Kaiser, K.L.; Niculescu, S.P.; Schultz, T.W. Probabilistic neural network modeling of the toxicity of chemicals to Tetrahymena pyriformis with molecular fragment descriptors. SAR QSAR Environ. Res. 2002, 13, 1, 57–67.

QsarDB Repository

Kaiser, K.L.; Niculescu, S.P.; Schultz, T.W. Probabilistic neural network modeling of the toxicity of chemicals to Tetrahymena pyriformis with molecular fragment descriptors. SAR QSAR Environ. Res. 2002, 13, 1, 57–67.

QDB archive DOI: 10.15152/QDB.64   DOWNLOAD

QsarDB content

Property pIGC50: 48-h Tetrahymena toxicity as log(1/IGC50) [log(L/mmol)]

Property pIGC50_est: 48-h Tetrahymena toxicity as log(1/IGC50) [log(L/mmol)]

Citing

When using this QDB archive, please cite (see details) it together with the original article:

  • Ruusmann, V. Data for: Probabilistic neural network modeling of the toxicity of chemicals to Tetrahymena pyriformis with molecular fragment descriptors. QsarDB repository, QDB.64. 2012. http://dx.doi.org/10.15152/QDB.64

  • Kaiser, K. L.; Niculescu, S. P.; Schultz, T. W. Probabilistic neural network modeling of the toxicity of chemicals to Tetrahymena pyriformis with molecular fragment descriptors. SAR QSAR Environ. Res. 2002, 13, 57–67. http://dx.doi.org/10.1080/10629360290002217

Metadata

Show full item record

Title: Kaiser, K.L.; Niculescu, S.P.; Schultz, T.W. Probabilistic neural network modeling of the toxicity of chemicals to Tetrahymena pyriformis with molecular fragment descriptors. SAR QSAR Environ. Res. 2002, 13, 1, 57–67.
Abstract:We present the results of an investigation into the use of a probabilistic neural network (PNN) based methodology to model the 48-60-h ICG50 (inhibitory concentration for population growth) sublethal toxicity to the ciliate Tetrahymena pyriformis. The information fed into the neural network is solely based on simple molecular descriptors as can be derived from the chemical structure. In contrast to most other toxicological models, the octanol/water partition coefficient is not used as an input parameter and no rules of thumb, or other substance selection-criteria, are involved. The model was trained on a 1,000 substances data set and validated using an 84 substances external test set. The associated analysis of errors confirms the excellent recognitive and predictive capabilities of the model.
URI:http://hdl.handle.net/10967/64
http://dx.doi.org/10.15152/QDB.64
Date:2012-05-23


Files in this item

NameDescriptionFormatSizeView
713745763.qdb.zipn/aapplication/zip4.482KbView/Open
Files associated with this item are distributed
under Creative Commons license.

This item appears in the following Collection(s)

Show full item record