High-Throughput Phenotypic Screening and Machine Learning Methods Enabled the Selection of Broad-Spectrum Low-Toxicity Antitrypanosomatidic Agents

Broad-spectrum anti-infective chemotherapy agents with activity against Trypanosomes, Leishmania, and Mycobacterium tuberculosis species were identified from a high-throughput phenotypic screening program of the 456 compounds belonging to the Ty-Box, an in-house industry database. Compound characterization using machine learning approaches enabled the identification and synthesis of 44 compounds with broad-spectrum antiparasitic activity and minimal toxicity against Trypanosoma brucei, Leishmania Infantum, and Trypanosoma cruzi. In vitro studies confirmed the predictive models identified in compound 40 which emerged as a new lead, featured by an innovative N-(5-pyrimidinyl)benzenesulfonamide scaffold and promising low micromolar activity against two parasites and low toxicity. Given the volume and complexity of data generated by the diverse high-throughput screening assays performed on the compounds of the Ty-Box library, the chemoinformatic and machine learning tools enabled the selection of compounds eligible for further evaluation of their biological and toxicological activities and aided in the decision-making process toward the design and optimization of the identified lead.

Multiple approaches to repurposing drugs for neuroblastoma

Neuroblastoma (NB) is the second leading extracranial solid tumor of early childhood with about two-thirds of cases presenting before the age of 5, and accounts for roughly 15 percent of all pediatric cancer fatalities in the United States. Treatments against NB are lacking, resulting in a low survival rate in high-risk patients. A repurposing approach using already approved or clinical stage compounds can be used for diseases for which the patient population is small, and the commercial market limited. We have used Bayesian machine learning, in vitro cell assays, and combination analysis to identify molecules with potential use for NB. We demonstrated that pyronaridine (SH-SY5Y IC50 1.70 µM, SK-N-AS IC50 3.45 µM), BAY 11-7082 (SH-SY5Y IC50 0.85 µM, SK-N-AS IC50 1.23 µM), niclosamide (SH-SY5Y IC50 0.87 µM, SK-N-AS IC50 2.33 µM) and fingolimod (SH-SY5Y IC50 4.71 µM, SK-N-AS IC50 6.11 µM) showed cytotoxicity against NB. As several of the molecules are approved drugs in the US or elsewhere, they may be repurposed more readily for NB treatment. Pyronaridine was also tested in combinations in SH-SY5Y cells and demonstrated an antagonistic effect with either etoposide or crizotinib. Whereas when crizotinib and etoposide were combined with each other they had a synergistic effect in these cells. We have also described several analogs of pyronaridine to explore the structure-activity relationship against cell lines. We describe multiple molecules demonstrating cytotoxicity against NB and the further evaluation of these molecules and combinations using other NB cells lines and in vivo models will be important in the future to assess translational potential.

Mycobacterium abscessus drug discovery using machine learning

The prevalence of infections by nontuberculous mycobacteria is increasing, having surpassed tuberculosis in the United States and much of the developed world. Nontuberculous mycobacteria occur naturally in the environment and are a significant problem for patients with underlying lung diseases such as bronchiectasis, chronic obstructive pulmonary disease, and cystic fibrosis. Current treatment regimens are lengthy, complicated, toxic and they are often unsuccessful as seen by disease recurrence. Mycobacterium abscessus is one of the most commonly encountered organisms in nontuberculous mycobacteria disease and it is the most difficult to eradicate. There is currently no systematically proven regimen that is effective for treating M. abscessus infections. Our approach to drug discovery integrates machine learning, medicinal chemistry and in vitro testing and has been previously applied to Mycobacterium tuberculosis. We have now identified several novel 1-(phenylsulfonyl)-1H-benzimidazol-2-amines that have weak activity on M. abscessus in vitro but may represent a starting point for future further medicinal chemistry optimization. We also address limitations still to be overcome with the machine learning approach for M. abscessus.

Remdesivir and EIDD-1931 Interact with Human Equilibrative Nucleoside Transporters 1 and 2: Implications for Reaching SARS-CoV-2 Viral Sanctuary Sites

Equilibrative nucleoside transporters (ENTs) are present at the blood-testis barrier (BTB), where they can facilitate antiviral drug disposition to eliminate a sanctuary site for viruses detectable in semen. The purpose of this study was to investigate ENT-drug interactions with three nucleoside analogs, remdesivir, molnupiravir, and molnupiravir's active metabolite, β-d-N⁴-hydroxycytidine (EIDD-1931), and four non-nucleoside molecules repurposed as antivirals for coronavirus disease 2019 (COVID-19). The study used three-dimensional pharmacophores for ENT1 and ENT2 substrates and inhibitors and Bayesian machine learning models to identify potential interactions with these transporters. In vitro transport experiments demonstrated that remdesivir was the most potent inhibitor of ENT-mediated [³H]uridine uptake (ENT1 IC₅₀: 39 μM; ENT2 IC₅₀: 77 μM), followed by EIDD-1931 (ENT1 IC₅₀: 259 μM; ENT2 IC₅₀: 467 μM), whereas molnupiravir was a modest inhibitor (ENT1 IC₅₀: 701 μM; ENT2 IC₅₀: 851 μM). Other proposed antivirals failed to inhibit ENT-mediated [³H]uridine uptake below 1 mM. Remdesivir accumulation decreased in the presence of 6-S-[(4-nitrophenyl)methyl]-6-thioinosine (NBMPR) by 30% in ENT1 cells (P = 0.0248) and 27% in ENT2 cells (P = 0.0054). EIDD-1931 accumulation decreased in the presence of NBMPR by 77% in ENT1 cells (P = 0.0463) and by 64% in ENT2 cells (P = 0.0132), which supported computational predictions that both are ENT substrates that may be important for efficacy against COVID-19. NBMPR failed to decrease molnupiravir uptake, suggesting that ENT interaction is likely inhibitory. Our combined computational and in vitro data can be used to identify additional ENT-drug interactions to improve our understanding of drugs that can circumvent the BTB. SIGNIFICANCE STATEMENT: This study identified remdesivir and EIDD-1931 as substrates of equilibrative nucleoside transporters 1 and 2. This provides a potential mechanism for uptake of these drugs into cells and may be important for antiviral potential in the testes and other tissues expressing these transporters.

