Publications

@article{Begue20264250,

title = {Exploring proteins and protein–ligand complexes through residue interaction networks},

author = {Sol C. Begue and Emanuela Leonardi and Giovanni Minervini and Silvio C. E. Tosatto},

url = {https://www.scopus.com/pages/publications/105033505349?origin=resultslist},

doi = {10.1038/s41596-026-01334-0},

issn = {17542189},

year  = {2026},

date = {2026-01-01},

journal = {Nature Protocols},

volume = {21},

number = {9},

pages = {4250 - 4277},

publisher = {Springer Nature},

abstract = {Protein structures provide a wealth of information regarding biological functions and underlying mechanisms. The growing availability of high-quality structure predictions and extended molecular simulations has further expanded the potential to leverage these data in a myriad of different ways. Yet, an abundance of data can obscure important information, making it difficult to focus on biologically relevant features. Residue interaction networks (RINs) address this challenge by condensing structural data into subsets of well-defined noncovalent molecular interactions. In this Protocol, we explore how the RIN generator (RING) software can be used to gain biological insights by constructing detailed RINs for proteins and protein–ligand complexes. We provide a step-by-step guide to performing both single- and multi-state protein analyses using the RING web server and a stand-alone software package. In addition, we include a dedicated procedure for sequential multi-file analysis, which can be performed exclusively through the command-line interface. All potential inputs and outputs are explained in detail, along with strategies for downstream data processing. Designed for researchers in biology and related fields with minimal or no programming experience, the entire workflow can be completed in <45 min. © Springer Nature Limited 2026.},

note = {Cited by: 0},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ghafouri2026c,

title = {Advances in the determination of disordered protein ensemble},

author = {Hamidreza Ghafouri and Silvio C. E. Tosatto and Alexander Miguel Monzon},

url = {https://www.scopus.com/pages/publications/105024913941?origin=resultslist},

doi = {10.1016/j.sbi.2025.103198},

issn = {0959440X},

year  = {2026},

date = {2026-01-01},

journal = {Current Opinion in Structural Biology},

volume = {96},

publisher = {Elsevier Ltd},

abstract = {Intrinsically disordered proteins (IDPs) play essential roles in regulation, signaling, and phase separation, yet their structural complexity cannot be captured by a single conformation. Instead, they populate dynamic ensembles that encode a context-dependent function. Recent advances in experimental techniques coupled with physics-based simulations, coarse-grained models, and machine learning, have transformed our ability to generate and interpret IDP ensembles. Integrative frameworks now combine complementary data with computational approaches to refine ensembles at both local and global levels. Nevertheless, challenges remain in benchmarking, error estimation, and modeling assemblies involving protein–protein and protein–nucleic acid interactions. We highlight recent progress and outline the emerging directions that will shape the next generation of ensemble determination methods. © 2025 The Author(s).},

note = {Cited by: 3; All Open Access; Green Open Access; Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Aleksander2026D1779,

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 Ivo Pedruzzi and Lucille Pourcel and Sylvain Poux and Catherine Rivoire and Shyamala Sundaram and Alex Bateman and Aduragbemi Adesina and Emily Bowler-Barnett and David Carpentier and Paul Denny and Alexandr Ignatchenko and Rizwan Ishtiaq and Antonia Lock and Yvonne Lussi and Michele Magrane and Maria J Martin and Sandra Orchard and Pedro Raposo and Elena Speretta and Nidhi Tyagi and Nadya Urakova and Kate Warner and Conny Wing-Hen Yu and Juancarlos Chan and Stavros Diamantakis and Mark Quinton-Tulloch and Daniela Raciti and Malcolm Fisher and Christina James-Zorn and Virgilio Ponferrada and Aaron Zorn and Doug Howe and Sridhar Ramachandran and Leyla Ruzicka and Monte Westerfield},

url = {https://www.scopus.com/pages/publications/105027746750?origin=resultslist},

doi = {10.1093/nar/gkaf1292},

issn = {03051048},

year  = {2026},

date = {2026-01-01},

journal = {Nucleic Acids Research},

volume = {54},

number = {D1},

pages = {D1779 - D1792},

publisher = {Oxford University Press},

abstract = {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. © 2025 The Author(s). Published by Oxford University Press.},

note = {Cited by: 109; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ghafouri2026,

title = {IDPEnsembleTools: An open-source library for analysis of conformational ensembles of disordered proteins},

author = {Hamidreza Ghafouri and Giacomo Janson and Silvio C. E. Tosatto and Alexander Miguel Monzon},

url = {https://www.scopus.com/pages/publications/105025600452?origin=resultslist},

