Utilizing random Forest QSAR models with optimized parameters for target identification and its application to target-fishing server

Leveraging new approach methodologies: ecotoxicological modelling of endocrine disrupting chemicals to Danio rerio through machine learning and toxicity studies

New approach methodologies (NAMs) offer information tailored to the intended application while reducing the use of animals. NAMs aim to develop quantitative structure-activity relationship (QSAR) and quantitive-Read-Across structure-activity relationship (q-RASAR) models to predict and categorize the acute toxicity of known and unknown endocrine-disrupting chemicals (EDCs) against zebrafish. EDCs are a diverse group of toxic substances that disrupt the endocrine system of humans and animals. The q-RASAR model was constructed and verified using validation metrics (R2 = 0.886 and Q2 = 0.814) which found to be more reliable model compare to QSAR model. The substructure fingerprint was well-fitted for the classification model and it was validated using 10-fold average accuracy (Q = 86.88%), specificity (Sp = 88.89%), Matthew's correlation curve (MCC = 0.621) and receiver operating characteristics (ROC = 0.828). The dataset of unknown substances revealed that phenolphthalein (Php) exhibited a significant level of toxicity based on q-RASAR model. The docking and simulation study indicated that the computationally derived important features successfully bound to the target zebrafish sex hormone binding globulin (zfSHBG). The experimental LC50 value of 0.790 mg L-1 was very close to the predicted value of 0.763 mg L-1, which provides high confidence to the developed model.

Polypharmacology prediction: the long road toward comprehensively anticipating small-molecule selectivity to de-risk drug discovery

INTRODUCTION

Small molecules often bind to multiple targets, a behavior termed polypharmacology. Anticipating polypharmacology is essential for drug discovery since unknown off-targets can modulate safety and efficacy - profoundly affecting drug discovery success. Unfortunately, experimental methods to assess selectivity present significant limitations and drugs still fail in the clinic due to unanticipated off-targets. Computational methods are a cost-effective, complementary approach to predict polypharmacology.

AREAS COVERED

This review aims to provide a comprehensive overview of the state of polypharmacology prediction and discuss its strengths and limitations, covering both classical cheminformatics methods and bioinformatic approaches. The authors review available data sources, paying close attention to their different coverage. The authors then discuss major algorithms grouped by the types of data that they exploit using selected examples.

EXPERT OPINION

Polypharmacology prediction has made impressive progress over the last decades and contributed to identify many off-targets. However, data incompleteness currently limits most approaches to comprehensively predict selectivity. Moreover, our limited agreement on model assessment challenges the identification of the best algorithms - which at present show modest performance in prospective real-world applications. Despite these limitations, the exponential increase of multidisciplinary Big Data and AI hold much potential to better polypharmacology prediction and de-risk drug discovery.

Multi-Target In-Silico modeling strategies to discover novel angiotensin converting enzyme and neprilysin dual inhibitors

Cardiovascular diseases, including heart failure, stroke, and hypertension, affect 608 million people worldwide and cause 32% of deaths. Combination therapy is required in 60% of patients, involving concurrent Renin-Angiotensin-Aldosterone-System (RAAS) and Neprilysin inhibition. This study introduces a novel multi-target in-silico modeling technique (mt-QSAR) to evaluate the inhibitory potential against Neprilysin and Angiotensin-converting enzymes. Using both linear (GA-LDA) and non-linear (RF) algorithms, mt-QSAR classification models were developed using 983 chemicals to predict inhibitory effects on Neprilysin and Angiotensin-converting enzymes. The Box-Jenkins method, feature selection method, and machine learning algorithms were employed to obtain the most predictive model with ~ 90% overall accuracy. Additionally, the study employed virtual screening of designed scaffolds (Chalcone and its analogues, 1,3-Thiazole, 1,3,4-Thiadiazole) applying developed mt-QSAR models and molecular docking. The identified virtual hits underwent successive filtration steps, incorporating assessments of drug-likeness, ADMET profiles, and synthetic accessibility tools. Finally, Molecular dynamic simulations were then used to identify and rank the most favourable compounds. The data acquired from this study may provide crucial direction for the identification of new multi-targeted cardiovascular inhibitors.

Machine learning-assisted search for novel coagulants: When machine learning can be efficient even if data availability is low

Design of new drugs is a challenging process: a candidate molecule should satisfy multiple conditions to act properly and make the least side-effect-perfect candidates selectively attach to and influence only targets, leaving off-targets intact. The amount of experimental data about various properties of molecules constantly grows, promoting data-driven approaches. However, the applicability of typical predictive machine learning techniques can be substantially limited by a lack of experimental data about a particular target. For example, there are many known Thrombin inhibitors (acting as anticoagulants), but a very limited number of known Protein C inhibitors (coagulants). In this study, we present our approach to suggest new inhibitor candidates by building an effective representation of chemical space. For this aim, we developed a deep learning model-autoencoder, trained on a large set of molecules in the SMILES format to map the chemical space. Further, we applied different sampling strategies to generate novel coagulant candidates. Symmetrically, we tested our approach on anticoagulant candidates, where we were able to predict their inhibition towards Thrombin. We also compare our approach with MegaMolBART-another deep learning generative model, but exploiting similar principles of navigation in a chemical space.