Machine Learning Models Identify Inhibitors of SARS-CoV-2

With the rapidly evolving SARS-CoV-2 variants of concern, there is an urgent need for the discovery of further treatments for the coronavirus disease (COVID-19). Drug repurposing is one of the most rapid strategies for addressing this need, and numerous compounds have already been selected for in vitro testing by several groups. These have led to a growing database of molecules with in vitro activity against the virus. Machine learning models can assist drug discovery through prediction of the best compounds based on previously published data. Herein, we have implemented several machine learning methods to develop predictive models from recent SARS-CoV-2 in vitro inhibition data and used them to prioritize additional FDA-approved compounds for in vitro testing selected from our in-house compound library. From the compounds predicted with a Bayesian machine learning model, lumefantrine, an antimalarial was selected for testing and showed limited antiviral activity in cell-based assays while demonstrating binding (K_d 259 nM) to the spike protein using microscale thermophoresis. Several other compounds which we prioritized have since been tested by others and were also found to be active in vitro. This combined machine learning and in vitro testing approach can be expanded to virtually screen available molecules with predicted activity against SARS-CoV-2 reference WIV04 strain and circulating variants of concern. In the process of this work, we have created multiple iterations of machine learning models that can be used as a prioritization tool for SARS-CoV-2 antiviral drug discovery programs. The very latest model for SARS-CoV-2 with over 500 compounds is now freely available at www.assaycentral.org.

Development of Machine Learning Models and the Discovery of a New Antiviral Compound against Yellow Fever Virus

Yellow fever (YF) is an acute viral hemorrhagic disease transmitted by infected mosquitoes. Large epidemics of YF occur when the virus is introduced into heavily populated areas with high mosquito density and low vaccination coverage. The lack of a specific small molecule drug treatment against YF as well as for homologous infections, such as zika and dengue, highlights the importance of these flaviviruses as a public health concern. With the advancement in computer hardware and bioactivity data availability, new tools based on machine learning methods have been introduced into drug discovery, as a means to utilize the growing high throughput screening (HTS) data generated to reduce costs and increase the speed of drug development. The use of predictive machine learning models using previously published data from HTS campaigns or data available in public databases, can enable the selection of compounds with desirable bioactivity and absorption, distribution, metabolism, and excretion profiles. In this study, we have collated cell-based assay data for yellow fever virus from the literature and public databases. The data were used to build predictive models with several machine learning methods that could prioritize compounds for in vitro testing. Five molecules were prioritized and tested in vitro from which we have identified a new pyrazolesulfonamide derivative with EC₅₀ 3.2 μM and CC₅₀ 24 μM, which represents a new scaffold suitable for hit-to-lead optimization that can expand the available drug discovery candidates for YF.

Quantum Machine Learning Algorithms for Drug Discovery Applications

The growing quantity of public and private data sets focused on small molecules screened against biological targets or whole organisms provides a wealth of drug discovery relevant data. This is matched by the availability of machine learning algorithms such as Support Vector Machines (SVM) and Deep Neural Networks (DNN) that are computationally expensive to perform on very large data sets with thousands of molecular descriptors. Quantum computer (QC) algorithms have been proposed to offer an approach to accelerate quantum machine learning over classical computer (CC) algorithms, however with significant limitations. In the case of cheminformatics, which is widely used in drug discovery, one of the challenges to overcome is the need for compression of large numbers of molecular descriptors for use on a QC. Here, we show how to achieve compression with data sets using hundreds of molecules (SARS-CoV-2) to hundreds of thousands of molecules (whole cell screening data sets for plague and M. tuberculosis) with SVM and the data reuploading classifier (a DNN equivalent algorithm) on a QC benchmarked against CC and hybrid approaches. This study illustrates the steps needed in order to be "quantum computer ready" in order to apply quantum computing to drug discovery and to provide the foundation on which to build this field.

Correction to "Using Bibliometric Analysis and Machine Learning to Identify Compounds Binding to Sialidase-1"

[This corrects the article DOI: 10.1021/acsomega.0c05591.].

Comparing the Pfizer Central Nervous System Multiparameter Optimization Calculator and a BBB Machine Learning Model

The ability to calculate whether small molecules will cross the blood-brain barrier (BBB) is an important task for companies working in neuroscience drug discovery. For a decade, scientists have relied on relatively simplistic rules such as Pfizer's central nervous system multiparameter optimization models (CNS-MPO) for guidance during the drug selection process. In parallel, there has been a continued development of more sophisticated machine learning models that utilize different molecular descriptors and algorithms; however, these models represent a "black box" and are generally less interpretable. In both cases, these methods predict the ability of small molecules to cross the BBB using the molecular structure information on its own without in vitro or in vivo data. We describe here the implementation of two versions of Pfizer's algorithm (Pf-MPO.v1 and Pf-MPO.v2) and compare it with a Bayesian machine learning model of BBB penetration trained on a data set of 2296 active and inactive compounds using extended connectivity fingerprint descriptors. The predictive ability of these approaches was compared with 40 known CNS active drugs initially used by Pfizer as their positive set for validation of the Pf-MPO.v1 score. 37/40 (92.5%) compounds were predicted as active by the Bayesian model, while only 30/40 (75%) received a desirable Pf-MPO.v1 score ≥4 and 33/40 (82.5%) received a desirable Pf-MPO.v2 score ≥4, suggesting the Bayesian model is more accurate than MPO algorithms. This also indicates machine learning models are more flexible and have better predictive power for BBB penetration than simple rule sets that require multiple, accurate descriptor calculations. Our machine learning model statistics are comparable to recent published studies. We describe the implications of these findings and how machine learning may have a role alongside more interpretable methods.

