Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published August 1, 2018 | Supplemental Material
Journal Article Open

Learned Protein Embeddings for Machine Learning

Abstract

Motivation: Machine-learning models trained on protein sequences and their measured functions can infer biological properties of unseen sequences without requiring an understanding of the underlying physical or biological mechanisms. Such models enable the prediction and discovery of sequences with optimal properties. Machine-learning models generally require that their inputs be vectors, and the conversion from a protein sequence to a vector representation affects the model's ability to learn. We propose to learn embedded representations of protein sequences that take advantage of the vast quantity of unmeasured protein sequence data available. These embeddings are low-dimensional and can greatly simplify downstream modeling. Results: The predictive power of Gaussian process models trained using embeddings is comparable to those trained on existing representations, which suggests that embeddings enable accurate predictions despite having orders of magnitude fewer dimensions. Moreover, embeddings are simpler to obtain because they do not require alignments, structural data, or selection of informative amino-acid properties. Visualizing the embedding vectors shows meaningful relationships between the embedded proteins are captured.

Additional Information

© 2018 The Author. Published by Oxford University Press. This article is published and distributed under the terms of the Oxford University Press, Standard Journals Publication Model (https://academic.oup.com/journals/pages/about_us/legal/notices). Availability and Implementation: The embedding vectors and code to reproduce the results are available at https://github.com/fhalab/embeddings_reproduction/. The authors wish to thank members of the Arnold lab, Justin Bois, and Yisong Yue for general advice and discussions on this project. This work is supported by the U.S. Army Research Office Institute for Collaborative Biotechnologies [W911F-09-0001 to F.H.A., K.K.Y.], the Donna and Benjamin M. Rosen Bioengineering Center [to K.K.Y.], the National Institutes of Health [F31MH102913, to C.N.B], and the National Science Foundation [GRF2017227007 to Z.W.]. Conflict of Interest: none declared.

Errata

The authors of the above paper wish to inform readers that the following article was incorrectly included as a reference: McIsaac, R.S. et al. (2014) Directed evolution of a far-red fluorescent rhodopsin. Proc. Natl. Acad. Sci. USA, 111, 13034–13039. The article which should have appeared in its place is: Engqvist, M.K.M. et al. (2015) Directed evolution of Gloeobacter violaceus rhodopsin spectral properties. Journal of Molecular Biology 427, 205-220.

Attached Files

Supplemental Material - bty178_supp.zip

Files

bty178_supp.zip
Files (345.1 kB)
Name Size Download all
md5:1d136830821978003c1daf716ff756aa
345.1 kB Preview Download

Additional details

Created:
August 19, 2023
Modified:
October 23, 2023