Prediction of compound-target interaction using several artificial intelligence algorithms and comparison with a consensus-based strategy

For understanding a chemical compound's mechanism of action and its side effects, as well as for drug discovery, it is crucial to predict its possible protein targets. This study examines 15 developed target-centric models (TCM) employing different molecular descriptions and machine learning algorithms. They were contrasted with 17 third-party models implemented as web tools (WTCM). In both sets of models, consensus strategies were implemented as potential improvement over individual predictions. The findings indicate that TCM reach f1-score values greater than 0.8. Comparing both approaches, the best TCM achieves values of 0.75, 0.61, 0.25 and 0.38 for true positive/negative rates (TPR, TNR) and false negative/positive rates (FNR, FPR); outperforming the best WTCM. Moreover, the consensus strategy proves to have the most relevant results in the top 20 % of target profiles. TCM consensus reach TPR and FNR values of 0.98 and 0; while on WTCM reach values of 0.75 and 0.24. The implemented computational tool with the TCM and their consensus strategy at: https://bioquimio.udla.edu.ec/tidentification01/ . Scientific Contribution: We compare and discuss the performances of 17 public compound-target interaction prediction models and 15 new constructions. We also explore a compound-target interaction prioritization strategy using a consensus approach, and we analyzed the challenging involved in interactions modeling.

In-silico target prediction by ensemble chemogenomic model based on multi-scale information of chemical structures and protein sequences

Identification and validation of bioactive small-molecule targets is a significant challenge in drug discovery. In recent years, various in-silico approaches have been proposed to expedite time- and resource-consuming experiments for target detection. Herein, we developed several chemogenomic models for target prediction based on multi-scale information of chemical structures and protein sequences. By combining the information of a compound with multiple protein targets together and putting these compound-target pairs into a well-established model, the scores to indicate whether there are interactions between compounds and targets can be derived, and thus a target prediction task can be completed by sorting the outputted scores. To improve the prediction performance, we constructed several chemogenomic models using multi-scale information of chemical structures and protein sequences, and the ensemble model with the best performance was used as our final model. The model was validated by various strategies and external datasets and the promising target prediction capability of the model, i.e., the fraction of known targets identified in the top-k (1 to 10) list of the potential target candidates suggested by the model, was confirmed. Compared with multiple state-of-art target prediction methods, our model showed equivalent or better predictive ability in terms of the top-k predictions. It is expected that our method can be utilized as a powerful computational tool to narrow down the potential targets for experimental testing.

Glutamate ionotropic receptor NMDA type subunit 1: A novel potential protein target of dapagliflozin against renal interstitial fibrosis

Renal interstitial fibrosis (RIF) is the final pathway for chronic kidney diseases (CKD) to end-stage renal disease, with no ideal therapy at present. Previous studies indicated that sodium glucose co-transporter-2 inhibitor (SGLT2i) dapagliflozin had the effect of anti-RIF, but the mechanism remains elusive and the renal protective effect could not be fully explained by singly targeting SGLT2. In this study, we aimed to explore the mechanism of dapagliflozin against RIF and identify novel potential targets. Firstly, dapagliflozin treatment improved pro-fibrotic indicators in unilateral ureteral obstruction mice and transforming growth factor beta 1 induced human proximal tubular epithelial cells. Then, transcriptomics and bioinformatics analysis were performed, and results revealed that dapagliflozin against RIF by regulating inflammation and oxidative stress related signals. Subsequently, targets prediction and analysis demonstrated that glutamate ionotropic receptor NMDA type subunit 1 (GRIN1) was a novel potential target of dapagliflozin, which was related to inflammation and oxidative stress related signals. Moreover, molecular dynamics simulation revealed that dapagliflozin could stably bind to GRIN1 protein and change its spatial conformation. Furthermore, human renal samples and Nephroseq data were used for GRIN1 expression evaluation, and the results showed that GRIN1 expression were increased in renal tissues of CKD and RIF patients than controls. Additionally, further studies demonstrated that dapagliflozin could reduce intracellular calcium influx in renal tubular cells, which depended on regulating GRIN1 protein but not gene. In conclusion, GRIN1 is probably a novel target of dapagliflozin against RIF.

