Lies and Liabilities: Computational Assessment of High-Throughput Screening Hits to Identify Artifact Compounds.

Hits from high-throughput screening (HTS) of chemical libraries are often false positives due to their interference with assay detection technology. In response, we generated the largest publicly available library of chemical liabilities and developed "Liability Predictor," a free web tool to predict HTS artifacts. More specifically, we generated, curated, and integrated HTS data sets for thiol reactivity, redox activity, and luciferase (firefly and nano) activity and developed and validated quantitative structure-interference relationship (QSIR) models to predict these nuisance behaviors. The resulting models showed 58-78% external balanced accuracy for 256 external compounds per assay. QSIR models developed and validated herein identify nuisance compounds among experimental hits more reliably than do popular PAINS filters. Both the models and the curated data sets were implemented in "Liability Predictor," publicly available at https://liability.mml.unc.edu/. "Liability Predictor" may be used as part of chemical library design or for triaging HTS hits.

Defining clinical outcome pathways.

Here, we propose a broad concept of 'Clinical Outcome Pathways' (COPs), which are defined as a series of key molecular and cellular events that underlie therapeutic effects of drug molecules. We formalize COPs as a chain of the following events: molecular initiating event (MIE) â†’ intermediate event(s) â†’ clinical outcome. We illustrate the concept with COP examples both for primary and alternative (i.e., drug repurposing) therapeutic applications. We also describe the elucidation of COPs for several drugs of interest using the publicly accessible Reasoning Over Biomedical Objects linked in Knowledge-Oriented Pathways (ROBOKOP) biomedical knowledge graph-mining tool. We propose that broader use of COP uncovered with the help of biomedical knowledge graph mining will likely accelerate drug discovery and repurposing efforts.

Knowledge-based approaches to drug discovery for rare diseases.

The conventional drug discovery pipeline has proven to be unsustainable for rare diseases. Herein, we discuss recent advances in biomedical knowledge mining applied to discovering therapeutics for rare diseases. We summarize current chemogenomics data of relevance to rare diseases and provide a perspective on the effectiveness of machine learning (ML) and biomedical knowledge graph mining in rare disease drug discovery. We illustrate the power of these methodologies using a chordoma case study. We expect that a broader application of knowledge graph mining and artificial intelligence (AI) approaches will expedite the discovery of viable drug candidates against both rare and common diseases.

Generative and reinforcement learning approaches for the automated de novo design of bioactive compounds.

Deep generative neural networks have been used increasingly in computational chemistry for de novo design of molecules with desired properties. Many deep learning approaches employ reinforcement learning for optimizing the target properties of the generated molecules. However, the success of this approach is often hampered by the problem of sparse rewards as the majority of the generated molecules are expectedly predicted as inactives. We propose several technical innovations to address this problem and improve the balance between exploration and exploitation modes in reinforcement learning. In a proof-of-concept study, we demonstrate the application of the deep generative recurrent neural network architecture enhanced by several proposed technical tricks to design inhibitors of the epidermal growth factor (EGFR) and further experimentally validate their potency. The proposed technical solutions are expected to substantially improve the success rate of finding novel bioactive compounds for specific biological targets using generative and reinforcement learning approaches.

Crowdsourced mapping of unexplored target space of kinase inhibitors.

Despite decades of intensive search for compounds that modulate the activity of particular protein targets, a large proportion of the human kinome remains as yet undrugged. Effective approaches are therefore required to map the massive space of unexplored compound-kinase interactions for novel and potent activities. Here, we carry out a crowdsourced benchmarking of predictive algorithms for kinase inhibitor potencies across multiple kinase families tested on unpublished bioactivity data. We find the top-performing predictions are based on various models, including kernel learning, gradient boosting and deep learning, and their ensemble leads to a predictive accuracy exceeding that of single-dose kinase activity assays. We design experiments based on the model predictions and identify unexpected activities even for under-studied kinases, thereby accelerating experimental mapping efforts. The open-source prediction algorithms together with the bioactivities between 95 compounds and 295 kinases provide a resource for benchmarking prediction algorithms and for extending the druggable kinome.

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.

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.

SCAM Detective: Accurate Predictor of Small, Colloidally Aggregating Molecules.

