Tuning neural and fuzzy-neural networks for toxicity modeling

P. Mazzatorta; E. Benfenati; C. D. Neagu; G. Gini

doi:10.1021/ci025585q

Tuning neural and fuzzy-neural networks for toxicity modeling

P. Mazzatorta, E. Benfenati, C. D. Neagu, G. Gini

Istituto di Ricerche Farmacologiche "Mario Negri"

Research output: Contribution to journal › Article › peer-review

Abstract

The need for general reliable models for predicting toxicity has led to the use of artificial intelligence. We applied neural and fuzzy-neural networks with the QSAR approach. We underline how the networks have to be tuned on the data sets generally involved in modeling toxicity. This study was conducted on 562 organic compounds in order to establish models for predictive the acute toxicity in fish.

Original language	English
Pages (from-to)	513-518
Number of pages	6
Journal	Journal of Chemical Information and Computer Sciences
Volume	43
Issue number	2
DOIs	https://doi.org/10.1021/ci025585q
Publication status	Published - Mar 2003

ASJC Scopus subject areas

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

Access to Document

10.1021/ci025585q

Cite this

@article{30949afc293242d4b56542bd5c1554c8,

title = "Tuning neural and fuzzy-neural networks for toxicity modeling",

abstract = "The need for general reliable models for predicting toxicity has led to the use of artificial intelligence. We applied neural and fuzzy-neural networks with the QSAR approach. We underline how the networks have to be tuned on the data sets generally involved in modeling toxicity. This study was conducted on 562 organic compounds in order to establish models for predictive the acute toxicity in fish.",

author = "P. Mazzatorta and E. Benfenati and Neagu, {C. D.} and G. Gini",

year = "2003",

month = mar,

doi = "10.1021/ci025585q",

language = "English",

volume = "43",

pages = "513--518",

journal = "Journal of Chemical Information and Computer Sciences",

issn = "0095-2338",

publisher = "American Chemical Society",

number = "2",

}

TY - JOUR

T1 - Tuning neural and fuzzy-neural networks for toxicity modeling

AU - Mazzatorta, P.

AU - Benfenati, E.

AU - Neagu, C. D.

AU - Gini, G.

PY - 2003/3

Y1 - 2003/3

N2 - The need for general reliable models for predicting toxicity has led to the use of artificial intelligence. We applied neural and fuzzy-neural networks with the QSAR approach. We underline how the networks have to be tuned on the data sets generally involved in modeling toxicity. This study was conducted on 562 organic compounds in order to establish models for predictive the acute toxicity in fish.

AB - The need for general reliable models for predicting toxicity has led to the use of artificial intelligence. We applied neural and fuzzy-neural networks with the QSAR approach. We underline how the networks have to be tuned on the data sets generally involved in modeling toxicity. This study was conducted on 562 organic compounds in order to establish models for predictive the acute toxicity in fish.

UR - http://www.scopus.com/inward/record.url?scp=0037362116&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037362116&partnerID=8YFLogxK

U2 - 10.1021/ci025585q

DO - 10.1021/ci025585q

M3 - Article

C2 - 12653515

AN - SCOPUS:0037362116

SN - 0095-2338

VL - 43

SP - 513

EP - 518

JO - Journal of Chemical Information and Computer Sciences

JF - Journal of Chemical Information and Computer Sciences

IS - 2

ER -

Tuning neural and fuzzy-neural networks for toxicity modeling

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this