Selecting Relevant Descriptors for Classification by Bayesian Estimates: A Comparison with Decision Trees and Support Vector Machines Approaches for Disparate Data Sets

Prediction of Cytochrome P450 Substrates Using the Explainable Multitask Deep Learning Models

Cytochromes P450 (P450s or CYPs) are the most important phase I metabolic enzymes in the human body and are responsible for metabolizing ∼75% of the clinically used drugs. P450-mediated metabolism is also closely associated with the formation of toxic metabolites and drug-drug interactions. Therefore, it is of high importance to predict if a compound is the substrate of a given P450 in the early stage of drug development. In this study, we built the multitask learning models to simultaneously predict the substrates of five major drug-metabolizing P450 enzymes, namely, CYP3A4, 2C9, 2C19, 2D6, and 1A2, based on the collected substrate data sets. Compared to the single-task model and conventional machine learning models, the multitask fingerprints and graph neural networks model achieved superior performance with the average AUC values of 90.8% on the test set. Notably, the multitask model demonstrated its good performance on the small amount of substrate data sets such as CYP1A2, 2C9, and 2C19. In addition, the Shapley additive explanation and the attention mechanism were used to reveal specific substructures associated with P450 substrates, which were further confirmed and complemented by the substructure mining tool and the literature.

Revolutionizing the structural design and determination of covalent-organic frameworks: principles, methods, and techniques

Covalent organic frameworks (COFs) represent an important class of crystalline porous materials with designable structures and functions. The interconnected organic monomers, featuring pre-designed symmetries and connectivities, dictate the structures of COFs, endowing them with high thermal and chemical stability, large surface area, and tunable micropores. Furthermore, by utilizing pre-functionalization or post-synthetic functionalization strategies, COFs can acquire multifunctionalities, leading to their versatile applications in gas separation/storage, catalysis, and optoelectronic devices. Our review provides a comprehensive account of the latest advancements in the principles, methods, and techniques for structural design and determination of COFs. These cutting-edge approaches enable the rational design and precise elucidation of COF structures, addressing fundamental physicochemical challenges associated with host-guest interactions, topological transformations, network interpenetration, and defect-mediated catalysis.

Quantum Machine Learning Predicting ADME-Tox Properties in Drug Discovery

In the drug discovery paradigm, the evaluation of absorption, distribution, metabolism, and excretion (ADME) and toxicity properties of new chemical entities is one of the most critical issues, which is a time-consuming process, immensely expensive, and poses formidable challenges in pharmaceutical R&D. In recent years, emerging technologies like artificial intelligence (AI), big data, and cloud technologies have garnered great attention to predict the ADME and toxicity of molecules. Currently, the blend of quantum computation and machine learning has attracted considerable attention in almost every field ranging from chemistry to biomedicine and several engineering disciplines as well. Quantum computers have the potential to bring advances in high-throughput experimental techniques and in screening billions of molecules by reducing development costs and time associated with the drug discovery process. Motivated by the efficiency of quantum kernel methods, we proposed a quantum machine learning (QML) framework consisting of a classical support vector classifier algorithm with a kernel-based quantum classifier. To demonstrate the feasibility of the proposed QML framework, the simplified molecular input line entry system (SMILES) notation-based string kernel, combined with a quantum support vector classifier, is used for the evaluation of chemical/drug ADME-Tox properties. The proposed quantum machine learning framework is validated and assessed via large-scale simulations. Based on our results from numerical simulations, the quantum model achieved the best performance as compared to classical counterparts in terms of the area under the curve of the receiver operating characteristic curve (AUC ROC; 0.80-0.95) for predicting outcomes on ADME-Tox data sets for small molecules, with a different number of features. The deployment of the proposed framework in the pharmaceutical industry would be extremely valuable in making the best decisions possible.