Small, colloidally aggregating molecules (SCAMs) are the most common source of false positives in high-throughput screening (HTS) campaigns. Although SCAMs can be experimentally detected and suppressed by the addition of detergent in the assay buffer, detergent sensitivity is not routinely monitored in HTS. Computational methods are thus needed to flag potential SCAMs during HTS triage. In this study, we have developed and rigorously validated quantitative structure-interference relationship (QSIR) models of detergent-sensitive aggregation in several HTS campaigns under various assay conditions and screening concentrations. In particular, we have modeled detergent-sensitive aggregation in an AmpC ß-lactamase assay, the preferred HTS counter-screen for aggregation, as well as in another assay that measures cruzain inhibition. Our models increase the accuracy of aggregation prediction by ∼53% in the ß-lactamase assay and by ∼46% in the cruzain assay compared to previously published methods. We also discuss the importance of both assay conditions and screening concentrations in the development of QSIR models for various interference mechanisms besides aggregation. The models developed in this study are publicly available for fast prediction within the SCAM detective web application (https://scamdetective.mml.unc.edu/).

Synthesis and Structure-Activity Relationships of DCLK1 Kinase Inhibitors Based on a 5,11-Dihydro-6H-benzo[e]pyrimido[5,4-b][1,4]diazepin-6-one Scaffold.

Doublecortin-like kinase 1 (DCLK1) is a serine/threonine kinase that is overexpressed in gastrointestinal cancers, including esophageal, gastric, colorectal, and pancreatic cancers. DCLK1 is also used as a marker of tuft cells, which regulate type II immunity in the gut. However, the substrates and functions of DCLK1 are understudied. We recently described the first selective DCLK1/2 inhibitor, DCLK1-IN-1, developed to aid the functional characterization of this important kinase. Here we describe the synthesis and structure-activity relationships of 5,11-dihydro-6H-benzo[e]pyrimido[5,4-b][1,4]diazepin-6-one DCLK1 inhibitors, resulting in the identification of DCLK1-IN-1.

Design, synthesis and evaluation of antiproliferative activity of fluorinated betulinic acid.

Betulinic acid (BA), a pentacyclic triterpenoid, exhibits broad spectrum antiproliferative activity, but generally with only modest potency. To improve BA's pharmacological properties, fluorine was introduced as a single atom at C-2, creating two diastereomers, or in a trifluoromethyl group at C-3. We evaluated the impact of these groups on antiproliferative activity against five human tumor cell lines. A racemic 2-F-BA (compound 6) showed significantly improved antiproliferative activity, while each diastereomer exhibited similar effects. We also demonstrated that 2-F-BA is a topoisomerase (Topo) I and IIα dual inhibitor in cell-based and cell-free assays. A hypothetical mode of binding to the Topo I-DNA suggested a difference between the hydrogen bonding of BA and 2-F-BA to DNA, which may account for the difference in bioactivity against Topo I.

SGC-GAK-1: A Chemical Probe for Cyclin G Associated Kinase (GAK).

We describe SGC-GAK-1 (11), a potent, selective, and cell-active inhibitor of cyclin G-associated kinase (GAK), together with a structurally related negative control SGC-GAK-1N (14). 11 was highly selective in an in vitro kinome-wide screen, but cellular engagement assays defined RIPK2 as a collateral target. We identified 18 as a potent RIPK2 inhibitor lacking GAK activity. Together, this chemical probe set can be used to interrogate GAK cellular biology.

Multi-Descriptor Read Across (MuDRA): A Simple and Transparent Approach for Developing Accurate Quantitative Structure-Activity Relationship Models.

Multiple approaches to quantitative structure-activity relationship (QSAR) modeling using various statistical or machine learning techniques and different types of chemical descriptors have been developed over the years. Oftentimes models are used in consensus to make more accurate predictions at the expense of model interpretation. We propose a simple, fast, and reliable method termed Multi-Descriptor Read Across (MuDRA) for developing both accurate and interpretable models. The method is conceptually related to the well-known kNN approach but uses different types of chemical descriptors simultaneously for similarity assessment. To benchmark the new method, we have built MuDRA models for six different end points (Ames mutagenicity, aquatic toxicity, hepatotoxicity, hERG liability, skin sensitization, and endocrine disruption) and compared the results with those generated with conventional consensus QSAR modeling. We find that models built with MuDRA show consistently high external accuracy similar to that of conventional QSAR models. However, MuDRA models excel in terms of transparency, interpretability, and computational efficiency. We posit that due to its methodological simplicity and reliable predictive accuracy, MuDRA provides a powerful alternative to a much more complex consensus QSAR modeling. MuDRA is implemented and freely available at the Chembench web portal ( https://chembench.mml.unc.edu/mudra ).

