Knowledge-Based Learning in Exploratory Science: Learning Rules to Predict Rodent Carcinogenicity

Authors:
Yongwon Lee;Bruce G. Buchanan;John M. Aronis
Affiliations:
Lockheed Martin Missiles and Space, 3251 Hanover Street, H1-43, B255, Palo Alto, CA 94304. E-mail: ylee@ict.atc.lmco.com;Department of Computer Science, University of Pittsburgh, Pittsburgh, PA 15260. E-mail: buchanan@cs.pitt.edu;Department of Computer Science, University of Pittsburgh, Pittsburgh, PA 15260. E-mail: aronis@cs.pitt.edu
Venue:
Machine Learning - Special issue on applications of machine learning and the knowledge discovery process
Year:
1998

Citing 10
Cited 19

C4.5: programs for machine learning

C4.5: programs for machine learning
Policies for the selection of bias in inductive machine learning

Policies for the selection of bias in inductive machine learning
Inductive Policy: The Pragmatics of Bias Selection

Machine Learning - Special issue on bias evaluation and selection
Scaling up inductive learning with massive parallelism

Machine Learning
Learning a robust rule set

Learning a robust rule set
Data mining and knowledge discovery in databases

Communications of the ACM
Mining scientific data

Communications of the ACM
Adaptive Fraud Detection

Data Mining and Knowledge Discovery
The CN2 Induction Algorithm

Machine Learning
The Induction of Rules for Predicting Chemical Carcinogenesis in Rodents

Proceedings of the 1st International Conference on Intelligent Systems for Molecular Biology

Guest Editors‘ Introduction: On Applied Research in MachineLearning

Machine Learning - Special issue on applications of machine learning and the knowledge discovery process
Machine Learning for the Detection of Oil Spills in Satellite Radar Images

Machine Learning - Special issue on applications of machine learning and the knowledge discovery process
Pharmacophore Discovery Using the Inductive Logic Programming System PROGOL

Machine Learning - Special issue on applications of machine learning and the knowledge discovery process
The Role of Occam‘s Razor in Knowledge Discovery

Data Mining and Knowledge Discovery
Expert-Driven Validation of Rule-Based User Models in Personalization Applications

Data Mining and Knowledge Discovery
The Computational Support of Scientific Discovery

Machine Learning and Its Applications, Advanced Lectures
The Computer-Aided Discovery of Scientific Knowledge

DS '98 Proceedings of the First International Conference on Discovery Science
Learning with Globally Predictive Tests

DS '98 Proceedings of the First International Conference on Discovery Science
Designing Views in HypothesisCreator: System for Assisting in Discovery

DS '99 Proceedings of the Second International Conference on Discovery Science
Computational Discovery of Communicable Knowledge: Symposium Report

DS '01 Proceedings of the 4th International Conference on Discovery Science
Automated Formulation of Reactions and Pathways in Nuclear Astrophysics: New Results

DS '01 Proceedings of the 4th International Conference on Discovery Science
Knowledge evaluation: Other evaluations: usefulness, novelty, and integration of interesting news measures

Handbook of data mining and knowledge discovery
Finding unexpected patterns in data

Data mining, rough sets and granular computing
Filtering Multi-Instance Problems to Reduce Dimensionality in Relational Learning

Journal of Intelligent Information Systems
Subgroup Discovery with CN2-SD

The Journal of Machine Learning Research
On the discovery of significant statistical quantitative rules

Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
Expert-guided subgroup discovery: methodology and application

Journal of Artificial Intelligence Research
Transfer learning of classification rules for biomarker discovery and verification from molecular profiling studies

Journal of Biomedical Informatics
Active subgroup mining: a case study in coronary heart disease risk group detection

Artificial Intelligence in Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we report on a multi-year collaboration amongcomputer scientists, toxicologists, chemists, and a statistician, inwhich the RL induction program was used to assist toxicologists inanalyzing relationships among various features of chemical compoundsand their carcinogenicity in rodents. Our investigation demonstratedthe utility of knowledge-based rule induction in the problem ofpredicting rodent carcinogenicity and the place of rule induction inthe overall process of discovery. Flexibility of the program inaccepting different definitions of background knowledge andpreferences was considered essential in this exploratory effort. Thisinvestigation has made significant contributions not only topredicting carcinogenicity and non-carcinogenicity in rodents, but tounderstanding how to extend a rule induction program into anexploratory data analysis tool.