Email updates

Keep up to date with the latest news and content from BMC Bioinformatics and BioMed Central.

This article is part of the supplement: Proceedings of the Neural Information Processing Systems (NIPS) Workshop on Machine Learning in Computational Biology (MLCB)

Open Access Research

Classifying and scoring of molecules with the NGN: new datasets, significance tests, and generalization

Eddie YT Ma1, Christopher JF Cameron2 and Stefan C Kremer2*

Author Affiliations

1 Department of Biology at the University of Waterloo, Waterloo, Ontario, Canada

2 School of Computer Science at the University of Guelph, Guelph, Ontario, Canada

For all author emails, please log on.

BMC Bioinformatics 2010, 11(Suppl 8):S4  doi:10.1186/1471-2105-11-S8-S4

Published: 26 October 2010


This paper demonstrates how a Neural Grammar Network learns to classify and score molecules for a variety of tasks in chemistry and toxicology. In addition to a more detailed analysis on datasets previously studied, we introduce three new datasets (BBB, FXa, and toxicology) to show the generality of the approach. A new experimental methodology is developed and applied to both the new datasets as well as previously studied datasets. This methodology is rigorous and statistically grounded, and ultimately culminates in a Wilcoxon significance test that proves the effectiveness of the system. We further include a complete generalization of the specific technique to arbitrary grammars and datasets using a mathematical abstraction that allows researchers in different domains to apply the method to their own work.


Our work can be viewed as an alternative to existing methods to solve the quantitative structure-activity relationship (QSAR) problem. To this end, we review a number approaches both from a methodological and also a performance perspective. In addition to these approaches, we also examined a number of chemical properties that can be used by generic classifier systems, such as feed-forward artificial neural networks. In studying these approaches, we identified a set of interesting benchmark problem sets to which many of the above approaches had been applied. These included: ACE, AChE, AR, BBB, BZR, Cox2, DHFR, ER, FXa, GPB, Therm, and Thr. Finally, we developed our own benchmark set by collecting data on toxicology.


Our results show that our system performs better than, or comparatively to, the existing methods over a broad range of problem types. Our method does not require the expert knowledge that is necessary to apply the other methods to novel problems.


We conclude that our success is due to the ability of our system to: 1) encode molecules losslessly before presentation to the learning system, and 2) leverage the design of molecular description languages to facilitate the identification of relevant structural attributes of the molecules over different problem domains.