Luciferase Advisor: High-Accuracy Model To Flag False Positive Hits in Luciferase HTS Assays

ChemFH: an integrated tool for screening frequent false positives in chemical biology and drug discovery

High-throughput screening rapidly tests an extensive array of chemical compounds to identify hit compounds for specific biological targets in drug discovery. However, false-positive results disrupt hit compound screening, leading to wastage of time and resources. To address this, we propose ChemFH, an integrated online platform facilitating rapid virtual evaluation of potential false positives, including colloidal aggregators, spectroscopic interference compounds, firefly luciferase inhibitors, chemical reactive compounds, promiscuous compounds, and other assay interferences. By leveraging a dataset containing 823 391 compounds, we constructed high-quality prediction models using multi-task directed message-passing network (DMPNN) architectures combining uncertainty estimation, yielding an average AUC value of 0.91. Furthermore, ChemFH incorporated 1441 representative alert substructures derived from the collected data and ten commonly used frequent hitter screening rules. ChemFH was validated with an external set of 75 compounds. Subsequently, the virtual screening capability of ChemFH was successfully confirmed through its application to five virtual screening libraries. Furthermore, ChemFH underwent additional validation on two natural products and FDA-approved drugs, yielding reliable and accurate results. ChemFH is a comprehensive, reliable, and computationally efficient screening pipeline that facilitates the identification of true positive results in assays, contributing to enhanced efficiency and success rates in drug discovery. ChemFH is freely available via https://chemfh.scbdd.com/.

Tackling assay interference associated with small molecules

Biochemical and cell-based assays are essential to discovering and optimizing efficacious and safe drugs, agrochemicals and cosmetics. However, false assay readouts stemming from colloidal aggregation, chemical reactivity, chelation, light signal attenuation and emission, membrane disruption, and other interference mechanisms remain a considerable challenge in screening synthetic compounds and natural products. To address assay interference, a range of powerful experimental approaches are available and in silico methods are now gaining traction. This Review begins with an overview of the scope and limitations of experimental approaches for tackling assay interference. It then focuses on theoretical methods, discusses strategies for their integration with experimental approaches, and provides recommendations for best practices. The Review closes with a summary of the critical facts and an outlook on potential future developments.

Orthogonal assay and QSAR modelling of Tox21 PPARγ antagonist in vitro high-throughput screening assay

Disruption of signalling mediated by the nuclear receptor peroxisome proliferator-activated receptor gamma (PPARγ) is associated with risk of cancer, metabolic diseases, and endocrine disruption. The purpose of this study was to identify environmental chemicals acting as PPARγ antagonists. Data from the Tox21 PPARγ antagonism assay were replicated using a reporter system in HEK293 cells. Two quantitative structure-activity relationship (QSAR) models were developed, and five REACH-registered substances predicted positive were tested in vitro. Reporter assay results were consistent with Tox21 data since all conflicting results could be explained by assay interference. QSAR models showed good predictive performance, and follow-up experiments revealed two PPARγ antagonists out of three non-interfering chemicals. In conclusion, the developed QSAR models and follow-up experiments are important steps in the discovery of potential endocrine- and metabolism-disrupting chemicals.

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.

Highly Accurate Filters to Flag Frequent Hitters in AlphaScreen Assays by Suggesting their Mechanism

AlphaScreen is one of the most widely used assay technologies in drug discovery due to its versatility, dynamic range and sensitivity. However, a presence of false positives and frequent hitters contributes to difficulties with an interpretation of measured HTS data. Although filters do exist to identify frequent hitters for AlphaScreen, they are frequently based on privileged scaffolds. The development of such filters is time consuming and requires deep domain knowledge. Recently, machine learning and artificial intelligence methods are emerging as important tools to advance drug discovery and chemoinformatics, including their application to identification of frequent hitters in screening assays. However, the relative performance and complementarity of the Machine Learning and scaffold-based techniques has not yet been comprehensively compared. In this study, we analysed filters based on the privileged scaffolds with filters built using machine learning. Our results demonstrate that machine-learning methods provide more accurate filters for identification of frequent hitters in AlphaScreen assays than scaffold-based methods and can be easily redeveloped once new data are measured. We present highly accurate models to identify frequent hitters in AlphaScreen assays.