Multiple Computational Approaches for Predicting Drug Interactions with Human Equilibrative Nucleoside Transporter 1

Equilibrativenucleoside transporters (ENTs) participate in the pharmacokinetics and disposition of nucleoside analog drugs. Understanding drug interactions with the ENTs may inform and facilitate the development of new drugs, including chemotherapeutics and antivirals that require access to sanctuary sites such as the male genital tract. This study created three-dimensional pharmacophores for ENT1 and ENT2 substrates and inhibitors using K_t and IC₅₀ data curated from the literature. Substrate pharmacophores for ENT1 and ENT2 are distinct, with partial overlap of hydrogen bond donors, whereas the inhibitor pharmacophores predominantly feature hydrogen bond acceptors. Mizoribine and ribavirin mapped to the ENT1 substrate pharmacophore and proved to be substrates of the ENTs. The presence of the ENT-specific inhibitor 6-S-[(4-nitrophenyl)methyl]-6-thioinosine (NBMPR) decreased mizoribine accumulation in ENT1 and ENT2 cells (ENT1, ∼70% decrease, P = 0.0046; ENT2, ∼50% decrease, P = 0.0012). NBMPR also decreased ribavirin accumulation in ENT1 and ENT2 cells (ENT1: ∼50% decrease, P = 0.0498; ENT2: ∼30% decrease, P = 0.0125). Darunavir mapped to the ENT1 inhibitor pharmacophore and NBMPR did not significantly influence darunavir accumulation in either ENT1 or ENT2 cells (ENT1: P = 0.28; ENT2: P = 0.53), indicating that darunavir's interaction with the ENTs is limited to inhibition. These computational and in vitro models can inform compound selection in the drug discovery and development process, thereby reducing time and expense of identification and optimization of ENT-interacting compounds. SIGNIFICANCE STATEMENT: This study developed computational models of human equilibrative nucleoside transporters (ENTs) to predict drug interactions and validated these models with two compounds in vitro. Identification and prediction of ENT1 and ENT2 substrates allows for the determination of drugs that can penetrate tissues expressing these transporters.

CATMoS: Collaborative Acute Toxicity Modeling Suite

BACKGROUND

Humans are exposed to tens of thousands of chemical substances that need to be assessed for their potential toxicity. Acute systemic toxicity testing serves as the basis for regulatory hazard classification, labeling, and risk management. However, it is cost- and time-prohibitive to evaluate all new and existing chemicals using traditional rodent acute toxicity tests. In silico models built using existing data facilitate rapid acute toxicity predictions without using animals.

OBJECTIVES

The U.S. Interagency Coordinating Committee on the Validation of Alternative Methods (ICCVAM) Acute Toxicity Workgroup organized an international collaboration to develop in silico models for predicting acute oral toxicity based on five different end points: Lethal Dose 50 (LD50 value, U.S. Environmental Protection Agency hazard (four) categories, Globally Harmonized System for Classification and Labeling hazard (five) categories, very toxic chemicals [LD50 (LD50≤50mg/kg)], and nontoxic chemicals (LD50>2,000mg/kg).

METHODS

An acute oral toxicity data inventory for 11,992 chemicals was compiled, split into training and evaluation sets, and made available to 35 participating international research groups that submitted a total of 139 predictive models. Predictions that fell within the applicability domains of the submitted models were evaluated using external validation sets. These were then combined into consensus models to leverage strengths of individual approaches.

RESULTS

The resulting consensus predictions, which leverage the collective strengths of each individual model, form the Collaborative Acute Toxicity Modeling Suite (CATMoS). CATMoS demonstrated high performance in terms of accuracy and robustness when compared with in vivo results.

DISCUSSION

CATMoS is being evaluated by regulatory agencies for its utility and applicability as a potential replacement for in vivo rat acute oral toxicity studies. CATMoS predictions for more than 800,000 chemicals have been made available via the National Toxicology Program's Integrated Chemical Environment tools and data sets (ice.ntp.niehs.nih.gov). The models are also implemented in a free, standalone, open-source tool, OPERA, which allows predictions of new and untested chemicals to be made. https://doi.org/10.1289/EHP8495.

Flavonoids from Pterogyne nitens as Zika virus NS2B-NS3 protease inhibitors

Although the widespread epidemic of Zika virus (ZIKV) and its neurological complications are well-known there are still no approved drugs available to treat this arboviral disease or vaccine to prevent the infection. Flavonoids from Pterogyne nitens have already demonstrated anti-flavivirus activity, although their target is unknown. In this study, we virtually screened an in-house database of 150 natural and semi-synthetic compounds against ZIKV NS2B-NS3 protease (NS2B-NS3p) using docking-based virtual screening, as part of the OpenZika project. As a result, we prioritized three flavonoids from P. nitens, quercetin, rutin and pedalitin, for experimental evaluation. We also used machine learning models, built with Assay Central® software, for predicting the activity and toxicity of these flavonoids. Biophysical and enzymatic assays generally agreed with the in silico predictions, confirming that the flavonoids inhibited ZIKV protease. The most promising hit, pedalitin, inhibited ZIKV NS2B-NS3p with an IC50 of 5 μM. In cell-based assays, pedalitin displayed significant activity at 250 and 500 µM, with slight toxicity in Vero cells. The results presented here demonstrate the potential of pedalitin as a candidate for hit-to-lead (H2L) optimization studies towards the discovery of antiviral drug candidates to treat ZIKV infections.

A Machine Learning Strategy for Drug Discovery Identifies Anti-Schistosomal Small Molecules

Schistosomiasis is a chronic and painful disease of poverty caused by the flatworm parasite Schistosoma. Drug discovery for antischistosomal compounds predominantly employs in vitro whole organism (phenotypic) screens against two developmental stages of Schistosoma mansoni, post-infective larvae (somules) and adults. We generated two rule books and associated scoring systems to normalize 3898 phenotypic data points to enable machine learning. The data were used to generate eight Bayesian machine learning models with the Assay Central software according to parasite’s developmental stage and experimental time point (≤24, 48, 72, and >72 h). The models helped predict 56 active and nonactive compounds from commercial compound libraries for testing. When these were screened against S. mansoni in vitro, the prediction accuracy for active and inactives was 61% and 56% for somules and adults, respectively; also, hit rates were 48% and 34%, respectively, far exceeding the typical 1–2% hit rate for traditional high throughput screens.

