Search

Abstract Traditional best practices for quantitative structure activity relationship (QSAR) modeling recommend dataset balancing and balanced accuracy (BA) as the key desired objective of model development. This study explores the value of the conventional norms in the context of using QSAR models for virtual screening of modern large and ultra-large chemical libraries. For this increasingly common task, we now recommend the use of models with the highest positive predictive value (PPV) built on imbalanced training sets as preferred virtual screening tools. This recommendation stems from practical considerations of how the results of virtual screening are used in experimental laboratories where only a small fraction of virtually screened molecules can be tested using standard well plates. As a proof of concept, we have developed QSAR models for five expansive datasets with different ratios of active and inactive molecules and compared model performance in virtual screening using BA, PPV, and other metrics. We show that training on imbalanced datasets achieves a hit rate at least 30% higher than using balanced datasets, and that the PPV metric captured this difference of performance with no parameter tuning. Importantly, hit rates were estimated for top scoring compounds organized in batches of the size of plates (for instance, 128 molecules) used in the experimental high throughput screening. Based on the results of our studies, we posit that QSAR models trained on imbalanced datasets with the highest PPV should be relied upon to identify and test hit compounds in early drug discovery studies.

Skin sensitization is a significant concern for chemical safety assessments. Traditional animal assays often fail to predict human responses accurately, and ethical constraints limit the collection of human data, necessitating a need for reliable in silico models of skin sensitization prediction. This study introduces HuSSPred, an in silico tool based on the Human Predictive Patch Test (HPPT). HuSSPred aims to enhance the reliability of predicting human skin sensitization effects for chemical agents to support their regulatory assessment. We have curated an extensive HPPT database and performed chemical space analysis and grouping. Binary and multiclass QSAR models were developed with Bayesian hyperparameter optimization. Model performance was evaluated via five-fold cross-validation. We performed model validation with reference data from the Defined Approaches for Skin Sensitization (DASS) app. HuSSPred models demonstrated strong predictive performance with CCR ranging from 55 to 88%, sensitivity between 48 and 89%, and specificity between 37 and 92%. The positive predictive value (PPV) ranged from 84 to 97%, versus negative predictive value (NPV) from 22 to 65%, and coverage was between 75 and 93%. Our models exhibited comparable or improved performance compared to existing tools, and the external validation showed the high accuracy and sensitivity of the developed models. HuSSPred provides a reliable, open-access, and ethical alternative to traditional testing for skin sensitization. Its high accuracy and reasonable coverage make it a valuable resource for regulatory assessments, aligning with the 3Rs principles. The publicly accessible HuSSPred web tool offers a user-friendly interface for predicting skin sensitization based on chemical structure.

Designing magic shotgun compounds, i.e., compounds hitting multiple targets using artificial intelligence (AI) systems based on machine learning (ML) and deep learning (DL) approaches, has a huge potential to revolutionize drug discovery. Such intelligent systems enable computers to create new chemical structures and predict their multi-target properties at a low cost and in a time-efficient manner. Most examples of AI applied to drug discovery are single-target oriented and there is still a lack of concise information regarding the application of this technology for the discovery of multi-target drugs or drugs with broad-spectrum action. In this review, we focus on current developments in AI systems for the next generation of automated design of multi-target drugs. We discuss how classical ML methods, cutting-edge generative models, and multi-task deep neural networks can help de novo design and hit-to-lead optimization of multi-target drugs. Moreover, we present state-of-the-art workflows and highlight some studies demonstrating encouraging experimental results, which pave the way for de novo drug design and multi-target drug discovery.