doi = {10.1002/pro.70427},

issn = {09618368},

year  = {2026},

date = {2026-01-01},

journal = {Protein Science},

volume = {35},

number = {1},

publisher = {John Wiley and Sons Inc},

abstract = {Intrinsically disordered proteins (IDPs) lack stable tertiary structure and instead exist as dynamic ensembles of conformations, playing essential roles in cellular regulation, signaling, and disease. As structural ensembles of IDPs become increasingly available through databases such as the Protein Ensemble Database (PED) and various computational generation methods, the need for systematic tools to analyze and compare these ensembles has grown. Here, we present IDPET (Intrinsically Disordered Protein Ensemble Tools), an open-source Python library designed to facilitate comprehensive analysis of IDP conformational ensembles. IDPET enables users to load and process ensembles from various sources and formats in parallel, compute global and local structural features, perform dimensionality reduction and clustering, and compare ensembles quantitatively using metrics based on Jensen–Shannon divergence (JSD). To demonstrate the package's functionalities, we analyze three ensembles of the unfolded drkN SH3 domain deposited in PED. This example illustrates how IDPET can extract structural descriptors, visualize conformational diversity, assess global and local features, and quantify differences between ensembles generated using distinct experimental and computational methods. By providing a reproducible and extensible framework, IDPET supports systematic exploration of ensemble features in IDPs. It is compatible with atomistic and coarse-grained models and can be easily integrated with community resources. © 2025 The Author(s). Protein Science published by Wiley Periodicals LLC on behalf of The Protein Society.},

note = {Cited by: 0; All Open Access; Green Open Access; Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Chiappinelli20263976,

title = {Effects of Mutations on Tandem-Repeat Proteins Conformation Mechanisms. Application to the Phosphatase PP2A},

author = {Matias Chiappinelli and Tadeo E. Saldaño and Silvio C E Tosatto and Sergei Grudinin and Gustavo Parisi and Sebastian Fernandez-Alberti},

url = {https://www.scopus.com/pages/publications/105035676703?origin=resultslist},

doi = {10.1021/acs.jcim.6c00133},

issn = {1549960X},

year  = {2026},

date = {2026-01-01},

journal = {Journal of chemical information and modeling},

volume = {66},

number = {7},

pages = {3976 - 3986},

abstract = {Tandem repeat proteins (TRPs) are composed of arrays of repeating structural units that assemble into extended, superhelical, or horseshoe-shaped architectures stabilized primarily by short-range interactions. The unique sequence-structure-dynamics-function relationships of TRPs have been the subject of extensive investigation, aiming to elucidate the molecular principles that distinguish them from globular proteins. Here we explore the effects of mutations on conformational mechanics of PR65, the HEAT-repeat scaffold of phosphatase PP2A that acts as an elastic connector between catalytic and regulatory subunits. We found that the effect of mutations on dynamics, that is associated with the collective conformational changes experienced by PR65 in its binding to the catalytic subunit, correlates with its evolutionary conservation. Besides, our study reveals a common pattern among repeat units in how mutations influence these dynamics, but it also highlights functional differences among the individual units. That is, mutations on individual units preserve a common influence on the collective dynamics of the TRP but their individual participation in function introduces additional differences in their corresponding effects of mutations. Finally, none of these aspects are observed for the subsequent conformational changes experienced during the binding of the dimer PR65-catalytic subunit complex with the regulatory subunit. We believe this work highlights both the similarities and differences between repeat units in how mutations affect their dynamics─insights that may advance our understanding of TRP mechanisms in pathogenicity─enable scaffold modifications for engineered ligand binding with diverse applications, and broadly expand our knowledge of TRP function.},

note = {Cited by: 0},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Farrell20261734,

title = {Open and sustainable AI: challenges, opportunities and the road ahead in the life sciences},

author = {Gavin Farrell and Eleni Adamidi and Rafael Andrade Buono and Mihail Anton and Omar Abdelghani Attafi and Salvador Capella Gutierrez and Emidio Capriotti and Leyla Jael Castro and Davide Cirillo and Lisa Crossman and Christophe Dessimoz and Alexandros Dimopoulos and Raúl Fernández-Díaz and Styliani-Christina Fragkouli and Carole Goble and Wei Gu and John M. Hancock and Alireza Khanteymoori and Tom Lenaerts and Fabio G. Liberante and Peter Maccallum and Alexander Miguel Monzon and Magnus Palmblad and Lucy Poveda and Ovidiu Radulescu and Denis C. Shields and Shoaib Sufi and Thanasis Vergoulis and Fotis Psomopoulos and Silvio C. E. Tosatto},

url = {https://www.scopus.com/pages/publications/105034198426?origin=resultslist},

doi = {10.1038/s41592-026-03037-6},

issn = {15487091},

year  = {2026},

date = {2026-01-01},

journal = {Nature Methods},

volume = {23},

number = {9},

pages = {1734 - 1745},

publisher = {Nature Research},

abstract = {Artificial intelligence (AI) has seen transformative breakthroughs in the life sciences, expanding possibilities to interpret biological information at an unprecedented capacity. To maximize return on growing investments and accelerate progress, it is urgent to address long-standing research challenges arising from the rapid adoption of AI methods. We review the erosion of trust in AI outputs driven by poor reusability and reproducibility, and highlight their impact on environmental sustainability. Furthermore, we discuss the fragmented components of the AI ecosystem and lack of guiding pathways to support open and sustainable AI model development. In response, this Perspective introduces practical open and sustainable AI recommendations mapped to over 300 ecosystem components and provides guiding implementation pathways. Our work connects researchers with relevant AI resources, facilitating the implementation of sustainable, reusable and reproducible AI. Built upon community consensus and aligned to existing efforts, these outputs will aid future policy development and structured pathways for guiding AI implementation. © Springer Nature America, Inc. 2026.},