Using Bibliometric Analysis and Machine Learning to Identify Compounds Binding to Sialidase-1

Rare diseases impact hundreds of millions of individuals worldwide. However, few therapies exist to treat the rare disease population because financial resources are limited, the number of patients affected is low, bioactivity data is often nonexistent, and very few animal models exist to support preclinical development efforts. Sialidosis is an ultrarare lysosomal storage disorder in which mutations in the NEU1 gene result in the deficiency of the lysosomal enzyme sialidase-1. This enzyme catalyzes the removal of sialic acid moieties from glycoproteins and glycolipids. Therefore, the defective or deficient protein leads to the buildup of sialylated glycoproteins as well as several characteristic symptoms of sialidosis including visual impairment, ataxia, hepatomegaly, dysostosis multiplex, and developmental delay. In this study, we used a bibliometric tool to generate links between lysosomal storage disease (LSD) targets and existing bioactivity data that could be curated in order to build machine learning models and screen compounds in silico. We focused on sialidase as an example, and we used the data curated from the literature to build a Bayesian model which was then used to score compound libraries and rank these molecules for in vitro testing. Two compounds were identified from in vitro testing using microscale thermophoresis, namely sulfameter (K _d 2.15 ± 1.02 μM) and mexenone (K _d 8.88 ± 4.02 μM), which validated our approach to identifying new molecules binding to this protein, which could represent possible drug candidates that can be evaluated further as potential chaperones for this ultrarare lysosomal disease for which there is currently no treatment. Combining bibliometric and machine learning approaches has the ability to assist in curating small molecule data and model building, respectively, for rare disease drug discovery. This approach also has the capability to identify new compounds that are potential drug candidates.

Bioactivity Comparison across Multiple Machine Learning Algorithms Using over 5000 Datasets for Drug Discovery

Machine learning methods are attracting considerable attention from the pharmaceutical industry for use in drug discovery and applications beyond. In recent studies, we and others have applied multiple machine learning algorithms and modeling metrics and, in some cases, compared molecular descriptors to build models for individual targets or properties on a relatively small scale. Several research groups have used large numbers of datasets from public databases such as ChEMBL in order to evaluate machine learning methods of interest to them. The largest of these types of studies used on the order of 1400 datasets. We have now extracted well over 5000 datasets from CHEMBL for use with the ECFP6 fingerprint and in comparison of our proprietary software Assay Central with random forest, k-nearest neighbors, support vector classification, naïve Bayesian, AdaBoosted decision trees, and deep neural networks (three layers). Model performance was assessed using an array of fivefold cross-validation metrics including area-under-the-curve, F1 score, Cohen's kappa, and Matthews correlation coefficient. Based on ranked normalized scores for the metrics or datasets, all methods appeared comparable, while the distance from the top indicated that Assay Central and support vector classification were comparable. Unlike prior studies which have placed considerable emphasis on deep neural networks (deep learning), no advantage was seen in this case. If anything, Assay Central may have been at a slight advantage as the activity cutoff for each of the over 5000 datasets representing over 570,000 unique compounds was based on Assay Central performance, although support vector classification seems to be a strong competitor. We also applied Assay Central to perform prospective predictions for the toxicity targets PXR and hERG to further validate these models. This work appears to be the largest scale comparison of these machine learning algorithms to date. Future studies will likely evaluate additional databases, descriptors, and machine learning algorithms and further refine the methods for evaluating and comparing such models.

Comparing Machine Learning Models for Aromatase (P450 19A1)

Aromatase, or cytochrome P450 19A1, catalyzes the aromatization of androgens to estrogens within the body. Changes in the activity of this enzyme can produce hormonal imbalances that can be detrimental to sexual and skeletal development. Inhibition of this enzyme can occur with drugs and natural products as well as environmental chemicals. Therefore, predicting potential endocrine disruption via exogenous chemicals requires that aromatase inhibition be considered in addition to androgen and estrogen pathway interference. Bayesian machine learning methods can be used for prospective prediction from the molecular structure without the need for experimental data. Herein, the generation and evaluation of multiple machine learning models utilizing different sources of aromatase inhibition data are described. These models are applied to two test sets for external validation with molecules relevant to drug discovery from the public domain. In addition, the performance of multiple machine learning algorithms was evaluated by comparing internal five-fold cross-validation statistics of the training data. These methods to predict aromatase inhibition from molecular structure, when used in concert with estrogen and androgen machine learning models, allow for a more holistic assessment of endocrine-disrupting potential of chemicals with limited empirical data and enable the reduction of the use of hazardous substances.

Predicting Drug Interactions with Human Equilibrative Nucleoside Transporters 1 and 2 Using Functional Knockout Cell Lines and Bayesian Modeling

