Abstract
The first challenge in the 2014 competition launched by the Teach-Discover-Treat (TDT) initiative asked for the development of a tutorial for ligand-based virtual screening, based on data from a primary phenotypic high-throughput screen (HTS) against malaria. The resulting Workflows were applied to select compounds from a commercial database, and a subset of those were purchased and tested experimentally for anti-malaria activity. Here, we present the two most successful Workflows, both using machine-learning approaches, and report the results for the 114 compounds tested in the follow-up screen. Excluding the two known anti-malarials quinidine and amodiaquine and 31 compounds already present in the primary HTS, a high hit rate of 57% was found.
Highlights
Teach-Discover-Treat (TDT) is an initiative that aims to provide high-quality tutorials of important tasks in computer-aided drug discovery, in order to impact education and drug discovery for neglected diseases[1]
We focus on Challenge 1: ligand-based virtual screening (VS) against malaria
The goal was to build a predictive model for anti-malaria activity based on a phenotypic high-throughput screen (HTS), and to use that model subsequently to select the set of compounds for screening
Summary
Teach-Discover-Treat (TDT) is an initiative that aims to provide high-quality tutorials of important tasks in computer-aided drug discovery, in order to impact education and drug discovery for neglected diseases[1]. To encourage the creation of high-quality tutorials by the computational chemistry community, competitions are launched with a series of different challenges, and the results/tutorials are made available through the website of the initiative We focus on Challenge 1: ligand-based virtual screening (VS) against malaria. The goal was to build a predictive model for anti-malaria activity based on a phenotypic high-throughput screen (HTS), and to use that model subsequently to select the set of compounds for screening. In a ligand-based VS, typically no structural information of the target is available, and the prediction of potentially active compounds is based on the principle that similar molecules exhibit similar activity[3]. The challenge is thereby to find an appropriate molecular description for similarity, which can depend heavily on the compound selection and/or target[4,5,6,7]. Machine-learning (ML) methods have emerged as an attractive tool to boost the predictive power of ligand-based VS approaches[8,9,10,11,12]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.