Chemically induced toxicity is the leading cause of recent extinction of honey bees. In this regard, we developed an innovative artificial intelligence-based web app (BeeToxAI) for assessing the acute toxicity of chemicals to Apis mellifera. Initially, we developed and externally validated QSAR models for classification (external set accuracy ∼91%) through the combination of Random Forest and molecular fingerprints to predict the potential for chemicals to cause acute contact toxicity and acute oral toxicity to honey bees. Then, we developed and externally validated regression QSAR models (R2 = 0.75) using Feedforward Neural Networks (FNNs). Afterward, the best models were implemented in the publicly available BeeToxAI web app (http://beetoxai.labmol.com.br/). The outputs of BeeToxAI are: toxicity predictions with estimated confidence, applicability domain estimation, and color-coded maps of relative structure fragment contributions to toxicity. As an additional assessment of BeeToxAI performance, we collected an external set of pesticides with known bee toxicity that were not included in our modeling dataset. BeeToxAI classification models were able to predict four out of five pesticides correctly. The acute contact toxicity model correctly predicted all of the eight pesticides. Here we demonstrate that BeeToxAI can be used as a rapid new approach methodology for predicting acute toxicity of chemicals in honey bees.

The World Health Organization classifies Leishmania as one of the 17 “neglected diseases” that burden tropical and sub-tropical climate regions with over half a million diagnosed cases each year. Despite this, currently available anti-leishmania drugs have high toxicity and the potential to be made obsolete by parasite drug resistance. We chose to analyze organoselenides for leishmanicidal potential given the reduced toxicity inherent to selenium and the displayed biological activity of organoselenides against Leishmania. Thus, the biological activities of 77 selenoesters and their N-aryl-propanamide derivatives were predicted using robust in silico models of Leishmania infantum, Leishmania amazonensis, Leishmania major, and Leishmania (Viannia) braziliensis. The models identified 28 compounds with >60% probability of demonstrating leishmanicidal activity against L. infantum, and likewise, 26 for L. amazonesis, 25 for L. braziliensis, and 23 for L. major. The in silico prediction of ADMET properties suggests high rates of oral absorption and good bioavailability for these compounds. In the in silico toxicity evaluation, only seven compounds showed signs of toxicity in up to one or two parameters. The methodology was corroborated with the ensuing experimental validation, which evaluated the inhibition of the Promastigote form of the Leishmania species under study. The activity of the molecules was determined by the IC50 value (µM); IC50 values < 20 µM indicated better inhibition profiles. Sixteen compounds were synthesized and tested for their activity. Eight molecules presented IC50 values < 20 µM for at least one of the Leishmania species under study, with compound NC34 presenting the strongest parasite inhibition profile. Furthermore, the methodology used was effective, as many of the compounds with the highest probability of activity were confirmed by the in vitro tests performed.

Leishmaniasis is a neglected tropical disease caused by parasites of the genus Leishmania (NTD) endemic in 98 countries. Although some drugs are available, current treatments deal with issues such as toxicity, low efficacy, and emergence of resistance. Therefore, there is an urgent need to identify new targets for the development of new antileishmanial drugs. Protein kinases (PKs), which play an essential role in many biological processes, have become potential drug targets for many parasitic diseases. A refined bioinformatics pipeline was applied in order to define and compare the kinomes of L. infantum and L. braziliensis, species that cause cutaneous and visceral manifestations of leishmaniasis in the Americas, the latter being potentially fatal if untreated. Respectively, 224 and 221 PKs were identified in L. infantum and L. braziliensis overall. Almost all unclassified eukaryotic PKs were assigned to six of nine major kinase groups and, consequently, most have been classified into family and subfamily. Furthermore, revealing the kinomes for both Leishmania species allowed for the prioritization of potential drug targets that could be explored for discovering new drugs against leishmaniasis. Finally, we used a drug repurposing approach and prioritized seven approved drugs and investigational compounds to be experimentally tested against Leishmania. Trametinib and NMS-1286937 inhibited the growth of L. infantum and L. braziliensis promastigotes and amastigotes and therefore might be good candidates for the drug repurposing pipeline. Keywords: Leishmania infantum, Leishmania braziliensis, Kinome, Kinases, Drug repurposing, Target prioritization

