Machine-Learning-Aided Engineering Hemoglobin as Carbene Transferase for Catalyzing Enantioselective Olefin Cyclopropanation

Hanqing Xie, Kaifeng Liu, Zhengqiang Li, Zhi Wang, Chunyu Wang, Fengxi Li, Weiwei Han, Lei Wang · 2024

Read Machine-Learning-Aided Engineering Hemoglobin as Carbene Transferase for Catalyzing Enantioselective Olefin Cyclopropanation by Hanqing Xie, Kaifeng Liu, Zhengqiang Li, Zhi Wang, Chunyu Wang, Fengxi Li, Weiwei Han, Lei Wang (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11672141.txt.

Description

Enzymes can be taught new chemistry, but searching their mutations by hand is slow and costly. The authors use machine learning to turn a hemoglobin into a carbene transferase, an enzyme that builds three-membered rings on carbon double bonds with a chosen handedness. A language model, trained to predict selectivity scores, screens designs before any lab work. Docking calculations narrow the search to key positions, and a small saturated library is built there. The model then scores 160,000 virtual mutants from that library.

Fifteen top-scoring mutants go to the bench. One, carrying two changes, delivers the best selectivity in water. Simulations explain why: three residues tighten the pocket entrance, steering how the reaction intermediate can form. The authors argue that pairing a learned predictor with a focused library cuts the cost of protein engineering sharply, and they offer their pipeline as a template for other enzyme redesign jobs.

Catalog record

CREATORHanqing Xie, Kaifeng Liu, Zhengqiang Li, Zhi Wang, Chunyu Wang, Fengxi Li, Weiwei Han, Lei Wang
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE30 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11672141

Browse the full library · About the Tower of Babel