ChemRxiv
These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
1/1
0/0

Analyzing Learned Molecular Representations for Property Prediction

preprint
revised on 30.07.2019 and posted on 30.07.2019 by Kevin Yang, Kyle Swanson, Wengong Jin, Connor Coley, philipp eiden, Hua Gao, Angel Guzman-Perez, Timothy Hopper, Brian P. Kelley, miriam mathea, Andrew Palmer, Volker Settels, Tommi S Jaakkola, Klavs F. Jensen, Regina Barzilay
Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: neural networks applied to computed molecular fingerprints or expert-crafted descriptors, and graph convolutional neural networks that construct a learned molecular representation by operating on the graph structure of the molecule. However, recent literature has yet to clearly determine which of these two methods is superior when generalizing to new chemical space. Furthermore, prior research has rarely examined these new models in industry research settings in comparison to existing employed models. In this paper, we benchmark models extensively on 19 public and 16 proprietary industrial datasets spanning a wide variety of chemical endpoints. In addition, we introduce a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets. Our empirical findings indicate that while approaches based on these representations have yet to reach the level of experimental reproducibility, our proposed model nevertheless offers significant improvements over models currently used in industrial workflows.

Funding

Machine Learning for Pharmaceutical Discovery and Synthesis Consortium

History

Email Address of Submitting Author

yangk@mit.edu

Institution

Massachusetts Institute of Technology

Country

USA

ORCID For Submitting Author

0000-0001-7221-6642

Declaration of Conflict of Interest

No conflicts to declare.

Exports