note = {Cited by: 3; All Open Access; Green Open Access; Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Mehdiabadi2026,

title = {Modeling intrinsically disordered regions from AlphaFold2 to AlphaFold3},

author = {Mahta Mehdiabadi and Silvio C. E. Tosatto and Damiano Piovesan},

url = {https://www.scopus.com/pages/publications/105026115828?origin=resultslist},

doi = {10.1002/pro.70426},

issn = {09618368},

year  = {2026},

date = {2026-01-01},

journal = {Protein Science},

volume = {35},

number = {1},

publisher = {John Wiley and Sons Inc},

abstract = {AlphaFold2 has demonstrated a remarkable success in predicting the structures of globular proteins and folded domains with near-experimental accuracy. However, it typically represents intrinsically disordered regions (IDRs), protein segments that lack a stable 3D structure under physiological conditions, as long extended loops that appear to float around the structured core. While AlphaFold2's static prediction cannot capture the conformational heterogeneity and the dynamic nature of IDRs, it performs well in predicting IDRs from sequence. AlphaFold3 introduces significant architectural and training modifications over its predecessor, including the use of cross-distillation aimed at reducing structural hallucinations in disordered regions. In this study, we look into how these models differ in representing IDRs. We evaluate the performance of AlphaFold3 and AlphaFold2 on disorder prediction, using the CAID3 benchmark. Our analysis shows that AlphaFold3 does not outperform AlphaFold2 in this benchmark. We observe that solvent accessibility remains a robust and consistent proxy for predicting intrinsic disorder across both models. However, changes in the predicted secondary structure content and pLDDT scores lead to different interpretations of disorder. Overall, our findings suggest that AlphaFold2 remains the preferred choice for identifying intrinsically disordered regions, as it avoids structural hallucinations while providing predictions comparable to those of AlphaFold3. © 2025 The Protein Society.},

note = {Cited by: 7; All Open Access; Green Open Access; Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Robles2026,

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/pages/publications/105031259193?origin=resultslist},

doi = {10.3390/genes17020219},

issn = {20734425},

year  = {2026},

date = {2026-01-01},

journal = {Genes},

volume = {17},

number = {2},

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

abstract = {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. © 2026 by the authors.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Mehdiabadi2026414,

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/pages/publications/105014118997?origin=resultslist},

doi = {10.1002/prot.70045},

issn = {08873585},

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

note = {Cited by: 12; All Open Access; Green Open Access; Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Osmanli2026423,

title = {Tandem repeats matter for the functional versatility of giant proteins},

author = {Zarifa Osmanli and Alexander Miguel Monzon and Silvio C. E. Tosatto},

url = {https://www.scopus.com/pages/publications/105033760847?origin=resultslist},

doi = {10.1016/j.tibs.2026.02.010},

issn = {09680004},

year  = {2026},

date = {2026-01-01},

journal = {Trends in Biochemical Sciences},

volume = {51},

number = {5},

pages = {423 - 426},

publisher = {Elsevier Ltd},

abstract = {Giant proteins play essential cellular roles but remain structurally challenging. Recent advances in structure determination and modeling reveal that tandem repeats are widespread in large proteins, providing modularity, adaptability, and multifunctionality. Examples including apolipoprotein B100, teneurins, and ryanodine receptors illustrate how repetition drives structural flexibility, regulatory precision, and evolutionary innovation. © 2026 Elsevier Ltd},

note = {Cited by: 1},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Bouhraoua2026,

title = {STRPsearch Web Server: A User-friendly Interface for Rapid and Accurate Prediction of Structured Tandem Repeat Proteins},

author = {Yousra Hind Bouhraoua and Zarifa Osmanli and Silvio C. E. Tosatto and Alexander Miguel Monzon},

url = {https://www.scopus.com/pages/publications/105034672381?origin=resultslist},

doi = {10.1016/j.jmb.2026.169755},

issn = {00222836},

year  = {2026},

date = {2026-01-01},

journal = {Journal of Molecular Biology},

volume = {438},

number = {18},

publisher = {Academic Press},

abstract = {Structured Tandem Repeat Proteins (STRPs) are a subset of repeat proteins characterized by recurring structural motifs, even in cases where sequence similarity between repeats is very low. Despite substantial sequence variability, STRPs preserve conserved secondary-structure elements that underpin a wide range of biological functions. Although millions of protein structures are now publicly available, the accurate detection of STRPs remains challenging. STRPsearch is a recently developed tool for the rapid identification and classification of STRPs. Here, we introduce the STRPsearch web server, an enhanced implementation featuring a user-friendly interface. The server is freely available https://strpsearch.biocomputingup.it/. © 2026 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license. http://creativecommons.org/licenses/by-nc-nd/4.0/},

note = {Cited by: 1; All Open Access; Green Open Access; Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ghafouri2026705,

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/pages/publications/105034187048?origin=resultslist},