Computer-aided analysis for identification of novel analogues of ketoprofen based on molecular docking, ADMET, drug-likeness and DFT studies for the treatment of inflammation

Computer-based drug design is increasingly used in strategies for discovering new molecules for therapeutic purposes. The targeted drug is ketoprofen (KTP), which belongs to the family of non-steroidal anti-inflammatory drugs, which are widely used for the treatment of pain, fever, inflammation and certain types of cancers. In an attempt to rationalize the search for 72 new potential anti-inflammatory compounds on the COX-2 enzyme, we carried out an in silico protocol that successfully combines molecular docking towards COX-2 receptor (5F1A), ADMET pharmacokinetic parameters, drug-likeness rules and molecular electrostatic potential (MEP). It was found that six of the compounds analyzed satisfy with the associated values to physico-chemical properties as key evaluation parameters for the drug-likeness and demonstrate a hydrophobic character which makes their solubility in aqueous media difficult and easy in lipids. All the compounds presented good ADMET profile and they showed an interaction with the amino acids responsible for anti-inflammatory activity of the COX-2 isoenzyme. The calculation of the MEP of the six analogues reveals new preferential sites involving the formation of new bonds. Consequently, this result allowed us to understand the origin of the potential increase in the anti-inflammatory activity of the candidates. Finally, it was obtained that six compounds have a binding mode, binding energy, and stability in the active site of COX-2 like the reference drug ketoprofen, suggesting that these compounds could become a powerful candidate in the inhibition of the COX-2 enzyme.Communicated by Ramaswamy H. Sarma.

Integrated System for On-Site Rapid and Safe Screening of COVID-19

Since the outbreak of coronavirus disease 2019 (COVID-19), the epidemic has been spreading around the world for more than 2 years. Rapid, safe, and on-site detection methods of COVID-19 are in urgent demand for the control of the epidemic. Here, we established an integrated system, which incorporates a machine-learning-based Fourier transform infrared spectroscopy technique for rapid COVID-19 screening and air-plasma-based disinfection modules to prevent potential secondary infections. A partial least-squares discrimination analysis and a convolutional neural network model were built using the collected infrared spectral dataset containing 857 training serum samples. Furthermore, the sensitivity, specificity, and prediction accuracy could all reach over 94% from the results of the field test regarding 968 blind testing samples. Additionally, the disinfection modules achieved an inactivation efficiency of 99.9% for surface and airborne tested bacteria. The proposed system is conducive and promising for point-of-care and on-site COVID-19 screening in the mass population.

On modeling and utilizing chemical compound information with deep learning technologies: A task-oriented approach

A large number of chemical compounds are available in databases such as PubChem and ZINC. However, currently known compounds, though large, represent only a fraction of possible compounds, which is known as chemical space. Many of these compounds in the databases are annotated with properties and assay data that can be used for drug discovery efforts. For this goal, a number of machine learning algorithms have been developed and recent deep learning technologies can be effectively used to navigate chemical space, especially for unknown chemical compounds, in terms of drug-related tasks. In this article, we survey how deep learning technologies can model and utilize chemical compound information in a task-oriented way by exploiting annotated properties and assay data in the chemical compounds databases. We first compile what kind of tasks are trying to be accomplished by machine learning methods. Then, we survey deep learning technologies to show their modeling power and current applications for accomplishing drug related tasks. Next, we survey deep learning techniques to address the insufficiency issue of annotated data for more effective navigation of chemical space. Chemical compound information alone may not be powerful enough for drug related tasks, thus we survey what kind of information, such as assay and gene expression data, can be used to improve the prediction power of deep learning models. Finally, we conclude this survey with four important newly developed technologies that are yet to be fully incorporated into computational analysis of chemical information.

Differential Multimolecule Fingerprint for Similarity Search─Making Use of Active and Inactive Compound Sets in Virtual Screening

In conventional fingerprint methods, the similarity between two molecules is calculated using the Tanimoto index as a numerical criterion. Thus, the query molecules in virtual screening should be most representative of the wanted compound class at hand. In the concept introduced here, all available active molecules form a multimolecule fingerprint in which the appearing features are weighted according to their respective frequency. The features of inactive molecules are treated likewise and the resulting values are subtracted from those of the active ones. The obtained differential multimolecule fingerprint (DMMFP) is thus specific for the respective class of compounds. To account for the noninteger representation within this fingerprint, a modified Sørensen-Dice coefficient is used to compute the similarity. Potentially active molecules yield positive scores, whereas presumably inactive ones are denoted by negative values. The concept was applied to Angiotensin-converting enzyme (ACE) inhibitors, β2-adrenoceptor ligands, leukotriene A4 hydrolase inhibitors, dopamine D3 antagonists, and cytochrome CYP2C9 substrates, for which experimental binding affinities are known and was tested against decoys from DUD-E and a further background database consisting of molecules from the dark chemical matter, which comprises compounds that appear as frequent hitters across multiple assays. Using the 166 publicly available keys of the MACCS fingerprint and the larger PubChem fingerprint, actives were recovered with very high sensitivity. Furthermore, three marketed ACE inhibitors as well as the carbonic anhydrase II inhibitor dorzolamide were detected in the dark chemical matter data set. For comparison, the DMMFP was also used with a Bayesian classifier, for which the specificity (correctly classified inactives) and likewise the accuracy was superior. Conversely, the similarity score produced by the Sørensen-Dice coefficient showed its potential for the early recognition of (potentially) active molecules.

