidroc/QAFFP_regression .

Relevance of physicochemical properties and functional pharmacology data to predict the clinical safety profile of direct oral anticoagulants

Direct oral anticoagulants (DOACs) have rapidly become the drug class of choice for anticoagulation therapy in secondary care. It is known that gastrointestinal hemorrhage are potential side effects of the DOAC drug class. In this study we have investigated the relevance of molecular structure and on/off-target pharmacology as a predictor of adverse drug reactions (ADRs) for the DOAC drug class. Use of the Reaxys MedChem module allowed for data mining of all possible reported off-target effects of the DOAC class members. For the first time, the MHRA Yellow card database in combination with prescribing rates in the United Kingdom (data for n = 30 566 936 DOAC Rx (up to 2017) and ADR data n = 22 275 (up to 2018)) were used for our data comparison of DOACs. From the underlying reported data, we were able to rank the DOACs in terms of the likely adverse events we would expect to observe. We identified potential risks of ADRs based on the DOACs pharmacology including the expected GI hemorrhage, but also the unexpected risk of stroke, pulmonary embolism and kidney injury. Statistically significant (P < .001) differences were found between all DOACs and their total number of ADRs. Although the risks are small, strong statistical correlation between observed pharmacology and national ADR data is observed in three out of the five areas of concern.

Similarity-Based Methods and Machine Learning Approaches for Target Prediction in Early Drug Discovery: Performance and Scope

Computational methods for predicting the macromolecular targets of drugs and drug-like compounds have evolved as a key technology in drug discovery. However, the established validation protocols leave several key questions regarding the performance and scope of methods unaddressed. For example, prediction success rates are commonly reported as averages over all compounds of a test set and do not consider the structural relationship between the individual test compounds and the training instances. In order to obtain a better understanding of the value of ligand-based methods for target prediction, we benchmarked a similarity-based method and a random forest based machine learning approach (both employing 2D molecular fingerprints) under three testing scenarios: a standard testing scenario with external data, a standard time-split scenario, and a scenario that is designed to most closely resemble real-world conditions. In addition, we deconvoluted the results based on the distances of the individual test molecules from the training data. We found that, surprisingly, the similarity-based approach generally outperformed the machine learning approach in all testing scenarios, even in cases where queries were structurally clearly distinct from the instances in the training (or reference) data, and despite a much higher coverage of the known target space.

Identification of Repurposable Drugs and Adverse Drug Reactions for Various Courses of COVID-19 Based on Single-Cell RNA Sequencing Data

Coronavirus disease 2019 (COVID-19) has impacted almost every part of human life worldwide, posing a massive threat to human health. There is no specific drug for COVID-19, highlighting the urgent need for the development of effective therapeutics. To identify potentially repurposable drugs, we employed a systematic approach to mine candidates from U.S. FDA-approved drugs and preclinical small-molecule compounds by integrating the gene expression perturbation data for chemicals from the Library of Integrated Network-Based Cellular Signatures project with a publicly available single-cell RNA sequencing dataset from mild and severe COVID-19 patients. We identified 281 FDA-approved drugs that have the potential to be effective against SARS-CoV-2 infection, 16 of which are currently undergoing clinical trials to evaluate their efficacy against COVID-19. We experimentally tested the inhibitory effects of tyrphostin-AG-1478 and brefeldin-a on the replication of the single-stranded ribonucleic acid (ssRNA) virus influenza A virus. In conclusion, we have identified a list of repurposable anti-SARS-CoV-2 drugs using a systems biology approach.

Repositioned Drugs for Inflammatory Diseases such as Sepsis, Asthma, and Atopic Dermatitis

The process of drug discovery and drug development consumes billions of dollars to bring a new drug to the market. Drug development is time consuming and sometimes, the failure rates are high. Thus, the pharmaceutical industry is looking for a better option for new drug discovery. Drug repositioning is a good alternative technology that has demonstrated many advantages over de novo drug development, the most important one being shorter drug development timelines. In the last two decades, drug repositioning has made tremendous impact on drug development technologies. In this review, we focus on the recent advances in drug repositioning technologies and discuss the repositioned drugs used for inflammatory diseases such as sepsis, asthma, and atopic dermatitis.