Equilibrative nucleoside transporters (ENTs) 1 and 2 facilitate nucleoside transport across the blood-testis barrier (BTB). Improving drug entry into the testes with drugs that use endogenous transport pathways may lead to more effective treatments for diseases within the reproductive tract. In this study, CRISPR/CRISPR-associated protein 9 was used to generate HeLa cell lines in which ENT expression was limited to ENT1 or ENT2. We characterized uridine transport in these cell lines and generated Bayesian models to predict interactions with the ENTs. Quantification of [³H]uridine uptake in the presence of the ENT-specific inhibitor S-(4-nitrobenzyl)-6-thioinosine (NBMPR) demonstrated functional loss of each transporter. Nine nucleoside reverse-transcriptase inhibitors and 37 nucleoside/heterocycle analogs were evaluated to identify ENT interactions. Twenty-one compounds inhibited uridine uptake and abacavir, nevirapine, ticagrelor, and uridine triacetate had different IC₅₀ values for ENT1 and ENT2. Total accumulation of four identified inhibitors was measured with and without NBMPR to determine whether there was ENT-mediated transport. Clofarabine and cladribine were ENT1 and ENT2 substrates, whereas nevirapine and lexibulin were ENT1 and ENT2 nontransported inhibitors. Bayesian models generated using Assay Central machine learning software yielded reasonably high internal validation performance (receiver operator characteristic > 0.7). ENT1 IC₅₀-based models were generated from ChEMBL; subvalidations using this training data set correctly predicted 58% of inhibitors when analyzing activity by percent uptake and 63% when using estimated-IC₅₀ values. Determining drug interactions with these transporters can be useful in identifying and predicting compounds that are ENT1 and ENT2 substrates and can thereby circumvent the BTB through this transepithelial transport pathway in Sertoli cells. SIGNIFICANCE STATEMENT: This study is the first to predict drug interactions with equilibrative nucleoside transporter (ENT) 1 and ENT2 using Bayesian modeling. Novel CRISPR/CRISPR-associated protein 9 functional knockouts of ENT1 and ENT2 in HeLa S3 cells were generated and characterized. Determining drug interactions with these transporters can be useful in identifying and predicting compounds that are ENT1 and ENT2 substrates and can circumvent the blood-testis barrier through this transepithelial transport pathway in Sertoli cells.

Computational Approaches to Identify Molecules Binding to Mycobacterium tuberculosis KasA

Tuberculosis is caused by Mycobacterium tuberculosis (Mtb) and is a deadly disease resulting in the deaths of approximately 1.5 million people with 10 million infections reported in 2018. Recently, a key condensation step in the synthesis of mycolic acids was shown to require β-ketoacyl-ACP synthase (KasA). A crystal structure of KasA with the small molecule DG167 was recently described, which provided a starting point for using computational structure-based approaches to identify additional molecules binding to this protein. We now describe structure-based pharmacophores, docking and machine learning studies with Assay Central as a computational tool for the identification of small molecules targeting KasA. We then tested these compounds using nanoscale differential scanning fluorimetry and microscale thermophoresis. Of note, we identified several molecules including the Food and Drug Administration (FDA)-approved drugs sildenafil and flubendazole with K _d values between 30-40 μM. This may provide additional starting points for further optimization.

Dispirotripiperazine-core compounds, their biological activity with a focus on broad antiviral property, and perspectives in drug design (mini-review)

Viruses are obligate intracellular parasites and have evolved to enter the host cell. To gain access they come into contact with the host cell through an initial adhesion, and some viruses from different genus may use heparan sulfate proteoglycans for it. The successful inhibition of this early event of the infection by synthetic molecules has always been an attractive target for medicinal chemists. Numerous reports have yielded insights into the function of compounds based on the dispirotripiperazine scaffold. Analysis suggests that this is a structural requirement for inhibiting the interactions between viruses and cell-surface heparan sulfate proteoglycans, thus preventing virus entry and replication. This review summarizes our current knowledge about the early history of development, synthesis, structure-activity relationships and antiviral evaluation of dispirotripiperazine-based compounds and where they are going in the future.

Comparison of Machine Learning Models for the Androgen Receptor

The androgen receptor (AR) is a target of interest for endocrine disruption research, as altered signaling can affect normal reproductive and neurological development for generations. In an effort to prioritize compounds with alternative methodologies, the U.S. Environmental Protection Agency (EPA) used in vitro data from 11 assays to construct models of AR agonist and antagonist signaling pathways. While these EPA ToxCast AR models require in vitro data to assign a bioactivity score, Bayesian machine learning methods can be used for prospective prediction from molecule structure alone. This approach was applied to multiple types of data corresponding to the EPA's AR signaling pathway with proprietary software, Assay Central. The training performance of all machine learning models, including six other algorithms, was evaluated by internal 5-fold cross-validation statistics. Bayesian machine learning models were also evaluated with external predictions of reference chemicals to compare prediction accuracies to published results from the EPA. The machine learning model group selected for further studies of endocrine disruption consisted of continuous AC50 data from the February 2019 release of ToxCast/Tox21. These efforts demonstrate how machine learning can be used to predict AR-mediated bioactivity and can also be applied to other targets of endocrine disruption.

Machine Learning Models for Estrogen Receptor Bioactivity and Endocrine Disruption Prediction

The U.S. Environmental Protection Agency (EPA) periodically releases in vitro data across a variety of targets, including the estrogen receptor (ER). In 2015, the EPA used these data to construct mathematical models of ER agonist and antagonist pathways to prioritize chemicals for endocrine disruption testing. However, mathematical models require in vitro data prior to predicting estrogenic activity, but machine learning methods are capable of prospective prediction from the molecular structure alone. The current study describes the generation and evaluation of Bayesian machine learning models grouped by the EPA's ER agonist pathway model using multiple data types with proprietary software, Assay Central. External predictions with three test sets of in vitro and in vivo reference chemicals with agonist activity classifications were compared to previous mathematical model publications. Training data sets were subjected to additional machine learning algorithms and compared with rank normalized scores of internal five-fold cross-validation statistics. External predictions were found to be comparable or superior to previous studies published by the EPA. When assessing six additional algorithms for the training data sets, Assay Central performed similarly at a reduced computational cost. This study demonstrates that machine learning can prioritize chemicals for future in vitro and in vivo testing of ER agonism.

Synergistic drug combinations and machine learning for drug repurposing in chordoma

Chordoma is a devastating rare cancer that affects one in a million people. With a mean-survival of just 6 years and no approved medicines, the primary treatments are surgery and radiation. In order to speed new medicines to chordoma patients, a drug repurposing strategy represents an attractive approach. Drugs that have already advanced through human clinical safety trials have the potential to be approved more quickly than de novo discovered medicines on new targets. We have taken two strategies to enable this: (1) generated and validated machine learning models of chordoma inhibition and screened compounds of interest in vitro. (2) Tested combinations of approved kinase inhibitors already being individually evaluated for chordoma. Several published studies of compounds screened against chordoma cell lines were used to generate Bayesian Machine learning models which were then used to score compounds selected from the NIH NCATS industry-provided assets. Out of these compounds, the mTOR inhibitor AZD2014, was the most potent against chordoma cell lines (IC50 0.35 µM U-CH1 and 0.61 µM U-CH2). Several studies have shown the importance of the mTOR signaling pathway in chordoma and suggest it as a promising avenue for targeted therapy. Additionally, two currently FDA approved drugs, afatinib and palbociclib (EGFR and CDK4/6 inhibitors, respectively) demonstrated synergy in vitro (CI50 = 0.43) while AZD2014 and afatanib also showed synergy (CI50 = 0.41) against a chordoma cell in vitro. These findings may be of interest clinically, and this in vitro- and in silico approach could also be applied to other rare cancers.

