Proteins with alternative folds reveal blind spots in AlphaFold-based protein structure prediction
원문 초록
In recent years, advances in artificial intelligence (AI) have transformed structural biology, particularly protein structure prediction. Though AI-based methods, such as AlphaFold (AF), often predict single conformations of proteins with high accuracy and confidence, predictions of alternative folds are often inaccurate, low-confidence, or simply not predicted at all. Here, we review three blind spots that alternative conformations reveal about AF-based protein structure prediction. First, proteins that assume conformations distinct from their training-set homologs can be mispredicted. Second, AF overrelies on its training set to predict alternative conformations. Third, degeneracies in pairwise representations can lead to high-confidence predictions inconsistent with experiment. These weaknesses suggest approaches to predict alternative folds more reliably.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Conformation-Aware Structure Prediction of Antigen-Recognizing Immune Proteins
MegaFold: System-Level Optimizations for Accelerating Protein Structure Prediction Models
PSBench: a large-scale benchmark for estimating the accuracy of protein complex structural models
Towards Interpretable Protein Structure Prediction with Sparse Autoencoders
Protein Large Language Models: A Comprehensive Survey
MotifBench: A standardized protein design benchmark for motif-scaffolding problems
토론
이 논문과 연결된 포럼 글이 아직 없습니다.