Combining unsupervised and supervised artificial neural networks to predict aquatic toxicity

Giuseppina Gini, Marian Viorel Craciun, Christoph König, Emilio Benfenati

Research output: Contribution to journalArticlepeer-review


Most quantitative structure-activity relationship (QSAR) models are linear relationships and significant for only a limited domain of compounds. Here we propose a data-driven approach with a flexible combination of unsupervised and supervised neural networks able to predict the toxicity of a large set of different chemicals while still respecting the QSAR postulates. Since QSAR is applicable only to similar compounds, which have similar biological and physicochemical properties, large numbers of compounds are clustered before building local models, and local models are ensembled to obtain the final result. The approach has been used to develop models to predict the fish toxicity of Pimephales promelas and Tetrahymena pyriformis, a protozoan.

Original languageEnglish
Pages (from-to)1897-1902
Number of pages6
JournalJournal of Chemical Information and Computer Sciences
Issue number6
Publication statusPublished - Nov 2004

ASJC Scopus subject areas

  • Chemistry(all)
  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics


Dive into the research topics of 'Combining unsupervised and supervised artificial neural networks to predict aquatic toxicity'. Together they form a unique fingerprint.

Cite this