Machine Learning Platform to Discover Novel Growth Inhibitors of Neisseria gonorrhoeae

PURPOSE

To advance fundamental biological and translational research with the bacterium Neisseria gonorrhoeae through the prediction of novel small molecule growth inhibitors via naïve Bayesian modeling methodology.

METHODS

Inspection and curation of data from the publicly available ChEMBL web site for small molecule growth inhibition data of the bacterium Neisseria gonorrhoeae resulted in a training set for the construction of machine learning models. A naïve Bayesian model for bacterial growth inhibition was utilized in a workflow to predict novel antibacterial agents against this bacterium of global health relevance from a commercial library of >10⁵ drug-like small molecules. Follow-up efforts involved empirical assessment of the predictions and validation of the hits.

RESULTS

Specifically, two small molecules were found that exhibited promising activity profiles and represent novel chemotypes for agents against N. gonorrrhoeae.

CONCLUSIONS

This represents, to the best of our knowledge, the first machine learning approach to successfully predict novel growth inhibitors of this bacterium. To assist the chemical tool and drug discovery fields, we have made our curated training set available as part of the Supplementary Material and the Bayesian model is accessible via the web. Graphical Abstract.

Comparing Machine Learning Algorithms for Predicting Drug-Induced Liver Injury (DILI)

Drug-induced liver injury (DILI) is one the most unpredictable adverse reactions to xenobiotics in humans and the leading cause of postmarketing withdrawals of approved drugs. To date, these drugs have been collated by the FDA to form the DILIRank database, which classifies DILI severity and potential. These classifications have been used by various research groups in generating computational predictions for this type of liver injury. Recently, groups from Pfizer and AstraZeneca have collated DILI in vitro data and physicochemical properties for compounds that can be used along with data from the FDA to build machine learning models for DILI. In this study, we have used these data sets, as well as the Biopharmaceutics Drug Disposition Classification System data set, to generate Bayesian machine learning models with our in-house software, Assay Central. The performance of all machine learning models was assessed through both the internal 5-fold cross-validation metrics and prediction accuracy of an external test set of compounds with known hepatotoxicity. The best-performing Bayesian model was based on the DILI-concern category from the DILIRank database with an ROC of 0.814, a sensitivity of 0.741, a specificity of 0.755, and an accuracy of 0.746. A comparison of alternative machine learning algorithms, such as k-nearest neighbors, support vector classification, AdaBoosted decision trees, and deep learning methods, produced similar statistics to those generated with the Bayesian algorithm in Assay Central. This study demonstrates machine learning models grouped in a tool called MegaTox that can be used to predict early-stage clinical compounds, as well as recent FDA-approved drugs, to identify potential DILI.

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.

Déjà vu: Stimulating open drug discovery for SARS-CoV-2

In the past decade we have seen two major Ebola virus outbreaks in Africa, the Zika virus in Brazil and the Americas and the current pandemic of coronavirus disease (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). There is a strong sense of déjà vu because there are still no effective treatments. In the COVID-19 pandemic, despite being a new virus, there are already drugs suggested as active in in vitro assays that are being repurposed in clinical trials. Promising SARS-CoV-2 viral targets and computational approaches are described and discussed. Here, we propose, based on open antiviral drug discovery approaches for previous outbreaks, that there could still be gaps in our approach to drug discovery.

Repurposing Approved Drugs as Inhibitors of Kv7.1 and Nav1.8 to Treat Pitt Hopkins Syndrome

PURPOSE

Pitt Hopkins Syndrome (PTHS) is a rare genetic disorder caused by mutations of a specific gene, transcription factor 4 (TCF4), located on chromosome 18. PTHS results in individuals that have moderate to severe intellectual disability, with most exhibiting psychomotor delay. PTHS also exhibits features of autistic spectrum disorders, which are characterized by the impaired ability to communicate and socialize. PTHS is comorbid with a higher prevalence of epileptic seizures which can be present from birth or which commonly develop in childhood. Attenuated or absent TCF4 expression results in increased translation of peripheral ion channels K_v7.1 and Na_v1.8 which triggers an increase in after-hyperpolarization and altered firing properties.

METHODS

We now describe a high throughput screen (HTS) of 1280 approved drugs and machine learning models developed from this data. The ion channels were expressed in either CHO (K_V7.1) or HEK293 (Na_v1.8) cells and the HTS used either ⁸⁶Rb⁺ efflux (K_V7.1) or a FLIPR assay (Na_v1.8).

RESULTS

The HTS delivered 55 inhibitors of K_v7.1 (4.2% hit rate) and 93 inhibitors of Na_v1.8 (7.2% hit rate) at a screening concentration of 10 μM. These datasets also enabled us to generate and validate Bayesian machine learning models for these ion channels. We also describe a structure activity relationship for several dihydropyridine compounds as inhibitors of Na_v1.8.

CONCLUSIONS

This work could lead to the potential repurposing of nicardipine or other dihydropyridine calcium channel antagonists as potential treatments for PTHS acting via Na_v1.8, as there are currently no approved treatments for this rare disorder.

Exploiting machine learning for end-to-end drug discovery and development

A variety of machine learning methods such as naive Bayesian, support vector machines and more recently deep neural networks are demonstrating their utility for drug discovery and development. These leverage the generally bigger datasets created from high-throughput screening data and allow prediction of bioactivities for targets and molecular properties with increased levels of accuracy. We have only just begun to exploit the potential of these techniques but they may already be fundamentally changing the research process for identifying new molecules and/or repurposing old drugs. The integrated application of such machine learning models for end-to-end (E2E) application is broadly relevant and has considerable implications for developing future therapies and their targeting.

