Unknown

Dataset Information

0

Differences in learning characteristics between support vector machine and random forest models for compound classification revealed by Shapley value analysis.

ABSTRACT: The random forest (RF) and support vector machine (SVM) methods are mainstays in molecular machine learning (ML) and compound property prediction. We have explored in detail how binary classification models derived using these algorithms arrive at their predictions. To these ends, approaches from explainable artificial intelligence (XAI) are applicable such as the Shapley value concept originating from game theory that we adapted and further extended for our analysis. In large-scale activity-based compound classification using models derived from training sets of increasing size, RF and SVM with the Tanimoto kernel produced very similar predictions that could hardly be distinguished. However, Shapley value analysis revealed that their learning characteristics systematically differed and that chemically intuitive explanations of accurate RF and SVM predictions had different origins.

SUBMITTER: Siemers FM 

PROVIDER: S-EPMC10097675 | biostudies-literature | 2023 Apr

REPOSITORIES: biostudies-literature

Json Xml
altmetric image

Publications

Differences in learning characteristics between support vector machine and random forest models for compound classification revealed by Shapley value analysis.

Siemers Friederike Maite FM   Bajorath Jürgen J  

Scientific reports 20230412 1

The random forest (RF) and support vector machine (SVM) methods are mainstays in molecular machine learning (ML) and compound property prediction. We have explored in detail how binary classification models derived using these algorithms arrive at their predictions. To these ends, approaches from explainable artificial intelligence (XAI) are applicable such as the Shapley value concept originating from game theory that we adapted and further extended for our analysis. In large-scale activity-bas  ...[more]

Similar Datasets

Unknown Support Vector Machine Classification and Regression Prioritize Different Structural Features for Binary Compound Activity and Potency Value Prediction.
| S-EPMC6045367 | biostudies-literature
Unknown Discovery of moiety preference by Shapley value in protein kinase family using random forest models.
| S-EPMC9011936 | biostudies-literature
Unknown A support vector machine and a random forest classifier indicates a 15-miRNA set related to osteosarcoma recurrence.
| S-EPMC5759858 | biostudies-literature
Unknown Support vector machine classification of streptavidin-binding aptamers.
| S-EPMC4057401 | biostudies-literature
Unknown Analysis of Asperger Syndrome Using Genetic-Evolutionary Random Support Vector Machine Cluster.
| S-EPMC6262410 | biostudies-other
Unknown DHSpred: support-vector-machine-based human DNase I hypersensitive sites prediction using the optimal features selected by random forest.
| S-EPMC5788611 | biostudies-literature
Unknown Comparative analyses between retained introns and constitutively spliced introns in Arabidopsis thaliana using random forest and support vector machine.
| S-EPMC4128822 | biostudies-literature
Unknown Design, synthesis and experimental validation of novel potential chemopreventive agents using random forest and support vector machine binary classifiers.
| S-EPMC5600879 | biostudies-literature
Unknown Ranking causal variants and associated regions in genome-wide association studies by the support vector machine and random forest.
| S-EPMC3089490 | biostudies-literature
Unknown Targeted Local Support Vector Machine for Age-Dependent Classification.
| S-EPMC4183366 | biostudies-literature