Skip directly to search Skip directly to A to Z list Skip directly to page options Skip directly to site content

NIOSHTIC-2 Publications Search

Search Results

Application of the random forest method in studies of local lymph node assay based skin sensitization data.

Authors
Li-S; Fedorowicz-A; Singh-H; Soderholm-S
Source
J Chem Inf Model 2005 Apr; 45(4):952-964
NIOSHTIC No.
20026682
Abstract
The random forest and classification tree modeling methods are used to build predictive models of the skin sensitization activity of a chemical. A new two-stage backward elimination algorithm for descriptor selection in the random forest method is introduced. The predictive performance of the random forest model was maximized by tuning voting thresholds to reflect the unbalanced size of classification groups in available data. Our results show that random forest with a proposed backward elimination procedure outperforms a single classification tree and the standard random forest method in predicting Local Lymph Node Assay based skin sensitization activity. The proximity measure obtained from the random forest is a natural similarity measure that can be used for clustering of chemicals. Based on this measure, the clustering analysis partitioned the chemicals into several groups sharing similar molecular patterns. The improved random forest method demonstrates the potential for future QSAR studies based on a large number of descriptors or when the number of available data points is limited.
Keywords
Lymph-nodes; Skin-sensitivity; Skin; Sensitization; Models; Statistical-analysis; Simulation-methods
Contact
Health Effects Laboratory Division, National Institute for Occupational Safety and Health, 1095 Willowdale Road, Morgantown, WV 26505
CODEN
JCISD8
Publication Date
20050401
Document Type
Journal Article
Email Address
swl4@cdc.gov
Fiscal Year
2005
NTIS Accession No.
NTIS Price
Issue of Publication
4
ISSN
0095-2338
NIOSH Division
HELD
Source Name
Journal of Chemical Information and Modeling
State
WV
TOP