2026-09-18T22:49:27Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1242322026-06-06T00:48:33Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Peter Szolovits.
Bair, Annamarie Elizabeth.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2020-03-24T15:35:30Z
2020-03-24T15:35:30Z
2019
2019
https://hdl.handle.net/1721.1/124232
1144932843
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 55-57).
Drug development is an important, but complicated and expensive process. By utilizing the power of deep learning, we aim to improve the current process of drug development. We model molecules as undirected graphs and use graph convolutions and self-attention to predict molecular properties. With a series of ablation studies, we demonstrate the added value of several key components in our network. We analyze two standard datasets: BBBP, which includes classication data on whether molecules pass the blood-brain barrier, and ClinTox, which includes toxicity information. Using our architecture, we are able to match state of the art performance on the BBBP prediction task.
by Annamarie Elizabeth Bair.
M.Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
57 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.
Molecular graph Self attention and graph convolution for drug discovery
Thesis
application/pdf
2020-03-24T15:35:29Z
Publication
Master
EECS
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="00cbde1e-fd7d-412f-8b2d-60707010147e">
<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>Molecular graph Self attention and graph convolution for drug discovery</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2019</PublicationDate>
<Authors>
<Author>
<DisplayName>Bair, Annamarie Elizabeth.</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>Drug development is an important, but complicated and expensive process. By utilizing the power of deep learning, we aim to improve the current process of drug development. We model molecules as undirected graphs and use graph convolutions and self-attention to predict molecular properties. With a series of ablation studies, we demonstrate the added value of several key components in our network. We analyze two standard datasets: BBBP, which includes classication data on whether molecules pass the blood-brain barrier, and ClinTox, which includes toxicity information. Using our architecture, we are able to match state of the art performance on the BBBP prediction task.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>