@article{SCOPUS_ID:105014118997,

title = {Critical Assessment of Protein Intrinsic Disorder Round 3 - Predicting Disorder in the Era of Protein Language Models},

author = {Mahta Mehdiabadi and Alessio Del Conte and Maria Victoria Nugnes and Maria Cristina Aspromonte and Silvio C. E. Tosatto and Damiano Piovesan},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105014118997&origin=inward},

doi = {10.1002/prot.70045},

year  = {2026},

date = {2026-01-01},

journal = {Proteins: Structure, Function and Bioinformatics},

volume = {94},

number = {1},

pages = {414-424},

publisher = {John Wiley and Sons Inc},

abstract = {© 2025 The Author(s). PROTEINS: Structure, Function, and Bioinformatics published by Wiley Periodicals LLC.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.},

note = {Cited by: 4; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105034187048,

title = {Toward a unified framework for determining conformational ensembles of disordered proteins},

author = {Hamidreza Ghafouri and Pavel Kadeřávek and Ana M. Melo and Maria Cristina Aspromonte and Pau Bernadó and Juan Cortés and Zsuzsanna Dosztányi and Gábor Erdős and Michael Feig and Giacomo Janson and Kresten Lindorff-Larsen and Frans A. A. Mulder and Peter Nagy and Richard Pestell and Damiano Piovesan and Marco Schiavina and Benjamin Schuler and Nathalie Sibille and Giulio Tesei and Peter Tompa and Michele Vendruscolo and Jiri Vondrasek and Wim Vranken and Lukas Zidek and Silvio C. E. Tosatto and Alexander Miguel Monzon},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105034187048&origin=inward},

doi = {10.1038/s41592-026-03003-2},

year  = {2026},

date = {2026-01-01},

journal = {Nature Methods},

volume = {23},

number = {4},

pages = {705-719},

publisher = {Nature Research},

abstract = {© Springer Nature America, Inc. 2026.Disordered proteins play essential roles in myriad cellular processes, yet their structural characterization remains a major challenge due to their dynamic and heterogeneous nature. Here we present a community-driven initiative to address this problem by advocating a unified framework for determining conformational ensembles of disordered proteins. Our aim is to integrate state-of-the-art experimental techniques with advanced computational methods, including knowledge-based sampling, enhanced molecular dynamics and machine learning models. The modular framework comprises three interconnected components: experimental data acquisition, computational ensemble generation and validation. The systematic development of this framework will ensure the accurate and reproducible determination of conformational ensembles of disordered proteins. We highlight the open challenges necessary to achieve this goal, including force-field accuracy, efficient sampling, and environmental dependence, advocating for collaborative benchmarking and standardized protocols.},

note = {Cited by: 0; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105027746750,

title = {The Gene Ontology knowledgebase in 2026},

author = {Suzi A Aleksander and James P Balhoff and Seth Carbon and J. Michael Cherry and Dustin Ebert and Marc Feuermann and Pascale Gaudet and Nomi L Harris and David P Hill and Patrick Kalita and Raymond Lee and Huaiyu Mi and Sierra Moxon and Christopher J Mungall and Anushya Muruganujan and Tremayne Mushayahama and Paul W Sternberg and Paul D Thomas and Kimberly Van Auken and Edith D Wong and Valerie Wood and Jolene Ramsey and Deborah A Siegele and Rex L Chisholm and Robert Dodson and Petra Fey and Maria Cristina Aspromonte and Maria Victoria Nugnes and Ximena Aixa Castro Naser and Silvio C. E Tosatto and Michelle Giglio and Suvarna Nadendla and Giulia Antonazzo and Helen Attrill and Nicholas H Brown and Gil Dos Santos and Steven Marygold and Katja Röper and Victor Strelets and Christopher J Tabone and Jim Thurmond and Pinglei Zhou and Rossana Zaru and Ruth C Lovering and Colin Logie and Daqing Chen and Alexandra Naba and Karen Christie and Lori Corbani and Li Ni and Dmitry Sitnikov and Cynthia Smith and James Seager and Laurel Cooper and Justin Elser and Pankaj Jaiswal and Parul Gupta and Sushma Naithani and Pascal Carme and Kim Rutherford and Jeffrey L De Pons and Melinda R Dwinell and G. Thomas Hayman and Mary L Kaldunski and Anne E Kwitek and Stanley J. F Laulederkind and Marek A Tutaj and Mahima Vedi and Shur-Jen Wang and Peter D'Eustachio and Lucila Aimo and Kristian Axelsen and Alan Bridge and Nevila Hyka-Nouspikel and Anne Morgat and Gene Goldbold and Stacia R Engel and Stuart R Miyasato and Robert S Nash and Gavin Sherlock and Shuai Weng and Erika Bakker and Tanya Z Berardini and Leonore Reiser and Andrea Auchincloss and Ghislaine Argoud-Puy and Marie-Claude Blatter and Emmanuel Boutet and Lionel Breuza and Cristina Casals-Casas and Elisabeth Coudert and Anne Estreicher and Maria Livia Famiglietti and Arnaud Gos and Nadine Gruaz-Gumowski and Chantal Hulo and Florence Jungo and Philippe Le Mercier and Damien Lieberherr and Patrick Masson and ...},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105027746750&origin=inward},

