Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction
Citations Over TimeTop 1% of 2017 papers
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.
Related Papers
- → An efficient experimental design for detecting departure from additivity in mixtures of many chemicals(1995)38 cited
- → The Absolute Additivity and Fuzzy Additivity of Sugeno Integral(2006)2 cited
- The generalized additivity,transformation theorem and the defect of additivity for fuzzy measures(2010)
- → Additive Aggregation Functions: Generalizations and Modifications of Additivity(2019)