SARS-CoV-2 NSP12 Protein Is Not an Interferon-β Antagonist

The coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is bringing an unprecedented health crisis to the world. To date, our understanding of the interaction between SARS-CoV-2 and host innate immunity is still limited. Previous studies reported that SARS-CoV-2 nonstructural protein 12 (NSP12) was able to suppress interferon-β (IFN-β) activation in IFN-β promoter luciferase reporter assays, which provided insights into the pathogenesis of COVID-19. In this study, we demonstrated that IFN-β promoter-mediated luciferase activity was reduced during coexpression of NSP12. However, we could show NSP12 did not affect IRF3 or NF-κB activation. Moreover, IFN-β production induced by Sendai virus (SeV) infection or other stimulus was not affected by NSP12 at mRNA or protein level. Additionally, the type I IFN signaling pathway was not affected by NSP12, as demonstrated by the expression of interferon-stimulated genes (ISGs). Further experiments revealed that different experiment systems, including protein tags and plasmid backbones, could affect the readouts of IFN-β promoter luciferase assays. In conclusion, unlike as previously reported, our study showed SARS-CoV-2 NSP12 protein is not an IFN-β antagonist. It also rings the alarm on the general usage of luciferase reporter assays in studying SARS-CoV-2. IMPORTANCE Previous studies investigated the interaction between SARS-CoV-2 viral proteins and interferon signaling and proposed that several SARS-CoV-2 viral proteins, including NSP12, could suppress IFN-β activation. However, most of these results were generated from IFN-β promoter luciferase reporter assay and have not been validated functionally. In our study, we found that, although NSP12 could suppress IFN-β promoter luciferase activity, it showed no inhibitory effect on IFN-β production or its downstream signaling. Further study revealed that contradictory results could be generated from different experiment systems. On one hand, we demonstrated that SARS-CoV-2 NSP12 could not suppress IFN-β signaling. On the other hand, our study suggests that caution needs to be taken with the interpretation of SARS-CoV-2-related luciferase assays.

SARS-CoV-2 NSP12 Protein Is Not an Interferon-β Antagonist

The coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is bringing an unprecedented health crisis to the world. To date, our understanding of the interaction between SARS-CoV-2 and host innate immunity is still limited. Previous studies reported that SARS-CoV-2 nonstructural protein 12 (NSP12) was able to suppress interferon-β (IFN-β) activation in IFN-β promoter luciferase reporter assays, which provided insights into the pathogenesis of COVID-19. In this study, we demonstrated that IFN-β promoter-mediated luciferase activity was reduced during coexpression of NSP12. However, we could show NSP12 did not affect IRF3 or NF-κB activation. Moreover, IFN-β production induced by Sendai virus (SeV) infection or other stimulus was not affected by NSP12 at mRNA or protein level. Additionally, the type I IFN signaling pathway was not affected by NSP12, as demonstrated by the expression of interferon-stimulated genes (ISGs). Further experiments revealed that different experiment systems, including protein tags and plasmid backbones, could affect the readouts of IFN-β promoter luciferase assays. In conclusion, unlike as previously reported, our study showed SARS-CoV-2 NSP12 protein is not an IFN-β antagonist. It also rings the alarm on the general usage of luciferase reporter assays in studying SARS-CoV-2. IMPORTANCE Previous studies investigated the interaction between SARS-CoV-2 viral proteins and interferon signaling and proposed that several SARS-CoV-2 viral proteins, including NSP12, could suppress IFN-β activation. However, most of these results were generated from IFN-β promoter luciferase reporter assay and have not been validated functionally. In our study, we found that, although NSP12 could suppress IFN-β promoter luciferase activity, it showed no inhibitory effect on IFN-β production or its downstream signaling. Further study revealed that contradictory results could be generated from different experiment systems. On one hand, we demonstrated that SARS-CoV-2 NSP12 could not suppress IFN-β signaling. On the other hand, our study suggests that caution needs to be taken with the interpretation of SARS-CoV-2-related luciferase assays.

Evaluation of Firefly and Renilla Luciferase Inhibition in Reporter-Gene Assays: A Case of Isoflavonoids