Network-based prediction of drug-target interactions using an arbitrary-order proximity embedded deep forest

MOTIVATION

Systematic identification of molecular targets among known drugs plays an essential role in drug repurposing and understanding of their unexpected side effects. Computational approaches for prediction of drug-target interactions (DTIs) are highly desired in comparison to traditional experimental assays. Furthermore, recent advances of multiomics technologies and systems biology approaches have generated large-scale heterogeneous, biological networks, which offer unexpected opportunities for network-based identification of new molecular targets among known drugs.

RESULTS

In this study, we present a network-based computational framework, termed AOPEDF, an arbitrary-order proximity embedded deep forest approach, for prediction of DTIs. AOPEDF learns a low-dimensional vector representation of features that preserve arbitrary-order proximity from a highly integrated, heterogeneous biological network connecting drugs, targets (proteins) and diseases. In total, we construct a heterogeneous network by uniquely integrating 15 networks covering chemical, genomic, phenotypic and network profiles among drugs, proteins/targets and diseases. Then, we build a cascade deep forest classifier to infer new DTIs. Via systematic performance evaluation, AOPEDF achieves high accuracy in identifying molecular targets among known drugs on two external validation sets collected from DrugCentral [area under the receiver operating characteristic curve (AUROC) = 0.868] and ChEMBL (AUROC = 0.768) databases, outperforming several state-of-the-art methods. In a case study, we showcase that multiple molecular targets predicted by AOPEDF are associated with mechanism-of-action of substance abuse disorder for several marketed drugs (such as aripiprazole, risperidone and haloperidol).

AVAILABILITY AND IMPLEMENTATION

Source code and data can be downloaded from https://github.com/ChengF-Lab/AOPEDF.

Dual graph convolutional neural network for predicting chemical networks

Background

Predicting of chemical compounds is one of the fundamental tasks in bioinformatics and chemoinformatics, because it contributes to various applications in metabolic engineering and drug discovery. The recent rapid growth of the amount of available data has enabled applications of computational approaches such as statistical modeling and machine learning method. Both a set of chemical interactions and chemical compound structures are represented as graphs, and various graph-based approaches including graph convolutional neural networks have been successfully applied to chemical network prediction. However, there was no efficient method that can consider the two different types of graphs in an end-to-end manner.

Results

We give a new formulation of the chemical network prediction problem as a link prediction problem in a graph of graphs (GoG) which can represent the hierarchical structure consisting of compound graphs and an inter-compound graph. We propose a new graph convolutional neural network architecture called dual graph convolutional network that learns compound representations from both the compound graphs and the inter-compound network in an end-to-end manner.

Conclusions

Experiments using four chemical networks with different sparsity levels and degree distributions shows that our dual graph convolution approach achieves high prediction performance in relatively dense networks, while the performance becomes inferior on extremely-sparse networks.

Peptide- and Drug-Functionalized Fluorescent Quantum Dots for Enhanced Cell Internalization and Bacterial Debilitation

This report illustrates a strategy for designing a nanoconjugate derived vector that efficiently delivers antimicrobial drug directly into bacterial cells. The nanoconjugate comprises of negatively charged CDTe@CdS quantum dots (QDs) with its surface functionalized using cationic BP-100 (KKLFKKILKYL-amide), a known cell-penetrating peptide (CPP), via electrostatic approach. The interactions between QD and CPP in QD-functionalized CPPs (QD-CPP) have been well analyzed using fluorescence spectroscopy, gel electrophoresis, and ζ-potential analysis. The QD-CPP conjugate was internalized into Gram negative (Escherichia coli) as well as Gram positive (Staphylococcus aureus) bacterial strains with confocal studies exhibiting a strong signal in tested microorganisms. Further, to check the applicability of QD-CPP conjugate as a delivery vector for generating an effective therapeutics, ampicillin molecules were conjugated on QD-CPP surface to generate QD-CPP-Amp conjugate. The CPP and drug molecules on the surface of QDs were well quantified using high-performance liquid chromatography (HPLC) data. It was observed that the internalization and bacterial debilitation of the QD-CPP-Amp conjugate is 2- to 4-fold effective as compared to that of bare ampicillin. The morphological changes to the bacterial cells upon the treatment with QD-CPP-Amp conjugates were noted with no cytotoxic effect on tested mammalian cell lines. The results inferred that the proposed QD-CPP vector provides a targeted and proficient approach for cellular internalization of cargo (drug) in bacterial cells with effective tracking through florescent QDs.

