Combining machine learning with structure-based protein design to predict and engineer post-translational modifications of proteins.

Post-translational modifications (PTMs) of proteins play a vital role in their function and stability. These modifications influence protein folding, signaling, protein-protein interactions, enzyme activity, binding affinity, aggregation, degradation, and much more. To date, over 400 types of PTMs have been described, representing chemical diversity well beyond the genetically encoded amino acids. Such modifications pose a challenge to the successful design of proteins, but also represent a major opportunity to diversify the protein engineering toolbox. To this end, we first trained artificial neural networks (ANNs) to predict eighteen of the most abundant PTMs, including protein glycosylation, phosphorylation, methylation, and deamidation. In a second step, these models were implemented inside the computational protein modeling suite Rosetta, which allows flexible combination with existing protocols to model the modified sites and understand their impact on protein stability as well as function. Lastly, we developed a new design protocol that either maximizes or minimizes the predicted probability of a particular site being modified. We find that this combination of ANN prediction and structure-based design can enable the modification of existing, as well as the introduction of novel, PTMs. The potential applications of our work include, but are not limited to, glycan masking of epitopes, strengthening protein-protein interactions through phosphorylation, as well as protecting proteins from deamidation liabilities. These applications are especially important for the design of new protein therapeutics where PTMs can drastically change the therapeutic properties of a protein. Our work adds novel tools to Rosetta's protein engineering toolbox that allow for the rational design of PTMs.

Adeno-associated virus serotype 2 capsid variants for improved liver-directed gene therapy.

BACKGROUND AND AIMS: Current liver-directed gene therapies look for adeno-associated virus (AAV) vectors with improved efficacy. With this background, capsid engineering is explored. Whereas shuffled capsid library screenings have resulted in potent liver targeting variants with one first vector in human clinical trials, modifying natural serotypes by peptide insertion has so far been less successful. Here, we now report on two capsid variants, MLIV.K and MLIV.A, both derived from a high-throughput in vivo AAV peptide display selection screen in mice. APPROACH AND RESULTS: The variants transduce primary murine and human hepatocytes at comparable efficiencies, a valuable feature in clinical development, and show significantly improved liver transduction efficacy, thereby allowing a dose reduction, and outperform parental AAV2 and AAV8 in targeting human hepatocytes in humanized mice. The natural heparan sulfate proteoglycan binding ability is markedly reduced, a feature that correlates with improved hepatocyte transduction. A further property that might contribute to the improved transduction efficacy is the lower capsid melting temperature. Peptide insertion also caused a moderate change in sensitivity to human sera containing anti-AAV2 neutralizing antibodies, revealing the impact of epitopes located at the basis of the AAV capsid protrusions. CONCLUSIONS: In conclusion, MLIV.K and MLIV.A are AAV peptide display variants selected in immunocompetent mice with improved hepatocyte tropism and transduction efficiency. Because these features are maintained across species, MLIV variants provide remarkable potential for translation of therapeutic approaches from mice to men.

Rosetta design with co-evolutionary information retains protein function.

Computational protein design has the ambitious goal of crafting novel proteins that address challenges in biology and medicine. To overcome these challenges, the computational protein modeling suite Rosetta has been tailored to address various protein design tasks. Recently, statistical methods have been developed that identify correlated mutations between residues in a multiple sequence alignment of homologous proteins. These subtle inter-dependencies in the occupancy of residue positions throughout evolution are crucial for protein function, but we found that three current Rosetta design approaches fail to recover these co-evolutionary couplings. Thus, we developed the Rosetta method ResCue (residue-coupling enhanced) that leverages co-evolutionary information to favor sequences which recapitulate correlated mutations, as observed in nature. To assess the protocols via recapitulation designs, we compiled a benchmark of ten proteins each represented by two, structurally diverse states. We could demonstrate that ResCue designed sequences with an average sequence recovery rate of 70%, whereas three other protocols reached not more than 50%, on average. Our approach had higher recovery rates also for functionally important residues, which were studied in detail. This improvement has only a minor negative effect on the fitness of the designed sequences as assessed by Rosetta energy. In conclusion, our findings support the idea that informing protocols with co-evolutionary signals helps to design stable and native-like proteins that are compatible with the different conformational states required for a complex function.

Combining Rosetta Sequence Design with Protein Language Model Predictions Using Evolutionary Scale Modeling (ESM) as Restraint.

Computational protein sequence design has the ambitious goal of modifying existing or creating new proteins; however, designing stable and functional proteins is challenging without predictability of protein dynamics and allostery. Informing protein design methods with evolutionary information limits the mutational space to more native-like sequences and results in increased stability while maintaining functions. Recently, language models, trained on millions of protein sequences, have shown impressive performance in predicting the effects of mutations. Assessing Rosetta-designed sequences with a language model showed scores that were worse than those of their original sequence. To inform Rosetta design protocols with language model predictions, we added a new metric to restrain the energy function during design using the Evolutionary Scale Modeling (ESM) model. The resulting sequences have better language model scores and similar sequence recovery, with only a minor decrease in the fitness as assessed by Rosetta energy. In conclusion, our work combines the strength of recent machine learning approaches with the Rosetta protein design toolbox.

Modifying immune responses to adeno-associated virus vectors by capsid engineering.

De novo immune responses are considered major challenges in gene therapy. With the aim to lower innate immune responses directly in cells targeted by adeno-associated virus (AAV) vectors, we equipped the vector capsid with a peptide known to interfere with Toll-like receptor signaling. Specifically, we genetically inserted in each of the 60 AAV2 capsid subunits the myeloid differentiation primary response 88 (MyD88)-derived peptide RDVLPGT, known to block MyD88 dimerization. Inserting the peptide neither interfered with capsid assembly nor with vector production yield. The novel capsid variant, AAV2.MB453, showed superior transduction efficiency compared to AAV2 in human monocyte-derived dendritic cells and in primary human hepatocyte cultures. In line with our hypothesis, AAV2.MB453 and AAV2 differed regarding innate immune response activation in primary human cells, particularly for type I interferons. Furthermore, mice treated with AAV2.MB453 showed significantly reduced CD8+ T cell responses against the transgene product for different administration routes and against the capsid following intramuscular administration. Moreover, humoral responses against the capsid were mitigated as indicated by delayed IgG2a antibody formation and an increased NAb50. To conclude, insertion of the MyD88-derived peptide into the AAV2 capsid improved early steps of host-vector interaction and reduced innate and adaptive immune responses.