QSAR Modeling and Prediction of Drug-Drug Interactions

Comprehensive Review of Drug-Drug Interaction Prediction Based on Machine Learning: Current Status, Challenges, and Opportunities

Detecting drug-drug interactions (DDIs) is an essential step in drug development and drug administration. Given the shortcomings of current experimental methods, the machine learning (ML) approach has become a reliable alternative, attracting extensive attention from the academic and industrial fields. With the rapid development of computational science and the growing popularity of cross-disciplinary research, a large number of DDI prediction studies based on ML methods have been published in recent years. To give an insight into the current situation and future direction of DDI prediction research, we systemically review these studies from three aspects: (1) the classic DDI databases, mainly including databases of drugs, side effects, and DDI information; (2) commonly used drug attributes, which focus on chemical, biological, and phenotypic attributes for representing drugs; (3) popular ML approaches, such as shallow learning-based, deep learning-based, recommender system-based, and knowledge graph-based methods for DDI detection. For each section, related studies are described, summarized, and compared, respectively. In the end, we conclude the research status of DDI prediction based on ML methods and point out the existing issues, future challenges, potential opportunities, and subsequent research direction.

Quantitative Structure-Activity Relationship in the Series of 5-Ethyluridine, N2-Guanine, and 6-Oxopurine Derivatives with Pronounced Anti-Herpetic Activity

A quantitative analysis of the relationship between the structure and inhibitory activity against the herpes simplex virus thymidine kinase (HSV-TK) was performed for the series of 5-ethyluridine, N2-guanine, and 6-oxopurines derivatives with pronounced anti-herpetic activity (IC50 = 0.09 ÷ 160,000 μmol/L) using the GUSAR 2019 software. On the basis of the MNA and QNA descriptors and whole-molecule descriptors using the self-consistent regression, 12 statistically significant consensus models for predicting numerical pIC50 values were constructed. These models demonstrated high predictive accuracy for the training and test sets. Molecular fragments of HSV-1 and HSV-2 TK inhibitors that enhance or diminish the anti-herpetic activity are considered. Virtual screening of the ChEMBL database using the developed QSAR models revealed 42 new effective HSV-1 and HSV-2 TK inhibitors. These compounds are promising for further research. The obtained data open up new opportunities for developing novel effective inhibitors of TK.

Exploration of phytochemical compounds against Marburg virus using QSAR, molecular dynamics, and free energy landscape

Marburg virus disease (MVD) is caused by the Marburg virus, a one-of-a-kind zoonotic RNA virus from the genus Filovirus. Thus, this current study employed AI-based QSAR and molecular docking-based virtual screening for identifying potential binders against the target protein (nucleoprotein (NP)) of the Marburg virus. A total of 2727 phytochemicals were used for screening, out of which the top three compounds (74977521, 90470472, and 11953909) were identified based on their predicted bioactivity (pIC50) and binding score (< - 7.4 kcal/mol). Later, MD simulation in triplicates and trajectory analysis were performed which showed that 11953909 and 74977521 had the most stable and consistent complex formations and had the most significant interactions with the highest number of hydrogen bonds. PCA (principal component analysis) and FEL (free energy landscape) analysis indicated that these compounds had favourable energy states for most of the conformations. The total binding free energy of the compounds using the MM/GBSA technique showed that 11953909 (ΔGTOTAL = - 30.78 kcal/mol) and 74977521 (ΔGTOTAL = - 30 kcal/mol) had the highest binding affinity with the protein. Overall, this in silico pipeline proposed that the phytochemicals 11953909 and 74977521 could be the possible binders of NP. This study aimed to find phytochemicals inhibiting the protein's function and potentially treating MVD.

Revolutionizing Medicinal Chemistry: The Application of Artificial Intelligence (AI) in Early Drug Discovery

Artificial intelligence (AI) has permeated various sectors, including the pharmaceutical industry and research, where it has been utilized to efficiently identify new chemical entities with desirable properties. The application of AI algorithms to drug discovery presents both remarkable opportunities and challenges. This review article focuses on the transformative role of AI in medicinal chemistry. We delve into the applications of machine learning and deep learning techniques in drug screening and design, discussing their potential to expedite the early drug discovery process. In particular, we provide a comprehensive overview of the use of AI algorithms in predicting protein structures, drug-target interactions, and molecular properties such as drug toxicity. While AI has accelerated the drug discovery process, data quality issues and technological constraints remain challenges. Nonetheless, new relationships and methods have been unveiled, demonstrating AI's expanding potential in predicting and understanding drug interactions and properties. For its full potential to be realized, interdisciplinary collaboration is essential. This review underscores AI's growing influence on the future trajectory of medicinal chemistry and stresses the importance of ongoing synergies between computational and domain experts.

Virtual patients, digital twins and causal disease models: paving the ground for in silico clinical trials

Computational models are being explored to simulate in silico the efficacy and safety of drug candidates and medical devices. Disease models that are based on patients' profiling data are being produced to represent interactomes of genes or proteins and to infer causality in the pathophysiology {AuQ: Edit OK?}, which makes it possible to mimic the impact of drugs on relevant targets. Virtual patients designed from medical records as well as digital twins were generated to simulate specific organs and to predict treatment efficacy at the individual patient level {AuQ: Edit OK?}. As the acceptance of digital evidence by regulators grows, predictive artificial intelligence (AI)-based models will support the design of confirmatory trials in humans and will accelerate the development of efficient drugs and medical devices.