A compound attributes-based predictive model for drug induced liver injury in humans

Drug induced liver injury (DILI) is one of the key safety concerns in drug development. To assess the likelihood of drug candidates with potential adverse reactions of liver, we propose a compound attributes-based approach to predicting hepatobiliary disorders that are routinely reported to US Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS). Specifically, we developed a support vector machine (SVM) model with recursive feature extraction, based on physicochemical and structural properties of compounds as model input. Cross validation demonstrates that the predictive model has a robust performance with averaged 70% of both sensitivity and specificity over 500 trials. An independent validation was performed on public benchmark drugs and the results suggest potential utility of our model for identifying safety alerts. This in silico approach, upon further validation, would ultimately be implemented, together with other in vitro safety assays, for screening compounds early in drug development.

Limitations of Animal Studies for Predicting Toxicity in Clinical Trials: Part 2: Potential Alternatives to the Use of Animals in Preclinical Trials

Dramatically rising costs in drug development are in large part because of the high failure rates in clinical phase trials. The poor correlation of animal studies to human toxicity and efficacy have led many developers to question the value of requiring animal studies in determining which drugs should enter in-human trials. Part 1 of this 2-part series examined some of the data regarding the lack of concordance between animal toxicity studies and human trials, as well as some of the potential reasons behind it. This second part of the series focuses on some alternatives to animal trials (hereafter referred to as animal research) as well as current regulatory discussions and developments regarding such alternatives.

Elucidating Compound Mechanism of Action and Predicting Cytotoxicity Using Machine Learning Approaches, Taking Prediction Confidence into Account

The modes of action (MoAs) of drugs frequently are unknown, because many are small molecules initially identified from phenotypic screens, giving rise to the need to elucidate their MoAs. In addition, the high attrition rate for candidate drugs in preclinical studies due to intolerable toxicity has motivated the development of computational approaches to predict drug candidate (cyto)toxicity as early as possible in the drug-discovery process. Here, we provide detailed instructions for capitalizing on bioactivity predictions to elucidate the MoAs of small molecules and infer their underlying phenotypic effects. We illustrate how these predictions can be used to infer the underlying antidepressive effects of marketed drugs. We also provide the necessary functionalities to model cytotoxicity data using single and ensemble machine-learning algorithms. Finally, we give detailed instructions on how to calculate confidence intervals for individual predictions using the conformal prediction framework. © 2019 by John Wiley & Sons, Inc.

Glutamine transporters as pharmacological targets: From function to drug design

Among the different targets of administered drugs, there are membrane transporters that play also a role in drug delivery and disposition. Moreover, drug-transporter interactions are responsible for off-target effects of drugs underlying their toxicity. The improvement of the drug design process is subjected to the identification of those membrane transporters mostly relevant for drug absorption, delivery and side effect production. A peculiar group of proteins with great relevance to pharmacology is constituted by the membrane transporters responsible for managing glutamine traffic in different body districts. The interest around glutamine metabolism lies in its physio-pathological role; glutamine is considered a conditionally essential amino acid because highly proliferative cells have an increased request of glutamine that cannot be satisfied only by endogenous synthesis. Then, glutamine transporters provide cells with this special nutrient. Among the glutamine transporters, SLC1A5, SLC6A14, SLC6A19, SLC7A5, SLC7A8 and some members of SLC38 family are the best characterized, so far, in both physiological and pathological conditions. Few 3D structures have been solved by CryoEM; other structural data on these transporters have been obtained by computational analysis. Interactions with drugs have been described for several transporters of this group. For some of them, the studies are at an advanced stage, for others, the studies are still in nuce and novel biochemical findings open intriguing perspectives.

