2026-09-18T20:55:43Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1231332026-06-06T01:03:04Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Regina Barzilay. Swanson, Kyle(Kyle W.) Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2019-12-05T18:05:17Z 2019-12-05T18:05:17Z 2019 2019 https://hdl.handle.net/1721.1/123133 1128814048 This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Thesis: M. Eng. in Computer Science and Engineering, Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 81-84). Developing new drugs relies heavily on understanding the various molecular properties of potential drug candidates. While experimental assays performed in the lab are the best source of information about molecular properties, these assays are slow and expensive. For this reason, there has been great interest in the potential of machine learning models to predict molecular properties without the need for experimental assays. However, recent literature has not yet clearly determined which machine learning models are optimal for molecular property prediction. In this thesis, I apply the Direct Message Passing Neural Network (D-MPNN) from [47, 48] to 19 publicly available property prediction datasets, and I demonstrate that it consistently outperforms prior machine learning models. Additionally, I introduce several optimizations to the D-MPNN which further enhance its performance and lead to new state-of-the-art results. by Kyle Swanson. M.Eng. in Computer Science and Engineering M.Eng.inComputerScienceandEngineering Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 84 pages eng Massachusetts Institute of Technology 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. http://dspace.mit.edu/handle/1721.1/7582 Electrical Engineering and Computer Science. Message passing neural networks for molecular property prediction Thesis application/pdf 2019-12-05T18:05:16Z Publication Master EECS unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="01a0846a-8ec6-4628-878d-4183f775c9fd"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Message passing neural networks for molecular property prediction</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2019</PublicationDate> <Authors> <Author> <DisplayName>Swanson, Kyle(Kyle W.)</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Electrical Engineering and Computer Science.</Keyword> <Abstract>Developing new drugs relies heavily on understanding the various molecular properties of potential drug candidates. While experimental assays performed in the lab are the best source of information about molecular properties, these assays are slow and expensive. For this reason, there has been great interest in the potential of machine learning models to predict molecular properties without the need for experimental assays. However, recent literature has not yet clearly determined which machine learning models are optimal for molecular property prediction. In this thesis, I apply the Direct Message Passing Neural Network (D-MPNN) from [47, 48] to 19 publicly available property prediction datasets, and I demonstrate that it consistently outperforms prior machine learning models. Additionally, I introduce several optimizations to the D-MPNN which further enhance its performance and lead to new state-of-the-art results.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>