Automated classification of the behavior of rats in the forced swimming test with support vector machines

Authors:
Holger Fröhlich;Andreas Hoenselaar;Jonas Eichner;Holger Rosenbrock;Gerald Birk;Andreas Zell
Affiliations:
Centre for Bioinformatics Tübingen, Sand 1, 72076 Tübingen, Germany;Centre for Bioinformatics Tübingen, Sand 1, 72076 Tübingen, Germany;Centre for Bioinformatics Tübingen, Sand 1, 72076 Tübingen, Germany;Boehringer Ingelheim Pharma GmbH & Co. KG, Birkendorfer Str. 65, 88397 Biberach/Riíí, Germany;Boehringer Ingelheim Pharma GmbH & Co. KG, Birkendorfer Str. 65, 88397 Biberach/Riíí, Germany;Centre for Bioinformatics Tübingen, Sand 1, 72076 Tübingen, Germany
Venue:
Neural Networks
Year:
2008

Citing 7
Cited 0

Support-Vector Networks

Machine Learning
Approximate statistical tests for comparing supervised classification learning algorithms

Neural Computation
LEDA: a platform for combinatorial and geometric computing

LEDA: a platform for combinatorial and geometric computing
Gene Selection for Cancer Classification using Support Vector Machines

Machine Learning
Kernel Methods for Pattern Analysis

Kernel Methods for Pattern Analysis
Optimal assignment kernels for attributed molecular graphs

ICML '05 Proceedings of the 22nd international conference on Machine learning
The evidence framework applied to classification networks

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

The forced swimming test of rats or mice is a frequently used behavioral test to evaluate compounds for antidepressant activity in vivo. The aim of this study was to replace the human observer, needed to score and analyze the behavior of animals, by a fully automated method. For this purpose, in a first step from a video recording of each rat, an activity profile was calculated, from which subsequently a set of meaningful properties was extracted. This set was finally used to train a Support Vector Machine (SVM). Furthermore, specialized kernel functions, namely the so-called time resolved p-spectrum and modified optimal assignment kernels, were developed to calculate the similarity of activity profiles. Our method allows for a very reliable discrimination of animals treated with antidepressants of different classes (tricyclics imipramine and desipramine as well as selective serotonin reuptake inhibitor, SSRI, fluoxetine) versus a vehicle-treated group. Moreover, our technique is able to classify between tricyclic antidepressants and SSRIs. The results of this work enabled the development of an automated and highly accurate behavior classification system.