Molecular Modeling and In Vitro Evaluation of Piplartine Analogs against Oral Squamous Cell Carcinoma

Cancer is a principal cause of death in the world, and providing a better quality of life and reducing mortality through effective pharmacological treatment remains a challenge. Among malignant tumor types, squamous cell carcinoma-esophageal cancer (EC) is usually located in the mouth, with approximately 90% located mainly on the tongue and floor of the mouth. Piplartine is an alkamide found in certain species of the genus Piper and presents many pharmacological properties including antitumor activity. In the present study, the cytotoxic potential of a collection of piplartine analogs against human oral SCC9 carcinoma cells was evaluated. The analogs were prepared via Fischer esterification reactions, alkyl and aryl halide esterification, and a coupling reaction with PyBOP using the natural compound 3,4,5-trimethoxybenzoic acid as a starting material. The products were structurally characterized using 1H and 13C nuclear magnetic resonance, infrared spectroscopy, and high-resolution mass spectrometry for the unpublished compounds. The compound 4-methoxy-benzyl 3,4,5-trimethoxybenzoate (9) presented an IC50 of 46.21 µM, high selectively (SI > 16), and caused apoptosis in SCC9 cancer cells. The molecular modeling study suggested a multi-target mechanism of action for the antitumor activity of compound 9 with CRM1 as the main target receptor.

Potential Health Benefits of Banana Phenolic Content during Ripening by Implementing Analytical and In Silico Techniques

Banana ranks as the fifth most cultivated agricultural crop globally, highlighting its crucial socio-economic role. The banana's health-promoting benefits are correlated with its composition in bioactive compounds, such as phenolic compounds. Thus, the present study attempts to evaluate the potential health benefits of banana phenolic content by combing analytical and in silico techniques. Particularly, the total phenolic content and antioxidant/antiradical activity of banana samples during ripening were determined spectrophotometrically. In parallel, liquid chromatography-tandem mass spectrometry (LC-MS/MS) analysis was implemented to unravel the variations in the phenolic profile of banana samples during ripening. Chlorogenic acid emerged as a ripening marker of banana, while apigenin and naringenin were abundant in the unripe fruit. In a further step, the binding potential of the elucidated phytochemicals was examined by utilizing molecular target prediction tools. Human carbonic anhydrase II (hCA-II) and XII (hCA-XII) enzymes were identified as the most promising targets and the inhibitory affinity of phenolic compounds was predicted through molecular docking studies. This class of enzymes is linked to a variety of pathological conditions, such as edema, obesity, hypertension, cancer, etc. The results assessment indicated that all assigned phenolic compounds constitute great candidates with potential inhibitory activity against CA enzymes.

Topology-enhanced molecular graph representation for anti-breast cancer drug selection

Background

Breast cancer is currently one of the cancers with a higher mortality rate in the world. The biological research on anti-breast cancer drugs focuses on the activity of estrogen receptors alpha (ER\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\alpha$$\end{document}α), the pharmacokinetic properties and the safety of the compounds, which, however, is an expensive and time-consuming process. Developments of deep learning bring potential to efficiently facilitate the candidate drug selection against breast cancer.

Methods

In this paper, we propose an Anti-Breast Cancer Drug selection method utilizing Gated Graph Neural Networks (ABCD-GGNN) to topologically enhance the molecular representation of candidate drugs. By constructing atom-level graphs through atomic descriptors for each distinct compound, ABCD-GGNN can topologically learn both the implicit structure and substructure characteristics of a candidate drug and then integrate the representation with explicit discrete molecular descriptors to generate a molecule-level representation. As a result, the representation of ABCD-GGNN can inductively predict the ER\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\alpha$$\end{document}α, the pharmacokinetic properties and the safety of each candidate drug. Finally, we design a ranking operator whose inputs are the predicted properties so as to statistically select the appropriate drugs against breast cancer.

Results

Extensive experiments conducted on our collected anti-breast cancer candidate drug dataset demonstrate that our proposed method outperform all the other representative methods in the tasks of predicting ER\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\alpha$$\end{document}α, and the pharmacokinetic properties and safety of the compounds. Extended result analysis demonstrates the efficiency and biological rationality of the operator we design to calculate the candidate drug ranking from the predicted properties.

Conclusion

In this paper, we propose the ABCD-GGNN representation method to efficiently integrate the topological structure and substructure features of the molecules with the discrete molecular descriptors. With a ranking operator applied, the predicted properties efficiently facilitate the candidate drug selection against breast cancer.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04913-6.

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.

Metabolomic profile and computational analysis for the identification of the potential anti-inflammatory mechanisms of action of the traditional medicinal plants Ocimum basilicum and Ocimum tenuiflorum

Ocimum basilicum and Ocimum tenuiflorum are two basil species widely used medicinally as an anti-inflammatory, antimicrobial and cardioprotective agent. This study focuses on the chemical characterization of the majoritarian compounds of both species and their anti-inflammatory potential. Up to 22 compounds such as various types of salvianolic acids, derivatives of rosmaniric acid and flavones were identified in both plants. The identified compounds were very similar between both plants and are consistent with previous finding in other studies in Portugal and Italy. Based on the identified molecules a consensus target prediction was carried out. Among the main predicted target proteins, we found a high representation of the carbonic anhydrase family (CA2, CA7 and CA12) and several key proteins from the arachidonic pathway (LOX5, PLA2, COX1 and COX2). Both pathways are well related to inflammation. The interaction between the compounds and these targets were explored through molecular docking and molecular dynamics simulation. Our results suggest that some molecules present in both plants can induce an anti-inflammatory response through a non-steroidal mechanism of action connected to the carbon dioxide metabolism.

