Abstract
Protein solubility is a key aspect for many biotechnological, biomedical and industrial processes, such as the production of active proteins and antibodies. In addition, understanding the molecular determinants of the solubility of proteins may be crucial to shed light on the molecular mechanisms of diseases caused by aggregation processes such as amyloidosis. Here we present SKADE, a novel Neural Network protein solubility predictor and we show how it can provide novel insight into the protein solubility mechanisms, thanks to its neural attention architecture. First, we show that SKADE positively compares with state of the art tools while using just the protein sequence as input. Then, thanks to the neural attention mechanism, we use SKADE to investigate the patterns learned during training and we analyse its decision process. We use this peculiarity to show that, while the attention profiles do not correlate with obvious sequence aspects such as biophysical properties of the aminoacids, they suggest that N- and C-termini are the most relevant regions for solubility prediction and are predictive for complex emergent properties such as aggregation-prone regions involved in beta-amyloidosis and contact density. Moreover, SKADE is able to identify mutations that increase or decrease the overall solubility of the protein, allowing it to be used to perform large scale in-silico mutagenesis of proteins in order to maximize their solubility.
Highlights
Proteins have evolved within the different cellular environments to improve or preserve their functions, maintaining at the same time a degree of hydrophobicity necessary to proper fold, and enough solubility to prevent protein precipitation
The solubility of proteins is a crucial biophysical aspect when it comes to understanding many human diseases and to improve the industrial processes for protein production
Thank to the attention mechanism, we show that i) our model implicitly learns complex patterns related to emergent, protein folding-related, aspects such as to recognize β-amyloidosis regions and that ii) the N-and C-termini are the regions with the highes signal fro solubility prediction
Summary
Proteins have evolved within the different cellular environments to improve or preserve their functions, maintaining at the same time a degree of hydrophobicity necessary to proper fold, and enough solubility to prevent protein precipitation. Solubility is a fundamental ingredient that must be properly balanced to maintain the protein functions and not aggregating [1]. Solubility deficit can hamper protein-based drug development, generating insoluble protein precipitates that can be toxic and may elicit an immune response in patients [6, 7]. Protein aggregation is considered an hallmark of more than forty human diseases, that span from neurodegenerative illness, to cancer and to metabolic disorders such as diabetes [8]. Since the soluble expression of proteins is crucial for protein production [9] for both pharmacological and research goals [10], in-silico bioinformatics models have been developed to predict i) the solubility of proteins [10,11,12,13] or ii) the solubility change upon mutation [9, 12, 14, 15], in order to, respectively, i) select the most likely soluble proteins [12] and ii) run in-silico mutagenesis to increase the solubility of existent proteins [9]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
