paper-with-me

홈 › Papers

Proteins with alternative folds reveal blind spots in AlphaFold-based protein structure prediction

2024-10-18 · Devlina Chakravarty, Myeongsang Lee, Lauren L. Porter

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.

📄 PDF Abstract BibTeX arXiv:2410.14898

Code (0)

등록된 구현이 없습니다.

Tasks

Protein Structure Prediction

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
AlphaFold 설명 없음

Similar Papers 제목 키워드 기반

Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models

2026-07-09 · Matteo Santelmo, Xiuying Wei, Israa Fakih, Felix Bauer 외 arxiv

Modern AI models achieve strong performance on many established benchmarks, yet they still fail on tasks that humans find almost trivial, such as manipulating a string or drawing a dog with five legs. These examples sugg…

Folding membrane proteins by deep transfer learning

2017-08-28 · Sheng Wang, Zhen Li, Yizhou Yu, Jinbo Xu

Computational elucidation of membrane protein (MP) structures is challenging partially due to lack of sufficient solved structures for homology modeling. Here we describe a high-throughput deep transfer learning method t…

Transfer Learning

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders

2025-06-24 · Matyas Bohacek, Thomas Fel, Maneesh Agrawala, Ekdeep Singh Lubana

Despite their impressive performance, generative image models trained on large-scale datasets frequently fail to produce images with seemingly simple concepts -- e.g., human hands or objects appearing in groups of four -…

Memorization

Multiscale differential geometry learning for protein flexibility analysis

2024-11-05 · Hongsong Feng, Jeffrey Y. Zhao, Guo-Wei Wei

Protein flexibility is crucial for understanding protein structures, functions, and dynamics, and it can be measured through experimental methods such as X-ray crystallography. Theoretical approaches have also been devel…

Prediction

Discovering Blind Spots in Reinforcement Learning

2018-05-23 · Ramya Ramakrishnan, Ece Kamar, Debadeepta Dey, Julie Shah 외

Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult to discover because the agent cannot predict the…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)