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

issn = {15487091},

year  = {2026},

date = {2026-01-01},

journal = {Nature Methods},

volume = {23},

number = {4},

pages = {705 - 719},

publisher = {Nature Research},

abstract = {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. © Springer Nature America, Inc. 2026.},

note = {Cited by: 6; All Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Wood2026,

title = {Empowering biological knowledgebases: advances in human-in-the-loop AI-driven literature curation},

author = {Valerie Wood and Matt Jeffryes and Andrew F. Green and Matthias Blum and Sandra Orchard and Simona Panni and Federica Quaglia and Raul Rodriguez-Esteban and James Seager and Silvio C. E. Tosatto and Ulrike Wittig and Melissa Harrison},

url = {https://www.scopus.com/pages/publications/105030612709?origin=resultslist},

doi = {10.1093/bioadv/vbag028},

issn = {26350041},

year  = {2026},

date = {2026-01-01},

journal = {Bioinformatics Advances},

volume = {6},

number = {1},

publisher = {Oxford University Press},

abstract = {Biological knowledgebases facilitate discovery across the life sciences by structuring experimental findings into human-readable and computable formats. These essential resources are maintained by a small number of professional biocurators worldwide and face combined chronic underfunding and the exponential growth of the literature. In this perspective, we review how artificial intelligence, particularly large language models and agentic systems, can augment literature-curation workflows. Applications include literature recommendation, entity recognition, data extraction, summarization, ontology development, and quality control with emphasis on published use cases at Global Core BioData Resources and ELIXIR Core Data Resources. We identify key challenges, including the scarcity of training data, difficulty in extracting complex relationships, and concerns about error propagation. To address these challenges, we propose a human-in-the-loop framework where generative artificial intelligence approaches accelerate routine tasks while curators provide critical evaluation and domain expertise. We also propose practical recommendations for the community, including the creation of shared benchmark datasets, harmonized evaluation frameworks, and best-practice guidelines for transparent human-in-the-loop AI deployment in biocuration. These synergistic partnerships will be critical to ensure biological rigour, accelerating knowledge integration while maintaining the quality essential for trusted biological resources. © The Author(s) 2026. Published by Oxford University Press.},

note = {Cited by: 2; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Godfrey2026,

title = {An episignature informed systematic analysis to ascertain the clinical significance and consequences of CHD8 missense variants},

author = {Molly Godfrey and Michael A. Levy and Christopher Campbell and Leigh Demain and Sarah Jenkinson and Sarah Hilton and Berta Almoguera and Meena Balasubramanian and Emilia K. Bijlsma and Fiona Blanco-Kelly and Emma M. M. Burkitt Wright and Gerarda Cappuccio and Kate E. Chandler and Koen Devriendt and Aranzazu Diaz de Bustamante and Maria K. Haanpää and Carolin Hörnig and Elizabeth A. Jones and Sinem Kocagil and Hannele Koillinen and Dhanya Lakshmi Narayanan and Emanuela Leonardi and Rajesh Madhu and Purvi Majethia and Alessandra Murgia and Elisabeth Rosser and Markus Schuelke and Anju Shukla and Emma Soengas-Gonda and Sarah Stewart and Yves Sznajer and Saoud Tahsin Swafiri and Maria Margarida Venancio and Renzo Guerrini and Martino Montomoli and Annalisa Vetro and Thomas Wright and David Gokhale and Bekim Sadikovic and Sofia Douzgou Houge and Siddharth Banka},

url = {https://www.scopus.com/pages/publications/105047009929?origin=resultslist},

doi = {10.1038/s41431-026-02209-4},

issn = {10184813},

year  = {2026},

date = {2026-01-01},

journal = {European Journal of Human Genetics},

publisher = {Springer Nature},

abstract = {Pathogenic CHD8 variants cause autosomal dominant ‘Intellectual developmental disorder with autism and macrocephaly’ (IDDAM) and are amongst the most common monogenic causes of autism. The clinical significance of CHD8 missense variants (MVs) frequently remains uncertain. Systematically applying ACGS/ACMG guidelines to 36 CHD8 MVs in 39 affected patients, only two variants were classified likely pathogenic (LP), with the remaining 34 classified variants of uncertain significance (VUS). We subclassified the variants according to posterior probability of pathogenicity (PPP), with 14 being at least tepid VUS (PPP ≥ 50%). Comprehensive phenotypic analysis revealed no discernible clinical differences between individuals carrying at least tepid VUS and others, offering no additional insight for variant classification. EpiSign™ testing revealed a CHD8-IDDAM episignature, as previously detected in patients with truncating/null variants, in 11 cases, allowing reclassification of 8 VUS (all previously classified at least tepid) as LP. Molecular modelling indicated that disease-causing (LP/P) CHD8 MVs are concentrated in structured and/or functional protein domains. Compared to truncating/null variants, disease-causing MVs were less often associated with attention issues and macrocephaly, but clinical features were otherwise similar. Additionally, three disease-causing MVs were inherited from unaffected/mildly affected parents. Overall, we show that determining the clinical significance of CHD8 MVs is challenging, even with detailed clinical information, but that incorporating episignature analysis increases diagnostic yield. Further, our results indicate that CHD8 MVs are likely to act via a loss-of-or reduced function mechanism. These findings reveal the importance and complexity of interpreting CHD8 MVs and will improve the diagnosis and understanding of CHD8-related disorders. © The Author(s) 2026.},

note = {Cited by: 0; All Open Access; Green Open Access; Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Nugnes2026D383,

