Molecular Graph Convolutions: Moving Beyond Fingerprints release_fys34ibpk5bm7kkpntdjy7n3qi

by Steven Kearnes, Kevin McCloskey, Marc Berndl, Vijay Pande, Patrick Riley

Released as a article .

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)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   accepted
Date   2016-08-18
Version   v3
Language   en ?
arXiv  1603.00856v3
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: b51e0384-dee1-477a-9d1b-2f257590ae29
API URL: JSON