Predictive classifier models built from natural products with antimalarial bioactivity using machine learning approach

Simple item page
dc.contributor.authorEgieyeh, Samuel
dc.contributor.authorSyce, James
dc.contributor.authorMalan, Sarel F.
dc.contributor.authorChristoffels, Alan
dc.date.accessioned2018-10-10T07:50:33Z
dc.date.available2018-10-10T07:50:33Z
dc.date.issued2018
dc.description.abstractIn view of the vast number of natural products with potential antiplasmodial bioactivity and cost of conducting antiplasmodial bioactivity assays, it may be judicious to learn from previous antiplasmodial bioassays and predict bioactivity of these natural products before experimental bioassays. This study set out to harness antimalarial bioactivity data of natural products to build accurate predictive models, utilizing classical machine learning approaches, which can find potential antimalarial hits from new sets of natural products. Classical machine learning approaches were used to build four classifier models (Naïve Bayesian, Voted Perceptron, Random Forest and Sequence Minimization Optimization of Support Vector Machines) from bioactivity data of natural products with in-vitro antiplasmodial activity (NAA) using a combination of the molecular descriptors and two-dimensional molecular fingerprints of the compounds. Models were evaluated with an independent test dataset. Possible chemical features associated with reported antimalarial activities of the compounds were also extracted. From the results, Random Forest (accuracy 82.81%, Kappa statistics 0.65 and Area under Receiver Operating Characteristics curve 0.91) and Sequential Minimization Optimization (accuracy 85.93%, Kappa statistics 0.72 and Area under Receiver Operating Characteristics curve 0.86) showed good predictive performance for the NAA dataset. The amine chemical group (specifically alkyl amines and basic nitrogen) was confirmed to be essential for antimalarial activity in active NAA dataset. This study built and evaluated classifier models that were used to predict the antiplasmodial bioactivity class (active or inactive) of a set of natural products from interBioScreen chemical library.en_US
dc.identifier.citationEgieyeh, S. (2018). Predictive classifier models built from natural products with antimalarial bioactivity using machine learning approach. PLoS ONE, 13(9): e0204644.en_US
dc.identifier.urihttps://doi.org/10.1371/journal. pone.0204644
dc.identifier.urihttp://hdl.handle.net/10566/4097
dc.language.isoenen_US
dc.privacy.showsubmitterFALSE
dc.publisherPublic Library of Scienceen_US
dc.rights© 2018 Egieyeh et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
dc.status.ispeerreviewedTRUE
dc.subjectAntiplasmodial bioactivity assaysen_US
dc.subjectPredict bioactivityen_US
dc.subjectNatural productsen_US
dc.subjectAntimalarial bioactivity dataen_US
dc.titlePredictive classifier models built from natural products with antimalarial bioactivity using machine learning approachen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Egieyeh_Predictive-classifier_2018.pdf
Size:
6.04 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Research Articles (SANBI)