Deep learning to design nuclear-targeting abiotic miniproteins
The Pentelute Lab aims to invent new chemistry for the efficient and selective modification of proteins, to ‘hijack’ these biological machines for efficient drug delivery into cells and to create new machines to rapidly and efficiently manufacture peptides and proteins.
Pentelute Lab, Chemistry, MIT, Chemistry Department, Boston, Cambridge, Biology, Peptides, Peptide, Proteins, Science, Rapid, Brad Pentelute, Brad,
portfolio_page-template-default,single,single-portfolio_page,postid-17744,bridge-core-3.0.1,qode-page-transition-enabled,ajax_fade,page_not_loaded,,paspartu_enabled,paspartu_on_top_fixed,paspartu_on_bottom_fixed,qode_grid_1200,qode_popup_menu_push_text_top,qode-theme-ver-28.7,qode-theme-bridge,disabled_footer_top,wpb-js-composer js-comp-ver-6.8.0,vc_responsive

Deep learning to design nuclear-targeting abiotic miniproteins

Deep learning to design nuclear-targeting abiotic miniproteins

Nature Chemistry volume 13, pages992–1000 (2021)

Carly K. Schissel, Somesh Mohapatra, Justin M. Wolfe, Colin M. Fadzen, Kamela Bellovoda, Chia-Ling Wu, Jenna A. Wood, Annika B. Malmberg, Andrei Loas, Rafael Gómez-Bombarelli & Bradley L. Pentelute


There are more amino acid permutations within a 40-residue sequence than atoms on Earth. This vast chemical search space hinders the use of human learning to design functional polymers. Here we show how machine learning enables the de novo design of abiotic nuclear-targeting miniproteins to traffic antisense oligomers to the nucleus of cells. We combined high-throughput experimentation with a directed evolution-inspired deep-learning approach in which the molecular structures of natural and unnatural residues are represented as topological fingerprints. The model is able to predict activities beyond the training dataset, and simultaneously deciphers and visualizes sequence–activity predictions. The predicted miniproteins, termed ‘Mach’, reach an average mass of 10 kDa, are more effective than any previously known variant in cells and can also deliver proteins into the cytosol. The Mach miniproteins are non-toxic and efficiently deliver antisense cargo in mice. These results demonstrate that deep learning can decipher design principles to generate highly active biomolecules that are unlikely to be discovered by empirical approaches.

2021, Publications