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/pages/publications/105027748200?origin=resultslist},

doi = {10.1093/nar/gkaf1175},

issn = {03051048},

year  = {2026},

date = {2026-01-01},

journal = {Nucleic Acids Research},

volume = {54},

number = {D1},

pages = {D383 - D392},

publisher = {Oxford University Press},

abstract = {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. © 2025 The Author(s). Published by Oxford University Press.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Grandi2026,

title = {Honokiol blocks tumor development and metastasis through mitochondrion-targeted effects},

author = {Martina Grandi and Francesco Boldrin and Giovanni Risato and Silvia Grillini and Natascia Tiso and Francesco Argenton and Emanuela Leonardi and Silvio Tosatto and Giancarlo Solaini and Alessandra Baracca and Valentina Giorgio},

url = {https://www.scopus.com/pages/publications/105029446962?origin=resultslist},

doi = {10.1038/s41419-026-08441-6},

issn = {20414889},

year  = {2026},

date = {2026-01-01},

journal = {Cell Death and Disease},

volume = {17},

number = {1},

publisher = {Springer Nature},

abstract = {IF1 is the natural inhibitor of the mitochondrial ATP synthase during hydrolytic activity. It has been found to be overexpressed in many tumors, where it acts as a pro-oncogenic protein. During oxidative phosphorylation, IF1 binds to a novel site on the OSCP subunit of ATP synthase and promotes tumorigenesis by protecting cancer cells from permeability transition pore (PTP)-dependent apoptosis. In this work, honokiol, a biphenolic compound, showed binding affinity for two sites on the OSCP subunit, as predicted by molecular docking analysis. It was shown to be effective in disrupting the IF1-OSCP interaction and sensitizing cancer cells to apoptosis. In vivo, xenografts of zebrafish injected with IF1-expressing HeLa cells showed tumor development. The same xenografts, treated with honokiol, showed a significant reduction in tumor mass, similar to untreated fish injected with IF1 KO HeLa cells. In vitro, honokiol inhibits colony formation in soft agar of IF1-expressing HeLa cells by promoting the PTP opening and cell death, without any effect on cell proliferation. Interestingly, honokiol was shown to block metastasis in fish xenografts and migration in a wound healing assay, by promoting mitochondrial swelling in both control and IF1 KO cell lines, when cells are moving to close the scratch area. In conclusion, honokiol appears to be a promising anti-cancer compound, with pro-apoptotic properties through the displacement of IF1 from the OSCP subunit of ATP synthase, and anti-metastatic effects that are due to mitochondrial PTP opening. © The Author(s) 2026.},

note = {Cited by: 2; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Poveda2026,

title = {The missing link in FAIR data policy: biodata resources in life sciences},

author = {Lucy Poveda and Gavin Farrell and Silvio C. E. Tosatto and Monique Zahn-Zabal and Patrick Ruch and Julien Gobeill and Robert M. Waterhouse and Christophe Dessimoz},

url = {https://www.scopus.com/pages/publications/105033513263?origin=resultslist},

doi = {10.1038/s41597-026-06690-w},

issn = {20524463},

year  = {2026},

date = {2026-01-01},

journal = {Scientific Data},

volume = {13},

number = {1},

publisher = {Nature Research},

abstract = {In the life sciences, FAIR principles have reshaped research policy, but their implementation still relies largely on individual researchers – many of whom lack the expertise or support needed to make data truly reusable. Realising FAIR’s promise requires sustained investment in the infrastructures that organise, standardise, and curate data: deposition databases and knowledgebases. These biodata resources are especially critical for AI, which depends on large, high-quality, and consistent data. Landmark advances like AlphaFold and the COVID-19 response illustrate how sustained curation and standardisation in expert resources such as UniProt and the Protein Data Bank have enabled rapid innovation. Yet biodata resources remain precariously funded, jeopardising long-term sustainability and the expert workforce they require. To support ambitious, data-driven science, funders must align policy and budgets by establishing dedicated mechanisms that allocate a small (e.g., 1%), but strategic and stable share, of research funding to core data infrastructures. This would maximise the value of public investment, strengthen open science and international collaboration, and unlock the full potential of FAIR. © The Author(s) 2026.},

note = {Cited by: 1; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Garrard2025,

title = {Fostering and sustaining collaborative innovation: Insights from ELIXIR Europe's life science Communities},

author = {Clare Garrard and Katharina F Heil and Maria Cristina Aspromonte and Bérénice Batut and Magda Chegkazi and John M Hancock and Elaine Harrison and Naveed Ishaque and Giselle Kerry and Eija Korpelainen and Jerry Lanfear and Corinne Martin and Sebastian Schaaf and Serena Scollen and Yun-Yun Tseng and Sameer Velankar and Juan Antonio Vizcaíno and Robert M Waterhouse and Egon Willighagen and Niklas Blomberg and Peter Maccallum},

url = {https://www.scopus.com/pages/publications/105025851995?origin=resultslist},

