ChemRxiv
These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
1/1
2 files

Deep Learning for Prediction and Optimization of Fast-Flow Peptide Synthesis

preprint
submitted on 13.07.2020 and posted on 14.07.2020 by Somesh Mohapatra, Nina Hartrampf, Mackenzie Poskus, Andrei Loas, Rafael Gomez-Bombarelli, Bradley L. Pentelute

Chemical synthesis of polypeptides involves stepwise formation of amide bonds on an immobilized solid support. The high yields required for efficient incorporation of each individual amino acid in the growing chain are often impacted by sequence-dependent events such as aggregation. Here we apply deep learning over ultraviolet-visible (UV-Vis) analytical data collected from 35,485 individual fluorenylmethyloxycarbonyl (Fmoc) deprotection reactions performed with an automated fast-flow peptide synthesizer. The integral, height and width of these time-resolved UV-Vis deprotection traces indirectly allow for analysis of the iterative amide coupling cycles on resin. The computational model maps structural representations of amino acids and peptide sequences to experimental synthesis parameters and predicts the outcome of deprotection reactions with less than 4% error. Our deep learning approach enables experimentally-aware computational design for prediction of Fmoc deprotection efficiency and minimization of aggregation events, building the foundation for real-time optimization of peptide synthesis in flow.

Funding

Novo Nordisk

MIT-SenseTime Alliance on Artificial Intelligence

Abdul Latif Jameel Clinic for Machine Learning in Health (J-Clinic)

History

Email Address of Submitting Author

blp@mit.edu

Institution

Massachusetts Institute of Technology

Country

United States

ORCID For Submitting Author

0000-0002-7242-801X

Declaration of Conflict of Interest

B.L.P. is a co-founder of Amide Technologies and Resolute Bio. Both companies focus on the development of protein and peptide therapeutics. B.L.P is co-inventor on U.S. Pat. Appl. 20170081358A1 (March 23, 2017) describing methods and systems for solid phase peptide synthesis and on U.S. Pat. 9,868,759 (January 16, 2018), U.S. Pat. 9,695,214 (July 4, 2017), and U.S. Pat. 9,169,287 (October 27, 2015) describing solid phase peptide synthesis processes and associated systems.

Exports