Recent Advances in In Silico Target Fishing

In silico target fishing, whose aim is to identify possible protein targets for a query molecule, is an emerging approach used in drug discovery due its wide variety of applications. This strategy allows the clarification of mechanism of action and biological activities of compounds whose target is still unknown. Moreover, target fishing can be employed for the identification of off targets of drug candidates, thus recognizing and preventing their possible adverse effects. For these reasons, target fishing has increasingly become a key approach for polypharmacology, drug repurposing, and the identification of new drug targets. While experimental target fishing can be lengthy and difficult to implement, due to the plethora of interactions that may occur for a single small-molecule with different protein targets, an in silico approach can be quicker, less expensive, more efficient for specific protein structures, and thus easier to employ. Moreover, the possibility to use it in combination with docking and virtual screening studies, as well as the increasing number of web-based tools that have been recently developed, make target fishing a more appealing method for drug discovery. It is especially worth underlining the increasing implementation of machine learning in this field, both as a main target fishing approach and as a further development of already applied strategies. This review reports on the main in silico target fishing strategies, belonging to both ligand-based and receptor-based approaches, developed and applied in the last years, with a particular attention to the different web tools freely accessible by the scientific community for performing target fishing studies.

Computational modeling predicts potential effects of the herbal infusion "horchata" against COVID-19

Bioactive plant-derived molecules have emerged as therapeutic alternatives in the fight against the COVID-19 pandemic. In this investigation, principal bioactive compounds of the herbal infusion “horchata” from Ecuador were studied as potential novel inhibitors of the SARS-CoV-2 virus. The chemical composition of horchata was determined through a HPLC-DAD/ESI-MSⁿ and GC–MS analysis while the inhibitory potential of the compounds on SARS-CoV-2 was determined by a computational prediction using various strategies, such as molecular docking and molecular dynamics simulations. Up to 51 different compounds were identified. The computational analysis of predicted targets reveals the compounds’ possible anti-inflammatory (no steroidal) and antioxidant effects. Three compounds were identified as candidates for M^pro inhibition: benzoic acid, 2-(ethylthio)-ethyl ester, l-Leucine-N-isobutoxycarbonyl-N-methyl-heptyl and isorhamnetin and for PL^pro: isorhamnetin-3-O-(6-Orhamnosyl-galactoside), dihydroxy-methoxyflavanone and dihydroxyphenyl)-5-hydroxy-4-oxochromen-7-yl]oxy-3,4,5-trihydroxyoxane-2-carboxylic acid. Our results suggest the potential of Ecuadorian horchata infusion as a starting scaffold for the development of new inhibitors of the SARS-CoV-2 M^pro and PL^pro enzymes.

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.

Novel Development of Predictive Feature Fingerprints to Identify Chemistry-Based Features for the Effective Drug Design of SARS-CoV-2 Target Antagonists and Inhibitors Using Machine Learning

A unique approach to bioactivity and chemical data curation coupled with random forest analyses has led to a series of target-specific and cross-validated predictive feature fingerprints (PFF) that have high predictability across multiple therapeutic targets and disease stages involved in the severe acute respiratory syndrome due to coronavirus 2 (SARS-CoV-2)-induced COVID-19 pandemic, which include plasma kallikrein, human immunodeficiency virus (HIV)-protease, nonstructural protein (NSP)5, NSP12, Janus kinase (JAK) family, and AT-1. The approach was highly accurate in determining the matched target for the different compound sets and suggests that the models could be used for virtual screening of target-specific compound libraries. The curation-modeling process was successfully applied to a SARS-CoV-2 phenotypic screen and could be used for predictive bioactivity estimation and prioritization for clinical trial selection; virtual screening of drug libraries for the repurposing of drug molecules; and analysis and direction of proprietary data sets.

Machine Learning Methods in Drug Discovery

The advancements of information technology and related processing techniques have created a fertile base for progress in many scientific fields and industries. In the fields of drug discovery and development, machine learning techniques have been used for the development of novel drug candidates. The methods for designing drug targets and novel drug discovery now routinely combine machine learning and deep learning algorithms to enhance the efficiency, efficacy, and quality of developed outputs. The generation and incorporation of big data, through technologies such as high-throughput screening and high through-put computational analysis of databases used for both lead and target discovery, has increased the reliability of the machine learning and deep learning incorporated techniques. The use of these virtual screening and encompassing online information has also been highlighted in developing lead synthesis pathways. In this review, machine learning and deep learning algorithms utilized in drug discovery and associated techniques will be discussed. The applications that produce promising results and methods will be reviewed.