Deciphering the enzymatic target of a new family of antischistosomal agents bearing a quinazoline scaffold using complementary computational tools

A previous phenotypic screening campaign led to the identification of a quinazoline derivative with promising in vitro activity against Schistosoma mansoni. Follow-up studies of the antischistosomal potential of this candidate are presented here. The in vivo studies in a S. mansoni mouse model show a significant reduction of total worms and a complete disappearance of immature eggs when administered concomitantly with praziquantel in comparison with the administration of praziquantel alone. This fact is of utmost importance because eggs are responsible for the pathology and transmission of the disease. Subsequently, the chemical optimisation of the structure in order to improve the metabolic stability of the parent compound was carried out leading to derivatives with improved drug-like properties. Additionally, the putative target of this new class of antischistosomal compounds was envisaged by using computational tools and the binding mode to the target enzyme, aldose reductase, was proposed.

Associating 197 Chinese herbal medicine with drug targets and diseases using the similarity ensemble approach

Chinese herbal medicine (CHM) addresses complex diseases through polypharmacological interactions. However, systematic studies of herbal medicine pharmacology remain challenging due to the complexity of CHM ingredients and their interactions with various targets. In this study, we aim to address this challenge with computational approaches. We investigated the herb-target-disease associations of 197 commonly prescribed CHMs using the similarity ensemble approach and DisGeNET database. We demonstrated that this method can be applied to associate herbs with their putative targets. In the case study of three well-known herbs, Radix Glycyrrhizae, Flos Lonicerae, and Rhizoma Coptidis, approximately 70% of the predicted targets were supported by scientific literature. By linking 406 targets to 2439 annotated diseases, we further analyzed the pharmacological functions of 197 herbs. Finally, we proposed a strategy of target-oriented herbal formula design and illustrated the target profiles for four common chronic diseases, namely, Alzheimer's disease, depressive disorder, hypertensive disease, and non-insulin-dependent diabetes mellitus. This computational approach holds great potential in the target identification of herbs, understanding the molecular mechanisms of CHM, and designing novel herbal formulas.

The kinase polypharmacology landscape of clinical PARP inhibitors

Polypharmacology plays an important role in defining response and adverse effects of drugs. For some mechanisms, experimentally mapping polypharmacology is commonplace, although this is typically done within the same protein class. Four PARP inhibitors have been approved by the FDA as cancer therapeutics, yet a precise mechanistic rationale to guide clinicians on which to choose for a particular patient is lacking. The four drugs have largely similar PARP family inhibition profiles, but several differences at the molecular and clinical level have been reported that remain poorly understood. Here, we report the first comprehensive characterization of the off-target kinase landscape of four FDA-approved PARP drugs. We demonstrate that all four PARP inhibitors have a unique polypharmacological profile across the kinome. Niraparib and rucaparib inhibit DYRK1s, CDK16 and PIM3 at clinically achievable, submicromolar concentrations. These kinases represent the most potently inhibited off-targets of PARP inhibitors identified to date and should be investigated further to clarify their potential implications for efficacy and safety in the clinic. Moreover, broad kinome profiling is recommended for the development of PARP inhibitors as PARP-kinase polypharmacology could potentially be exploited to modulate efficacy and side-effect profiles.

Utility of Physicochemical Properties for the Prediction of Toxicological Outcomes: Takeda Perspective

The role that physicochemical properties play toward increasing the likelihood of toxicity findings in in vivo studies has been well reported, albeit sometimes with different conclusions. We decided to understand the role that physicochemical properties play toward the prediction of in vivo toxicological outcomes for Takeda chemistry using 284 internal compounds. In support of the previously reported "3/75 rule", reducing lipophilicity of molecules decreases toxicity odds noticeably; however, we also found that the trend of toxicity odds is different between compounds classified by their ionization state. For basic molecules, the odds of in vivo toxicity outcomes were significantly impacted by both lipophilicity and polar surface area, whereas neutral molecules were impacted less so. Through an analysis of several project-related compounds, we herein demonstrate that the utilization of the 3/75 rule coupled with consideration of ionization state is a rational strategy for medicinal chemistry design of safer drugs.