Artificial intelligence and machine-learning approaches in structure and ligand-based discovery of drugs affecting central nervous system

CNS disorders are indications with a very high unmet medical needs, relatively smaller number of available drugs, and a subpar satisfaction level among patients and caregiver. Discovery of CNS drugs is extremely expensive affair with its own unique challenges leading to extremely high attrition rates and low efficiency. With explosion of data in information age, there is hardly any aspect of life that has not been touched by data driven technologies such as artificial intelligence (AI) and machine learning (ML). Drug discovery is no exception, emergence of big data via genomic, proteomic, biological, and chemical technologies has driven pharmaceutical giants to collaborate with AI oriented companies to revolutionise drug discovery, with the goal of increasing the efficiency of the process. In recent years many examples of innovative applications of AI and ML techniques in CNS drug discovery has been reported. Research on therapeutics for diseases such as schizophrenia, Alzheimer's and Parkinsonism has been provided with a new direction and thrust from these developments. AI and ML has been applied to both ligand-based and structure-based drug discovery and design of CNS therapeutics. In this review, we have summarised the general aspects of AI and ML from the perspective of drug discovery followed by a comprehensive coverage of the recent developments in the applications of AI/ML techniques in CNS drug discovery.

Machine learning to predict metabolic drug interactions related to cytochrome P450 isozymes

Drug–drug interaction (DDI) often causes serious adverse reactions and thus results in inestimable economic and social loss. Currently, comprehensive DDI evaluation has become a major challenge in pharmaceutical research due to the time-consuming and costly process of the experimental assessment and it is of high necessity to develop effective in silico methods to predict and evaluate DDIs accurately and efficiently. In this study, based on a large number of substrates and inhibitors related to five important CYP450 isozymes (CYP1A2, CYP2C9, CYP2C19, CYP2D6 and CYP3A4), a series of high-performance predictive models for metabolic DDIs were constructed by two machine learning methods (random forest and XGBoost) and 4 different types of descriptors (MOE_2D, CATS, ECFP4 and MACCS). To reduce the uncertainty of individual models, the consensus method was applied to yield more reliable predictions. A series of evaluations illustrated that the consensus models were more reliable and robust for the DDI predictions of new drug combination. For the internal validation, the whole prediction accuracy and AUC value of the DDI models were around 0.8 and 0.9, respectively. When it was applied to the external datasets, the model accuracy was 0.793 and 0.795 for multi-level validation and external validation, respectively. Furthermore, we also compared our model with some recently published tools and then applied the final model to predict FDA-approved drugs and proposed 54,013 possible drug pairs with potential DDIs. In summary, we developed a powerful DDI predictive model from the perspective of the CYP450 enzyme family and it will help a lot in the future drug development and clinical pharmacy research.

Dietary Inhibitors of CYP3A4 Are Revealed Using Virtual Screening by Using a New Deep-Learning Classifier

CYP3A4 is the main human enzyme responsible for phase I metabolism of dietary compounds, prescribed drugs and xenobiotics, steroid hormones, and bile acids. The inhibition of CYP3A4 activity might impair physiological mechanisms, including the endocrine system and response to drug admission. Here, we aimed to discover new CYP3A4 inhibitors from food and dietary supplements. A deep-learning model was built that classifies compounds as either an inhibitor or noninhibitor, with a high specificity of 0.997. We used this classifier to virtually screen ∼60,000 dietary compounds. Of the 115 identified potential inhibitors, only 31 were previously suggested. Many herbals, as predicted here, might cause impaired metabolism of drugs, and endogenous hormones and bile acids. Additionally, by applying Lipinski's rules of five, 17 compounds were also classified as potential intestine local inhibitors. New CYP3A4 inhibitors predicted by the model, bilobetin and picropodophyllin, were assayed in vitro.

Relationships between the Structure and Severe Drug-Induced Liver Injury for Low, Medium, and High Doses of Drugs

Assessment of structure-activity relationships (SARs) for predicting severe drug-induced liver injury (DILI) is essential since in vivo and in vitro preclinical methods cannot detect many druglike compounds disrupting liver functions. To date, plenty of SAR models for the prediction of DILI have been developed; however, none of them considered the route of drug administration and daily dose, which may introduce significant bias into prediction results. We have created a dataset of 617 drugs with parenteral and oral administration routes and consistent information on DILI severity. We have found a clear relationship between route, dose, and DILI severity. According to SAR, nearly 40% of moderate- and non-DILI-causing drugs would cause severe DILI if they were administered at high oral doses. We have proposed the following approach to predict severe DILI. New compounds recommended to be used at low oral doses (<∼10 mg daily), or parenterally, can be considered not causing severe DILI. DILI for compounds administered at medium oral doses (∼10-100 mg daily; 22.2% of drugs under consideration) can be considered unpredictable because reasonable SAR models were not obtained due to the small size and heterogeneity of the corresponding dataset. The DILI potential of the compounds recommended to be used at high oral doses (more than ∼100 mg daily) can be estimated using SAR modeling. The balanced accuracy of the approach calculated by a 10-fold cross-validation procedure is 0.803. The developed approach can be used to estimate severe DILI for druglike compounds proposed to use at low and high oral doses or parenterally at the early stages of drug development.

