Browse views: by Year, by Function, by GLF, by Subfunction, by Conference, by Journal

High-Throughput Melanin-Binding Affinity and In Silico Methods to Aid in the Prediction of Drug Exposure in Ocular Tissue

Reilly, John and Williams, Sarah and Forster, Cornelia and Kansara, Viralbhai and End, Peter and Serrano-Wu, Michael (2015) High-Throughput Melanin-Binding Affinity and In Silico Methods to Aid in the Prediction of Drug Exposure in Ocular Tissue. Journal of pharmaceutical sciences, 104 (12). pp. 3997-4001. ISSN 1520-6017; 0022-3549

Abstract

Drugs possessing the ability to bind to melanin-rich tissue, such as the eye, are linked with higher ocular exposure, and therefore have the potential to affect the efficacy and safety profiles of therapeutics. An in silico method could rapidly assess the melanin binding properties of large numbers of compounds and assist in compound design where the binding to melanin binding is a factor. Previous studies have reported the development of in silico QSAR models based on training sets of relatively small and mostly similar compounds. In this study, we report the development of an in silico model built using the Random Forest algorithm, which is capable of quickly assessing compounds as low, medium or high melanin binders. The model was trained using a relatively larger and more diverse dataset of molecules which cover a broader range of melanin binding affinities, than what has been previously published. The model uses melanin binding data generated from an in house high-affinity chromatography method. This method was validated against a rigorous in house radiolabelled assay and in vivo studies. Additionally, the in silico model identified several physiochemical descriptors from this more diverse data set which agree with those previously found and could be considered in the design of compounds where melanin binding modulation is desired .

Item Type: Article
Keywords: Melanin, affinity chromatography, QSAR, in silico, random forest
Date Deposited: 12 Oct 2016 00:45
Last Modified: 12 Oct 2016 00:45
URI: https://oak.novartis.com/id/eprint/10320

Search

Email Alerts

Register with OAK to receive email alerts for saved searches.