Prediction of Compound Bioactivities Using Heat-Diffusion Equation

Machine learning is expected to improve low throughput and high assay cost in cell-based phenotypic screening. However, it is still a challenge to apply machine learning to achieving sufficiently complex phenotypic screening due to imbalanced datasets, non-linear prediction, and unpredictability of new chemotypes. Here, we developed a prediction model based on the heat-diffusion equation (PM-HDE) to address this issue. The algorithm was verified as feasible for virtual compound screening using biotest data of 946 assay systems registered with PubChem. PM-HDE was then applied to actual screening. Based on supervised learning of the data of about 50,000 compounds from biological phenotypic screening with motor neurons derived from ALS-patient-induced pluripotent stem cells, virtual screening of >1.6 million compounds was implemented. We confirmed that PM-HDE enriched the hit compounds and identified new chemotypes. This prediction model could overcome the inflexibility in machine learning, and our approach could provide a novel platform for drug discovery.

•

Prediction model based on heat-diffusion equation (PM-HDE) was constructed

•

PM-HDE succeeded in increasing the hit ratio and identifying potent compounds

•

PM-HDE discovered new chemotypes in compound evaluation with an ALS-patient iPSC panel

•

PM-HDE could represent an algorithm for future drug discovery with AI

There remain many intractable diseases with no treatment available, including amyotrophic lateral sclerosis (ALS), for which the development of a cure is crucial. However, compound screening for drug development demands time, energy, and cost, and therefore artificial intelligence (AI) is expected to improve the efficiency of drug discovery. We built a novel machine-learning algorithm to predict hit compounds in compound screening using the heat-diffusion equation (HDE). This prediction model harbors the potential to solve issues that have been challenging for conventional machine learning and to exhibit accurate performance leading to the discovery of new drugs. In fact, the HDE model predicted hits with new chemotypes among millions of compounds for ALS therapeutics using a panel of large numbers of ALS patient-derived induced pluripotent stem cell models (ALS-patient iPSC panel). This algorithm could contribute to the acceleration and development of future drug discoveries using AI.

An up-to-date overview of computational polypharmacology in modern drug discovery

INTRODUCTION

In recent years, computational polypharmacology has gained significant attention to study the promiscuous nature of drugs. Despite tremendous challenges, community-wide efforts have led to a variety of novel approaches for predicting drug polypharmacology. In particular, some rapid advances using machine learning and artificial intelligence have been reported with great success.

AREAS COVERED

In this article, the authors provide a comprehensive update on the current state-of-the-art polypharmacology approaches and their applications, focusing on those reports published after our 2017 review article. The authors particularly discuss some novel, groundbreaking concepts, and methods that have been developed recently and applied to drug polypharmacology studies.

EXPERT OPINION

Polypharmacology is evolving and novel concepts are being introduced to counter the current challenges in the field. However, major hurdles remain including incompleteness of high-quality experimental data, lack of in vitro and in vivo assays to characterize multi-targeting agents, shortage of robust computational methods, and challenges to identify the best target combinations and design effective multi-targeting agents. Fortunately, numerous national/international efforts including multi-omics and artificial intelligence initiatives as well as most recent collaborations on addressing the COVID-19 pandemic have shown significant promise to propel the field of polypharmacology forward.

Ontological model of multi-agent Smart-system for predicting drug properties based on modified algorithms of artificial immune systems

BACKGROUND

Currently, due to the huge progress in the field of information technologies and computer equipment, it is important to use modern approaches of artificial intelligence in order to process extensive chemical information at creating new drugs with desired properties. The interdisciplinary of research creates additional difficulties in creating new drugs. Currently, there are no universal algorithms and software for predicting the "structure-property" dependence of drug compounds that can take into account the needs of specialists in this field. In this regard, the development of a modern Smart-system based on the promising bio-inspired approach of artificial immune systems for predicting the structure-property dependence of drug compounds is relevant. The aim of this work is to develop a multi-agent Smart-system for predicting the "structure-property" dependence of drug compounds using the ontological approach and modified algorithms of artificial immune systems using the example of drug compounds of the sulfonamide group. The proposed system makes it possible to increase the accuracy of prediction models of the "structure-property" dependence, to reduce the time and financial costs for obtaining candidate drug compounds.

METHODS

During the creation of a Smart-system, there are used multi-agent and ontological approaches, which allow to structure input and output data, optimally to distribute computing resources and to coordinate the work of the system. As a promising approach for processing a large amount of chemical information, extracting informative descriptors and for the creation of an optimal data set, as well as further predicting the properties of medicinal compounds, there are considered modified algorithms of artificial immune systems and various algorithms of artificial intelligence.

RESULTS

There was developed an ontological model of a multi-agent Smart-system. There are presented the results of the «structure-property» dependence simulation based on a modified grey wolf optimization algorithm and artificial immune systems. During the simulation, there was used information from the Mol-Instincts sulfonamide descriptor database.