Hybrid In Silico Approach Reveals Novel Inhibitors of Multiple SARS-CoV-2 Variants

The National Center for Advancing Translational Sciences (NCATS) has been actively generating SARS-CoV-2 high-throughput screening data and disseminates it through the OpenData Portal (https://opendata.ncats.nih.gov/covid19/). Here, we provide a hybrid approach that utilizes NCATS screening data from the SARS-CoV-2 cytopathic effect reduction assay to build predictive models, using both machine learning and pharmacophore-based modeling. Optimized models were used to perform two iterative rounds of virtual screening to predict small molecules active against SARS-CoV-2. Experimental testing with live virus provided 100 (∼16% of predicted hits) active compounds (efficacy > 30%, IC50 ≤ 15 μM). Systematic clustering analysis of active compounds revealed three promising chemotypes which have not been previously identified as inhibitors of SARS-CoV-2 infection. Further investigation resulted in the identification of allosteric binders to host receptor angiotensin-converting enzyme 2; these compounds were then shown to inhibit the entry of pseudoparticles bearing spike protein of wild-type SARS-CoV-2, as well as South African B.1.351 and UK B.1.1.7 variants.

Deep learning identifies synergistic drug combinations for treating COVID-19

Effective treatments for COVID-19 are urgently needed. However, discovering single-agent therapies with activity against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been challenging. Combination therapies play an important role in antiviral therapies, due to their improved efficacy and reduced toxicity. Recent approaches have applied deep learning to identify synergistic drug combinations for diseases with vast preexisting datasets, but these are not applicable to new diseases with limited combination data, such as COVID-19. Given that drug synergy often occurs through inhibition of discrete biological targets, here we propose a neural network architecture that jointly learns drug-target interaction and drug-drug synergy. The model consists of two parts: a drug-target interaction module and a target-disease association module. This design enables the model to utilize drug-target interaction data and single-agent antiviral activity data, in addition to available drug-drug combination datasets, which may be small in nature. By incorporating additional biological information, our model performs significantly better in synergy prediction accuracy than previous methods with limited drug combination training data. We empirically validated our model predictions and discovered two drug combinations, remdesivir and reserpine as well as remdesivir and IQ-1S, which display strong antiviral SARS-CoV-2 synergy in vitro. Our approach, which was applied here to address the urgent threat of COVID-19, can be readily extended to other diseases for which a dearth of chemical-chemical combination data exists.

A critical overview of computational approaches employed for COVID-19 drug discovery

COVID-19 has resulted in huge numbers of infections and deaths worldwide and brought the most severe disruptions to societies and economies since the Great Depression. Massive experimental and computational research effort to understand and characterize the disease and rapidly develop diagnostics, vaccines, and drugs has emerged in response to this devastating pandemic and more than 130 000 COVID-19-related research papers have been published in peer-reviewed journals or deposited in preprint servers. Much of the research effort has focused on the discovery of novel drug candidates or repurposing of existing drugs against COVID-19, and many such projects have been either exclusively computational or computer-aided experimental studies. Herein, we provide an expert overview of the key computational methods and their applications for the discovery of COVID-19 small-molecule therapeutics that have been reported in the research literature. We further outline that, after the first year the COVID-19 pandemic, it appears that drug repurposing has not produced rapid and global solutions. However, several known drugs have been used in the clinic to cure COVID-19 patients, and a few repurposed drugs continue to be considered in clinical trials, along with several novel clinical candidates. We posit that truly impactful computational tools must deliver actionable, experimentally testable hypotheses enabling the discovery of novel drugs and drug combinations, and that open science and rapid sharing of research results are critical to accelerate the development of novel, much needed therapeutics for COVID-19.

HIFs: New arginine mimic inhibitors of the Hv1 channel with improved VSD-ligand interactions

The human voltage-gated proton channel Hv1 is a drug target for cancer, ischemic stroke, and neuroinflammation. It resides on the plasma membrane and endocytic compartments of a variety of cell types, where it mediates outward proton movement and regulates the activity of NOX enzymes. Its voltage-sensing domain (VSD) contains a gated and proton-selective conduction pathway, which can be blocked by aromatic guanidine derivatives such as 2-guanidinobenzimidazole (2GBI). Mutation of Hv1 residue F150 to alanine (F150A) was previously found to increase 2GBI apparent binding affinity more than two orders of magnitude. Here, we explore the contribution of aromatic interactions between the inhibitor and the channel in the presence and absence of the F150A mutation, using a combination of electrophysiological recordings, classic mutagenesis, and site-specific incorporation of fluorinated phenylalanines via nonsense suppression methodology. Our data suggest that the increase in apparent binding affinity is due to a rearrangement of the binding site allowed by the smaller residue at position 150. We used this information to design new arginine mimics with improved affinity for the nonrearranged binding site of the wild-type channel. The new compounds, named “Hv1 Inhibitor Flexibles” (HIFs), consist of two “prongs,” an aminoimidazole ring, and an aromatic group connected by extended flexible linkers. Some HIF compounds display inhibitory properties that are superior to those of 2GBI, thus providing a promising scaffold for further development of high-affinity Hv1 inhibitors.

Simplex representation of molecular structure as universal QSAR/QSPR tool

We review the development and application of the Simplex approach for the solution of various QSAR/QSPR problems. The general concept of the simplex method and its varieties are described. The advantages of utilizing this methodology, especially for the interpretation of QSAR/QSPR models, are presented in comparison to other fragmentary methods of molecular structure representation. The utility of SiRMS is demonstrated not only in the standard QSAR/QSPR applications, but also for mixtures, polymers, materials, and other complex systems. In addition to many different types of biological activity (antiviral, antimicrobial, antitumor, psychotropic, analgesic, etc.), toxicity and bioavailability, the review examines the simulation of important properties, such as water solubility, lipophilicity, as well as luminescence, and thermodynamic properties (melting and boiling temperatures, critical parameters, etc.). This review focuses on the stereochemical description of molecules within the simplex approach and details the possibilities of universal molecular stereo-analysis and stereochemical configuration description, along with stereo-isomerization mechanism and molecular fragment "topography" identification.