Explainable Molecular Sets: Using Information Theory to Generate Meaningful Descriptions of Groups of Molecules

Algorithmically identifying the meaningful similarities between an assortment of molecules is a critical chemical problem, and one which is only gaining in relevance as data-driven chemistry continues to progress. Effectively addressing this challenge can be achieved through a reformulation of the problem into information theory, cluster-based supervised classification, and the implementation of key concepts, particularly information entropy and mutual information. These concepts are combined with unsupervised learning atop learned chemical spaces to generate meaningful labels for arbitrary collections of molecules. An open-source and highly extensible codebase is provided to undertake these experiments, demonstrate the viability of the approach on known clusters, and glean insights into the learned representations of chemical space within message-passing neural networks, an architecture not readily permitting interpretability. This approach facilitates the interoperability between human chemical knowledge and the algorithmically derived insights, which will continue to become more prevalent in the coming years.

Sunitinib-Containing Carborane Pharmacophore with the Ability to Inhibit Tyrosine Kinases Receptors FLT3, KIT and PDGFR-β, Exhibits Powerful In Vivo Anti-Glioblastoma Activity

Simple Summary

Glioblastoma is one of the most aggressive central nervous system tumors. Combinations of therapies, such as tyrosine kinase receptor inhibition and boron neutron capture therapy (BNCT), could offer greater patients benefits over single-therapies. The aim of our study was to assess the potential of sunitinib-carborane hybrid compound 1 as an anti-glioblastoma agent. We confirmed for 1 the ability to inhibit tyrosine kinase receptors, which could promote canonical and non-canonical effects, absence of mutagenicity, ability to cross the blood–brain barrier, and powerful in vivo anti-glioblastoma activity. The overall attractive profile of 1 makes it an interesting compound for a bimodal therapeutic strategy against high grade gliomas.

Abstract

Malignant gliomas are the most common malignant and aggressive primary brain tumors in adults, the prognosis being—especially for glioblastomas—extremely poor. There are no effective treatments yet. However, tyrosine kinase receptor (TKR) inhibitors and boron neutron capture therapy (BNCT), together, have been proposed as future therapeutic strategies. In this sense in our ongoing project of developing new anti-glioblastoma drugs, we identified a sunitinib-carborane hybrid agent, 1, with both in vitro selective cytotoxicity and excellent BNCT-behavior. Consequently, we studied the ability of compound 1 to inhibit TKRs, its promotion of cellular death processes, and its effects on the cell cycle. Moreover, we analyzed some relevant drug-like properties of 1, i.e., mutagenicity and ability to cross the blood–brain barrier. These results encouraged us to perform an in vivo anti-glioblastoma proof of concept assay. It turned out to be a selective FLT3, KIT, and PDGFR-β inhibitor and increased the apoptotic glioma-cell numbers and arrested sub-G1-phase cell cycle. Its in vivo activity in immunosuppressed mice bearing U87 MG human glioblastoma evidenced excellent anti-tumor behavior.