CONCLUSION

The developed multi-agent Smart-system using ontological models allows visually to present the structure and interrelationships of agents functioning, which greatly facilitates the development of software and reduces time and financial costs during the development of new drugs.

Using Predicted Bioactivity Profiles to Improve Predictive Modeling

Predictive modeling is a cornerstone in early drug development. Using information for multiple domains or across prediction tasks has the potential to improve the performance of predictive modeling. However, aggregating data often leads to incomplete data matrices that might be limiting for modeling. In line with previous studies, we show that by generating predicted bioactivity profiles, and using these as additional features, prediction accuracy of biological endpoints can be improved. Using conformal prediction, a type of confidence predictor, we present a robust framework for the calculation of these profiles and the evaluation of their impact. We report on the outcomes from several approaches to generate the predicted profiles on 16 datasets in cytotoxicity and bioactivity and show that efficiency is improved the most when including the p-values from conformal prediction as bioactivity profiles.

Virtual screening web servers: designing chemical probes and drug candidates in the cyberspace

The interplay between life sciences and advancing technology drives a continuous cycle of chemical data growth; these data are most often stored in open or partially open databases. In parallel, many different types of algorithms are being developed to manipulate these chemical objects and associated bioactivity data. Virtual screening methods are among the most popular computational approaches in pharmaceutical research. Today, user-friendly web-based tools are available to help scientists perform virtual screening experiments. This article provides an overview of internet resources enabling and supporting chemical biology and early drug discovery with a main emphasis on web servers dedicated to virtual ligand screening and small-molecule docking. This survey first introduces some key concepts and then presents recent and easily accessible virtual screening and related target-fishing tools as well as briefly discusses case studies enabled by some of these web services. Notwithstanding further improvements, already available web-based tools not only contribute to the design of bioactive molecules and assist drug repositioning but also help to generate new ideas and explore different hypotheses in a timely fashion while contributing to teaching in the field of drug development.

Benzimidazolyl-pyrazolo[3,4-b]pyridinones, Selective Inhibitors of MOLT-4 Leukemia Cell Growth and Sea Urchin Embryo Spiculogenesis: Target Quest

1,3-Substituted pyrazolo[3,4-b]pyridinones 11-18 were synthesized by a three-component condensation of Meldrum's acid with aryl aldehydes and 1,3-substituted 5-aminopyrazoles. Their biological activity was evaluated using the in vivo phenotypic sea urchin embryo assay and the in vitro cytotoxicity screen against human cancer cell lines. In the sea urchin embryo model, 1-benzimidazolyl-pyrazolo[3,4-b]pyridinones 11 caused inhibition of hatching and spiculogenesis at sub-micromolar concentrations. These compounds also selectively and potently inhibited growth of the MOLT-4 leukemia cell line. Subsequent structure-activity relationship studies determined the benzimidazolyl fragment as an essential pharmacophore for both effects. We applied numerous techniques for target identification. A preliminary QSAR target identification search did not result in tangible leads. Attempts to prepare a relevant photoaffinity probe that retained potency in both assays were not successful. Compounds 11 were further characterized for their activity in a wild-type versus Notch-mutant leukemia cell lines, and in in vitro panels of kinases and matrix metalloproteinases. Using a series of diverse modulators of spiculogenesis as standards, we excluded multiple signaling networks including Notch, Wnt/β-catenin, receptor tyrosine kinases (VEGF/VEGFR, FGF/FGFR), PI3K, and Raf-MEK-ERK as possible targets of 11. On the other hand, matrix metalloproteinase-9/hatching enzyme was identified as one potential target.

Deep learning classification for improved bicoherence feature based on cyclic modulation and cross-correlation

This paper aims to present an improved bicoherence spectrum (IBS) combined with cyclic modulation spectrum (CMS) and cross-correlation that is suitable for classification of hydrophone signals involving deep learning (DL). First, the proposed feature utilizes the all-phase fast Fourier transform to modify the spectrum leakage caused by CMS; this can be used to detect line spectra with low signal-to-noise ratios (SNRs). Second, the cross-correlation and bispectrum are both exploited to suppress non-periodic line spectra interference from CMS. Based on numerous numerical simulations and experimental verification, compared with CMS and conventional bispectrum, the prominent characteristics of IBS include: detecting higher-precision periodic harmonics without single-line interference, superior robustness under low SNR, and greatly reducing the data redundancy. In addition, to test the performance of IBS for DL application, three deep belief network (DBN)-based classifiers-DBN-softmax, DBN-support vector machine, and DBN-random forest-are introduced and employed for five experimental scenarios (including ships and underwater source). The results indicate that benefiting from DBN pre-training, the IBS classification accuracy of DBN-based models is generally higher than 80%.

