Exploiting cheminformatic and machine learning to navigate the available chemical space of potential small molecule inhibitors of SARS-CoV-2

Molecular design of hydroxamic acid-based derivatives as urease inhibitors of Helicobacter pylori

Helicobacter pylori is the main causative agent of gastric cancer, especially non-cardiac gastric cancers. This bacterium relies on urease producing much ammonia to colonize the host. Herein, the study provides valuable insights into structural patterns driving urease inhibition for high-activity molecules designed via exploring known inhibitors. Firstly, an ensemble model was devised to predict the inhibitory activity of novel compounds in an automated workflow (R2 = 0.761) that combines four machine learning approaches. The dataset was characterized in terms of chemical space, including molecular scaffolds, clustering analysis, distribution for physicochemical properties, and activity cliffs. Through these analyses, the hydroxamic acid group and the benzene ring responsible for distinct activity were highlighted. Activity cliff pairs uncovered substituents of the benzene ring on hydroxamic acid derivatives are key structures for substantial activity enhancement. Moreover, 11 hydroxamic acid derivatives were designed, named mol1-11. Results of molecular dynamic simulations showed that the mol9 exhibited stabilization of the active site flap's closed conformation and are expected to be promising drug candidates for Helicobacter pylori infection and further in vitro, in vivo, and clinical trials to demonstrate in future.

Exploring chemical space, scaffold diversity, and activity landscape of spleen tyrosine kinase active inhibitors

This study aims to comprehensively characterize 576 inhibitors targeting Spleen Tyrosine Kinase (SYK), a non-receptor tyrosine kinase primarily found in haematopoietic cells, with significant relevance to B-cell receptor function. The objective is to gain insights into the structural requirements essential for potent activity, with implications for various therapeutic applications. Through chemoinformatic analyses, we focus on exploring the chemical space, scaffold diversity, and structure-activity relationships (SAR). By leveraging ECFP4 and MACCS fingerprints, we elucidate the relationship between chemical compounds and visualize the network using RDKit and NetworkX platforms. Additionally, compound clustering and visualization of the associated chemical space aid in understanding overall diversity. The outcomes include identifying consensus diversity patterns to assess global chemical space diversity. Furthermore, incorporating pairwise activity differences enhances the activity landscape visualization, revealing heterogeneous SAR patterns. The dataset analysed in this work has three activity cliff generators, CHEMBL3415598, CHEMBL4780257, and CHEMBL3265037, compounds with high affinity to SYK are very similar to compounds analogues with reasonable potency differences. Overall, this study provides a critical analysis of SYK inhibitors, uncovering potential scaffolds and chemical moieties crucial for their activity, thereby advancing the understanding of their therapeutic potential.

Staying Ahead of the Game: How SARS-CoV-2 has Accelerated the Application of Machine Learning in Pandemic Management

In recent years, machine learning (ML) techniques have garnered considerable interest for their potential use in accelerating the rate of drug discovery. With the emergence of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic, the utilization of ML has become even more crucial in the search for effective antiviral medications. The pandemic has presented the scientific community with a unique challenge, and the rapid identification of potential treatments has become an urgent priority. Researchers have been able to accelerate the process of identifying drug candidates, repurposing existing drugs, and designing new compounds with desirable properties using machine learning in drug discovery. To train predictive models, ML techniques in drug discovery rely on the analysis of large datasets, including both experimental and clinical data. These models can be used to predict the biological activities, potential side effects, and interactions with specific target proteins of drug candidates. This strategy has proven to be an effective method for identifying potential coronavirus disease 2019 (COVID-19) and other disease treatments. This paper offers a thorough analysis of the various ML techniques implemented to combat COVID-19, including supervised and unsupervised learning, deep learning, and natural language processing. The paper discusses the impact of these techniques on pandemic drug development, including the identification of potential treatments, the understanding of the disease mechanism, and the creation of effective and safe therapeutics. The lessons learned can be applied to future outbreaks and drug discovery initiatives.

