Alphafold Is Not Yet Ready to Predict Single Mutation Protein Stability

The central problem of structural bioinformatics was solved by Alphafold.It has been vastly superior at predicting protein structures after being given an arbitrary sequence of amino acids that comprise a protein. This milestone achievement led to speculations that the neural network must have somehow internalized the underlying physics of proteins and should work beyond the task it was designed for.

Russian researchers tried to apply AlphaFold to another central task of structural bioinformatics: predicting the impact of single mutations on protein stability.

The study’s principal investigator, Assistant Professor Dmitry Ivankov of Skoltech Bio said Alphafold’s single mutation stability predictions contradicted known experimental findings.

Ivankov emphasized that AlphaFold’s creators never actually claimed that the AI was applicable to other tasks besides predicting protein structures based on their amino acid sequences. But some machine learning enthusiasts were quick to prophesy the end of structural bioinformatics.

Here is the PLOS One paper.

Using AlphaFold to predict the impact of single mutations on protein stability and function. (2023)

1 thought on “Alphafold Is Not Yet Ready to Predict Single Mutation Protein Stability”

Comments are closed.