Artificial intelligence and machine learning-aided drug discovery in central nervous system diseases: State-of-the-arts and future directions

Neurological disorders significantly outnumber diseases in other therapeutic areas. However, developing drugs for central nervous system (CNS) disorders remains the most challenging area in drug discovery, accompanied with the long timelines and high attrition rates. With the rapid growth of biomedical data enabled by advanced experimental technologies, artificial intelligence (AI) and machine learning (ML) have emerged as an indispensable tool to draw meaningful insights and improve decision making in drug discovery. Thanks to the advancements in AI and ML algorithms, now the AI/ML-driven solutions have an unprecedented potential to accelerate the process of CNS drug discovery with better success rate. In this review, we comprehensively summarize AI/ML-powered pharmaceutical discovery efforts and their implementations in the CNS area. After introducing the AI/ML models as well as the conceptualization and data preparation, we outline the applications of AI/ML technologies to several key procedures in drug discovery, including target identification, compound screening, hit/lead generation and optimization, drug response and synergy prediction, de novo drug design, and drug repurposing. We review the current state-of-the-art of AI/ML-guided CNS drug discovery, focusing on blood-brain barrier permeability prediction and implementation into therapeutic discovery for neurological diseases. Finally, we discuss the major challenges and limitations of current approaches and possible future directions that may provide resolutions to these difficulties.

Synergistic and Antagonistic Drug Combinations against SARS-CoV-2

Antiviral drug development for coronavirus disease 2019 (COVID-19) is occurring at an unprecedented pace, yet there are still limited therapeutic options for treating this disease. We hypothesized that combining drugs with independent mechanisms of action could result in synergy against SARS-CoV-2, thus generating better antiviral efficacy. Using in silico approaches, we prioritized 73 combinations of 32 drugs with potential activity against SARS-CoV-2 and then tested them in vitro. Sixteen synergistic and eight antagonistic combinations were identified; among 16 synergistic cases, combinations of the US Food and Drug Administration (FDA)-approved drug nitazoxanide with remdesivir, amodiaquine, or umifenovir were most notable, all exhibiting significant synergy against SARS-CoV-2 in a cell model. However, the combination of remdesivir and lysosomotropic drugs, such as hydroxychloroquine, demonstrated strong antagonism. Overall, these results highlight the utility of drug repurposing and preclinical testing of drug combinations for discovering potential therapies to treat COVID-19.

Advancing computer-aided drug discovery (CADD) by big data and data-driven machine learning modeling

Advancing a new drug to market requires substantial investments in time as well as financial resources. Crucial bioactivities for drug candidates, including their efficacy, pharmacokinetics (PK), and adverse effects, need to be investigated during drug development. With advancements in chemical synthesis and biological screening technologies over the past decade, a large amount of biological data points for millions of small molecules have been generated and are stored in various databases. These accumulated data, combined with new machine learning (ML) approaches, such as deep learning, have shown great potential to provide insights into relevant chemical structures to predict in vitro, in vivo, and clinical outcomes, thereby advancing drug discovery and development in the big data era.

Discovery of Synergistic and Antagonistic Drug Combinations against SARS-CoV-2 In Vitro

COVID-19 is undoubtedly the most impactful viral disease of the current century, afflicting millions worldwide. As yet, there is not an approved vaccine, as well as limited options from existing drugs for treating this disease. We hypothesized that combining drugs with independent mechanisms of action could result in synergy against SARS-CoV-2. Using in silico approaches, we prioritized 73 combinations of 32 drugs with potential activity against SARS-CoV-2 and then tested them in vitro . Overall, we identified 16 synergistic and 8 antagonistic combinations, 4 of which were both synergistic and antagonistic in a dose-dependent manner. Among the 16 synergistic cases, combinations of nitazoxanide with three other compounds (remdesivir, amodiaquine and umifenovir) were the most notable, all exhibiting significant synergy against SARS-CoV-2. The combination of nitazoxanide, an FDA-approved drug, and remdesivir, FDA emergency use authorization for the treatment of COVID-19, demonstrate a strong synergistic interaction. Notably, the combination of remdesivir and hydroxychloroquine demonstrated strong antagonism. Overall, our results emphasize the importance of both drug repurposing and preclinical testing of drug combinations for potential therapeutic use against SARS-CoV-2 infections.

QSAR without borders

Prediction of chemical bioactivity and physical properties has been one of the most important applications of statistical and more recently, machine learning and artificial intelligence methods in chemical sciences. This field of research, broadly known as quantitative structure-activity relationships (QSAR) modeling, has developed many important algorithms and has found a broad range of applications in physical organic and medicinal chemistry in the past 55+ years. This Perspective summarizes recent technological advances in QSAR modeling but it also highlights the applicability of algorithms, modeling methods, and validation practices developed in QSAR to a wide range of research areas outside of traditional QSAR boundaries including synthesis planning, nanotechnology, materials science, biomaterials, and clinical informatics. As modern research methods generate rapidly increasing amounts of data, the knowledge of robust data-driven modelling methods professed within the QSAR field can become essential for scientists working both within and outside of chemical research. We hope that this contribution highlighting the generalizable components of QSAR modeling will serve to address this challenge.

