Adaptive modelling of structured molecular representations for toxicity prediction

Carlo Bertinetto, Celia Duce, Alessio Micheli, Roberto Solaro, Maria Rosaria Tiné*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

We investigated the possibility of modelling structure-toxicity relationships by direct treatment of the molecular structure (without using descriptors) through an adaptive model able to retain the appropriate structural information. With respect to traditional descriptor-based approaches, this provides a more general and flexible way to tackle prediction problems that is particularly suitable when little or no background knowledge is available. Our method employs a tree-structured molecular representation, which is processed by a recursive neural network (RNN). To explore the realization of RNN modelling in toxicological problems, we employed a data set containing growth impairment concentrations (IGC50) for Tetrahymena pyriformis.

Original languageEnglish
Title of host publicationInternational Conference of Computational Methods in Sciences and Engineering 2009, ICCMSE 2009
PublisherAIP
Pages721-724
Number of pages4
ISBN (Print)9780735411227
DOIs
Publication statusPublished - 2012
MoE publication typeA4 Article in a conference publication
EventInternational Conference of Computational Methods in Sciences and Engineering - Rhodes, Greece
Duration: 29 Sep 20094 Oct 2009

Publication series

Name AIP Conference Proceedings
PublisherAIP
Number1
Volume1504
ISSN (Electronic)1551-7616

Conference

ConferenceInternational Conference of Computational Methods in Sciences and Engineering
Abbreviated titleICCMSE
CountryGreece
CityRhodes
Period29/09/200904/10/2009

Keywords

  • IGC
  • QSAR/QSPR
  • Recursive Neural Network
  • Structured Representation
  • Tetrahymena pyriformis
  • Toxicity

Fingerprint Dive into the research topics of 'Adaptive modelling of structured molecular representations for toxicity prediction'. Together they form a unique fingerprint.

Cite this