2026-09-18T20:12:48Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1629892025-10-07T04:13:03Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Barzilay, Regina
Qi, Richard
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2025-10-06T17:38:25Z
2025-10-06T17:38:25Z
2025-05
2025-06-23T14:03:19.049Z
https://hdl.handle.net/1721.1/162989
Scaling inference-time compute for deep learning models has led to superhuman performance in games and enhanced reasoning capabilities for language models. However, similar gains have not yet been made in the field of biomolecular structure prediction. We introduce a new paradigm for inference-time search by adding architectural components and a finetuning procedure to state-of-the-art structure prediction models that give rise to a discrete latent space. We implement algorithms for searching and sampling in this discrete latent space and conduct experiments on a small model, demonstrating an increase in oracle and top-1-selected accuracy for predicted protein-protein complex structures.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Inference Time Search for Protein Structure Prediction
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="6c3ebf9e-51fe-46fc-890d-7c30bcb88cfd">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Inference Time Search for Protein Structure Prediction</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2025-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Qi, Richard</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Scaling inference-time compute for deep learning models has led to superhuman performance in games and enhanced reasoning capabilities for language models. However, similar gains have not yet been made in the field of biomolecular structure prediction. We introduce a new paradigm for inference-time search by adding architectural components and a finetuning procedure to state-of-the-art structure prediction models that give rise to a discrete latent space. We implement algorithms for searching and sampling in this discrete latent space and conduct experiments on a small model, demonstrating an increase in oracle and top-1-selected accuracy for predicted protein-protein complex structures.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>