Artificial Intelligence for Drug Toxicity and Safety

Interventional pharmacology is one of medicine's most potent weapons against disease. These drugs, however, can result in damaging side effects and must be closely monitored. Pharmacovigilance is the field of science that monitors, detects, and prevents adverse drug reactions (ADRs). Safety efforts begin during the development process, using in vivo and in vitro studies, continue through clinical trials, and extend to postmarketing surveillance of ADRs in real-world populations. Future toxicity and safety challenges, including increased polypharmacy and patient diversity, stress the limits of these traditional tools. Massive amounts of newly available data present an opportunity for using artificial intelligence (AI) and machine learning to improve drug safety science. Here, we explore recent advances as applied to preclinical drug safety and postmarketing surveillance with a specific focus on machine and deep learning (DL) approaches.

Development of Multi-Target Chemometric Models for the Inhibition of Class I PI3K Enzyme Isoforms: A Case Study Using QSAR-Co Tool

The present work aims at establishing multi-target chemometric models using the recently launched quantitative structure–activity relationship (QSAR)-Co tool for predicting the activity of inhibitor compounds against different isoforms of phosphoinositide 3-kinase (PI3K) under various experimental conditions. The inhibitors of class I phosphoinositide 3-kinase (PI3K) isoforms have emerged as potential therapeutic agents for the treatment of various disorders, especially cancer. The cell-based enzyme inhibition assay results of PI3K inhibitors were curated from the CHEMBL database. Factors such as the nature and mutation of cell lines that may significantly alter the assay outcomes were considered as important experimental elements for mt-QSAR model development. The models, in turn, were developed using two machine learning techniques as implemented in QSAR-Co: linear discriminant analysis (LDA) and random forest (RF). Both techniques led to models with high accuracy (ca. 90%). Several molecular fragments were extracted from the current dataset, and their quantitative contributions to the inhibitory activity against all the proteins and experimental conditions under study were calculated. This case study also demonstrates the utility of QSAR-Co tool in solving multi-factorial and complex chemometric problems. Additionally, the combination of different in silico methods employed in this work can serve as a valuable guideline to speed up early discovery of PI3K inhibitors.

Computational Molecular Modeling of Pin1 Inhibition Activity of Quinazoline, Benzophenone, and Pyrimidine Derivatives

Pin1 (peptidyl-prolyl cis-trans isomerase NIMA-interacting 1) is directly involved in cancer cell-cycle regulation because it catalyses the cis-trans isomerization of prolyl amide bonds in proteins. In this sense, a modeling evaluation of the inhibition of Pin1 using quinazoline, benzophenone, and pyrimidine derivatives was performed by using multilinear, random forest, SMOreg, and IBK regression algorithms on a dataset of 51 molecules, which was divided randomly in 78% for the training and 22% for the test set. Topological descriptors were used as independent variables and the biological activity (pIC50) as a dependent variable. The most robust individual model contained 9 features, and its predictive capability was statistically validated by the correlation coefficient for adjusting, 10-fold cross validation, test set, and bootstrapping with values of 0.910, 0.819, 0.841, and 0.803, respectively. In order to improve the prediction of the pIC50 values, the aggregation of the individual models was performed through the construction of an ensemble, and the most robust one was constructed by two individual models (LR3 and RF1) by applying the IBK algorithm, and a substantial improvement in predictive performance is reflected in the values of R2ADJ = 0.982, Q2CV = 0.962, and Q2EXT = 0.918. Mean square errors <0.165 and good fitting between calculated and experimental pIC50 values suggest a robustness on the prediction of pIC50. Regarding the docking simulation, a binding affinity between the molecules and the active site for the Pin1 inhibition into the protein (3jyj) was estimated through the calculation of the binding free energy (BE), with values in the range of −5.55 to −8.00 kcal/mol, implying a stabilizing interaction molecule receptor. The ligand interaction diagrams between the drugs and amino acid in the binding site for the three most active compounds denoted a good wrapper of these organic compounds into the protein mainly by polar amino acids.

A New Approach for Drug Target and Bioactivity Prediction: The Multifingerprint Similarity Search Algorithm (MuSSeL)

We present MuSSeL, a multifingerprint similarity search algorithm, able to predict putative drug targets for a given query small molecule as well as to return a quantitative assessment of its bioactivity in terms of K_i or IC₅₀ values. Predictions are automatically made exploiting a large collection of high quality experimental bioactivity data available from ChEMBL (version 22.1) combining, in a consensus-like approach, predictions resulting from a similarity search performed using 13 different fingerprint definitions. Importantly, the herein proposed algorithm is also effective in detecting and handling activity cliffs. A calibration set including small molecules present in the last updated version of ChEMBL (version 23) was employed to properly tune the algorithm parameters. Three randomly built external sets were instead challenged for model performances. The potential use of MuSSeL was also challenged by a prospective exercise for the prediction of five bioactive compounds taken from articles published in the Journal of Medicinal Chemistry just few months ago. The paper emphasizes the importance of implementing multifingerprint consensus strategies to increase the confidence in prediction of similarity search algorithms and provides a fast and easy-to-run tool for drug target and bioactivity prediction.

