MORF: Multi-view oblique random forest for hepatotoxicity prediction
Summary: Hepatotoxicity prediction is significant in drug development, so the experts expect to get effective and reliable references. Based on the consideration that the hepatotoxicity data involve multiple types of features, this paper proposes a multi-view oblique random forest (MORF) for hepatot...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004225000148 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Summary: Hepatotoxicity prediction is significant in drug development, so the experts expect to get effective and reliable references. Based on the consideration that the hepatotoxicity data involve multiple types of features, this paper proposes a multi-view oblique random forest (MORF) for hepatotoxicity prediction by considering each type of feature as an independent view. The Householder transformation is employed to get the inclined cut hyperplane in each view. Two versions of the multi-view oblique decision tree (ODT) algorithms were designed by generating optimal nodes based on selecting proper hyperplanes from different views, named ODT-N and ODT-R. These two types of ODT algorithms serve as the base learners to construct two MORF. Experiments conducted on the hepatotoxicity data provide performance comparisons among different algorithms, and the results confirm that our algorithms can fully utilize the information in different views. |
|---|---|
| ISSN: | 2589-0042 |