Biochemistry, Genetics and Molecular Biology · Molecular Biology
AlphaFold3 reliably identifies disorder in individual proteins, matching AlphaFold2 and specialized prediction tools. But its results for assemblies of disordered proteins vary substantially between runs, making success difficult to predict from interface features alone.
Researchers evaluated three AI systems on hundreds of molecules bound to a SARS-CoV-2 protein and in three prospective drug screens. The results suggest that combining AI-based predictions with traditional docking may help prioritize candidates, although no single approach worked best in every test.
Researchers describe a streamlined workflow for producing and testing designed proteins at much greater scale than standard laboratory methods. By using pooled DNA and partial automation, the approach could characterize more than 1,000 designs at about $5 per construct.
