论文信息 - Relating Chemical Structure to Activity: An Application of the Neural Folding Architecture

Relating Chemical Structure to Activity: An Application of the Neural Folding Architecture

This paper is based on the neural folding architecture (FA). The FA is a recurrent neural network architecture which is especially suited for adaptive structure processing, i.e. learning approximations of mappings from symbolic term structures to IR n. The main objective of this paper is to demonstrate that the FA can be successfully applied to approximate quantitative structure activity relationships (QSARs), which play an important role during a drug design process. Several approaches for the conversion of a QSAR problem to suitable learning tasks for the FA are presented. Finally the FA is applied to a well-known QSAR benchmark, viz. the inhibition of E. coli dihydrofolate reductase by triazines. The achieved results are compared with results of other machine learning approaches on the same QSAR benchmark, and prove that the FA is signiicantly better. activity relationships, inhibition of E. coli dihydrofolate reductase by triazines.

C. Goller | Sc Thorsten

[1] C. Mason. American Chemical Society , 1941, Science.

[2] S. Makram-Ebeid,et al. A rationalized error back-propagation learning algorithm , 1989, International 1989 Joint Conference on Neural Networks.

[3] Jonathan D. Hirst,et al. Quantitative structure-activity relationships by neural networks and inductive logic programming. II. The inhibition of dihydrofolate reductase by triazines , 1994, J. Comput. Aided Mol. Des..

[4] Christoph Goller,et al. Inductive Learning in Symbolic Domains Using Structure-Driven Recurrent Neural Networks , 1996, KI.

[5] Christoph Goller,et al. Learning task-dependent distributed representations by backpropagation through structure , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[6] P. Schulz. Some Experiments on the Applicability of Folding Architecture Networks to Guide Theorem Proving , 1997 .

[7] G. S. Johnson,et al. An Information-Intensive Approach to the Molecular Pharmacology of Cancer , 1997, Science.

[8] Christoph Goller,et al. A connectionist approach for learning search-control heuristics for automated deduction systems , 1999, DISKI.