doi = {10.12688/f1000research.168288.1},

issn = {20461402},

year  = {2025},

date = {2025-01-01},

journal = {F1000Research},

volume = {14},

publisher = {F1000 Research Ltd},

abstract = {Communities of experts collaborating on scientific or technical projects are drivers of innovation across the life sciences. The ELIXIR research infrastructure organises scientific- and technological-themed communities as one of its key mechanisms to ensure that services are user-focused, while at the same time facilitating collaboration and creating scientific impact through the life science data generated across Europe. ELIXIR has rapidly expanded its communities portfolio in response to unmet needs and has developed a comprehensive process framework to facilitate the work of these communities. The ELIXIR Communities framework is made up of a suite of tools and processes that ensure effective community evolution and management, covering how communities are established, led, supported, and can collaborate across ELIXIR and beyond. Being aware of similar approaches in other contexts and in the interests of furthering community development in other research infrastructures and similar organisations, we share insights into the ELIXIR Communities framework and outline the skill set of a community manager and what this looks like in the ELIXIR context. Finally, to show the benefits of the communities, we share concrete examples of how the ELIXIR Communities have had an impact on the scientific landscape. By showcasing these outcomes we hope to demonstrate not only to other research infrastructures, but also to funders, that supporting scientific communities provides a valuable return on investment. We hope that these examples will encourage life scientists who may be interested in joining the ELIXIR Communities, and research infrastructure professionals whose roles require structured engagement with domain experts and users. Copyright: © 2025 Garrard C et al.},

note = {Cited by: 1; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Begue20251072,

title = {Decoding protein structures with residue interaction networks},

author = {Sol C. Begue and Emanuela Leonardi and Silvio C. E. Tosatto},

url = {https://www.scopus.com/pages/publications/105015207644?origin=resultslist},

doi = {10.1016/j.tibs.2025.08.006},

issn = {09680004},

year  = {2025},

date = {2025-01-01},

journal = {Trends in Biochemical Sciences},

volume = {50},

number = {12},

pages = {1072 - 1085},

publisher = {Elsevier Ltd},

abstract = {The rise of AlphaFold and similar structure predictors has made it possible to determine the 3D structure of almost any protein from its amino acid sequence. Residue interaction networks (RINs), graphs where residues are represented as nodes and interactions as edges, provide a powerful framework for analyzing and interpreting this surge in structural data. Here, we provide a comprehensive introduction to RINs, exploring different approaches to constructing and analyzing them, including their integration with molecular dynamics (MD) simulations and artificial intelligence (AI). To illustrate their versatility, we present different case studies where RINs have been applied to investigate thermostability, allosterism, post-translational modifications (PTMs), homology, and evolution. Finally, we discuss future directions for RINs, emphasizing opportunities for refinement and broader integration into structural biology. © 2025 The Author(s)},

note = {Cited by: 8; All Open Access; Green Open Access; Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Osmanli2025,

title = {GeomeTRe: accurate calculation of geometrical descriptors of tandem repeat proteins},

author = {Zarifa Osmanli and Elisa Ferrero and Alexander Miguel Monzon and Silvio C. E Tosatto and Damiano Piovesan},

url = {https://www.scopus.com/pages/publications/105012381789?origin=resultslist},

doi = {10.1093/bioinformatics/btaf395},

issn = {13674803},

year  = {2025},

date = {2025-01-01},

journal = {Bioinformatics},

volume = {41},

number = {7},

publisher = {Oxford University Press},

abstract = {Motivation Structured tandem repeat proteins (STRPs) are characterized by preserved structural motifs arranged in a modular way. The structural and functional diversity of STRPs makes them particularly important for studying evolution and novel structure-function relationships, and ultimately for designing new synthetic proteins with specific functions. One crucial aspect of their classification is the estimation of geometrical parameters, which can provide better insight into their properties and the relationship between the spatial arrangement of repeated units and protein function. Calculating geometric descriptors for STRPs is challenging because naturally occurring repeats are not "perfect"and often contain insertions and deletions. Existing tools for predicting structural symmetry work well on simple cases but often fail for most natural proteins. Results Here, we present GeomeTRe, an algorithm that calculates geometrical descriptors such as curvature (yaw), twist (roll), and pitch for a protein structure with known repeat unit positions. The algorithm simulates the movement of consecutive units, identifies rotational axes, and calculates the corresponding Tait-Bryan angles. GeomeTRe's parameters can enhance STRP annotation and classification by identifying variations in geometric arrangements among different functional groups. The package is fast and suitable for processing large protein structure datasets when repeat region information (e.g. from RepeatsDB) is available. © 2025 The Author(s).},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Piovesan2025D495,

title = {MOBIDB in 2025: integrating ensemble properties and function annotations for intrinsically disordered proteins},

author = {Damiano Piovesan and Alessio Del Conte and Mahta Mehdiabadi and Maria Cristina Aspromonte and Matthias Blum and Giulio Tesei and Sören Bülow and Kresten Lindorff-Larsen and Silvio C. E. Tosatto},

url = {https://www.scopus.com/pages/publications/85213063415?origin=resultslist},

doi = {10.1093/nar/gkae969},

issn = {03051048},

year  = {2025},

date = {2025-01-01},

journal = {Nucleic Acids Research},

volume = {53},

number = {D1},

pages = {D495 - D503},

publisher = {Oxford University Press},

abstract = {The MobiDB database (URL: https://mobidb.org/) aims to provide structural and functional information about intrinsic protein disorder, aggregating annotations from the literature, experimental data, and predictions for all known protein sequences. Here, we describe the improvements made to our resource to capture more information, simplify access to the aggregated data, and increase documentation of all MobiDB features. Compared to the previous release, all underlying pipeline modules were updated. The prediction module is ten times faster and can detect if a predicted disordered region is structurally extended or compact. The PDB component is now able to process large cryo-EM structures extending the number of processed entries. The entry page has been restyled to highlight functional aspects of disorder and all graphical modules have been completely reimplemented for better flexibility and faster rendering. The server has been improved to optimise bulk downloads. Annotation provenance has been standardised by adopting ECO terms. Finally, we propagated disorder function (IDPO and GO terms) from the DisProt database exploiting sequence similarity and protein embeddings. These improvements, along with the addition of comprehensive training material, offer a more intuitive interface and novel functional knowledge about intrinsic disorder. © The Author(s) 2024. Published by Oxford University Press on behalf of Nucleic Acids Research.},

note = {Cited by: 59; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Longhi2025,

title = {When artificial intelligence meets protein research},

author = {Sonia Longhi and Salvador Ventura and Sandra Macedo-Ribeiro and Leandro G. Radusky and Jovana Kovačević and R. Gonzalo Parra and Miguel A. Andrade-Navarro and Andrey V. Kajava and Zuzana Bednáriková and Alexander Monzon and Rita Vilaça},

url = {https://www.scopus.com/pages/publications/105016106568?origin=resultslist},

doi = {10.12688/openreseurope.20628.1},

issn = {27325121},

year  = {2025},

date = {2025-01-01},

journal = {Open Research Europe},

volume = {5},

publisher = {F1000 Research Ltd},

abstract = {The 2024 Nobel Prizes in Chemistry and Physics mark a watershed moment in the convergence of artificial intelligence (AI) and molecular biology. This article explores how AI, particularly deep learning and neural networks, has revolutionized protein science through breakthroughs in structure prediction and computational design. It highlights the contributions of 2024 Nobel laureates John Hopfield, Geoffrey Hinton, David Baker, Demis Hassabis, and John Jumper, whose foundational work laid the groundwork for AI tools such as AlphaFold. These tools are transforming our understanding of protein folding, and the dynamics of non-globular proteins, including intrinsically disordered proteins. While AI-driven methods have made predicting protein structures faster and more accessible, they also underscore ongoing scientific challenges, including the dynamics of protein folding and amyloid aggregation. European initiatives, such as the COST Actions NGP-net (BM1405) and ML4NGP (CA21160), are spearheading efforts to bridge these gaps by integrating AI and experimental data in the study of non-globular proteins. Together, these developments signal a transformative shift in biology, paving the way for novel discoveries in medicine, biotechnology, and materials science. Copyright: © 2025 Longhi S et al.},

note = {Cited by: 2; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Clementel2025,

title = {ngx-mol-viewers: Angular components for interactive molecular visualization in bioinformatics},

author = {Damiano Clementel and Alessio Del Conte and Alexander Miguel Monzon and Silvio C. E. Tosatto},

url = {https://www.scopus.com/pages/publications/105011353218?origin=resultslist},

doi = {10.3389/fbinf.2025.1586744},

issn = {26737647},

year  = {2025},

date = {2025-01-01},

journal = {Frontiers in Bioinformatics},

volume = {5},

publisher = {Frontiers Media SA},

abstract = {Advancements in bioinformatics have been propelled by technologies like machine learning and have resulted in substantial increases in data generated from both empirical observations and computational models. Hence, well-known biological databases are growing in size and centrality by integrating data from different sources. While the primary goal of these databases is to collect and distribute data through application programming interfaces (APIs), providing visualization and analysis tools directly on the browser interface is crucial for users to understand the data, which increases the usefulness and overall impact of the databases. Currently, some front-end frameworks are available for the sustained development of the user interface (UI) and user experience (UX) of these resources. Angular is one of the most popular frameworks to be broadly adopted within the BioCompUP laboratory. This work describes a library of reusable and customizable components that can be easily integrated into the Angular framework to provide visualizations of various aspects of protein molecules, such as their sequences, structures, and annotations. Currently, the library includes three main independent components. The first is the ngx-structure-viewer, which allows visualization of molecules through the MolStar three-dimensional viewer. The second is the ngx-sequence-viewer, which provides visualization and annotation capabilities for a single sequence or multiple sequence alignments. The third the ngx-features-viewer, enables the mapping and visualization of various biological annotations onto the same molecule. All these tools are available for download through the Node Package Manager (NPM), and more information is available at https://biocomputingup.github.io/ngx-mol-viewers/ (under development). Copyright © 2025 Clementel, Del Conte, Monzon and Tosatto.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Mehdiabadi2025,

title = {MobiDB-lite 4.0: faster prediction of intrinsic protein disorder and structural compactness},