DDIGIP: predicting drug-drug interactions based on Gaussian interaction profile kernels

BACKGROUND

A drug-drug interaction (DDI) is defined as a drug effect modified by another drug, which is very common in treating complex diseases such as cancer. Many studies have evidenced that some DDIs could be an increase or a decrease of the drug effect. However, the adverse DDIs maybe result in severe morbidity and even morality of patients, which also cause some drugs to withdraw from the market. As the multi-drug treatment becomes more and more common, identifying the potential DDIs has become the key issue in drug development and disease treatment. However, traditional biological experimental methods, including in vitro and vivo, are very time-consuming and expensive to validate new DDIs. With the development of high-throughput sequencing technology, many pharmaceutical studies and various bioinformatics data provide unprecedented opportunities to study DDIs.

RESULT

In this study, we propose a method to predict new DDIs, namely DDIGIP, which is based on Gaussian Interaction Profile (GIP) kernel on the drug-drug interaction profiles and the Regularized Least Squares (RLS) classifier. In addition, we also use the k-nearest neighbors (KNN) to calculate the initial relational score in the presence of new drugs via the chemical, biological, phenotypic data of drugs. We compare the prediction performance of DDIGIP with other competing methods via the 5-fold cross validation, 10-cross validation and de novo drug validation.

CONLUSION

In 5-fold cross validation and 10-cross validation, DDRGIP method achieves the area under the ROC curve (AUC) of 0.9600 and 0.9636 which are better than state-of-the-art method (L1 Classifier ensemble method) of 0.9570 and 0.9599. Furthermore, for new drugs, the AUC value of DDIGIP in de novo drug validation reaches 0.9262 which also outperforms the other state-of-the-art method (Weighted average ensemble method) of 0.9073. Case studies and these results demonstrate that DDRGIP is an effective method to predict DDIs while being beneficial to drug development and disease treatment.

Prediction of Severity of Drug-Drug Interactions Caused by Enzyme Inhibition and Activation

Drug-drug interactions (DDIs) severity assessment is a crucial problem because polypharmacy is increasingly common in modern medical practice. Many DDIs are caused by alterations of the plasma concentrations of one drug due to another drug inhibiting and/or inducing the metabolism or transporter-mediated disposition of the victim drug. Accurate assessment of clinically relevant DDIs for novel drug candidates represents one of the significant tasks of contemporary drug research and development and is important for practicing physicians. This work is a development of our previous investigations and aimed to create a model for the severity of DDIs prediction. PASS program and PoSMNA descriptors were implemented for prediction of all five classes of DDIs severity according to OpeRational ClassificAtion (ORCA) system: contraindicated (class 1), provisionally contraindicated (class 2), conditional (class 3), minimal risk (class 4), no interaction (class 5). Prediction can be carried out both for known drugs and for new, not yet synthesized substances using only their structural formulas. Created model provides an assessment of DDIs severity by prediction of different ORCA classes from the first most dangerous class to the fifth class when DDIs do not take place in the human organism. The average accuracy of DDIs class prediction is about 0.75.

Comprehensive ensemble in QSAR prediction for drug discovery

Background

Quantitative structure-activity relationship (QSAR) is a computational modeling method for revealing relationships between structural properties of chemical compounds and biological activities. QSAR modeling is essential for drug discovery, but it has many constraints. Ensemble-based machine learning approaches have been used to overcome constraints and obtain reliable predictions. Ensemble learning builds a set of diversified models and combines them. However, the most prevalent approach random forest and other ensemble approaches in QSAR prediction limit their model diversity to a single subject.

Results

The proposed ensemble method consistently outperformed thirteen individual models on 19 bioassay datasets and demonstrated superiority over other ensemble approaches that are limited to a single subject. The comprehensive ensemble method is publicly available at http://data.snu.ac.kr/QSAR/.

Conclusions

We propose a comprehensive ensemble method that builds multi-subject diversified models and combines them through second-level meta-learning. In addition, we propose an end-to-end neural network-based individual classifier that can automatically extract sequential features from a simplified molecular-input line-entry system (SMILES). The proposed individual models did not show impressive results as a single model, but it was considered the most important predictor when combined, according to the interpretation of the meta-learning.

Novel Consensus Architecture To Improve Performance of Large-Scale Multitask Deep Learning QSAR Models

Advances in the development of high-throughput screening and automated chemistry have rapidly accelerated the production of chemical and biological data, much of them freely accessible through literature aggregator services such as ChEMBL and PubChem. Here, we explore how to use this comprehensive mapping of chemical biology space to support the development of large-scale quantitative structure-activity relationship (QSAR) models. We propose a new deep learning consensus architecture (DLCA) that combines consensus and multitask deep learning approaches together to generate large-scale QSAR models. This method improves knowledge transfer across different target/assays while also integrating contributions from models based on different descriptors. The proposed approach was validated and compared with proteochemometrics, multitask deep learning, and Random Forest methods paired with various descriptors types. DLCA models demonstrated improved prediction accuracy for both regression and classification tasks. The best models together with their modeling sets are provided through publicly available web services at https://predictor.ncats.io .