High-throughput screening and Bayesian machine learning for copper-dependent inhibitors of Staphylococcus aureus

One potential source of new antibacterials is through probing existing chemical libraries for copper-dependent inhibitors (CDIs), i.e., molecules with antibiotic activity only in the presence of copper. Recently, our group demonstrated that previously unknown staphylococcal CDIs were frequently present in a small pilot screen. Here, we report the outcome of a larger industrial anti-staphylococcal screen consisting of 40 771 compounds assayed in parallel, both in standard and in copper-supplemented media. Ultimately, 483 had confirmed copper-dependent IC50 values under 50 μM. Sphere-exclusion clustering revealed that these hits were largely dominated by sulfur-containing motifs, including benzimidazole-2-thiones, thiadiazines, thiazoline formamides, triazino-benzimidazoles, and pyridinyl thieno-pyrimidines. Structure-activity relationship analysis of the pyridinyl thieno-pyrimidines generated multiple improved CDIs, with activity likely dependent on ligand/ion coordination. Molecular fingerprint-based Bayesian classification models were built using Discovery Studio and Assay Central, a new platform for sharing and distributing cheminformatic models in a portable format, based on open-source tools. Finally, we used the latter model to evaluate a library of FDA-approved drugs for copper-dependent activity in silico. Two anti-helminths, albendazole and thiabendazole, scored highly and are known to coordinate copper ions, further validating the model's applicability.

Carboranylanilinoquinazoline EGFR-inhibitors: toward ‘lead-to-candidate’ stage in the drug-development pipeline

Background: Carboranylanilinoquinazoline-hybrids, developed for boron neutron capture therapy, have demonstrated cytotoxicity against murine-glioma cells with EGFR-inhibition ability. In addition, their adequate aqueous/metabolic stabilities and ability to cross blood–brain barrier make them good leads as to become antiglioma drugs. Aim: Analyze drug-like properties of representative carboranylanilinoquinazolines. Materials & methods: To expand carboranylanilinoquinazolines therapeutic spectrum, we studied their ability to act against glioma-mammal cells, U-87 MG and other tyrosine kinase-overexpress cells, HT-29. Additionally, we predicted theoretically and studied experimentally drug-like properties, in other words, organization for economic cooperation and development-recommended toxicity-studies and, due to some aqueous-solubility problems, and vehicularization for oral and intravenous administrations. Conclusion: We have identified a promising drug-candidate with broad activity spectrum, appropriate drug-like properties, adequate toxicological behavior and able ability to be loaded in suitable vehicles.

Antitumor Cannabinoid Chemotypes: Structural Insights

Cannabis has long been known to limit or prevent nausea and vomiting, lack of appetite, and pain. For this reason, cannabinoids have been successfully used in the treatment of some of the unwanted side effects caused by cancer chemotherapy. Besides their palliative effects, research from the past two decades has demonstrated their promising potential as antitumor agents in a wide variety of tumors. Cannabinoids of endogenous, phytogenic, and synthetic nature have been shown to impact the proliferation of cancer through the modulation of different proteins involved in the endocannabinoid system such as the G protein-coupled receptors CB1, CB2, and GRP55, the ionotropic receptor TRPV1, or the fatty acid amide hydrolase (FAAH). In this article, we aim to structurally classify the antitumor cannabinoid chemotypes described so far according to their targets and types of cancer. In a drug discovery approach, their in silico pharmacokinetic profile has been evaluated in order to identify appropriate drug-like profiles, which should be taken into account for further progress toward the clinic. This analysis may provide structural insights into the selection of specific cannabinoid scaffolds for the development of antitumor drugs for the treatment of particular types of cancer.

Conservation and Relevance of Pharmacophore Point Types

Pharmacophore models in general use a variety of features for distinct chemical characteristics, such as hydrogen-bond properties, lipohilicity, and ionizability. Usually, features have to match onto their identical type. To clarify if this stringent one-to-one assignment is justified, we investigated a set of 581 unique ligands from the BindingDB with known orientation inside the respective binding pockets and conducted a statistical analysis of the likelihood of observed exchanges in between the pharmacophore features, respectively their degree of conservation. To find out if certain features are obsolete, we derived a ranking to determine the most relevant ones. We found that the most conserved one-to-one feature is the negative ionizable (acids), followed by hydrogen-bond donor, positive ionizable (basic nitrogens), hydrogen-bond acceptor, aromatic, nonaromatic π-systems, and other lipophilic characteristics. The most likely exchanges were found between carboxylate groups and hydrogen-bond acceptors and likewise between basic nitrogens and hydrogen-bond donors, which reflects the characteristics of Lewis acids and bases. Exchanges between hydrogen-bond donors and hydrogen-bond acceptors are hardly more likely than by chance. The kind of target (e.g., kinase, phosphatase, protease, phosphodiesterase, nuclear receptor, metal-containing, or transmembrane protein) did not show substantial influence on the degree of conservation. The relevance of the actual pharmacophore features was found to be strongly dependent on the applied ranking scheme. Mutual information ranks all hydrophobic features as least important, whereas the aromatic feature is put into second place by using a geometric series. Both ranking schemes see the negative ionizable feature of higher significance than the positively ionizable feature.

