Name: | Description: | Size: | Format: | |
---|---|---|---|---|
272.29 KB | Adobe PDF |
Advisor(s)
Abstract(s)
Artificial neural networks (ANNs) have several
applications; one of them is the prediction of biological
activity. Here, ANNs were applied to a set of 32 compounds
with anticancer activity assayed experimentally against two
cancer cell lines (A2780 and T-47D). Using training and
test sets, the obtained correlation coefficients between
experimental and calculated values of activity, for A2780,
were 0.804 and 0.829, respectively, and for T-47D, we got
0.820 for the training set and 0.927 for the test set. Com paring multiple linear regression and ANN models, the
latter were better suited in establishing relationships
between compounds’ structure and their anticancer activity.
Description
Keywords
Backpropagation algorithm Correlation coefficients Heuristics Learning algorithms Machine learning Neural network models Nonlinear models Prediction methods Radial base function network . Faculdade de Ciências Exatas e da Engenharia
Citation
Sousa, I. J., Padrón, J. M., & Fernandes, M. X. (2013). Generation of artificial neural networks models in anticancer study. Neural Computing and Applications, 23, 577-582.
Publisher
Springer