4D- quantitative structure-activity relationship modeling: making a comeback

Introduction: Predictive Quantitative Structure-Activity Relationship (QSAR) modeling has become an essential methodology for rapidly assessing various properties of chemicals. The vast majority of these QSAR models utilize numerical descriptors derived from the two- and/or three-dimensional structures of molecules. However, the conformation-dependent characteristics of flexible molecules and their dynamic interactions with biological target(s) is/are not encoded by these descriptors, leading to limited prediction performances and reduced interpretability. 2D/3D QSAR models are successful for virtual screening, but typically suffer at lead optimization stages. That is why conformation-dependent 4D-QSAR modeling methods were developed two decades ago. However, these methods have always suffered from the associated computational cost. Recently, 4D-QSAR has been experiencing a significant come-back due to rapid advances in GPU-accelerated molecular dynamic simulations and modern machine learning techniques. Areas covered: Herein, the authors briefly review the literature regarding 4D-QSAR modeling and describe its modern workflow called MD-QSAR. Challenges and current limitations are also highlighted. Expert opinion: The development of hyper-predictive MD-QSAR models could represent a disruptive technology for analyzing, understanding, and optimizing dynamic protein-ligand interactions with countless applications for drug discovery and chemical toxicity assessment. Therefore, there has never been a better time and relevance for molecular modeling teams to engage in hyper-predictive MD-QSAR modeling.

Drug-drug interaction prediction using PASS

Simultaneous use of the drugs may lead to undesirable Drug-Drug Interactions (DDIs) in the human body. Many DDIs are associated with changes in drug metabolism that performed by Drug-Metabolizing Enzymes (DMEs). In this case, DDI manifests itself as a result of the effect of one drug on the biotransformation of other drug(s), its slowing down (in the case of inhibiting DME) or acceleration (in case of induction of DME), which leads to a change in the pharmacological effect of the drugs combination. We used OpeRational ClassificAtion (ORCA) system for categorizing DDIs. ORCA divides DDIs into five classes: contraindicated (class 1), provisionally contraindicated (class 2), conditional (class 3), minimal risk (class 4), no interaction (class 5). We collected a training set consisting of several thousands of drug pairs. Algorithm of PASS program was used for the first, second and third classes DDI prediction. Chemical descriptors called PoSMNA (Pairs of Substances Multilevel Neighbourhoods of Atoms) were developed and implemented in PASS software to describe in a machine-readable format drug substances pairs instead of the single molecules. The average accuracy of DDI class prediction is about 0.84. A freely available web resource for DDI prediction was developed (http://way2drug.com/ddi/).

Assessment of the cardiovascular adverse effects of drug-drug interactions through a combined analysis of spontaneous reports and predicted drug-target interactions

Adverse drug effects (ADEs) are one of the leading causes of death in developed countries and are the main reason for drug recalls from the market, whereas the ADEs that are associated with action on the cardiovascular system are the most dangerous and widespread. The treatment of human diseases often requires the intake of several drugs, which can lead to undesirable drug-drug interactions (DDIs), thus causing an increase in the frequency and severity of ADEs. An evaluation of DDI-induced ADEs is a nontrivial task and requires numerous experimental and clinical studies. Therefore, we developed a computational approach to assess the cardiovascular ADEs of DDIs. This approach is based on the combined analysis of spontaneous reports (SRs) and predicted drug-target interactions to estimate the five cardiovascular ADEs that are induced by DDIs, namely, myocardial infarction, ischemic stroke, ventricular tachycardia, cardiac failure, and arterial hypertension. We applied a method based on least absolute shrinkage and selection operator (LASSO) logistic regression to SRs for the identification of interacting pairs of drugs causing corresponding ADEs, as well as noninteracting pairs of drugs. As a result, five datasets containing, on average, 3100 potentially ADE-causing and non-ADE-causing drug pairs were created. The obtained data, along with information on the interaction of drugs with 1553 human targets predicted by PASS Targets software, were used to create five classification models using the Random Forest method. The average area under the ROC curve of the obtained models, sensitivity, specificity and balanced accuracy were 0.837, 0.764, 0.754 and 0.759, respectively. The predicted drug targets were also used to hypothesize the potential mechanisms of DDI-induced ventricular tachycardia for the top-scoring drug pairs. The created five classification models can be used for the identification of drug combinations that are potentially the most or least dangerous for the cardiovascular system.

Prediction of Drug-Drug Interactions Related to Inhibition or Induction of Drug-Metabolizing Enzymes

Drug-drug interaction (DDI) is the phenomenon of alteration of the pharmacological activity of a drug(s) when another drug(s) is co-administered in cases of so-called polypharmacy. There are three types of DDIs: pharmacokinetic (PK), pharmacodynamic, and pharmaceutical. PK is the most frequent type of DDI, which often appears as a result of the inhibition or induction of drug-metabolising enzymes (DME). In this review, we summarise in silico methods that may be applied for the prediction of the inhibition or induction of DMEs and describe appropriate computational methods for DDI prediction, showing the current situation and perspectives of these approaches in medicinal and pharmaceutical chemistry. We review sources of information on DDI, which can be used in pharmaceutical investigations and medicinal practice and/or for the creation of computational models. The problem of the inaccuracy and redundancy of these data are discussed. We provide information on the state-of-the-art physiologically- based pharmacokinetic modelling (PBPK) approaches and DME-based in silico methods. In the section on ligand-based methods, we describe pharmacophore models, molecular field analysis, quantitative structure-activity relationships (QSAR), and similarity analysis applied to the prediction of DDI related to the inhibition or induction of DME. In conclusion, we discuss the problems of DDI severity assessment, mention factors that influence severity, and highlight the issues, perspectives and practical using of in silico methods.