Fragment-based structural exploration and chemico-biological interaction study of HDAC3 inhibitors through non-linear pattern recognition, chemical space, and binding mode of interaction analysis

HDAC3 is an emerging target for the identification and discovery of novel drug candidates against several disease conditions including cancer. Here, a fragment-based non-linear machine learning (ML) method along with chemical space exploration followed by a structure-based binding mode of interaction analysis study was carried out on some HDAC3 inhibitors to obtain the key structural features modulating HDAC3 inhibition. Both the ML and chemical space analysis identified several physicochemical and structural properties namely lipophilicity, polar and relative polar surface area, arylcarboxamide moiety, bulky fused aromatic group, n-alkyl, and cinnamoyl moieties, the higher number of oxygen atoms, π-electrons for the substituted tetrahydrofuronaphthodioxolone moiety favorable for higher HDAC3 inhibition. Moreover, hydrogen bond forming capabilities, the length and substitution position of the linker moiety, the importance of phenyl ring in the linker motif, the contribution of heterocyclic cap moieties for effective inhibitor binding at the HDAC3 catalytic site that correspondingly affects the HDAC3 inhibitory potency. Again, macrocyclic ring structure and cyclohexyl cap moiety are responsible for lower HDAC3 inhibition. The MD simulation study of selected compounds explained strong binding patterns at the HDAC3 active site as evidenced by the lower RMSD and RMSF values. Nevertheless, it also explained the importance of the crucial structural fragments derived from the fragment-based analysis during ligand-enzyme interactions. Therefore, the outcomes of this current structural analysis will be a useful tool for fragment-based drug discovery of effective HDAC3 inhibitors for clinical therapeutics in the future.Communicated by Ramaswamy H. Sarma.

Deep Generation Model Guided by the Docking Score for Active Molecular Design

A deep generation model, as a novel drug design and discovery tool, shows obvious advantages in generating compounds with novel backbones and has been applied successfully in the field of drug discovery. However, it is still a challenge to generate molecules with expected properties, especially high activity. Here, to obtain compounds both with novelty and high activity to a target, we proposed a conditional molecular generation model COMG by considering the docking score and 3D pharmacophore matching during molecular generation. The proposed model was based on the conditional variational autoencoder architecture constrained by the pharmacophore matching score. During Bayesian optimization, the docking score was applied to enhance the target relevance of generated compounds. Furthermore, to overcome the problem of high structural similarity caused by Bayesian optimization, the idea of the scaffold memory unit was also introduced. The evaluation results of COMG show that our model not only can improve the structural diversity of generated molecules but also can effectively improve the proportion of target-related drug-active molecules. The obtained results indicate that our proposed model COMG is a useful drug design tool.

Could the fibromyalgia syndrome be triggered or enhanced by COVID-19?

Fibromyalgia (FM) is a complex disease with an uncertain aetiology and intricate pathophysiology. Although its genesis is not fully explained, potential environmental factors, such as viral infections might trigger FM or worsen patients' clinical outcomes. The SARS-CoV-2 virus may affect central and peripheral nervous systems, leading to musculoskeletal, neurological, and psychological disturbances. These symptoms might persist at least 12 months beyond the recovery, often referred to as post-COVID syndrome, which resembles FM syndrome. In this sense, we argued the potential consequences of COVID-19 exclusively on FM syndrome. First, we have described post-COVID syndrome and its painful symptoms. Afterwards, we argued whether FM syndrome could be triggered or enhanced by COVID-19 infection or by numerous and persistent stressors imposed daily by the pandemic setting (isolation, uncertainty, depression, mental stress, generalized anxiety, and fear of the virus). In addition, we have demonstrated similarities between pathophysiological mechanisms and cardinal symptoms of FM and COVID-19, speculating that SARS-CoV-2 might represent a critical mediator of FM or an exacerbator of its symptoms once both syndromes share similar mechanisms and complaints. Therefore, pharmacologic and non-pharmacological approaches commonly used to treat FM could serve as strategic therapies to attenuate painful and neurological manifestations of post-COVID syndrome. Although it is still theoretical, clinicians and researchers should be alert of patients who develop symptoms similar to FM or those who had their FM symptoms increased post-COVID to manage them better.