Malaria is an infectious disease that affects over 216 million people worldwide, killing over 445,000 patients annually. Due to the constant emergence of parasitic resistance to the current antimalarial drugs, the discovery of new drug candidates is a major global health priority. Aiming to make the drug discovery processes faster and less expensive, we developed binary and continuous Quantitative Structure-Activity Relationships (QSAR) models implementing deep learning for predicting antiplasmodial activity and cytotoxicity of untested compounds. Then, we applied the best models for a virtual screening of a large database of chemical compounds. The top computational predictions were evaluated experimentally against asexual blood stages of both sensitive and multi-drug-resistant Plasmodium falciparum strains. Among them, two compounds, LabMol-149 and LabMol-152, showed potent antiplasmodial activity at low nanomolar concentrations (EC50

The poor aqueous solubility of active pharmaceutical ingredients (APIs) places a limit on their therapeutic potential. Cyclodextrins (CDs) have been shown to improve the solubility of APIs, but the magnitude of the improvement depends on the structure of both the CDs and APIs. We have developed quantitative structure–property relationship (QSPR) models that predict the stability of the complexes formed by a popular poorly soluble antibiotic, cefuroxime axetil (CA) and different CDs. We applied this model to five CA–CD systems not included in the modeling set. Two out of three systems predicted to have poor stability and poor CA solubility, and both CA–CD systems predicted to have high stability and high CA solubility were confirmed experimentally. One of the CDs that significantly improved CA solubility, methyl-βCD, is described here for the first time, and we propose this CD as a novel promising excipient. Computational approaches and models developed and validated in this study could help accelerate the development of multifunctional CDs-based formulations.

Virtual screening (VS) has emerged in drug discovery as a powerful computational approach to screen large libraries of small molecules for new hits with desired properties that can then be tested experimentally. Similar to other computational approaches, VS intention is not to replace in vitro or in vivo assays, but to speed up the discovery process, to reduce the number of candidates to be tested experimentally, and to rationalize their choice. Moreover, VS has become very popular in pharmaceutical companies and academic organizations due to its time-, cost-, resources-, and labor-saving. Among the VS approaches, quantitative structure–activity relationship (QSAR) analysis is the most powerful method due to its high and fast throughput and good hit rate. As the first preliminary step of a QSAR model development, relevant chemogenomics data are collected from databases and the literature. Then, chemical descriptors are calculated on different levels of representation of molecular structure, ranging from 1D to nD, and then correlated with the biological property using machine learning techniques. Once developed and validated, QSAR models are applied to predict the biological property of novel compounds. Although the experimental testing of computational hits is not an inherent part of QSAR methodology, it is highly desired and should be performed as an ultimate validation of developed models. In this mini-review, we summarize and critically analyze the recent trends of QSAR-based VS in drug discovery and demonstrate successful applications in identifying perspective compounds with desired properties. Moreover, we provide some recommendations about the best practices for QSAR-based VS along with the future perspectives of this approach.

The development of novel therapeutics is urgently required for diseases where existing treatments are failing due to the emergence of resistance. This is particularly pertinent for parasitic infections of the tropics and sub-tropics, referred to collectively as neglected tropical diseases, where the commercial incentives to develop new drugs are weak. One such disease is schistosomiasis, a highly prevalent acute and chronic condition caused by a parasitic helminth infection, with three species of the genus Schistosoma infecting humans. Currently, a single 40-year old drug, praziquantel, is available to treat all infective species, but its use in mass drug administration is leading to signs of drug-resistance emerging. To meet the challenge of developing new therapeutics against this disease, we developed an innovative computational drug repurposing pipeline supported by phenotypic screening. The approach highlighted several protein kinases as interesting new biological targets for schistosomiasis as they play an essential role in many parasite's biological processes. Focusing on this target class, we also report the first elucidation of the kinome of Schistosoma japonicum, as well as updated kinomes of S. mansoni and S. haematobium. In comparison with the human kinome, we explored these kinomes to identify potential targets of existing inhibitors which are unique to Schistosoma species, allowing us to identify novel targets and suggest approved drugs that might inhibit them. These include previously suggested schistosomicidal agents such as bosutinib, dasatinib, and imatinib as well as new inhibitors such as vandetanib, saracatinib, tideglusib, alvocidib, dinaciclib, and 22 newly identified targets such as CHK1, CDC2, WEE, PAKA, MEK1. Additionally, the primary and secondary targets in Schistosoma of those approved drugs are also suggested, allowing for the development of novel therapeutics against this important yet neglected disease.