Cheminformatics-driven discovery of polymeric micelle formulations for poorly soluble drugs

Many drug candidates fail therapeutic development because of poor aqueous solubility. We have conceived a computer-aided strategy to enable polymeric micelle-based delivery of poorly soluble drugs. We built models predicting both drug loading efficiency (LE) and loading capacity (LC) using novel descriptors of drug-polymer complexes. These models were employed for virtual screening of drug libraries, and eight drugs predicted to have either high LE and high LC or low LE and low LC were selected. Three putative positives, as well as three putative negative hits, were confirmed experimentally (implying 75% prediction accuracy). Fortuitously, simvastatin, a putative negative hit, was found to have the desired micelle solubility. Podophyllotoxin and simvastatin (LE of 95% and 87% and LC of 43% and 41%, respectively) were among the top five polymeric micelle-soluble compounds ever studied experimentally. The success of the strategy described herein suggests its broad utility for designing drug delivery systems.

Comparison of Quantitative and Qualitative (Q)SAR Models Created for the Prediction of Ki and IC50 Values of Antitarget Inhibitors

Estimation of interaction of drug-like compounds with antitargets is important for the assessment of possible toxic effects during drug development. Publicly available online databases provide data on the experimental results of chemical interactions with antitargets, which can be used for the creation of (Q)SAR models. The structures and experimental Ki and IC50 values for compounds tested on the inhibition of 30 antitargets from the ChEMBL 20 database were used. Data sets with Ki and IC50 values including more than 100 compounds were created for each antitarget. The (Q)SAR models were created by GUSAR software using quantitative neighborhoods of atoms (QNA), multilevel neighborhoods of atoms (MNA) descriptors, and self-consistent regression. The accuracy of (Q)SAR models was validated by the fivefold cross-validation procedure. The balanced accuracy was higher for qualitative SAR models (0.80 and 0.81 for Ki and IC50 values, respectively) than for quantitative QSAR models (0.73 and 0.76 for Ki and IC50 values, respectively). In most cases, sensitivity was higher for SAR models than for QSAR models, but specificity was higher for QSAR models. The mean R 2 and RMSE were 0.64 and 0.77 for Ki values and 0.59 and 0.73 for IC50 values, respectively. The number of compounds falling within the applicability domain was higher for SAR models than for the test sets.

Quantitative structure-activity relationship of the thymidylate synthase inhibitors of Mus musculus in the series of quinazolin-4-one and quinazolin-4-imine derivatives

A quantitative structure-activity relationship analysis of the 2-methylquinazolin-4-one and quinazolin-4-imine derivatives, well-known antifolate thymidylate synthase (TYMS) inhibitors, has been performed in the range IC₅₀ = 0.4÷380000.0 nmoL/L using the GUSAR 2013 program. Based on the MNA and QNA descriptors using the self-consistent regression, 6 statistically significant consensus models for predicting the IC₅₀ numerical values have been constructed. These models demonstrate high and moderate prognostic accuracies for the training and external validation test sets, respectively. The molecular fragments of TYMS inhibitors regulating their antitumor activity are identified. The obtained data open opportunities for developing novel promising inhibitors of TYMS.

A novel integrated action crossing method for drug-drug interaction prediction in non-communicable diseases

BACKGROUND AND OBJECTIVE

Drug-drug interaction (DDI) is one of the main causes of toxicity and treatment inefficacy. This work focuses on non-communicable diseases (NCDs), the non-transmissible and long-lasting diseases since they are the leading cause of death globally. Drugs that are used in NCDs increase the probability of DDIs as a result of long time usage. This work proposes an Integrated Action Crossing (IAC) method that is effective in predicting the NCDs DDIs based on pharmacokinetic (PK) mechanism.

METHODS

Drug-Enzyme (CYP450) and Drug-Transporter actions including substrate, inhibitor and inducer affect the PK mechanism of other drugs. Hence, this paper proposes an enzyme and transporter protein integrated action crossing method for DDIs prediction in NCDs. The NCDs Drugs information was retrieved from the DrugBank database and the actions of enzymes and transporter proteins that were crossed and integrated. The datasets were generated for machine training.

RESULTS

Three machine learning approaches: Support Vector Machine, k-Nearest Neighbors, and Neural Networks were used for the assessment of the method. Performance evaluation was performed through five-fold cross validation and the different datasets and learning methods were compared. Two layers NNs achieved the best performance at the accuracy of 83.15% (F-Measure 85.23% and AUC 0.901).

CONCLUSIONS

The IAC method delivers better performance compared to the conventional method for the identification of NCDs DDIs.

ChemDIS-Mixture: an online tool for analyzing potential interaction effects of chemical mixtures

The assessment of bioactivity and toxicity for mixtures remains a challenging work. Although several computational models have been developed to accelerate the evaluation of chemical-chemical interaction, a specific biological endpoint should be defined before applying the models that usually relies on clinical and experimental data. The development of computational methods is desirable for identifying potential biological endpoints of mixture interactions. To facilitate the identification of potential effects of mixture interactions, a novel online system named ChemDIS-Mixture is proposed to analyze the shared target proteins, and common enriched functions, pathways, and diseases affected by multiple chemicals. Venn diagram tools have been implemented for easy analysis and visualization of interaction targets and effects. Case studies have been provided to demonstrate the capability of ChemDIS-Mixture for identifying potential effects of mixture interactions in clinical studies. ChemDIS-Mixture provides useful functions for the identification of potential effects of coexposure to multiple chemicals. ChemDIS-Mixture is freely accessible at http://cwtung.kmu.edu.tw/chemdis/mixture .