ADMET-score - a comprehensive scoring function for evaluation of chemical drug-likeness

Chemical absorption, distribution, metabolism, excretion, and toxicity (ADMET), play key roles in drug discovery and development. A high-quality drug candidate should not only have sufficient efficacy against the therapeutic target, but also show appropriate ADMET properties at a therapeutic dose. A lot of in silico models are hence developed for prediction of chemical ADMET properties. However, it is still not easy to evaluate the drug-likeness of compounds in terms of so many ADMET properties. In this study, we proposed a scoring function named the ADMET-score to evaluate drug-likeness of a compound. The scoring function was defined on the basis of 18 ADMET properties predicted via our web server admetSAR. The weight of each property in the ADMET-score was determined by three parameters: the accuracy rate of the model, the importance of the endpoint in the process of pharmacokinetics, and the usefulness index. The FDA-approved drugs from DrugBank, the small molecules from ChEMBL and the old drugs withdrawn from the market due to safety concerns were used to evaluate the performance of the ADMET-score. The indices of the arithmetic mean and p-value showed that the ADMET-score among the three data sets differed significantly. Furthermore, we learned that there was no obvious linear correlation between the ADMET-score and QED (quantitative estimate of drug-likeness). These results suggested that the ADMET-score would be a comprehensive index to evaluate chemical drug-likeness, and might be helpful for users to select appropriate drug candidates for further development.

The current limits in virtual screening and property prediction

Beyond finding inhibitors that show high binding affinity to the respective target, there is the challenge of optimizing their properties with respect to metabolic and toxicological issues, as well as further off-target effects. To reduce the experimental effort of synthesizing and testing actual substances in corresponding assays, virtual screening has become an indispensable toolbox in preclinical development. The scope of application covers the prediction of molecular properties including solubility, metabolic liability and binding to antitargets, such as the hERG channel. Furthermore, prediction of binding sites and drugable targets are emerging aspects of virtual screening. Issues involved with the currently applied computational models including machine learning algorithms are outlined, such as limitations to the accuracy of prediction and overfitting.

IMPPAT: A curated database of Indian Medicinal Plants, Phytochemistry And Therapeutics

Phytochemicals of medicinal plants encompass a diverse chemical space for drug discovery. India is rich with a flora of indigenous medicinal plants that have been used for centuries in traditional Indian medicine to treat human maladies. A comprehensive online database on the phytochemistry of Indian medicinal plants will enable computational approaches towards natural product based drug discovery. In this direction, we present, IMPPAT, a manually curated database of 1742 Indian Medicinal Plants, 9596 Phytochemicals, And 1124 Therapeutic uses spanning 27074 plant-phytochemical associations and 11514 plant-therapeutic associations. Notably, the curation effort led to a non-redundant in silico library of 9596 phytochemicals with standard chemical identifiers and structure information. Using cheminformatic approaches, we have computed the physicochemical, ADMET (absorption, distribution, metabolism, excretion, toxicity) and drug-likeliness properties of the IMPPAT phytochemicals. We show that the stereochemical complexity and shape complexity of IMPPAT phytochemicals differ from libraries of commercial compounds or diversity-oriented synthesis compounds while being similar to other libraries of natural products. Within IMPPAT, we have filtered a subset of 960 potential druggable phytochemicals, of which majority have no significant similarity to existing FDA approved drugs, and thus, rendering them as good candidates for prospective drugs. IMPPAT database is openly accessible at: https://cb.imsc.res.in/imppat.