Multiple Machine Learning Comparisons of HIV Cell-based and Reverse Transcriptase Data Sets

The human immunodeficiency virus (HIV) causes over a million deaths every year and has a huge economic impact in many countries. The first class of drugs approved were nucleoside reverse transcriptase inhibitors. A newer generation of reverse transcriptase inhibitors have become susceptible to drug resistant strains of HIV, and hence, alternatives are urgently needed. We have recently pioneered the use of Bayesian machine learning to generate models with public data to identify new compounds for testing against different disease targets. The current study has used the NIAID ChemDB HIV, Opportunistic Infection and Tuberculosis Therapeutics Database for machine learning studies. We curated and cleaned data from HIV-1 wild-type cell-based and reverse transcriptase (RT) DNA polymerase inhibition assays. Compounds from this database with ≤1 μM HIV-1 RT DNA polymerase activity inhibition and cell-based HIV-1 inhibition are correlated (Pearson r = 0.44, n = 1137, p < 0.0001). Models were trained using multiple machine learning approaches (Bernoulli Naive Bayes, AdaBoost Decision Tree, Random Forest, support vector classification, k-Nearest Neighbors, and deep neural networks as well as consensus approaches) and then their predictive abilities were compared. Our comparison of different machine learning methods demonstrated that support vector classification, deep learning, and a consensus were generally comparable and not significantly different from each other using 5-fold cross validation and using 24 training and test set combinations. This study demonstrates findings in line with our previous studies for various targets that training and testing with multiple data sets does not demonstrate a significant difference between support vector machine and deep neural networks.

Ebola Virus Bayesian Machine Learning Models Enable New in Vitro Leads

We have previously described the first Bayesian machine learning models from FDA-approved drug screens, for identifying compounds active against the Ebola virus (EBOV). These models led to the identification of three active molecules in vitro: tilorone, pyronaridine, and quinacrine. A follow-up study demonstrated that one of these compounds, tilorone, has 100% in vivo efficacy in mice infected with mouse-adapted EBOV at 30 mg/kg/day intraperitoneal. This suggested that we can learn from the published data on EBOV inhibition and use it to select new compounds for testing that are active in vivo. We used these previously built Bayesian machine learning EBOV models alongside our chemical insights for the selection of 12 molecules, absent from the training set, to test for in vitro EBOV inhibition. Nine molecules were directly selected using the model, and eight of these molecules possessed a promising in vitro activity (EC50 < 15 μM). Three further compounds were selected for an in vitro evaluation because they were antimalarials, and compounds of this class like pyronaridine and quinacrine have previously been shown to inhibit EBOV. We identified the antimalarial drug arterolane (IC50 = 4.53 μM) and the anticancer clinical candidate lucanthone (IC50 = 3.27 μM) as novel compounds that have EBOV inhibitory activity in HeLa cells and generally lack cytotoxicity. This work provides further validation for using machine learning and medicinal chemistry expertize to prioritize compounds for testing in vitro prior to more costly in vivo tests. These studies provide further corroboration of this strategy and suggest that it can likely be applied to other pathogens in the future.

Halogen Substitution Influences Ketamine Metabolism by Cytochrome P450 2B6: In Vitro and Computational Approaches

Ketamine is analgesic at anesthetic and subanesthetic doses, and it has been used recently to treat depression. Biotransformation mediates ketamine effects, influencing both systemic elimination and bioactivation. CYP2B6 is the major catalyst of hepatic ketamine N-demethylation and metabolism at clinically relevant concentrations. Numerous CYP2B6 substrates contain halogens. CYP2B6 readily forms halogen-protein (particularly Cl-π) bonds, which influence substrate selectivity and active site orientation. Ketamine is chlorinated, but little is known about the metabolism of halogenated analogs. This investigation evaluated halogen substitution effects on CYP2B6-catalyzed ketamine analogs N-demethylation in vitro and modeled interactions with CYP2B6 using various computational approaches. Ortho phenyl ring halogen substituent changes caused substantial (18-fold) differences in K_m, on the order of Br (bromoketamine, 10 μM) < Cl < F < H (deschloroketamine, 184 μM). In contrast, V_max varied minimally (83-103 pmol/min/pmol CYP). Thus, apparent substrate binding affinity was the major consequence of halogen substitution and the major determinant of N-demethylation. Docking poses of ketamine and analogs were similar, sharing a π-stack with F297. Libdock scores were deschloroketamine < bromoketamine < ketamine < fluoroketamine. A Bayesian log K_m model generated with Assay Central had a ROC of 0.86. The probability of activity at 15 μM for ketamine and analogs was predicted with this model. Deschloroketamine scores corresponded to the experimental K_m, but the model was unable to predict activity with fluoroketamine. The binding pocket of CYP2B6 also suggested a hydrophobic component to substrate docking, on the basis of a strong linear correlation ( R² = 0.92) between lipophilicity ( Alog P) and metabolism (log K_m) of ketamine and analogs. This property may be the simplest design criteria to use when considering similar compounds and CYP2B6 affinity.

High Throughput and Computational Repurposing for Neglected Diseases

Purpose

Neglected tropical diseases (NTDs) represent are a heterogeneous group of communicable diseases that are found within the poorest populations of the world. There are 23 NTDs that have been prioritized by the World Health Organization, which are endemic in 149 countries and affect more than 1.4 billion people, costing these developing economies billions of dollars annually. The NTDs result from four different causative pathogens: protozoa, bacteria, helminth and virus. The majority of the diseases lack effective treatments. Therefore, new therapeutics for NTDs are desperately needed.

Methods

We describe various high throughput screening and computational approaches that have been performed in recent years. We have collated the molecules identified in these studies and calculated molecular properties.