Drug-target interaction prediction with tree-ensemble learning and output space reconstruction

Background

Computational prediction of drug-target interactions (DTI) is vital for drug discovery. The experimental identification of interactions between drugs and target proteins is very onerous. Modern technologies have mitigated the problem, leveraging the development of new drugs. However, drug development remains extremely expensive and time consuming. Therefore, in silico DTI predictions based on machine learning can alleviate the burdensome task of drug development. Many machine learning approaches have been proposed over the years for DTI prediction. Nevertheless, prediction accuracy and efficiency are persisting problems that still need to be tackled. Here, we propose a new learning method which addresses DTI prediction as a multi-output prediction task by learning ensembles of multi-output bi-clustering trees (eBICT) on reconstructed networks. In our setting, the nodes of a DTI network (drugs and proteins) are represented by features (background information). The interactions between the nodes of a DTI network are modeled as an interaction matrix and compose the output space in our problem. The proposed approach integrates background information from both drug and target protein spaces into the same global network framework.

Results

We performed an empirical evaluation, comparing the proposed approach to state of the art DTI prediction methods and demonstrated the effectiveness of the proposed approach in different prediction settings. For evaluation purposes, we used several benchmark datasets that represent drug-protein networks. We show that output space reconstruction can boost the predictive performance of tree-ensemble learning methods, yielding more accurate DTI predictions.

Conclusions

We proposed a new DTI prediction method where bi-clustering trees are built on reconstructed networks. Building tree-ensemble learning models with output space reconstruction leads to superior prediction results, while preserving the advantages of tree-ensembles, such as scalability, interpretability and inductive setting.

DeepCPI: A Deep Learning-based Framework for Large-scale in silico Drug Screening

Accurate identification of compound–protein interactions (CPIs) in silico may deepen our understanding of the underlying mechanisms of drug action and thus remarkably facilitate drug discovery and development. Conventional similarity- or docking-based computational methods for predicting CPIs rarely exploit latent features from currently available large-scale unlabeled compound and protein data and often limit their usage to relatively small-scale datasets. In the present study, we propose DeepCPI, a novel general and scalable computational framework that combines effective feature embedding (a technique of representation learning) with powerful deep learning methods to accurately predict CPIs at a large scale. DeepCPI automatically learns the implicit yet expressive low-dimensional features of compounds and proteins from a massive amount of unlabeled data. Evaluations of the measured CPIs in large-scale databases, such as ChEMBL and BindingDB, as well as of the known drug–target interactions from DrugBank, demonstrated the superior predictive performance of DeepCPI. Furthermore, several interactions among small-molecule compounds and three G protein-coupled receptor targets (glucagon-like peptide-1 receptor, glucagon receptor, and vasoactive intestinal peptide receptor) predicted using DeepCPI were experimentally validated. The present study suggests that DeepCPI is a useful and powerful tool for drug discovery and repositioning. The source code of DeepCPI can be downloaded from https://github.com/FangpingWan/DeepCPI.

A Novel Approach for Drug-Target Interactions Prediction Based on Multimodal Deep Autoencoder

Drug targets are biomacromolecules or biomolecular structures that bind to specific drugs and produce therapeutic effects. Therefore, the prediction of drug-target interactions (DTIs) is important for disease therapy. Incorporating multiple similarity measures for drugs and targets is of essence for improving the accuracy of prediction of DTIs. However, existing studies with multiple similarity measures ignored the global structure information of similarity measures, and required manual extraction features of drug-target pairs, ignoring the non-linear relationship among features. In this paper, we proposed a novel approach MDADTI for DTIs prediction based on MDA. MDADTI applied random walk with restart method and positive pointwise mutual information to calculate the topological similarity matrices of drugs and targets, capturing the global structure information of similarity measures. Then, MDADTI applied multimodal deep autoencoder to fuse multiple topological similarity matrices of drugs and targets, automatically learned the low-dimensional features of drugs and targets, and applied deep neural network to predict DTIs. The results of 5-repeats of 10-fold cross-validation under three different cross-validation settings indicated that MDADTI is superior to the other four baseline methods. In addition, we validated the predictions of the MDADTI in six drug-target interactions reference databases, and the results showed that MDADTI can effectively identify unknown DTIs.

