Literature DB >> 34366864

A Comparison of Nine Machine Learning Mutagenicity Models and Their Application for Predicting Pyrrolizidine Alkaloids.

Christoph Helma1, Verena Schöning2, Jürgen Drewe3,4, Philipp Boss5.   

Abstract

Random forest, support vector machine, logistic regression, neural networks and k-nearest neighbor (n class="Chemical">lazar) algorithms, were applied to a new n>n class="Species">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.
Copyright © 2021 Helma, Schöning, Drewe and Boss.

Entities:  

Keywords:  CDK; lazar; machine learning; mutagenicity; openbabel; pyrrolizidine alkaloids; tensorflow

Year:  2021        PMID: 34366864      PMCID: PMC8339974          DOI: 10.3389/fphar.2021.708050

Source DB:  PubMed          Journal:  Front Pharmacol        ISSN: 1663-9812            Impact factor:   5.810


  1 in total

1.  Modeling Structure-Activity Relationship of AMPK Activation.

Authors:  Jürgen Drewe; Ernst Küsters; Felix Hammann; Matthias Kreuter; Philipp Boss; Verena Schöning
Journal:  Molecules       Date:  2021-10-28       Impact factor: 4.411

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.