Evaluation of an\nAffinity-Enhanced Anti-SARS-CoV2\nNanobody Design Workflow Using Machine Learning and Molecular Dynamics

<i>In silico</i> optimization of protein binding\nhas\nreceived a great deal of attention in the recent years. Since <i>in silico</i> prefiltering of strong binders is fast and cheap\ncompared to <i>in vitro</i> library screening methods, the\nadvent of powerful hardware and advanced machine learning algorithms\nhas made this strategy more accessible and preferred. These advances\nhave already impacted the global response to pandemic threats. In\nthis study, we proposed and tested a workflow for designing nanobodies\ntargeting the SARS-CoV-2 spike protein receptor binding domain (S-RBD)\nusing machine learning techniques complemented by molecular dynamics\nsimulations. We evaluated the feasibility of this workflow using a\ntest set of 3 different nanobodies and 2 different S-RBD variants,\nfrom <i>in silico</i> design and bacterial expression to\nbinding assays of the designed nanobody mutants. We successfully designed\nnanobodies that were subsequently tested against both the wild-type\n(Wuhan type) and the delta variant S-RBD and found 2 of them to be\nstronger binders compared to the wild-type nanobody. We use this case\nstudy to describe both the strengths and weaknesses of this <i>in silico</i> assisted nanobody design strategy.