Exploiting butyrylcholinesterase inhibitors through a combined 3-D pharmacophore modeling, QSAR, molecular docking, and molecular dynamics investigation†

Alzheimer's disease (AD), a neurodegenerative condition associated with ageing, can occur. AD gradually impairs memory and cognitive function, which leads to abnormal behavior, incapacity, and reliance. By 2050, there will likely be 100 million cases of AD in the world's population. Acetylcholinesterase (AChE) and butyrylcholinesterase (BuChE) inhibition are significant components of AD treatment. This work developed models using the genetic method multiple linear regression, atom-based, field-based, and 3-D pharmacophore modelling. Due to internal and external validation, all of the models have solid statistical (R² > 0.81 and Q² > 0.77) underpinnings. From a pre-plated CNS library (6055), we discovered a hit compound using virtual screening on a QSAR model. Through molecular docking, additional hit compounds were investigated (XP mode). Finally, a molecular dynamics simulation revealed that the Molecule5093-4BDS complex was stable (100 ns). Finally, the expected ADME properties for the hit compounds (Molecule5093, Molecule1076, Molecule4412, Molecule1053, and Molecule3344) were found. According to the results of our investigation and the prospective hit compounds, BuChE inhibitors may be used as a treatment for AD.

Alzheimer's disease (AD), a neurodegenerative condition associated with ageing, can occur.

Small molecules in the treatment of COVID-19

The outbreak of COVID-19 has become a global crisis, and brought severe disruptions to societies and economies. Until now, effective therapeutics against COVID-19 are in high demand. Along with our improved understanding of the structure, function, and pathogenic process of SARS-CoV-2, many small molecules with potential anti-COVID-19 effects have been developed. So far, several antiviral strategies were explored. Besides directly inhibition of viral proteins such as RdRp and M^pro, interference of host enzymes including ACE2 and proteases, and blocking relevant immunoregulatory pathways represented by JAK/STAT, BTK, NF-κB, and NLRP3 pathways, are regarded feasible in drug development. The development of small molecules to treat COVID-19 has been achieved by several strategies, including computer-aided lead compound design and screening, natural product discovery, drug repurposing, and combination therapy. Several small molecules representative by remdesivir and paxlovid have been proved or authorized emergency use in many countries. And many candidates have entered clinical-trial stage. Nevertheless, due to the epidemiological features and variability issues of SARS-CoV-2, it is necessary to continue exploring novel strategies against COVID-19. This review discusses the current findings in the development of small molecules for COVID-19 treatment. Moreover, their detailed mechanism of action, chemical structures, and preclinical and clinical efficacies are discussed.

Comparative analysis of an anthraquinone and chalcone derivatives-based virtual combinatorial library. A cheminformatics "proof-of-concept" study

A Laplacian scoring algorithm for gene selection and the Gini coefficient to identify the genes whose expression varied least across a large set of samples were the state-of-the-art methods used here. These methods have not been trialed for their feasibility in cheminformatics. This was a maiden attempt to investigate a complete comparative analysis of an anthraquinone and chalcone derivatives-based virtual combinatorial library. This computational "proof-of-concept" study illustrated the combinatorial approach used to explain how the structure of the selected natural products (NPs) undergoes molecular diversity analysis. A virtual combinatorial library (1.6 M) based on 20 anthraquinones and 24 chalcones was enumerated. The resulting compounds were optimized to the near drug-likeness properties, and the physicochemical descriptors were calculated for all datasets including FDA, Non-FDA, and NPs from ZINC 15. UMAP and PCA were applied to compare and represent the chemical space coverage of each dataset. Subsequently, the Laplacian score and Gini coefficient were applied to delineate feature selection and selectivity among properties, respectively. Finally, we demonstrated the diversity between the datasets by employing Murcko's and the central scaffolds systems, calculating three fingerprint descriptors and analyzing their diversity by PCA and SOM. The optimized enumeration resulted in 1,610,268 compounds with NP-Likeness, and synthetic feasibility mean scores close to FDA, Non-FDA, and NPs datasets. The overlap between the chemical space of the 1.6 M database was more prominent than with the NPs dataset. A Laplacian score prioritized NP-likeness and hydrogen bond acceptor properties (1.0 and 0.923), respectively, while the Gini coefficient showed that all properties have selective effects on datasets (0.81-0.93). Scaffold and fingerprint diversity indicated that the descending order for the tested datasets was FDA, Non-FDA, NPs and 1.6 M. Virtual combinatorial libraries based on NPs can be considered as a source of the combinatorial compound with NP-likeness properties. Furthermore, measuring molecular diversity is supposed to be performed by different methods to allow for comparison and better judgment.

