Critical Assessment of Protein Intrinsic Disorder Round 3 ‐ Predicting Disorder in the Era of Protein Language Models
Open Access
- 26 August 2025
- journal article
- Published by Wiley in Proteins: Structure, Function, and Bioinformatics
- Vol. 94 (1) , 414-424
Abstract
Intrinsic disorder (ID) in proteins is a complex phenomenon, encompassing a continuum from entirely disordered regions to structured domains with flexible segments. The absence of a ground truth for all forms of disorder, combined with the possibility of structural transitions between ordered and disordered states under specific conditions, makes accurate prediction of ID especially challenging. The Critical Assessment of Protein Intrinsic Disorder (CAID) evaluates ID prediction methods using diverse benchmarks derived from DisProt, a manually curated database of experimentally validated annotations. This paper presents findings from the third round (CAID3), in which 24 new methods were assessed along with the predictors from previous rounds. Compared to CAID2, the top‐performing methods in CAID3 demonstrated significant gains in average precision: over 31% improvement in predicting linker regions, and 15% in disorder prediction. This round introduces a new binding sub‐challenge focused on identifying binding regions within known IDR boundaries. The results indicate that this task remains challenging, highlighting the potential for improvement. The top‐performing methods in CAID3 are mostly new and commonly used embeddings from protein language models (pLMs), underscoring the growing impact of pLMs in tackling the complexities of disordered proteins and advancing ID prediction.Keywords
Funding Information
- Ministry of Education, University and Research
- European Cooperation in Science and Technology
- Ministry of Education
- European Research Executive Agency
This publication has 54 references indexed in Scilit:
- PredIDR2: Improving accuracy of protein intrinsic disorder prediction by updating deep convolutional neural network and supplementing DisProt dataInternational Journal of Biological Macromolecules, 2025
- DisorderUnetLM: Validating ProteinUnet for efficient protein intrinsic disorder predictionComputers in Biology and Medicine, 2024
- flDPnn2: Accurate and Fast Predictor of Intrinsic Disorder in ProteinsJournal of Molecular Biology, 2024
- DisPredict3.0: Prediction of intrinsically disordered regions/proteins using protein language modelApplied Mathematics and Computation, 2024
- Critical assessment of protein intrinsic disorder prediction (CAID) ‐ Results of round 2Proteins: Structure, Function, and Bioinformatics, 2023
- Intrinsic protein disorder and conditional folding in AlphaFoldDBProtein Science, 2022
- Embeddings from protein language models predict conservation and variant effectsHuman Genetics, 2021
- Learning the protein language: Evolution, structure, and functionCell Systems, 2021
- SPOT-Disorder2: Improved Protein Intrinsic Disorder Prediction by Ensembled Deep LearningGenomics, Proteomics & Bioinformatics, 2019
- The Pairwise Energy Content Estimated from Amino Acid Composition Discriminates between Folded and Intrinsically Unstructured ProteinsJournal of Molecular Biology, 2005