R. Illanes

ProtGPT3 is an open-source family of protein language models that enables controlled protein generation through alignment and prompting, showing effectiveness in generating functional proteins.

An enzyme-specific conditional language model generates active carbonic anhydrases and lactate dehydrogenases to user specification, some under 40% identity to natural proteins, with no retraining.

The paper identifies two enzymes in wax worm saliva that oxidize and depolymerize polyethylene, overcoming a key bottleneck in plastic biodegradation.