Quantum machine learning for chemistry and physics

Machine learning (ML) has emerged as a formidable force for identifying hidden but pertinent patterns within a given data set with the objective of subsequent generation of automated predictive behavior. In recent years, it is safe to conclude that ML and its close cousin, deep learning (DL), have ushered in unprecedented developments in all areas of physical sciences, especially chemistry. Not only classical variants of ML, even those trainable on near-term quantum hardwares have been developed with promising outcomes. Such algorithms have revolutionized materials design and performance of photovoltaics, electronic structure calculations of ground and excited states of correlated matter, computation of force-fields and potential energy surfaces informing chemical reaction dynamics, reactivity inspired rational strategies of drug designing and even classification of phases of matter with accurate identification of emergent criticality. In this review we shall explicate a subset of such topics and delineate the contributions made by both classical and quantum computing enhanced machine learning algorithms over the past few years. We shall not only present a brief overview of the well-known techniques but also highlight their learning strategies using statistical physical insight. The objective of the review is not only to foster exposition of the aforesaid techniques but also to empower and promote cross-pollination among future research in all areas of chemistry which can benefit from ML and in turn can potentially accelerate the growth of such algorithms.

Drug repurposing for identification of potential spike inhibitors for SARS-CoV-2 using molecular docking and molecular dynamics simulations

For the last two years, the COVID-19 pandemic has continued to bring consternation on most of the world. According to recent WHO estimates, there have been more than 5.6 million deaths worldwide. The virus continues to evolve all over the world, thus requiring both vigilance and the necessity to find and develop a variety of therapeutic treatments, including the identification of specific antiviral drugs. Multiple studies have confirmed that SARS-CoV-2 utilizes its membrane-bound spike protein to recognize human angiotensin-converting enzyme 2 (ACE2). Thus, preventing spike-ACE2 interactions is a potentially viable strategy for COVID-19 treatment as it would block the virus from binding and entering into a host cell. This work aims to identify potential drugs using an in silico approach. Molecular docking was carried out on both approved drugs and substances previously tested in vivo. This step was followed by a more detailed analysis of selected ligands by molecular dynamics simulations to identify the best molecules that thwart the ability of the virus to interact with the ACE2 receptor. Because the SARS-CoV-2 virus evolves rapidly due to a plethora of immunocompromised hosts, the compounds were tested against five different known lineages. As a result, we could identify substances that work well on individual lineages and those showing broader efficacy. The most promising candidates among the currently used drugs were zafirlukast and simeprevir with an average binding affinity of -22 kcal/mol for spike proteins originating from various lineages. The first compound is a leukotriene receptor antagonist that is used to treat asthma, while the latter is a protease inhibitor used for hepatitis C treatment. From among the in vivo tested substances that concurrently exhibit promising free energy of binding and ADME parameters (indicating a possible oral administration) we selected the compound BDBM50136234. In conclusion, these molecules are worth exploring further by in vitro and in vivo studies against SARS-CoV-2.

Approaches for enhancing the analysis of chemical space for drug discovery

INTRODUCTION

Chemical space is a powerful, general, and practical conceptual framework in drug discovery and other areas in chemistry that addresses the diversity of molecules and it has various applications. Moreover, chemical space is a cornerstone of chemoinformatics as a scientific discipline. In response to the increase in the set of chemical compounds in databases, generators of chemical structures, and tools to calculate molecular descriptors, novel approaches to generate visual representations of chemical space in low dimensions are emerging and evolving. Such approaches include a wide range of commercial and free applications, software, and open-source methods.