Firefly luciferase is susceptible to inhibition and stabilization by compounds under investigation for biological activity and toxicity. This can lead to false-positive results in in vitro cell-based assays. However, firefly luciferase remains one of the most commonly used reporter genes. Here, we evaluated isoflavonoids for inhibition of firefly luciferase. These natural compounds are often studied using luciferase reporter-gene assays. We used a quantitative structure–activity relationship (QSAR) model to compare the results of in silico predictions with a newly developed in vitro assay that enables concomitant detection of inhibition of firefly and Renilla luciferases. The QSAR model predicted a moderate to high likelihood of firefly luciferase inhibition for all of the 11 isoflavonoids investigated, and the in vitro assays confirmed this for seven of them: daidzein, genistein, glycitein, prunetin, biochanin A, calycosin, and formononetin. In contrast, none of the 11 isoflavonoids inhibited Renilla luciferase. Molecular docking calculations indicated that isoflavonoids interact favorably with the D-luciferin binding pocket of firefly luciferase. These data demonstrate the importance of reporter-enzyme inhibition when studying the effects of such compounds and suggest that this in vitro assay can be used to exclude false-positives due to firefly or Renilla luciferase inhibition, and to thus define the most appropriate reporter gene.

The right tools for the job: the central role for next generation chemical probes and chemistry-based target deconvolution methods in phenotypic drug discovery

The reconnection of the scientific community with phenotypic drug discovery has created exciting new possibilities to develop therapies for diseases with highly complex biology. It promises to revolutionise fields such as neurodegenerative disease and regenerative medicine, where the development of new drugs has consistently proved elusive. Arguably, the greatest challenge in readopting the phenotypic drug discovery approach exists in establishing a crucial chain of translatability between phenotype and benefit to patients in the clinic. This remains a key stumbling block for the field which needs to be overcome in order to fully realise the potential of phenotypic drug discovery. Excellent quality chemical probes and chemistry-based target deconvolution techniques will be a crucial part of this process. In this review, we discuss the current capabilities of chemical probes and chemistry-based target deconvolution methods and evaluate the next advances necessary in order to fully support phenotypic screening approaches in drug discovery.

Nuisance compounds in cellular assays

Compounds that exhibit assay interference or undesirable mechanisms of bioactivity ("nuisance compounds") are routinely encountered in cellular assays, including phenotypic and high-content screening assays. Much is known regarding compound-dependent assay interferences in cell-free assays. However, despite the essential role of cellular assays in chemical biology and drug discovery, there is considerably less known about nuisance compounds in more complex cell-based assays. In our view, a major obstacle to realizing the full potential of chemical biology will not just be difficult-to-drug targets or even the sheer number of targets, but rather nuisance compounds, due to their ability to waste significant resources and erode scientific trust. In this review, we summarize our collective academic, government, and industry experiences regarding cellular nuisance compounds. We describe assay design strategies to mitigate the impact of nuisance compounds and suggest best practices to efficiently address these compounds in complex biological settings.

Benchmarking the mechanisms of frequent hitters: limitation of PAINS alerts

In 2010, the pan-assay interference compounds (PAINS) rule was proposed to identify false-positive compounds, especially frequent hitters (FHs), in biological screening campaigns, and has rapidly become an essential component in drug design. However, the specific mechanisms remain unknown, and the result validation and follow-up processing schemes are still unclear. In this review, a large benchmark collection of >600,000 compounds sourced from databases and the literature, including six common false-positive mechanisms, was used to evaluate the detection ability of PAINS. In addition, 400 million purchasable molecules from the ZINC database were also applied to PAINS screening. The results indicate that the PAINS rule is not suitable for the screening of all types of false-positive results and needs more improvement.

Scopy: an integrated negative design python library for desirable HTS/VS database design

BACKGROUND

High-throughput screening (HTS) and virtual screening (VS) have been widely used to identify potential hits from large chemical libraries. However, the frequent occurrence of 'noisy compounds' in the screened libraries, such as compounds with poor drug-likeness, poor selectivity or potential toxicity, has greatly weakened the enrichment capability of HTS and VS campaigns. Therefore, the development of comprehensive and credible tools to detect noisy compounds from chemical libraries is urgently needed in early stages of drug discovery.

RESULTS

In this study, we developed a freely available integrated python library for negative design, called Scopy, which supports the functions of data preparation, calculation of descriptors, scaffolds and screening filters, and data visualization. The current version of Scopy can calculate 39 basic molecular properties, 3 comprehensive molecular evaluation scores, 2 types of molecular scaffolds, 6 types of substructure descriptors and 2 types of fingerprints. A number of important screening rules are also provided by Scopy, including 15 drug-likeness rules (13 drug-likeness rules and 2 building block rules), 8 frequent hitter rules (four assay interference substructure filters and four promiscuous compound substructure filters), and 11 toxicophore filters (five human-related toxicity substructure filters, three environment-related toxicity substructure filters and three comprehensive toxicity substructure filters). Moreover, this library supports four different visualization functions to help users to gain a better understanding of the screened data, including basic feature radar chart, feature-feature-related scatter diagram, functional group marker gram and cloud gram.