Results

Numerous global repurposing efforts have yielded some promising compounds for various neglected tropical diseases. These compounds when analyzed as one would expect appear drug-like. Several large datasets are also now in the public domain and this enables machine learning models to be constructed that then facilitate the discovery of new molecules for these pathogens.

Conclusions

In the space of a few years many groups have either performed experimental or computational repurposing high throughput screens against neglected diseases. These have identified compounds which in many cases are already approved drugs. Such approaches perhaps offer a more efficient way to develop treatments which are generally not a focus for global pharmaceutical companies because of the economics or the lack of a viable market. Other diseases could perhaps benefit from these repurposing approaches.

Electronic supplementary material

The online version of this article (10.1007/s11095-018-2558-3) contains supplementary material, which is available to authorized users.

Comparing Multiple Machine Learning Algorithms and Metrics for Estrogen Receptor Binding Prediction

Many chemicals that disrupt endocrine function have been linked to a variety of adverse biological outcomes. However, screening for endocrine disruption using in vitro or in vivo approaches is costly and time-consuming. Computational methods, e.g., quantitative structure-activity relationship models, have become more reliable due to bigger training sets, increased computing power, and advanced machine learning algorithms, such as multilayered artificial neural networks. Machine learning models can be used to predict compounds for endocrine disrupting capabilities, such as binding to the estrogen receptor (ER), and allow for prioritization and further testing. In this work, an exhaustive comparison of multiple machine learning algorithms, chemical spaces, and evaluation metrics for ER binding was performed on public data sets curated using in-house cheminformatics software (Assay Central). Chemical features utilized in modeling consisted of binary fingerprints (ECFP6, FCFP6, ToxPrint, or MACCS keys) and continuous molecular descriptors from RDKit. Each feature set was subjected to classic machine learning algorithms (Bernoulli Naive Bayes, AdaBoost Decision Tree, Random Forest, Support Vector Machine) and Deep Neural Networks (DNN). Models were evaluated using a variety of metrics: recall, precision, F1-score, accuracy, area under the receiver operating characteristic curve, Cohen's Kappa, and Matthews correlation coefficient. For predicting compounds within the training set, DNN has an accuracy higher than that of other methods; however, in 5-fold cross validation and external test set predictions, DNN and most classic machine learning models perform similarly regardless of the data set or molecular descriptors used. We have also used the rank normalized scores as a performance-criteria for each machine learning method, and Random Forest performed best on the validation set when ranked by metric or by data sets. These results suggest classic machine learning algorithms may be sufficient to develop high quality predictive models of ER activity.

Comparing and Validating Machine Learning Models for Mycobacterium tuberculosis Drug Discovery

Tuberculosis is a global health dilemma. In 2016, the WHO reported 10.4 million incidences and 1.7 million deaths. The need to develop new treatments for those infected with Mycobacterium tuberculosis ( Mtb) has led to many large-scale phenotypic screens and many thousands of new active compounds identified in vitro. However, with limited funding, efforts to discover new active molecules against Mtb needs to be more efficient. Several computational machine learning approaches have been shown to have good enrichment and hit rates. We have curated small molecule Mtb data and developed new models with a total of 18,886 molecules with activity cutoffs of 10 μM, 1 μM, and 100 nM. These data sets were used to evaluate different machine learning methods (including deep learning) and metrics and to generate predictions for additional molecules published in 2017. One Mtb model, a combined in vitro and in vivo data Bayesian model at a 100 nM activity yielded the following metrics for 5-fold cross validation: accuracy = 0.88, precision = 0.22, recall = 0.91, specificity = 0.88, kappa = 0.31, and MCC = 0.41. We have also curated an evaluation set ( n = 153 compounds) published in 2017, and when used to test our model, it showed the comparable statistics (accuracy = 0.83, precision = 0.27, recall = 1.00, specificity = 0.81, kappa = 0.36, and MCC = 0.47). We have also compared these models with additional machine learning algorithms showing Bayesian machine learning models constructed with literature Mtb data generated by different laboratories generally were equivalent to or outperformed deep neural networks with external test sets. Finally, we have also compared our training and test sets to show they were suitably diverse and different in order to represent useful evaluation sets. Such Mtb machine learning models could help prioritize compounds for testing in vitro and in vivo.

Assessment of Substrate-Dependent Ligand Interactions at the Organic Cation Transporter OCT2 Using Six Model Substrates

Organic cation transporter (OCT) 2 mediates the entry step for organic cation secretion by renal proximal tubule cells and is a site of unwanted drug-drug interactions (DDIs). But reliance on decision tree-based predictions of DDIs at OCT2 that depend on IC₅₀ values can be suspect because they can be influenced by choice of transported substrate; for example, IC₅₀ values for the inhibition of metformin versus MPP transport can vary by 5- to 10-fold. However, it is not clear whether the substrate dependence of a ligand interaction is common among OCT2 substrates. To address this question, we screened the inhibitory effectiveness of 20 µM concentrations of several hundred compounds against OCT2-mediated uptake of six structurally distinct substrates: MPP, metformin, N,N,N-trimethyl-2-[methyl(7-nitrobenzo[c][1,2,5]oxadiazol-4-yl)amino]ethanaminium (NBD-MTMA), TEA, cimetidine, and 4-4-dimethylaminostyryl-N-methylpyridinium (ASP). Of these, MPP transport was least sensitive to inhibition. IC₅₀ values for 20 structurally diverse compounds confirmed this profile, with IC₅₀ values for MPP averaging 6-fold larger than those for the other substrates. Bayesian machine-learning models of ligand-induced inhibition displayed generally good statistics after cross-validation and external testing. Applying our ASP model to a previously published large-scale screening study for inhibition of OCT2-mediated ASP transport resulted in comparable statistics, with approximately 75% of "active" inhibitors predicted correctly. The differential sensitivity of MPP transport to inhibition suggests that multiple ligands can interact simultaneously with OCT2 and supports the recommendation that MPP not be used as a test substrate for OCT2 screening. Instead, metformin appears to be a comparatively representative OCT2 substrate for both in vitro and in vivo (clinical) use.