AF2-Mutation: Adversarial Sequence Mutations against AlphaFold2 on Protein Tertiary Structure Prediction

Abstract

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.

References in corpus (7)

• Deep Text Classification Can be Fooled
• Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
• Adversarial Examples that Fool both Computer Vision and Time-Limited Humans
• TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP
• Enhancing the Transferability of Adversarial Attacks through Variance Tuning
• Adversarial Machine Learning in Wireless Communications using RF Data: A Review
• Protein Folding Neural Networks Are Not Robust