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

Abstract

Firefly luciferase is an enzyme that has found ubiquitous use in biological assays in high-throughput screening (HTS) campaigns. The inhibition of luciferase in such assays could lead to a false positive result. This issue has been known for a long time, and there have been significant efforts to identify luciferase inhibitors in order to enhance recognition of false positives in screening assays. However, although a large amount of publicly accessible luciferase counterscreen data is available, to date little effort has been devoted to building a chemoinformatic model that can identify such molecules in a given data set. In this study we developed models to identify these molecules using various methods, such as molecular docking, SMARTS screening, pharmacophores, and machine learning methods. Among the structure-based methods, the pharmacophore-based method showed promising results, with a balanced accuracy of 74.2%. However, machine-learning approaches using associative neural networks outperformed all of the other methods explored, producing a final model with a balanced accuracy of 89.7%. The high predictive accuracy of this model is expected to be useful for advising which compounds are potential luciferase inhibitors present in luciferase HTS assays. The models developed in this work are freely available at the OCHEM platform at http://ochem.eu .

Analysis and Modelling of False Positives in GPCR Assays

“…Different descriptors available in OCHEM include CDK, Dragon 6 and 7, ISHIDA fragmentor, among others. Their detailed description can be found elsewhere [4]. Associative Neural Networks (ASNN) [11], Deep Neural Network (DNN) [12], Extreme Gradient Boost (XGBOOST) [13], and Least Squares Support Vector Machine (LSSVM) [14] algorithms were analyzed for training the models.…”

“…In such HTS, identifying false positives is a challenge. False positives may be compounds that interfere with the assay detection technology in some way, such as inhibiting luciferase in luciferase-based system [4], or quenching fluorescence where it is the final readout [5]. There may also be compounds that are not specific to the target protein, but are promiscuous, either to a narrow or broad class of proteins [6].…”

“…In the previous study we developed a machine learning method to flag potential frequent hitters for luciferase assays [4]. In this study we investigated whether the developed methodology can be extended to identify false positives for GPCR assays.…”

Inhibitor Bias in Luciferase-Based Luminescence Assays

“…Since assays for FLuc inhibitors carried out over time frequently yielded false negatives [ 5 , 11 ], FLuc inhibitors were selected for our analysis if they were classified as active at least once. To remove potential assay interference molecules from designated FLuc inhibitors, pan-assay interference compounds [ 12 ] and likely colloidal aggregators [ 13 ] were removed using computational filters.…”

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

“…Hit Dexter 2.0 covers both primary andc onfirmatory dose-response assays and classifies compoundsa sp romiscuous or not with an MCC of 0.64 and aR OC AUC of 0.96. Astudy from Ghosh et al [19] applied machine-learning, pharmacophore analysis and molecular docking to flag false positive hits in Luciferase HTS assays. These three approaches yieldeda balanceda ccuracy of 89.7, 74.2, and 67.2 %r espectively.…”