Helmholtz Gemeinschaft

Search
Browse
Statistics
Feeds

A comparison of nine machine learning mutagenicity models and their application for predicting pyrrolizidine alkaloids

[thumbnail of Original Article]
Preview
PDF (Original Article) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
4MB

Item Type:Article
Title:A comparison of nine machine learning mutagenicity models and their application for predicting pyrrolizidine alkaloids
Creators Name:Helma, C., Schöning, V., Drewe, J. and Boss, P.
Abstract:Random forest, support vector machine, logistic regression, neural networks and k-nearest neighbor (lazar) algorithms, were applied to a new Salmonella mutagenicity dataset with 8,290 unique chemical structures utilizing MolPrint2D and Chemistry Development Kit (CDK) descriptors. Crossvalidation accuracies of all investigated models ranged from 80 to 85% which is comparable with the interlaboratory variability of the Salmonella mutagenicity assay. Pyrrolizidine alkaloid predictions showed a clear distinction between chemical groups, where otonecines had the highest proportion of positive mutagenicity predictions and monoesters the lowest.
Keywords:Mutagenicity, Lazar, Openbabel, CDK, Machine Learning, Tensorflow, Pyrrolizidine Alkaloids
Source:Frontiers in Pharmacology
ISSN:1663-9812
Publisher:Frontiers Media SA
Volume:12
Page Range:708050
Date:22 July 2021
Official Publication:https://doi.org/10.3389/fphar.2021.708050
PubMed:View item in PubMed

Repository Staff Only: item control page

Downloads

Downloads per month over past year

Open Access
MDC Library