Evaluating data mining algorithms using molecular dynamics trajectories

Authors:
Vasileios A. Tatsis;Christos Tjortjis;Panagiotis Tzirakis
Affiliations:
Department of Engineering Informatics and Telecommunications, Section of Applied Informatics, University of Western Macedonia, Vermiou & Ligeris, Kozani 50100, Greece;Department of Computer Science, University of Ioannina, Ioannina 45110, Greece;Department of Engineering Informatics and Telecommunications, Section of Applied Informatics, University of Western Macedonia, Vermiou & Ligeris, Kozani 50100, Greece
Venue:
International Journal of Data Mining and Bioinformatics
Year:
2013

Citing 24
Cited 0

Instance-Based Learning Algorithms

Machine Learning
Very Simple Classification Rules Perform Well on Most Commonly Used Datasets

Machine Learning
Bagging predictors

Machine Learning
From data mining to knowledge discovery: an overview

Advances in knowledge discovery and data mining
Random Forests

Machine Learning
The Power of Decision Tables

ECML '95 Proceedings of the 8th European Conference on Machine Learning
Classification by Voting Feature Intervals

ECML '97 Proceedings of the 9th European Conference on Machine Learning
Logistic Model Trees

Machine Learning
Data Mining: Concepts and Techniques

Data Mining: Concepts and Techniques
Improvements to Platt's SMO Algorithm for SVM Classifier Design

Neural Computation
Rotation Forest: A New Classifier Ensemble Method

IEEE Transactions on Pattern Analysis and Machine Intelligence
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
An improved methodology on information distillation by mining program source code

Data & Knowledge Engineering
Fuzzy lattice reasoning (FLR) classifier and its application for ambient ozone estimation

International Journal of Approximate Reasoning
Scoring and summarising gene product clusters using the Gene Ontology

International Journal of Data Mining and Bioinformatics
A comparison of multiple classification methods for diagnosis of Parkinson disease

Expert Systems with Applications: An International Journal
The WEKA data mining software: an update

ACM SIGKDD Explorations Newsletter
Evaluation of ensemble methods for diagnosing of valvular heart disease

Expert Systems with Applications: An International Journal
Learning Bayesian networks with integration of indirect prior knowledge

International Journal of Data Mining and Bioinformatics
Robust classification ensemble method for microarray data

International Journal of Data Mining and Bioinformatics
Estimating continuous distributions in Bayesian classifiers

UAI'95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence
Ensembles of balanced nested dichotomies for multi-class problems

PKDD'05 Proceedings of the 9th European conference on Principles and Practice of Knowledge Discovery in Databases
Using rotation forest for protein fold prediction problem: an empirical study

EvoBIO'10 Proceedings of the 8th European conference on Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics
Heuristic rule-based regression via dynamic reduction to classification

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two

Quantified Score

Hi-index	0.00

Visualization

Abstract

Molecular dynamics simulations provide a sample of a molecule's conformational space. Experiments on the µs time scale, resulting in large amounts of data, are nowadays routine. Data mining techniques such as classification provide a way to analyse such data. In this work, we evaluate and compare several classification algorithms using three data sets which resulted from computer simulations, of a potential enzyme mimetic biomolecule. We evaluated 65 classifiers available in the well-known data mining toolkit Weka, using 'classification' errors to assess algorithmic performance. Results suggest that: i 'meta' classifiers perform better than the other groups, when applied to molecular dynamics data sets; ii Random Forest and Rotation Forest are the best classifiers for all three data sets; and iii classification via clustering yields the highest classification error. Our findings are consistent with bibliographic evidence, suggesting a 'roadmap' for dealing with such data.