Conditional VAE Designs Novel PHA Synthase Variants
Researchers (Tenkanen et al.) publish March 19, 2026 in PLoS Computational Biology reporting the use of a conditional variational autoencoder to design approximately 10,000 PHA synthase sequences from UniProt training data. They selected 16 candidates for yeast expression and validated two novel enzymes—with 87 and 98 amino-acid substitutions—produced polyhydroxybutyrate (PHB) in Saccharomyces cerevisiae. This demonstrates generative AI can create active variants of complex dimeric enzymes.
Scoring Rationale
High novelty and peer-reviewed in vivo validation drive score, tempered by narrow focus on PHA synthases and class I enzymes.
Practice interview problems based on real data
1,500+ SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
