Insight into the protein solubility driving forces with neural attention

• DOI: 10.1371/journal.pcbi.1007722
• Publication Date: 2020-04-30T18:13:21Z
• Authors: Daniele Raimondi; Gabriele Orlando; Piero Fariselli; Yves Moreau
• Keywords: Protein sequencing; Sequence (biology)

Protein solubility is a key aspect for many biotechnological, biomedical and industrial processes, such as the production of active proteins antibodies. In addition, understanding molecular determinants may be crucial to shed light on mechanisms diseases caused by aggregation processes amyloidosis. Here we present SKADE, novel Neural Network protein predictor show how it can provide insight into mechanisms, thanks its neural attention architecture. First, that SKADE positively compares with state art tools while using just sequence input. Then, mechanism, use investigate patterns learned during training analyse decision process. We this peculiarity that, profiles do not correlate obvious aspects biophysical properties aminoacids, they suggest N- C-termini are most relevant regions prediction predictive complex emergent aggregation-prone involved in beta-amyloidosis contact density. Moreover, able identify mutations increase or decrease overall protein, allowing used perform large scale in-silico mutagenesis order maximize their solubility.