CONCLUSION

Scopy provides a comprehensive Python package to filter out compounds with undesirable properties or substructures, which will benefit the design of high-quality chemical libraries for drug design and discovery. It is freely available at https://github.com/kotori-y/Scopy.

Structural Analysis and Identification of False Positive Hits in Luciferase-Based Assays

Luciferase-based bioluminescence detection techniques are highly favored in high-throughput screening (HTS), in which the firefly luciferase (FLuc) is the most commonly used variant. However, FLuc inhibitors can interfere with the activity of luciferase, which may result in false positive signals in HTS assays. In order to reduce the unnecessary cost of time and money, an in silico prediction model for FLuc inhibitors is highly desirable. In this study, we built an extensive data set consisting of 20 888 FLuc inhibitors and 198 608 noninhibitors, and then developed a group of classification models based on the combination of three machine learning (ML) algorithms and four types of molecular representations. The best prediction model based on XGBoost and ECFP4 and MOE2d descriptors yielded a balanced accuracy (BA) of 0.878 and an area under the receiver operating characteristic curve (AUC) value of 0.958 for the validation set, and a BA of 0.886 and an AUC of 0.947 for the test set. Three external validation sets, including set 1 (3231 FLuc inhibitors and 69 783 noninhibitors), set 2 (695 FLuc inhibitors and 75 913 noninhibitors), and set 3 (1138 FLuc inhibitors and 8155 noninhibitors), were used to verify the predictive ability of our models. The BA values for the three external validation sets given by the best model are 0.864, 0.845, and 0.791, respectively. In addition, the important features or structural fragments related to FLuc inhibitors were recognized by the Shapley additive explanations (SHAP) method along with their influences on predictions, which may provide valuable clues to detecting undesirable luciferase inhibitors. Based on the important and explanatory features, 16 rules were proposed for detecting FLuc inhibitors, which can achieve a correction rate of 70% for FLuc inhibitors. Furthermore, a comparison with existing prediction rules and models for FLuc inhibitors used in virtual screening verified the high reliability of the models and rules proposed in this study. We also used the model to screen three curated chemical databases, and almost 10% of the molecules in the evaluated databases were predicted as inhibitors, highlighting the potential risk of false positives in luciferase-based assays. Finally, a public web server called ChemFLuc was developed (http://admet.scbdd.com/chemfluc/index/), and it offers a free available service to predict potential FLuc inhibitors.

Characterisation of utrophin modulator SMT C1100 as a non-competitive inhibitor of firefly luciferase

Firefly luciferase (FLuc) is a powerful tool for molecular and cellular biology, and popular in high-throughput screening and drug discovery. However, FLuc assays have been plagued with positive and negative artefacts due to stabilisation and inhibition by small molecules from a range of chemical classes. Here we disclose Phase II clinical compound SMT C1100 for the treatment of Duchenne muscular dystrophy as an FLuc inhibitor (K_D of 0.40 ± 0.15 µM). Enzyme kinetic studies using SMT C1100 and other non-competitive inhibitors including resveratrol and NFκBAI4 identified previously undescribed modes of inhibition with respect to FLuc's luciferyl adenylate intermediate. Employing a photoaffinity strategy to identify SMT C1100's binding site, a photolabelled SMT C1100 probe instead underwent FLuc-dependent photooxidation. Our findings support novel binding sites on FLuc for non-competitive inhibitors.

Identification of Compounds That Interfere with High-Throughput Screening Assay Technologies

A significant challenge in high-throughput screening (HTS) campaigns is the identification of assay technology interference compounds. A Compound Interfering with an Assay Technology (CIAT) gives false readouts in many assays. CIATs are often considered viable hits and investigated in follow-up studies, thus impeding research and wasting resources. In this study, we developed a machine-learning (ML) model to predict CIATs for three assay technologies. The model was trained on known CIATs and non-CIATs (NCIATs) identified in artefact assays and described by their 2D structural descriptors. Usual methods identifying CIATs are based on statistical analysis of historical primary screening data and do not consider experimental assays identifying CIATs. Our results show successful prediction of CIATs for existing and novel compounds and provide a complementary and wider set of predicted CIATs compared to BSF, a published structure-independent model, and to the PAINS substructural filters. Our analysis is an example of how well-curated datasets can provide powerful predictive models despite their relatively small size.