AF2-Mutation: Adversarial Sequence Mutations against AlphaFold2 on Protein Tertiary Structure Prediction
This work addresses the vulnerability of protein structure prediction models like AF2 to adversarial mutations, which is crucial for ensuring reliability in computational biology applications.
The paper tackles the robustness of AlphaFold2 (AF2) against sequence mutations by generating adversarial sequences via an evolutionary approach, showing that modifying just three residues can alter AF2's predictions by 46.61 in lDDT score on CASP14 data and identifying critical residues in SPNS2 to expedite experimental processes.
Deep learning-based approaches, such as AlphaFold2 (AF2), have significantly advanced protein tertiary structure prediction, achieving results comparable to real biological experimental methods. While AF2 has shown limitations in predicting the effects of mutations, its robustness against sequence mutations remains to be determined. Starting with the wild-type (WT) sequence, we investigate adversarial sequences generated via an evolutionary approach, which AF2 predicts to be substantially different from WT. Our experiments on CASP14 reveal that by modifying merely three residues in the protein sequence using a combination of replacement, deletion, and insertion strategies, the alteration in AF2's predictions, as measured by the Local Distance Difference Test (lDDT), reaches 46.61. Moreover, when applied to a specific protein, SPNS2, our proposed algorithm successfully identifies biologically meaningful residues critical to protein structure determination and potentially indicates alternative conformations, thus significantly expediting the experimental process.