Deep diversification of an AAV capsid protein by machine learning

Abstract

Nature provides abundant examples of protein families with highly diverged sequences. The ability to design new protein homologs has many applications, yet synthetic approaches have been unable to generate similarly diverse protein sequences with functional activity in the lab [1, 2]. New technologies offer a solution: high-throughput DNA synthesis and sequencing technologies allow thousands of designed sequences to be assayed in parallel, enabling deep diversification guided by machine learning (ML) models that relate protein sequence to function without detailed biophysical or mechanistic modeling. Here we apply deep learning to design novel adeno-associated virus (AAV) capsid proteins, a challenging target of great utility for gene therapy. Focusing on a 28-amino acid segment spanning buried and exposed regions, we generated 201,426 highly diverse variants of the AAV2 wildtype (WT) sequence, yielding 110,689 viable synthetic capsids, 57,348 of which surpass the average diversity of natural AAV serotype sequences with 12-29 mutations across this region. Even when trained on limited data, deep neural network models accurately predicted capsid viability across highly diverse variants. Deep diversification enables the design of AAV capsids with completely synthetic sequences for the universal treatment of all patients regardless of prior exposure to natural AAV, while demonstrating a general approach that makes vast areas of functional but previously unreachable sequence space accessible.EK, PJO, NJ, SS, GMC performed research while at Harvard University and EK, SS also performed research while at Dyno Therapeutics. EK, SS, and GMC hold equity at Dyno Therapeutics. A full list of GMC's tech transfer, advisory roles, and funding sources can be found on the lab's website: http://arep.med.harvard.edu/gmc/tech.html . Harvard University has filed a provisional patent application for inventions related to this work. DHB, AB, LJC, PR performed research as part of their employment at Google LLC. Google is a technology company that sells machine learning services as part of its business. Data availabilityExperimental data for all 3 experiments will be deposited on a public repository (NCBI SRA ( https://www.ncbi.nlm.nih.gov/sra ) , id: SUB7629680) by publication date. Code availabilityThe TensorFlow 1.3 API was used to implement and train all models using the architectures described in Methods. The training and validation datasets used for creating each model are available as part of the experimental dataset released as described in the preceding section. The code required to construct the A 39 training data and also to synthesize, process, and analyze the experimental data is provided for download, together with ipython notebooks that reproduce the analysis figures from the main text.10 284 1 0.40%

Neural networks to learn protein sequence-function relationships from deep mutational scanning data

“…Another challenging future direction in protein sequence-function modeling will be assessing how well trained models can extrapolate to sequences outside the training distribution, such as variants with higher-order mutations [32, 33]. All of our quantitative evaluations involved test set variants that had similar characteristics to the training set variants.…”

Synthetic biology as driver for the biologization of materials sciences

“…The trained models were used to design icosahedral capsids based on highly diverse protein sequences. In total, 201,426 variants were predicted of which 110,689 were experimentally verified to be viable as AAV capsid [ 333 ]. This approach unlocked vast areas of functional but previously unreachable sequence space, providing new opportunities, not only for viral vector design but also in general for the design of protein-based (nano-) materials.…”

Potent programmable antiviral against dengue virus in primary human cells by Cas13b RNP with short spacer and delivery by VLP

“…Although immune response against exogenous Cas13 protein could reduce its therapeutic activity in repeated dosing, the diversity of CRISPR-Cas13 and recent advances in protein engineering may help alleviate this issue. [34][35][36] Viral proteins of several human RNA viruses and interferon stimulated genes (ISGs) were shown to dampen RNAi activity. 37 In contrast, since CRISPR-Cas13 is of bacterial origin, it is likely that mammalian viruses have never interacted with it in nature and are likely not able to counter it right away.…”