AREAS COVERED

The current state of chemical space in drug design and discovery is reviewed. The topics discussed herein include advances for efficient navigation in chemical space, the use of this concept in assessing the diversity of different data sets, exploring structure-property/activity relationships for one or multiple endpoints, and compound library design. Recent advances in methodologies for generating visual representations of chemical space have been highlighted, thereby emphasizing open-source methods.

EXPERT OPINION

Quantitative and qualitative generation and analysis of chemical space require novel approaches for handling the increasing number of molecules and their information available in chemical databases (including emerging ultra-large libraries). In addition, it is of utmost importance to note that chemical space is a conceptual framework that goes beyond visual representation in low dimensions. However, the graphical representation of chemical space has several practical applications in drug discovery and beyond.

Probing marine brown macroalgal phlorotannins as antiviral candidate against SARS-CoV-2: molecular docking and dynamics simulation approach

Abstract

Over the past year, owing to the emergent demand for the search for potential COVID-19 therapeutics, identifying alternative candidates from biological sources is one of the sustainable ways to reinforce the drug discovery process. Marine macroalgae have numerous advantages because of the richest availability of underexploited bioactive compounds. Polyphenolic compounds like phlorotannins obtained from brown macroalgae are reported as proven antiviral and immunostimulatory agents. Thus, the present study evaluated the possibility of phlorotannins as antagonists to the multiple target proteins essential for SARS-CoV-2 replication. Twenty different types of potent phlorotannins were targeted against druggable target proteins, viz., 3CLpro, RdRp, and Spro using AutoDock molecular docking, drug-likeness were assessed by ADMET profiling (QikProp module). Further, validated with 200 ns molecular dynamics (MD) simulation (Desmond module) for the top-ranked phlorotannins based on docking binding affinities. Among the twenty phlorotannins studied, eckol hexacetate, phlorofucofuroeckol, fucofuroeckol, and bifuhalol-hexacetate showed significant binding affinities across the selected targets. Besides, MD simulations highlighted Glu166, Gln189, Cys145, and Thr190 tetrad as potential interaction sites to inhibit 3CLpro's activity. Moreover, phlorotannins were confirmed to be druglike, with no major deviation observed in ADMET-profiling. Hence, phlorotannins could be therapeutic candidates against SARS-CoV-2. However, further investigations are needed to prove its efficacy as an antiviral agent. Conclusively, this study may envisage that the novel finding could notably impact the advancement of antiviral interventions for COVID-19 in the near future.

Graphical Abstract

Supplementary Information

The online version contains supplementary material available at 10.1007/s11030-022-10383-y.

Anti-diabetics and antimicrobials: Harmony of mutual interplay

Diabetes is one of the four major non-communicable diseases, and appointed by the world health organization as the seventh leading cause of death worldwide. The scientists have turned over every rock in the corners of medical sciences in order to come up with better understanding and hence more effective treatments of diabetes. The continuous research on the subject has elucidated the role of immune disorders and inflammation as definitive factors in the trajectory of diabetes, assuring that blood glucose adjustments would result in a relief in the systemic stress leading to minimizing inflammation. On a parallel basis, microbial infections usually take advantage of immunity disorders and propagate creating a pro-inflammatory environment, all of which can be reversed by antimicrobial treatment. Standing at the crossroads between diabetes, immunity and infection, we aim in this review at projecting the interplay between immunity and diabetes, shedding the light on the overlapping playgrounds for the activity of some antimicrobial and anti-diabetic agents. Furthermore, we focused on the anti-diabetic drugs that can confer antimicrobial or anti-virulence activities.

