An adaptive model for learning molecular endpoints

Walsh, Ian; Vullo, Alessandro; Pollastri, Gianluca

doi:10.4230/DagSemProc.09081.3

Document

An adaptive model for learning molecular endpoints

Authors Ian Walsh, Alessandro Vullo, Gianluca Pollastri

Part of: Volume: Dagstuhl Seminar Proceedings, Volume 9081
Part of: Series: Dagstuhl Seminar Proceedings (DagSemProc)
License: Creative Commons Attribution 4.0 International license
Publication Date: 2009-06-23

PDF

File

PDF

DagSemProc.09081.3.pdf

Filesize: 0.61 MB
16 pages

Document Identifiers

DOI: 10.4230/DagSemProc.09081.3
URN: urn:nbn:de:0030-drops-20367

Subject Classification

Keywords

Recursive neural networks
qsar
qspr
small molecules

Metrics

Access Statistics
Total Accesses (updated on a weekly basis)

0

PDF Downloads

0

Metadata Views

Abstract

I will describe a recursive neural network that deals with undirected graphs, and its application to predicting property labels or activity values of small molecules.
The model is entirely general, in that it can process any undirected graph with a finite number of nodes by factorising it into a number of directed graphs with the same skeleton. 
The model's only input in the applications I will present is the graph representing the chemical structure of the molecule. In spite of its simplicity, the model outperforms or matches the state of the art in three of the four tasks, and in the fourth is outperformed only by a method resorting to a very problem-specific feature.

Cite As Get BibTex

Ian Walsh, Alessandro Vullo, and Gianluca Pollastri. An adaptive model for learning molecular endpoints. In Similarity-based learning on structures. Dagstuhl Seminar Proceedings, Volume 9081, pp. 1-16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2009) https://doi.org/10.4230/DagSemProc.09081.3

Author Details

Ian Walsh

Alessandro Vullo

Gianluca Pollastri

Questions / Remarks / Feedback

Feedback for Dagstuhl Publishing

Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail