Biosensor and machine learning-aided engineering of an amaryllidaceae enzyme
Problem
Industrial biomanufacturing of therapeutic Amaryllidaceae alkaloids like the Alzheimer's drug galantamine is slow, and supply relies on extraction from low-yielding daffodils.
Why it matters
Galantamine is a recognized Alzheimer's medication currently sourced from low-yield plant extraction.
What the AI did
A structure-based residual neural network (MutComputeX) generated activity-enriched variants of a plant methyltransferase, which were rapidly screened using a directed-evolution biosensor for the key alkaloid branchpoint.
Results
Biosensor with EC50 = 20 μM developed; activity-enriched methyltransferase variants generated (final yields not stated in source)
Impact
The paper demonstrates an ML-guided biosensor workflow for biocatalyst development in E. coli.
Record
| Venue | Nature Communications |
|---|---|
| Published | 2024 |
| Work type | article |
| Authors | Simon d’Oelsnitz, Daniel J. Diaz, Wantae Kim, Daniel J. Acosta, Tyler L. Dangerfield, Mason W. Schechter, Matthew B. Minus, James R. Howard et al. |
| Citations | 56 (OpenAlex, at import time) |
| References | 65 |
| Model or method | MutComputeX (structure-based residual neural network) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41467-024-46356-y |
| Open access | gold |
| Keywords | biosensor, machine learning, enzyme engineering, galantamine, directed evolution, alkaloids |
Importance rating
significant — thousands to millions affected
Abstract states galantamine is a recognized Alzheimer's medication currently extracted from low-yielding daffodils; industrial biomanufacturing bottleneck affects drug supply, but no scale numbers given.