ChaperoNet: Distillation of Language Model Semantics to Folded Three-Dimensional Protein Structures
Name
costa-allanc-SM-MAS-2021-thesis.pdf
Description
Thesis PDF
Size
7.26 MB
Format
Adobe PDF
Checksum (MD5)
3e947a5820f99bd06bc644be59e2eede
Author(s)
Costa, Allan dos Santos (Allan S.)
Advisor(s)
Jacobson, Joseph M.
Date Issued
September 2021
Publisher
Massachusetts Institute of Technology
Abstract
Determining the structure of proteins has been a long-standing goal in biology. Lan- guage models have been recently deployed to capture the evolutionary semantics of protein sequences, and as an emergent property, were found to be structural learn- ers. Enriched with multiple sequence alignments (MSA), these transformer models were able to capture significant information about a protein’s tertiary structure. In this work, we show how such structural information can be recovered by processing language model embeddings, and introduce a two-stage folding pipeline to directly es- timate three-dimensional folded structures from protein sequences. We envision that this pipeline will provide a basis for efficient, end-to-end protein structure prediction through protein language modeling.
MIT Department
Program in Media Arts and Sciences (Massachusetts Institute of Technology)
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link