Haste makes waste: A critical review of docking-based virtual screening in drug repurposing for SARS-CoV-2 main protease (M-pro) inhibition

This review makes a critical evaluation of 61 peer‐reviewed manuscripts that use a docking step in a virtual screening (VS) protocol to predict SARS‐CoV‐2 M‐pro (M‐pro) inhibitors in approved or investigational drugs. Various manuscripts predict different compounds, even when they use a similar initial dataset and methodology, and most of them do not validate their methodology or results. In addition, a set of known 150 SARS‐CoV‐2 M‐pro inhibitors extracted from the literature and a second set of 81 M‐pro inhibitors and 113 inactive compounds obtained from the COVID Moonshot project were used to evaluate the reliability of using docking scores as feasible predictors of the potency of a SARS‐CoV‐2 M‐pro inhibitor. Using two SARS‐CoV‐2 M‐pro structures and five protein‐ligand docking programs, we proved that the correlation between the pIC₅₀ and docking scores is not good. Neither was any correlation found between the pIC₅₀ and the ∆G calculated with an MM‐GBSA method. When a group of experimentally known inactive compounds was added, neither the docking scores or the ∆G were able to distinguish between compounds with or without M‐pro experimental inhibitory activity. Performances improved when covalent and noncovalent inhibitors were treated separately, but were not good enough to fully support using a docking score as a cutoff value for selecting new putative M‐pro inhibitors or predicting the relative bioactivity of a compound by comparison with a reference compound. The two sets of known SARS‐CoV‐2 M‐pro inhibitors presented here could be used for validating future VS protocols which aim to predict M‐pro inhibitors.

Integrating heterogeneous data to facilitate COVID-19 drug repurposing

In the COVID-19 pandemic, drug repositioning has presented itself as an alternative to the time-consuming process of generating new drugs. This review describes a drug repurposing process that is based on a new data-driven approach: we put forward five information paths that associate COVID-19-related genes and COVID-19 symptoms with drugs that directly target these gene products, that target the symptoms or that treat diseases that are symptomatically or genetically similar to COVID-19. The intersection of the five information paths results in a list of 13 drugs that we suggest as potential candidates against COVID-19. In addition, we have found information in published studies and in clinical trials that support the therapeutic potential of the drugs in our final list.

Navigating into the Chemical Space of Monoamine Oxidase Inhibitors by Artificial Intelligence and Cheminformatics Approach

The monoamine oxidase (MAO) enzyme class is a prevalent target for many neurodegenerative and depressive disorders. Even though scrutinization of many promising drugs for the treatment of MAO inhibition has been carried out in recent times, a conclusive structural requirement for potent activity needs to be developed. Numerous approaches have been examined for the identification of structural features for potent MAO inhibitors (MAOIs) that mainly involve an array of computational studies, synthetic approaches, and biological evaluation. In this paper, we have analyzed ∼2200 well-known MAOIs to expand perceptions in the chemical space of MAOIs. The physicochemical properties of the MAOIs disclosed a discernible hydrophobic feature making a bunch discrete from the central nervous system (CNS) acting drugs, as exposed using the principal component analysis (PCA). The Murcko scaffold structure study revealed unfavorable and favorable scaffold structures, in both data sets, with the highest biological activity shown by the 3-phenyl-2H-chromen-2-one scaffold. This scaffold showed a polypharmacological effect. R-group disintegration and automatic structure-activity relationship (SAR) study resulted in identification of substructures responsible for the inhibitory bioactivity of the MAO-A and MAO-B enzymes. Moreover, with activity cliff analysis, significant biological activity was detected by simple molecular conversion in the chemical compound structure. In addition, we used the machine learning tool to generate a hypothesis wherein pyrazole, benzene ring, and amide containing structural functionalities can exhibit potential biological activities. This hypothesis revealed that CNS target drugs, C4155, C13390, C21265, C43862, C31524, C24810, C37100, C42075, and C43644, could be repurposed as valuable candidates for the MAO-B enzyme. For researchers, this study will bring new perceptions in the discovery and development of MAOIs and direct lead and hit optimization for the progress of small molecules beneficial for MAO-targeting associated diseases.

Recent progress on the prospective application of machine learning to structure-based virtual screening

As more bioactivity and protein structure data become available, scoring functions (SFs) using machine learning (ML) to leverage these data sets continue to gain further accuracy and broader applicability. Advances in our understanding of the optimal ways to train and evaluate these ML-based SFs have introduced further improvements. One of these advances is how to select the most suitable decoys (molecules assumed inactive) to train or test an ML-based SF on a given target. We also review the latest applications of ML-based SFs for prospective structure-based virtual screening (SBVS), with a focus on the observed improvement over those using classical SFs. Finally, we provide recommendations for future prospective SBVS studies based on the findings of recent methodological studies.

