Format

Send to

Choose Destination
J Chem Inf Model. 2017 Aug 28;57(8):1757-1772. doi: 10.1021/acs.jcim.6b00601. Epub 2017 Jul 25.

Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction.

Author information

1
Department of Chemical Engineering, Massachusetts Institute of Technology , 77 Massachusetts Avenue, Cambridge, Massachusetts 02139, United States.
2
Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology , 77 Massachusetts Avenue, Cambridge, Massachusetts 02139, United States.

Abstract

The task of learning an expressive molecular representation is central to developing quantitative structure-activity and property relationships. Traditional approaches rely on group additivity rules, empirical measurements or parameters, or generation of thousands of descriptors. In this paper, we employ a convolutional neural network for this embedding task by treating molecules as undirected graphs with attributed nodes and edges. Simple atom and bond attributes are used to construct atom-specific feature vectors that take into account the local chemical environment using different neighborhood radii. By working directly with the full molecular graph, there is a greater opportunity for models to identify important features relevant to a prediction task. Unlike other graph-based approaches, our atom featurization preserves molecule-level spatial information that significantly enhances model performance. Our models learn to identify important features of atom clusters for the prediction of aqueous solubility, octanol solubility, melting point, and toxicity. Extensions and limitations of this strategy are discussed.

PMID:
28696688
DOI:
10.1021/acs.jcim.6b00601
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for American Chemical Society
Loading ...
Support Center