Are learned molecular representations ready for prime time?
Name
1127567158-MIT.pdf
Size
3.5 MB
Format
Adobe PDF
Checksum (MD5)
2ad9799c72480c0934d5ec2811d2e519
Author(s)
Yang, Kevin,M. Eng.Massachusetts Institute of Technology.
Advisor(s)
Regina Barzilay.
Date Issued
2019
Publisher
Massachusetts Institute of Technology
Abstract
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 molecular graph. In this paper, I benchmark models extensively on 15 proprietary industrial datasets spanning a wide variety of chemical endpoints. In addition, I introduce a graph convolutional model that consistently 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, the proposed model nevertheless offers significant improvements over models currently used in industrial workflows. In addition, I demonstrate that similar models show promise in the molecular generation setting.
Description
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 65-69).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.
Persistent DSpace Link