Combining Ensemble Learning with a Fragment-Based Topological Approach To Generate New Molecular Diversity in Drug Discovery: In Silico Design of Hsp90 Inhibitors

Machine learning methods have revolutionized modern science, providing fast and accurate solutions to multiple problems. However, they are commonly treated as "black boxes". Therefore, in important scientific fields such as medicinal chemistry and drug discovery, machine learning methods are restricted almost exclusively to the task of performing predictions of large and heterogeneous data sets of chemicals. The lack of interpretability prevents the full exploitation of the machine learning models as generators of new chemical knowledge. This work focuses on the development of an ensemble learning model for the prediction and design of potent dual heat shock protein 90 (Hsp90) inhibitors. The model displays accuracy higher than 80% in both training and test sets. To use the ensemble model as a generator of new chemical knowledge, three steps were followed. First, a physicochemical and/or structural interpretation was provided for each molecular descriptor present in the ensemble learning model. Second, the term "pseudolinear equation" was introduced within the context of machine learning to calculate the relative quantitative contributions of different molecular fragments to the inhibitory activity against the two Hsp90 isoforms studied here. Finally, by assembling the fragments with positive contributions, new molecules were designed, being predicted as potent Hsp90 inhibitors. According to Lipinski's rule of five, the designed molecules were found to exhibit potentially good oral bioavailability, a primordial property that chemicals must have to pass early stages in drug discovery. The present approach based on the combination of ensemble learning and fragment-based topological design holds great promise in drug discovery, and it can be adapted and applied to many different scientific disciplines.

Machine Learning Based Toxicity Prediction: From Chemical Structural Description to Transcriptome Analysis

Toxicity prediction is very important to public health. Among its many applications, toxicity prediction is essential to reduce the cost and labor of a drug's preclinical and clinical trials, because a lot of drug evaluations (cellular, animal, and clinical) can be spared due to the predicted toxicity. In the era of Big Data and artificial intelligence, toxicity prediction can benefit from machine learning, which has been widely used in many fields such as natural language processing, speech recognition, image recognition, computational chemistry, and bioinformatics, with excellent performance. In this article, we review machine learning methods that have been applied to toxicity prediction, including deep learning, random forests, k-nearest neighbors, and support vector machines. We also discuss the input parameter to the machine learning algorithm, especially its shift from chemical structural description only to that combined with human transcriptome data analysis, which can greatly enhance prediction accuracy.

A bioinformatics potpourri

The 16th International Conference on Bioinformatics (InCoB) was held at Tsinghua University, Shenzhen from September 20 to 22, 2017. The annual conference of the Asia-Pacific Bioinformatics Network featured six keynotes, two invited talks, a panel discussion on big data driven bioinformatics and precision medicine, and 66 oral presentations of accepted research articles or posters. Fifty-seven articles comprising a topic assortment of algorithms, biomolecular networks, cancer and disease informatics, drug-target interactions and drug efficacy, gene regulation and expression, imaging, immunoinformatics, metagenomics, next generation sequencing for genomics and transcriptomics, ontologies, post-translational modification, and structural bioinformatics are the subject of this editorial for the InCoB2017 supplement issues in BMC Genomics, BMC Bioinformatics, BMC Systems Biology and BMC Medical Genomics. New Delhi will be the location of InCoB2018, scheduled for September 26-28, 2018.

Machine Learning-based Virtual Screening and Its Applications to Alzheimer's Drug Discovery: A Review

BACKGROUND

Virtual Screening (VS) has emerged as an important tool in the drug development process, as it conducts efficient in silico searches over millions of compounds, ultimately increasing yields of potential drug leads. As a subset of Artificial Intelligence (AI), Machine Learning (ML) is a powerful way of conducting VS for drug leads. ML for VS generally involves assembling a filtered training set of compounds, comprised of known actives and inactives. After training the model, it is validated and, if sufficiently accurate, used on previously unseen databases to screen for novel compounds with desired drug target binding activity.

OBJECTIVE

The study aims to review ML-based methods used for VS and applications to Alzheimer's Disease (AD) drug discovery.

METHODS

To update the current knowledge on ML for VS, we review thorough backgrounds, explanations, and VS applications of the following ML techniques: Naïve Bayes (NB), k-Nearest Neighbors (kNN), Support Vector Machines (SVM), Random Forests (RF), and Artificial Neural Networks (ANN).

RESULTS

All techniques have found success in VS, but the future of VS is likely to lean more largely toward the use of neural networks - and more specifically, Convolutional Neural Networks (CNN), which are a subset of ANN that utilize convolution. We additionally conceptualize a work flow for conducting ML-based VS for potential therapeutics for AD, a complex neurodegenerative disease with no known cure and prevention. This both serves as an example of how to apply the concepts introduced earlier in the review and as a potential workflow for future implementation.

CONCLUSION

Different ML techniques are powerful tools for VS, and they have advantages and disadvantages albeit. ML-based VS can be applied to AD drug development.