doi = {10.1093/nar/gkaf1292},

year  = {2026},

date = {2026-01-01},

journal = {Nucleic Acids Research},

volume = {54},

number = {D1},

pages = {D1779-D1792},

publisher = {Oxford University Press},

abstract = {© 2025 The Author(s). Published by Oxford University Press.The Gene Ontology (GO) knowledgebase (https://geneontology.org) is a comprehensive resource describing the functions of genes. The GO knowledgebase is regularly updated and improved. We describe here the major updates that have been made in the past 3 years. The ontology and annotations have been expanded and revised, particularly in several areas of biology: cellular metabolism, multi-organism interactions (e.g. host-pathogen), extracellular matrix proteins, chromatin remodeling (e.g. the "histone code"), and noncoding RNA functions. We have released version 2 of a comprehensive set of integrated, reviewed annotations for human genes, which we call the "functionome."We have also dramatically increased the number of GO-CAM models, with over 1500 models of metabolic and signaling pathways, primarily in human, mouse, budding and fission yeast, and fruit fly. Finally, we discuss our current recommendations and future prospects of AI in the use and development of GO.},

note = {Cited by: 9; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105027748200,

title = {DisProt in 2026: enhancing intrinsically disordered proteins accessibility, deposition, and annotation},

author = {Maria Victoria Nugnes and Kamel Eddine Adel Bouhraoua and Mehdi Zoubiri and Rita Pancsa and Erzsébet Fichó and Alexander M Monzon and Ana M Melo and Edoardo Salladini and Emanuela Leonardi and Federica Quaglia and Daniyal Nasiribavil and Hamidreza Ghafouri and Gobeill Julien and Emilie Pasche and Patrick Ruch and Paul Van Rijen and László Dobson and Marco Schiavina and Trinidad Cordero and Zsófia E Kálmán and Ximena Castro and Valentín Iglesias and István Reményi and Mahta Mehdiabadi and Gábor Erdős and Zsuzsanna Dosztányi and Peter Tompa and Damiano Piovesan and Silvio C. E Tosatto and Maria Cristina Aspromonte},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105027748200&origin=inward},

doi = {10.1093/nar/gkaf1175},

year  = {2026},

date = {2026-01-01},

journal = {Nucleic Acids Research},

volume = {54},

number = {D1},

pages = {D383-D392},

publisher = {Oxford University Press},

abstract = {© 2025 The Author(s). Published by Oxford University Press.DisProt (https://disprot.org/) is an open database integrating experimental evidence on intrinsically disordered proteins (IDPs), intrinsically disordered regions (IDRs), and their functions. Over the past two years, the database has grown over 20%, now comprising 3201 IDPs and 13 347 pieces of evidence, including over 1500 new structural state annotations and >1300 new function annotations. DisProt has systematically adopted the Minimum Information About Disorder Experiments (MIADE) guidelines, more than doubling annotations with experimental details and improving the interpretability of disorder-related experiments. The website has evolved into a hybrid knowledgebase and deposition system, introducing a Deposition Page that allows direct submissions by external users. Through BLAST-based homology propagation in MobiDB, DisProt disorder regions and linear interacting peptides have been extended from hundreds to hundreds of thousands of proteins across >11 000 organisms. This new release marks a paradigm shift by integrating computational predictions as valid evidence and introducing major updates and restructuring of the IDP Ontology, enhancing accuracy, interoperability, and semantic clarity. DisProt continues to support community engagement through training resources together with DisTriage, an AI-based literature triage tool, providing curators with regularly updated lists of prioritized publications.},

note = {Cited by: 4; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105031259193,

title = {Missense Constraint in Intrinsically Disordered Proteins Enhances Missense Variant Interpretation in Neurodevelopmental Disorders},

author = {Nazareth D. J. Robles and Silvio C. E. Tosatto and Maria Cristina Aspromonte},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105031259193&origin=inward},

doi = {10.3390/genes17020219},

year  = {2026},

date = {2026-01-01},

journal = {Genes},

volume = {17},

number = {2},

publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},

abstract = {© 2026 by the authors.Background/Objectives: Interpreting missense variants in intrinsically disordered proteins (IDPs) remains a major challenge, as these proteins lack stable structure and are under-represented in experimental and clinical annotations. Variants occurring in IDPs are disproportionately classified as variants of uncertain significance (VUS), reflecting the absence of appropriate predictive tools rather than true biological neutrality. Here, we address this challenge using a curated dataset of neurodevelopmental disorder (NDD)-associated proteins. Methods: We integrated curated and predicted disorder annotations from DisProt and MobiDB to characterize the structural landscape of 339 NDD-associated proteins. To quantify a regional genetic constraint, we recalculated the Missense Tolerance Ratio (MTR) using a published framework adapted to the recent gnomAD release (v4.1.0). Integration with 33,124 ClinVar-reported missense variants revealed that, while mean constraint levels differ only modestly across structural states, ordered and structural transition regions show the strongest depletion of missense variation. Results: MTR identifies localized low-tolerance subregions within IDRs, indicating that these regions are not uniformly permissive and can harbor functionally essential elements. Conclusions: Overall, our results demonstrate that missense constraint in NDD proteins is highly localized and context-dependent, and that integrating high-quality disorder annotations with updated MTR profiles can improve the prioritization and interpretation of missense variants in IDRs and IDPs.},

note = {Cited by: 0; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}