Prediction of Effective Drug Combinations by an Improved Naïve Bayesian Algorithm

Drug combinatorial therapy is a promising strategy for combating complex diseases due to its fewer side effects, lower toxicity and better efficacy. However, it is not feasible to determine all the effective drug combinations in the vast space of possible combinations given the increasing number of approved drugs in the market, since the experimental methods for identification of effective drug combinations are both labor- and time-consuming. In this study, we conducted systematic analysis of various types of features to characterize pairs of drugs. These features included information about the targets of the drugs, the pathway in which the target protein of a drug was involved in, side effects of drugs, metabolic enzymes of the drugs, and drug transporters. The latter two features (metabolic enzymes and drug transporters) were related to the metabolism and transportation properties of drugs, which were not analyzed or used in previous studies. Then, we devised a novel improved naïve Bayesian algorithm to construct classification models to predict effective drug combinations by using the individual types of features mentioned above. Our results indicated that the performance of our proposed method was indeed better than the naïve Bayesian algorithm and other conventional classification algorithms such as support vector machine and K-nearest neighbor.

Predicting drug-drug interactions through drug structural similarities and interaction networks incorporating pharmacokinetics and pharmacodynamics knowledge

Drug–drug interactions (DDIs) may lead to adverse effects and potentially result in drug withdrawal from the market. Predicting DDIs during drug development would help reduce development costs and time by rigorous evaluation of drug candidates. The primary mechanisms of DDIs are based on pharmacokinetics (PK) and pharmacodynamics (PD). This study examines the effects of 2D structural similarities of drugs on DDI prediction through interaction networks including both PD and PK knowledge. Our assumption was that a query drug (Dq) and a drug to be examined (De) likely have DDI if the drugs in the interaction network of De are structurally similar to Dq. A network of De describes the associations between the drugs and the proteins relating to PK and PD for De. These include target proteins, proteins interacting with target proteins, enzymes, and transporters for De. We constructed logistic regression models for DDI prediction using only 2D structural similarities between each Dq and the drugs in the network of De. The results indicated that our models could effectively predict DDIs. It was found that integrating structural similarity scores of the drugs relating to both PK and PD of De was crucial for model performance. In particular, the combination of the target- and enzyme-related scores provided the largest increase of the predictive power.Graphical abstract

Positive-Unlabeled Learning for inferring drug interactions based on heterogeneous attributes

BACKGROUND

Investigating and understanding drug-drug interactions (DDIs) is important in improving the effectiveness of clinical care. DDIs can occur when two or more drugs are administered together. Experimentally based DDI detection methods require a large cost and time. Hence, there is a great interest in developing efficient and useful computational methods for inferring potential DDIs. Standard binary classifiers require both positives and negatives for training. In a DDI context, drug pairs that are known to interact can serve as positives for predictive methods. But, the negatives or drug pairs that have been confirmed to have no interaction are scarce. To address this lack of negatives, we introduce a Positive-Unlabeled Learning method for inferring potential DDIs.

RESULTS

The proposed method consists of three steps: i) application of Growing Self Organizing Maps to infer negatives from the unlabeled dataset; ii) using a pairwise similarity function to quantify the overlap between individual features of drugs and iii) using support vector machine classifier for inferring DDIs. We obtained 6036 DDIs from DrugBank database. Using the proposed approach, we inferred 589 drug pairs that are likely to not interact with each other; these drug pairs are used as representative data for the negative class in binary classification for DDI prediction. Moreover, we classify the predicted DDIs as Cytochrome P450 (CYP) enzyme-Dependent and CYP-Independent interactions invoking their locations on the Growing Self Organizing Map, due to the particular importance of these enzymes in clinically significant interaction effects. Further, we provide a case study on three predicted CYP-Dependent DDIs to evaluate the clinical relevance of this study.

CONCLUSION

Our proposed approach showed an absolute improvement in F1-score of 14 and 38% in comparison to the method that randomly selects unlabeled data points as likely negatives, depending on the choice of similarity function. We inferred 5300 possible CYP-Dependent DDIs and 592 CYP-Independent DDIs with the highest posterior probabilities. Our discoveries can be used to improve clinical care as well as the research outcomes of drug development.

QSAR models of human data can enrich or replace LLNA testing for human skin sensitization

Skin sensitization is a major environmental and occupational health hazard. Although many chemicals have been evaluated in humans, there have been no efforts to model these data to date. We have compiled, curated, analyzed, and compared the available human and LLNA data. Using these data, we have developed reliable computational models and applied them for virtual screening of chemical libraries to identify putative skin sensitizers. The overall concordance between murine LLNA and human skin sensitization responses for a set of 135 unique chemicals was low (R = 28-43%), although several chemical classes had high concordance. We have succeeded to develop predictive QSAR models of all available human data with the external correct classification rate of 71%. A consensus model integrating concordant QSAR predictions and LLNA results afforded a higher CCR of 82% but at the expense of the reduced external dataset coverage (52%). We used the developed QSAR models for virtual screening of CosIng database and identified 1061 putative skin sensitizers; for seventeen of these compounds, we found published evidence of their skin sensitization effects. Models reported herein provide more accurate alternative to LLNA testing for human skin sensitization assessment across diverse chemical data. In addition, they can also be used to guide the structural optimization of toxic compounds to reduce their skin sensitization potential.