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 April 30, 2019 | Submitted + Published + Supplemental Material
Journal Article Open

Machine learning-assisted directed protein evolution with combinatorial libraries

Abstract

To reduce experimental effort associated with directed protein evolution and to explore the sequence space encoded by mutating multiple positions simultaneously, we incorporate machine learning into the directed evolution workflow. Combinatorial sequence space can be quite expensive to sample experimentally, but machine-learning models trained on tested variants provide a fast method for testing sequence space computationally. We validated this approach on a large published empirical fitness landscape for human GB1 binding protein, demonstrating that machine learning-guided directed evolution finds variants with higher fitness than those found by other directed evolution approaches. We then provide an example application in evolving an enzyme to produce each of the two possible product enantiomers (i.e., stereodivergence) of a new-to-nature carbene Si–H insertion reaction. The approach predicted libraries enriched in functional enzymes and fixed seven mutations in two rounds of evolution to identify variants for selective catalysis with 93% and 79% ee (enantiomeric excess). By greatly increasing throughput with in silico modeling, machine learning enhances the quality and diversity of sequence solutions for a protein engineering problem.

Additional Information

© 2019 National Academy of Sciences. Published under the PNAS license. Contributed by Frances H. Arnold, March 18, 2019 (sent for review February 4, 2019; reviewed by Marc Ostermeier and Justin B. Siegel). The authors thank Yisong Yue for initial guidance and Scott Virgil (Caltech Center for Catalysis and Chemical Synthesis) for providing critical instrument support; and Kevin Yang, Anders Knight, Oliver Brandenburg, and Ruijie Kelly Zhang for helpful discussions. This work is supported by National Science Foundation Grant GRF2017227007 (to Z.W.), the Rothenberg Innovation Initiative Program (S.B.J.K. and F.H.A.), and the Jacobs Institute for Molecular Engineering for Medicine at Caltech (S.B.J.K. and F.H.A.). Author contributions: Z.W., S.B.J.K., R.D.L., and F.H.A. designed research; Z.W. and B.J.W. performed research; Z.W. contributed new reagents/analytic tools; Z.W., S.B.J.K., R.D.L., and B.J.W. analyzed data; and Z.W., S.B.J.K., R.D.L., B.J.W., and F.H.A. wrote the paper. Reviewers: M.O., Johns Hopkins University; and J.B.S., UC Davis Health System. The authors declare no conflict of interest. Data deposition: The data reported in this paper have been deposited in the ProtaBank database, https://www.protabank.org, at https://www.protabank.org/study_analysis/mnqBQFjF3/. This article contains supporting information online at www.pnas.org/lookup/suppl/doi:10.1073/pnas.1901979116/-/DCSupplemental.

Attached Files

Published - 8852.full.pdf

Submitted - 1902.07231.pdf

Supplemental Material - pnas.1901979116.sapp.pdf

Files

1902.07231.pdf
Files (5.6 MB)
Name Size Download all
md5:768f5fd79ba410450326dc5cf6f451e1
3.1 MB Preview Download
md5:f42f909fac63c7f2edefeb4b9b8dd5e1
962.2 kB Preview Download
md5:3481f2168d9b7a2bc0b66fa3c2ae59f1
1.5 MB Preview Download

Additional details

Created:
August 22, 2023
Modified:
October 20, 2023