Modeling Kinase Inhibition Using Highly Confident Data Sets
- 30 April 2018
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 58 (5) , 957-967
Abstract
Protein kinases form a consistent class of promising drug targets, and several efforts have been made to predict the activity of small-molecules against a representative part of the kinome. This study continues our previous work (Bora, A.; Avram, S.; Ciucanu, I.; Raica, M.; Avram, S., Predictive Models for Fast and Effective Profiling of Kinase Inhibitors. J. Chem. Inf. Model. 2016, 56, 895−905; www.chembioinf.ro), aiming to build and measure the performance of ligand-based kinase inhibitor prediction models. Here, we analyzed kinase-inhibitor pairs with multiple activity points extracted from ChEMBL database, and identified the main sources of inconsistency. Our results indicate that lower IC50 values are usually less affected by errors and reflect more accurately the structure-activity relationship of the molecules against the target, ideally for quantitative structure-activity relationship (QSAR) studies. Further, we modeled the activity of 104 kinases using unbiased target-specific activity points. The performance of predictors built on extensive connectivity fingerprints (ECFP4) and 2D-pharmacophore fingerprints (PFPs) are compared by means of tolerance intervals (TIs, 95%/95%) in virtual screening (VS) and classification (CLS) tasks, using external random (RandSets) and diversity-based (DivSets) test sets. We found the two encodings to perform superior to each other on different kinases in VS, and PFP-models to perform consistently better in classifying actives (higher sensitivity). Next, we combined the two encoding into a single one (PFPECFP) and demonstrate that, especially in VS (as indicated by the exponential receiver-operating curve enrichment metric, eROCE), for the vast majority of kinases, model-performance increased compared to individual fingerprint models. These findings are highlighted in the more challenging DivSets compared to RandSets. The current paper explores the boundaries of inhibitor predictors for individual kinases to enhance VS and ultimately aid the discovery of novel compounds with desirable polypharmacology.Keywords
Funding Information
- Academia Rom?na (1.2.4/2017)
- Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii (PN-II-RU-TE-2014-4-0422)
This publication has 44 references indexed in Scilit:
- What general conclusions can we draw from kinase profiling data sets?Biochimica et Biophysica Acta (BBA) - Proteins and Proteomics, 2013
- Dissecting Kinase Profiling Data to Predict Activity and Understand Cross-Reactivity of Kinase InhibitorsJournal of Chemical Information and Modeling, 2012
- Reorganizing the protein space at the Universal Protein Resource (UniProt)Nucleic Acids Research, 2011
- Hot Spots of Inorganic Nitrogen Availability in an Alpine-Subalpine Ecosystem, Colorado Front RangeEcosystems, 2011
- Extended-Connectivity FingerprintsJournal of Chemical Information and Modeling, 2010
- Targeting the cancer kinome through polypharmacologyNature Reviews Cancer, 2010
- Aldo‐keto reductase 1C subfamily genes in skin are UV‐inducible: possible role in keratinocytes survivalExperimental Dermatology, 2009
- The selectivity of protein kinase inhibitors: a further updateBiochemical Journal, 2007
- Similarity-based virtual screening using 2D fingerprintsDrug Discovery Today, 2006
- Comparison of topological descriptors for similarity-based virtual screening using multiple bioactive reference structuresOrganic & Biomolecular Chemistry, 2004