SwissADME: a free web tool to evaluate pharmacokinetics, drug-likeness and medicinal chemistry friendliness of small molecules

To be effective as a drug, a potent molecule must reach its target in the body in sufficient concentration, and stay there in a bioactive form long enough for the expected biologic events to occur. Drug development involves assessment of absorption, distribution, metabolism and excretion (ADME) increasingly earlier in the discovery process, at a stage when considered compounds are numerous but access to the physical samples is limited. In that context, computer models constitute valid alternatives to experiments. Here, we present the new SwissADME web tool that gives free access to a pool of fast yet robust predictive models for physicochemical properties, pharmacokinetics, drug-likeness and medicinal chemistry friendliness, among which in-house proficient methods such as the BOILED-Egg, iLOGP and Bioavailability Radar. Easy efficient input and interpretation are ensured thanks to a user-friendly interface through the login-free website http://www.swissadme.ch. Specialists, but also nonexpert in cheminformatics or computational chemistry can predict rapidly key parameters for a collection of molecules to support their drug discovery endeavours.

In silico approach for the discovery of new PPARγ modulators among plant-derived polyphenols

Peroxisome proliferator-activated receptor gamma (PPARγ) is a well-characterized member of the PPAR family that is predominantly expressed in adipose tissue and plays a significant role in lipid metabolism, adipogenesis, glucose homeostasis, and insulin sensitization. Full agonists of synthetic thiazolidinediones (TZDs) have been therapeutically used in clinical practice to treat type 2 diabetes for many years. Although it can effectively lower blood glucose levels and improve insulin sensitivity, the administration of TZDs has been associated with severe side effects. Based on recent evidence obtained with plant-derived polyphenols, the present in silico study aimed at finding new selective human PPARγ (hPPARγ) modulators that are able to improve glucose homeostasis with reduced side effects compared with TZDs. Docking experiments have been used to select compounds with strong binding affinity (ΔG values ranging from −10.0±0.9 to −11.4±0.9 kcal/mol) by docking against the binding site of several X-ray structures of hPPARγ. These putative modulators present several molecular interactions with the binding site of the protein. Additionally, most of the selected compounds have favorable druggability and good ADMET properties. These results aim to pave the way for further bench-scale analysis for the discovery of new modulators of hPPARγ that do not induce any side effects.

Multivariate statistical analysis methods in QSAR

The emphasis of this review is particularly on multivariate statistical methods currently used in quantitative structure–activity relationship (QSAR) studies.

admetSAR: a comprehensive source and free tool for assessment of chemical ADMET properties

Absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties play key roles in the discovery/development of drugs, pesticides, food additives, consumer products, and industrial chemicals. This information is especially useful when to conduct environmental and human hazard assessment. The most critical rate limiting step in the chemical safety assessment workflow is the availability of high quality data. This paper describes an ADMET structure-activity relationship database, abbreviated as admetSAR. It is an open source, text and structure searchable, and continually updated database that collects, curates, and manages available ADMET-associated properties data from the published literature. In admetSAR, over 210,000 ADMET annotated data points for more than 96,000 unique compounds with 45 kinds of ADMET-associated properties, proteins, species, or organisms have been carefully curated from a large number of diverse literatures. The database provides a user-friendly interface to query a specific chemical profile, using either CAS registry number, common name, or structure similarity. In addition, the database includes 22 qualitative classification and 5 quantitative regression models with highly predictive accuracy, allowing to estimate ecological/mammalian ADMET properties for novel chemicals. AdmetSAR is accessible free of charge at http://www.admetexp.org.

Decision tree models for data mining in hit discovery

INTRODUCTION

Decision tree induction (DTI) is a powerful means of modeling data without much prior preparation. Models are readable by humans, robust and easily applied in real-world applications, features that are mutually exclusive in other commonly used machine learning paradigms. While DTI is widely used in disciplines ranging from economics to medicine, they are an intriguing option in pharmaceutical research, especially when dealing with large data stores.

AREAS COVERED

This review covers the automated technologies available for creating decision trees and other rules efficiently, even from large datasets such as chemical libraries. The authors discuss the need for properly documented and validated models. Lastly, the authors cover several case studies in hit discovery, drug metabolism and toxicology, and drug surveillance, and compare them with other established techniques.

EXPERT OPINION

DTI is a competitive and easy-to-use tool in basic research as well as in hit and drug discovery. Its strengths lie in its ability to handle all sorts of different data formats, the visual nature of the models, and the small computational effort needed for implementation in real-world systems. Limitations include lack of robustness and over-fitted models for certain types of data. As with any modeling technique, proper validation and quality measures are of utmost importance.