Prediction of repurposed drugs for Coronaviruses using artificial intelligence and machine learning

The world is facing the COVID-19 pandemic caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). Likewise, other viruses of the Coronaviridae family were responsible for causing epidemics earlier. To tackle these viruses, there is a lack of approved antiviral drugs. Therefore, we have developed robust computational methods to predict the repurposed drugs using machine learning techniques namely Support Vector Machine, Random Forest, k-Nearest Neighbour, Artificial Neural Network, and Deep Learning. We used the experimentally validated drugs/chemicals with anticorona activity (IC50/EC50) from 'DrugRepV' repository. The unique entries of SARS-CoV-2 (142), SARS (221), MERS (123), and overall Coronaviruses (414) were subdivided into the training/testing and independent validation datasets, followed by the extraction of chemical/structural descriptors and fingerprints (17968). The highly relevant features were filtered using the recursive feature selection algorithm. The selected chemical descriptors were used to develop prediction models with Pearson's correlation coefficients ranging from 0.60 to 0.90 on training/testing. The robustness of the predictive models was further ensured using external independent validation datasets, decoy datasets, applicability domain, and chemical analyses. The developed models were used to predict promising repurposed drug candidates against coronaviruses after scanning the DrugBank. Top predicted molecules for SARS-CoV-2 were further validated by molecular docking against the spike protein complex with ACE receptor. We found potential repurposed drugs namely Verteporfin, Alatrofloxacin, Metergoline, Rescinnamine, Leuprolide, and Telotristat ethyl with high binding affinity. These 'anticorona' computational models would assist in antiviral drug discovery against SARS-CoV-2 and other Coronaviruses.

Machine learning techniques applied to the drug design and discovery of new antivirals: a brief look over the past decade

Introduction: Drug design and discovery of new antivirals will always be extremely important in medicinal chemistry, taking into account known and new viral diseases that are yet to come. Although machine learning (ML) have shown to improve predictions on the biological potential of chemicals and accelerate the discovery of drugs over the past decade, new methods and their combinations have improved their performance and established promising perspectives regarding ML in the search for new antivirals.Areas covered: The authors consider some interesting areas that deal with different ML techniques applied to antivirals. Recent innovative studies on ML and antivirals were selected and analyzed in detail. Also, the authors provide a brief look at the past to the present to detect advances and bottlenecks in the area.Expert opinion: From classical ML techniques, it was possible to boost the searches for antivirals. However, from the emergence of new algorithms and the improvement in old approaches, promising results will be achieved every day, as we have observed in the case of SARS-CoV-2. Recent experience has shown that it is possible to use ML to discover new antiviral candidates from virtual screening and drug repurposing.

Machine Learning in Discovery of New Antivirals and Optimization of Viral Infections Therapy

Nowadays, computational approaches play an important role in the design of new drug-like compounds and optimization of pharmacotherapeutic treatment of diseases. The emerging growth of viral infections, including those caused by the Human Immunodeficiency Virus (HIV), Ebola virus, recently detected coronavirus, and some others, leads to many newly infected people with a high risk of death or severe complications. A huge amount of chemical, biological, clinical data is at the disposal of the researchers. Therefore, there are many opportunities to find the relationships between the particular features of chemical data and the antiviral activity of biologically active compounds based on machine learning approaches. Biological and clinical data can also be used for building models to predict relationships between viral genotype and drug resistance, which might help determine the clinical outcome of treatment. In the current study, we consider machine-learning approaches in the antiviral research carried out during the past decade. We overview in detail the application of machine-learning methods for the design of new potential antiviral agents and vaccines, drug resistance prediction, and analysis of virus-host interactions. Our review also covers the perspectives of using the machine-learning approaches for antiviral research, including Dengue, Ebola viruses, Influenza A, Human Immunodeficiency Virus, coronaviruses, and some others.