Malaria is a life-threatening infectious disease caused by parasites of the genus Plasmodium, affecting more than 200 million people worldwide every year and leading to about a half million deaths. Malaria parasites of humans have evolved resistance to all current antimalarial drugs, urging for the discovery of new effective compounds. Given that the inhibition of deoxyuridine triphosphatase of Plasmodium falciparum (PfdUTPase) induces wrong insertions in plasmodial DNA and consequently leading the parasite to death, this enzyme is considered an attractive antimalarial drug target. Using a combi-QSAR (quantitative structure-activity relationship) approach followed by virtual screening and in vitro experimental evaluation, we report herein the discovery of novel chemical scaffolds with in vitro potency against asexual blood stages of both P. falciparum multidrug-resistant and sensitive strains and against sporogonic development of P. berghei. We developed 2D- and 3D-QSAR models using a series of nucleosides reported in the literature as PfdUTPase inhibitors. The best models were combined in a consensus approach and used for virtual screening of the ChemBridge database, leading to the identification of five new virtual PfdUTPase inhibitors. Further in vitro testing on P. falciparum multidrug-resistant (W2) and sensitive (3D7) parasites showed that compounds LabMol-144 and LabMol-146 demonstrated fair activity against both strains and presented good selectivity versus mammalian cells. In addition, LabMol-144 showed good in vitro inhibition of P. berghei ookinete formation, demonstrating that hit-to-lead optimization based on this compound may also lead to new antimalarials with transmission blocking activity.

Medicinal chemists continue to be fascinated by chalcone derivatives because of their simple chemistry, ease of hydrogen atom manipulation, straightforward synthesis, and a variety of promising biological activities. However, chalcones have still not garnered deserved attention, especially considering their high potential as chemical sources for designing and developing new effective drugs. In this review, we summarize current methodological developments towards the design and synthesis of new chalcone derivatives and state-of-the-art medicinal chemistry strategies (bioisosterism, molecular hybridization, and pro-drug design). We also highlight the applicability of computer-assisted drug design approaches to chalcones and address how this may contribute to optimizing research outputs and lead to more successful and cost-effective drug discovery endeavors. Lastly, we present successful examples of the use of chalcones and suggest possible solutions to existing limitations.

Enoxaparin is a low-molecular weight heparin used to treat thrombotic disorders. Following the fatal contamination of the heparin supply chain in 2007–2008, the U.S. Pharmacopeia (USP) and U.S. Food and Drug Administration (FDA) have worked extensively to modernize the unfractionated heparin and enoxaparin monographs. As a result, the determination of molecular weight (MW) has been added to the monograph as a measure to strengthen the quality testing and to increase the protection of the global supply of this life-saving drug. The current USP calibrant materials used for enoxaparin MW determination are composed of a mixture of oligosaccharides; however, they are difficult to reproduce as the calibrants have ill-defined structures due to the heterogeneity of the heparin parent material. To address this issue, we describe a promising approach consisting of a predictive computational model built from a library of chemoenzymatically synthesized heparin oligosaccharides for enoxaparin MW determination. Here, we demonstrate that this test can be performed with greater efficiency by coupling synthetic oligosaccharides with the power of computational modeling. Our approach is expected to improve the MW measurement for enoxaparin.

Cheminformatics is an interdisciplinary field between chemistry and informatics, which has evolved considerably since its inception in the 1960s. Initially, the cheminformatics community dealt primarily with practical and technical aspects of chemical structure representation, manipulation, and processing, while modern research explores a new role: the exploration and interpretation of large chemical databases and the discovery of new compounds with desired activity and safety profiles. Despite the recent release of several hallmark reviews addressing methods and application of cheminformatics written in Portuguese, so far there are no scientific articles presenting cheminformatics research to the Brazilian scientific community yet. To address this gap, we aim to introduce the field of cheminformatics to both students and researchers in a simple and didactic way by narrating important historical facts and contextualizing information within the scope of various applications.