Machine learning approaches and databases for prediction of drug-target interaction: a survey paper

The task of predicting the interactions between drugs and targets plays a key role in the process of drug discovery. There is a need to develop novel and efficient prediction approaches in order to avoid costly and laborious yet not-always-deterministic experiments to determine drug–target interactions (DTIs) by experiments alone. These approaches should be capable of identifying the potential DTIs in a timely manner. In this article, we describe the data required for the task of DTI prediction followed by a comprehensive catalog consisting of machine learning methods and databases, which have been proposed and utilized to predict DTIs. The advantages and disadvantages of each set of methods are also briefly discussed. Lastly, the challenges one may face in prediction of DTI using machine learning approaches are highlighted and we conclude by shedding some lights on important future research directions.

Phosphine-Activated Lysine Analogues for Fast Chemical Control of Protein Subcellular Localization and Protein SUMOylation

The Staudinger reduction and its variants have exceptional compatibility with live cells but can be limited by slow kinetics. Herein we report new small-molecule triggers that turn on proteins through a Staudinger reduction/self-immolation cascade with substantially improved kinetics and yields. We achieved this through site-specific incorporation of a new set of azidobenzyloxycarbonyl lysine derivatives in mammalian cells. This approach allowed us to activate proteins by adding a nontoxic, bioorthogonal phosphine trigger. We applied this methodology to control a post-translational modification (SUMOylation) in live cells, using native modification machinery. This work significantly improves the rate, yield, and tunability of the Staudinger reduction-based activation, paving the way for its application in other proteins and organisms.

Target identification among known drugs by deep learning from heterogeneous networks

Without foreknowledge of the complete drug target information, development of promising and affordable approaches for effective treatment of human diseases is challenging. Here, we develop deepDTnet, a deep learning methodology for new target identification and drug repurposing in a heterogeneous drug-gene-disease network embedding 15 types of chemical, genomic, phenotypic, and cellular network profiles. Trained on 732 U.S. Food and Drug Administration-approved small molecule drugs, deepDTnet shows high accuracy (the area under the receiver operating characteristic curve = 0.963) in identifying novel molecular targets for known drugs, outperforming previously published state-of-the-art methodologies. We then experimentally validate that deepDTnet-predicted topotecan (an approved topoisomerase inhibitor) is a new, direct inhibitor (IC50 = 0.43 μM) of human retinoic-acid-receptor-related orphan receptor-gamma t (ROR-γt). Furthermore, by specifically targeting ROR-γt, topotecan reveals a potential therapeutic effect in a mouse model of multiple sclerosis. In summary, deepDTnet offers a powerful network-based deep learning methodology for target identification to accelerate drug repurposing and minimize the translational gap in drug development.

Biological representation of chemicals using latent target interaction profile

Background

Computational prediction of a phenotypic response upon the chemical perturbation on a biological system plays an important role in drug discovery, and many other applications. Chemical fingerprints are a widely used feature to build machine learning models. However, the fingerprints that are derived from chemical structures ignore the biological context, thus, they suffer from several problems such as the activity cliff and curse of dimensionality. Fundamentally, the chemical modulation of biological activities is a multi-scale process. It is the genome-wide chemical-target interactions that modulate chemical phenotypic responses. Thus, the genome-scale chemical-target interaction profile will more directly correlate with in vitro and in vivo activities than the chemical structure. Nevertheless, the scope of direct application of the chemical-target interaction profile is limited due to the severe incompleteness, biasness, and noisiness of bioassay data.

Results

To address the aforementioned problems, we developed a novel chemical representation method: Latent Target Interaction Profile (LTIP). LTIP embeds chemicals into a low dimensional continuous latent space that represents genome-scale chemical-target interactions. Subsequently LTIP can be used as a feature to build machine learning models. Using the drug sensitivity of cancer cell lines as a benchmark, we have shown that the LTIP robustly outperforms chemical fingerprints regardless of machine learning algorithms. Moreover, the LTIP is complementary with the chemical fingerprints. It is possible for us to combine LTIP with other fingerprints to further improve the performance of bioactivity prediction.

Conclusions

Our results demonstrate the potential of LTIP in particular and multi-scale modeling in general in predictive modeling of chemical modulation of biological activities.