Computer-Aided Discovery and Characterization of Novel Ebola Virus Inhibitors.

The Ebola virus (EBOV) causes severe human infection that lacks effective treatment. A recent screen identified a series of compounds that block EBOV-like particle entry into human cells. Using data from this screen, quantitative structure-activity relationship models were built and employed for virtual screening of a ∼17 million compound library. Experimental testing of 102 hits yielded 14 compounds with IC50 values under 10 µM, including several sub-micromolar inhibitors, and more than 10-fold selectivity against host cytotoxicity. These confirmed hits include FDA-approved drugs and clinical candidates with non-antiviral indications, as well as compounds with novel scaffolds and no previously known bioactivity. Five selected hits inhibited BSL-4 live-EBOV infection in a dose-dependent manner, including vindesine (0.34 µM). Additional studies of these novel anti-EBOV compounds revealed their mechanisms of action, including the inhibition of NPC1 protein, cathepsin B/L, and lysosomal function. Compounds identified in this study are among the most potent and well-characterized anti-EBOV inhibitors reported to date.

Quantitative high-throughput phenotypic screening of pediatric cancer cell lines identifies multiple opportunities for drug repurposing.

Drug repurposing approaches have the potential advantage of facilitating rapid and cost-effective development of new therapies. Particularly, the repurposing of drugs with known safety profiles in children could bypass or streamline toxicity studies. We employed a phenotypic screening paradigm on a panel of well-characterized cell lines derived from pediatric solid tumors against a collection of ∼3,800 compounds spanning approved drugs and investigational agents. Specifically, we employed titration-based screening where compounds were tested at multiple concentrations for their effect on cell viability. Molecular and cellular target enrichment analysis indicated that numerous agents across different therapeutic categories and modes of action had an antiproliferative effect, notably antiparasitic/protozoal drugs with non-classic antineoplastic activity. Focusing on active compounds with dosing and safety information in children according to the Children's Pharmacy Collaborative database, we identified compounds with therapeutic potential through further validation using 3D tumor spheroid models. Moreover, we show that antiparasitic agents induce cell death via apoptosis induction. This study demonstrates that our screening platform enables the identification of chemical agents with cytotoxic activity in pediatric cancer cell lines of which many have known safety/toxicity profiles in children. These agents constitute attractive candidates for efficacy studies in pre-clinical models of pediatric solid tumors.

Chemotext: A Publicly Available Web Server for Mining Drug-Target-Disease Relationships in PubMed.

Elucidation of the mechanistic relationships between drugs, their targets, and diseases is at the core of modern drug discovery research. Thousands of studies relevant to the drug-target-disease (DTD) triangle have been published and annotated in the Medline/PubMed database. Mining this database affords rapid identification of all published studies that confirm connections between vertices of this triangle or enable new inferences of such connections. To this end, we describe the development of Chemotext, a publicly available Web server that mines the entire compendium of published literature in PubMed annotated by Medline Subject Heading (MeSH) terms. The goal of Chemotext is to identify all known DTD relationships and infer missing links between vertices of the DTD triangle. As a proof-of-concept, we show that Chemotext could be instrumental in generating new drug repurposing hypotheses or annotating clinical outcomes pathways for known drugs. The Chemotext Web server is freely available at http://chemotext.mml.unc.edu .

Design and Profiling of a Subcellular Targeted Optogenetic cAMP-Dependent Protein Kinase.

Although the cAMP-dependent protein kinase (PKA) is ubiquitously expressed, it is sequestered at specific subcellular locations throughout the cell, thereby resulting in compartmentalized cellular signaling that triggers site-specific behavioral phenotypes. We developed a three-step engineering strategy to construct an optogenetic PKA (optoPKA) and demonstrated that, upon illumination, optoPKA migrates to specified intracellular sites. Furthermore, we designed intracellular spatially segregated reporters of PKA activity and confirmed that optoPKA phosphorylates these reporters in a light-dependent fashion. Finally, proteomics experiments reveal that light activation of optoPKA results in the phosphorylation of known endogenous PKA substrates as well as potential novel substrates.