Molecular Graph Convolutions: Moving Beyond Fingerprints
release_fys34ibpk5bm7kkpntdjy7n3qi
by
Steven Kearnes, Kevin McCloskey, Marc Berndl, Vijay Pande, Patrick
Riley
2016
Abstract
Molecular "fingerprints" encoding structural information are the workhorse of
cheminformatics and machine learning in drug discovery applications. However,
fingerprint representations necessarily emphasize particular aspects of the
molecular structure while ignoring others, rather than allowing the model to
make data-driven decisions. We describe molecular "graph convolutions", a
machine learning architecture for learning from undirected graphs, specifically
small molecules. Graph convolutions use a simple encoding of the molecular
graph---atoms, bonds, distances, etc.---which allows the model to take greater
advantage of information in the graph structure. Although graph convolutions do
not outperform all fingerprint-based methods, they (along with other
graph-based methods) represent a new paradigm in ligand-based virtual screening
with exciting opportunities for future improvement.
In text/plain
format
Archived Files and Locations
application/pdf 2.2 MB
file_vujn54djfvabjjo3dufn7pcdti
|
arxiv.org (repository) web.archive.org (webarchive) |
1603.00856v3
access all versions, variants, and formats of this works (eg, pre-prints)