Predicting and Interpreting Protein Developability Via Transfer of Convolutional Sequence Representation.

Engineered proteins have emerged as novel diagnostics, therapeutics, and catalysts. Often, poor protein developability─quantified by expression, solubility, and stability─hinders utility. The ability to predict protein developability from amino acid sequence would reduce the experimental burden when selecting candidates. Recent advances in screening technologies enabled a high-throughput (HT) developability dataset for 105 of 1020 possible variants of protein ligand scaffold Gp2. In this work, we evaluate the ability of neural networks to learn a developability representation from a HT dataset and transfer this knowledge to predict recombinant expression beyond observed sequences. The model convolves learned amino acid properties to predict expression levels 44% closer to the experimental variance compared to a non-embedded control. Analysis of learned amino acid embeddings highlights the uniqueness of cysteine, the importance of hydrophobicity and charge, and the unimportance of aromaticity, when aiming to improve the developability of small proteins. We identify clusters of similar sequences with increased recombinant expression through nonlinear dimensionality reduction and we explore the inferred expression landscape via nested sampling. The analysis enables the first direct visualization of the fitness landscape and highlights the existence of evolutionary bottlenecks in sequence space giving rise to competing subpopulations of sequences with different developability. The work advances applied protein engineering efforts by predicting and interpreting protein scaffold expression from a limited dataset. Furthermore, our statistical mechanical treatment of the problem advances foundational efforts to characterize the structure of the protein fitness landscape and the amino acid characteristics that influence protein developability.

mTOR-mediated dedifferentiation of the retinal pigment epithelium initiates photoreceptor degeneration in mice.

Retinal pigment epithelial (RPE) cell dysfunction plays a central role in various retinal degenerative diseases, but knowledge is limited regarding the pathways responsible for adult RPE stress responses in vivo. RPE mitochondrial dysfunction has been implicated in the pathogenesis of several forms of retinal degeneration. Here we have shown that postnatal ablation of RPE mitochondrial oxidative phosphorylation in mice triggers gradual epithelium dedifferentiation, typified by reduction of RPE-characteristic proteins and cellular hypertrophy. The electrical response of the retina to light decreased and photoreceptors eventually degenerated. Abnormal RPE cell behavior was associated with increased glycolysis and activation of, and dependence upon, the hepatocyte growth factor/met proto-oncogene pathway. RPE dedifferentiation and hypertrophy arose through stimulation of the AKT/mammalian target of rapamycin (AKT/mTOR) pathway. Administration of an oxidant to wild-type mice also caused RPE dedifferentiation and mTOR activation. Importantly, treatment with the mTOR inhibitor rapamycin blunted key aspects of dedifferentiation and preserved photoreceptor function for both insults. These results reveal an in vivo response of the mature RPE to diverse stressors that prolongs RPE cell survival at the expense of epithelial attributes and photoreceptor function. Our findings provide a rationale for mTOR pathway inhibition as a therapeutic strategy for retinal degenerative diseases involving RPE stress.