AlphaFold may struggle to predict how single mutations affect protein stability
In short: While AlphaFold revolutionized structural biology by predicting 3D protein structures from sequences, researchers investigated whether it could also predict how specific mutations change a protein's stability and function. By comparing AlphaFold's output metrics against experimental data on protein stability (ΔΔG) and fluorescence levels in GFP, the team found a very weak or non-existent correlation between the AI's predictions and real-world results.
This research is significant because predicting the effects of mutations is crucial for understanding diseases and engineering new proteins. The study used a computational approach, extracting metrics like pLDDT from AlphaFold predictions before and after single mutations to see if they aligned with known experimental values.
A major limitation of this study is that it focuses on the current capabilities of AlphaFold's output metrics rather than the underlying physics of protein folding, suggesting that structure prediction does not automatically equate to functional prediction.
Why it matters: Predicting a protein's shape is a major milestone, but it doesn't mean AI can yet predict how mutations will change that protein's behavior.
Opens the Intellect+ feed with this card first. Swipe up for the next one.
Sources
- Source: Research: Pak et al. (2023). Using AlphaFold to predict the impact of single mutations on protein stability and function. PloS one. · cc by
To cite this card, link to https://intellectplus.co.uk/app/science-research-alphafold-may-struggle-to-predict-how-single-mutations-affec.
How we source, check and correct cards: Editorial standards.
General information, not professional advice. Spotted an error? Flag the card or see corrections and complaints.
Intellect Plus is a visual educational discovery platform for exploring fascinating facts and ideas. Brain Food, Not Brain Rot. What is Intellect Plus?
Related
More in Science · Latest · A–Z · All topics
