Predictive Toxicology of Chemicals: Experiences and Impact of AI Tools
Papers from 1999 AAAI Spring Symposium
Giuseppina C. Gini and Alan R. Katritzky, Program Cochairs
Technical Report SS-99-01 published by The AAAI Press, Menlo Park, California. This technical report is also available in book and CD format.
Contents
Preface / v
Giuseppina C. Gini and Alan R. Katritzky
Panel 1 (Chair A. Richard)
Toxicity — Data Bases, Their Quality, and the User Needs.
Long Term Development of Toxicology Databases: The Experience Gathered By the Joint Research Centre of the European Commission Within The ECDIN And IUCLID Projects / 1
Flavio Argentesi and Annabelle Ascher
The Requirements for Registration of Plant Protection Products In The EU / 5
P. Ciocca, P. Grasso
Data Quality Issues In Toxicological Knowledge Discovery / 8
Christoph Helma, Eva Gottmann, Stefan Kramer, and Bernhard Pfahringer
Invited Paper: QSPR and QSAR Models Derived with CODESSA Multipurpose Statistical Analysis Software / 12
Mati Karelson, Uko Maran, Yilin Wang, and Alan R. Katritzky
Panel 2 (Chair A. Katritzky)
Representations of Chemicals — Possibilities, Comparison and Uses
Discovering Substructures in the Chemical Toxicity Domain / 24
Ravindra N. Chittimoori, Lawrence B. Holder, and Diane J. Cook
A Graphical Technique for Preliminary Assessment of Effects on DNA Sequences from Toxic Substances / 28
A. Nandy, C. Raychaudhury, S. C. Basak
On Characterization of Pharmacophore / 32
Milan Randic
Similarity, Diversity, and the Comparison of Molecular Structures / 36
Guido Sello
COMET: The Approach Of A Project In Evaluating Toxicity / 40
E. Benfenati, S. Pelagatti, P. Grasso, G. Gini
Utilization of Predictive Toxicology Software and Similar Tools For Health Risk Assessment of Chemicals and Polymers / 44
Ranjan Bose
The Utility of Multiple Random Sampling in the Development of SAR Models / 45
N. B. Sussman, O. T. Macina, H. G. Claycamp, S. G. Grant, H. S. Rosenkranz
Multiple Formula Approach for Structure-Cytotoxicity/Antiviral Activity Relationship Studies of Nucleoside Analogs / 49
Mathew L. Lesniewski, Ravi R. Parakulam, Merideth R. Marquis, and
Chun-che Tsai
Structure-Cytotoxicity/Antiviral Activity Relationship Studies of Nucleoside Analogs Using Structure-Activity Maps / 53
Ravi R. Parakulam, Mathew L. Lesniewski, Michael A. Marquis II, and Chun-che Tsai
A Comprehensive Approach to Argumentation / 56
Philip N. Judson and Jonathan Vessey
Argumentation and Risk Assessment / 60
Simon Parsons, John Fox, and Andrew Coulson
Using Inductive Logic Programming to Construct Structure-Activity Relationships / 64
Ashwin Srinivasan and Ross D. King
Panel 3 (Chair A. Srinivasan)
Decision Trees and the Logic Approach
Prediction of Chemical Carcinogenicity in Rodents by Machine Learning of Decision Trees and Rule Sets / 74
Dennis Bahler and Douglas W. Bristol
Finding Frequent Substructures In Chemical Compounds / 78
Luc Dehaspe, Hannu Toivonen, and Ross Donald King
A Distributed Solution to the PTE Problem / 82
Ignacio Giráldez, Charles Elkan, Daniel Borrajo
Representational/Efficiency Issues In Toxicological Knowledge Discovery / 86
Bernhard Pfahringer, Eva Gottmann, Stefan Kramer, Christoph Helma
Rule Generation by Means of Lattice Theory / 90
R. Brüggemann S. Pudenz, H-G. Bartel
Overview of Different Artificial Intelligence Approaches Combined with a Deductive Logic-based Expert System for Predicting Chemical Toxicity / 94
Ferenc Darvas, Atkos PappI, Alex Allerdyce, Emilio Benfenati, Giuseppina Gini, Milofi Tichy, Nicholas Sobb, and Aida Citti
Discovery of Knowledge about Drug Side Effects in Clinical Databases based on Rough Set Model / 100
Shosaku Tsumoto
Development of Knowledge Rules for Cancer Expert System for Prediction of Carcinogenic Potential of Chemicals: USEPA Approach / 104
Yin-tak Woo, David Y. Lai, Joseph C. Arcos, and Mary F. Argus
Use of Statistical And Neural Net Methods In Predicting Toxicity Of Chemicals: A Hierarchical QSAR Approach / 108
Subhash C. Basak, David W. Opitz, Krishnan Balasubramanian, Brian D. Gute, Gregory D. Grunwald
Artificial Neural Networks As Statistical Tools In SAR/QSAR Modeling / 112
H. G. Claycamp, N. B. Sussman, O. Macina, H. S. Rosenkranz
Computational Intelligence and Predictive Toxicology / 116
Adolf Grauel, L. A. Ludwig, I. Renners, F. Berk
Combining Recursive Partitioning and Uncertain Reasoning for Data Exploration and Characteristic Prediction / 119
Kristen L. Mello and Steven D. Brown
A QSAR - Bayesian Neural Network Model To Identify Molecular Properties Causing Eye Irritation In Cationic Surfactants / 123
Grace Y. Patlewicz, Wael El-Deredy
A Hybrid Approach To Risk Assessment For Multiple Pathway Chemical Exposures / 127
T. Rajkumar
Predicting Rodent Carcinogenicity in a Set of 30 Test Agents Using Discriminant Analysis and Bayesian Classifiers / 131
Carol A. Wellington
Dennis R. Bahler
Invited PaperAdaptive Structure Processing with ANN: Is It Useful For Chemical Applications? / 135
Christoph Goller
Some Results for the Prediction Of Carcinogenicity Using Hybrid Systems / 138
Giuseppina Gini, Marco Lorenzini, Angela Vittore, Emilio Benfenati, and Paola Grasso
Membrane-Interaction QSAR Analysis: Application To The Estimation of Eye Irritation of Organic Compounds / 144
Amit S. Kulkarni, A. J. Hopfinger, and Jose S. Duca
Predicting Chemical Carcinogenesis in Rodents with Artificial Neural Networks and Symbolic Rules Extracted from Trained Networks / 148
Brian A. Stone, Dennis Bahler
Predictive Toxicology and Mixtures of Chemicals / 148
Milofi Tichy, Vaclav Borek Dohalsky, Marian Rucki, Ladislav Felt
AAAI Digital Library
AAAI relies on your generous support through membership and donations. If you find these resources useful, we would be grateful for your support.