Adaptive modelling of structured molecular representations for toxicity prediction

Carlo Bertinetto; Celia Duce; Alessio Micheli; Roberto Solaro; Maria Rosaria Tiné

doi:10.1063/1.4771796

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

Not published at Aalto University

University of Pisa

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

2 Citations (Scopus)

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 language	English
Title of host publication	International Conference of Computational Methods in Sciences and Engineering 2009, ICCMSE 2009
Publisher	American Institute of Physics
Pages	721-724
Number of pages	4
ISBN (Print)	9780735411227
DOIs	https://doi.org/10.1063/1.4771796
Publication status	Published - 2012
MoE publication type	A4 Conference publication
Event	International Conference of Computational Methods in Sciences and Engineering - Rhodes, Greece Duration: 29 Sept 2009 → 4 Oct 2009

Publication series

Name	AIP Conference Proceedings
Publisher	AIP
Number	1
Volume	1504
ISSN (Electronic)	1551-7616

Conference

Conference	International Conference of Computational Methods in Sciences and Engineering
Abbreviated title	ICCMSE
Country/Territory	Greece
City	Rhodes
Period	29/09/2009 → 04/10/2009

Keywords

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

Access to Document

10.1063/1.4771796

Cite this

Bertinetto, C., Duce, C., Micheli, A., Solaro, R., & Tiné, M. R. (2012). Adaptive modelling of structured molecular representations for toxicity prediction. In International Conference of Computational Methods in Sciences and Engineering 2009, ICCMSE 2009 (pp. 721-724). ( AIP Conference Proceedings; Vol. 1504, No. 1). American Institute of Physics. https://doi.org/10.1063/1.4771796

@inproceedings{9bfc1ee152e64ee69b3544864eaafbf4,

title = "Adaptive modelling of structured molecular representations for toxicity prediction",

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.",

keywords = "IGC, QSAR/QSPR, Recursive Neural Network, Structured Representation, Tetrahymena pyriformis, Toxicity",

author = "Carlo Bertinetto and Celia Duce and Alessio Micheli and Roberto Solaro and Tin{\'e}, {Maria Rosaria}",

year = "2012",

doi = "10.1063/1.4771796",

language = "English",

isbn = "9780735411227",

series = " AIP Conference Proceedings",

publisher = "American Institute of Physics",

number = "1",

pages = "721--724",

booktitle = "International Conference of Computational Methods in Sciences and Engineering 2009, ICCMSE 2009",

address = "United States",

note = "International Conference of Computational Methods in Sciences and Engineering , ICCMSE ; Conference date: 29-09-2009 Through 04-10-2009",

}

Bertinetto, C, Duce, C, Micheli, A, Solaro, R & Tiné, MR 2012, Adaptive modelling of structured molecular representations for toxicity prediction. in International Conference of Computational Methods in Sciences and Engineering 2009, ICCMSE 2009. AIP Conference Proceedings, no. 1, vol. 1504, American Institute of Physics, pp. 721-724, International Conference of Computational Methods in Sciences and Engineering , Rhodes, Greece, 29/09/2009. https://doi.org/10.1063/1.4771796

Adaptive modelling of structured molecular representations for toxicity prediction. / Bertinetto, Carlo; Duce, Celia; Micheli, Alessio et al.
International Conference of Computational Methods in Sciences and Engineering 2009, ICCMSE 2009. American Institute of Physics, 2012. p. 721-724 ( AIP Conference Proceedings; Vol. 1504, No. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Adaptive modelling of structured molecular representations for toxicity prediction

AU - Bertinetto, Carlo

AU - Duce, Celia

AU - Micheli, Alessio

AU - Solaro, Roberto

AU - Tiné, Maria Rosaria

PY - 2012

Y1 - 2012

N2 - 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.

AB - 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.

KW - IGC

KW - QSAR/QSPR

KW - Recursive Neural Network

KW - Structured Representation

KW - Tetrahymena pyriformis

KW - Toxicity

UR - http://www.scopus.com/inward/record.url?scp=84873136072&partnerID=8YFLogxK

U2 - 10.1063/1.4771796

DO - 10.1063/1.4771796

M3 - Conference article in proceedings

AN - SCOPUS:84873136072

SN - 9780735411227

T3 - AIP Conference Proceedings

SP - 721

EP - 724

BT - International Conference of Computational Methods in Sciences and Engineering 2009, ICCMSE 2009

PB - American Institute of Physics

T2 - International Conference of Computational Methods in Sciences and Engineering

Y2 - 29 September 2009 through 4 October 2009

ER -

Adaptive modelling of structured molecular representations for toxicity prediction

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this