author = {Mahta Mehdiabadi and Matthias Blum and Giulio Tesei and Soren Bulow and Kresten Lindorff-Larsen and Silvio C. E. Tosatto and Damiano Piovesan},

url = {https://www.scopus.com/pages/publications/105007010286?origin=resultslist},

doi = {10.1093/bioinformatics/btaf297},

issn = {13674803},

year  = {2025},

date = {2025-01-01},

journal = {Bioinformatics},

volume = {41},

number = {5},

publisher = {Oxford University Press},

abstract = {Motivation: In recent years, many disorder predictors have been developed to identify intrinsically disordered regions (IDRs) in proteins, achieving high accuracy. However, it may be difficult to interpret differences in predictions across methods. Consensus methods offer a simple solution, highlighting reliable predictions while filtering out uncertain positions. Here, we present a new version of MobiDB-lite, a consensus method designed to predict long IDRs and classify them based on compositional biases and conformational properties. Results: MobiDB-lite 4.0 pipeline was optimized to be ten times faster than the previous version. It now provides compactness annotations based on predicted apparent scaling exponent. The newly added features and disorder subclassifications allow the users to get a comprehensive insight into the protein’s function and characteristics. MobiDB-lite 4.0 is integrated into the MobiDB and DisProt databases. A version without the compactness predictor is integrated into InterProScan, propagating MobiDB-lite annotations to UniProtKB. Availability and implementation: The MobiDB-lite 4.0 source code and a Docker container are available from the GitHub repository: https://github.com/BioComputingUP/MobiDB-lite. © The Author(s) 2025. Published by Oxford University Press.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{DelConte2025,

title = {DRMAAtic: Dramatically improve your cluster potential},

author = {Alessio Del Conte and Hamidreza Ghafouri and Damiano Clementel and Ivan Mičetić and Damiano Piovesan and Silvio C. E Tosatto and Alexander Miguel Monzon},

url = {https://www.scopus.com/pages/publications/105008238034?origin=resultslist},

doi = {10.1093/bioadv/vbaf112},

issn = {26350041},

year  = {2025},

date = {2025-01-01},

journal = {Bioinformatics Advances},

volume = {5},

number = {1},

publisher = {Oxford University Press},

abstract = {Motivation The accessibility and usability of high-performance computing (HPC) resources remain significant challenges in bioinformatics, particularly for researchers lacking extensive technical expertise. While Distributed Resource Managers (DRMs) optimize resource utilization, the complexities of interfacing with these systems often hinder broader adoption. DRMAAtic addresses these challenges by integrating the Distributed Resource Management Application API (DRMAA) with a user-friendly RESTful interface, simplifying job management across diverse HPC environments. This framework empowers researchers to submit, monitor, and retrieve computational jobs securely and efficiently, without requiring deep knowledge of underlying cluster configurations. Results We present DRMAAtic, a flexible and scalable tool that bridges the gap between web interfaces and HPC infrastructures. Built on the Django REST Framework, DRMAAtic supports seamless job submission and management via HTTP calls. Its modular architecture enables integration with any DRM supporting DRMAA APIs and offers robust features such as role-based access control, throttling mechanisms, and dependency management. Successful applications of DRMAAtic include the RING web server for protein structure analysis, the CAID Prediction Portal for disorder and binding predictions, and the Protein Ensemble Database deposition server. These deployments demonstrate DRMAAtic's potential to enhance computational workflows, improve resource efficiency, and facilitate open science in life sciences. © 2025 The Author(s).},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Granocchio2025815,

title = {Expanding the clinical phenotype of SHANK2-related disorders: childhood apraxia of speech in a patient with a novel SHANK2 pathogenic variant},

author = {Elisa Granocchio and Luca Andreoli and Santina Magazù and Daniela Sarti and Emanuela Leonardi and Alessandra Murgia and Claudia Ciaccio},

url = {https://www.scopus.com/pages/publications/85191992890?origin=resultslist},

doi = {10.1007/s00787-024-02452-4},

issn = {10188827},

year  = {2025},

date = {2025-01-01},

journal = {European Child and Adolescent Psychiatry},

volume = {34},

number = {2},

pages = {815 - 817},

publisher = {Springer Science and Business Media Deutschland GmbH},

note = {Cited by: 2},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{CastroNaser2025,

title = {Integrative Multi-Omics Characterization and Structural Insights into the Poorly Annotated Integrin ITGA6 X1X2 Isoform in Mammals},

author = {Ximena Aixa Castro Naser and Alessandro Cestaro and Silvio C. E. Tosatto and Emanuela Leonardi},

url = {https://www.scopus.com/pages/publications/105020094912?origin=resultslist},

doi = {10.3390/genes16101134},

issn = {20734425},

year  = {2025},

date = {2025-01-01},

journal = {Genes},

volume = {16},

number = {10},

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

abstract = {Background: Accurate annotation of gene isoforms remains one of the major obstacles in translating genomic data into meaningful biological insight. Laminin-binding integrins, particularly integrin α6 (ITGA6), exemplify this challenge through their complex splicing patterns. The rare ITGA6 X1X2 isoform, generated by the alternative inclusion of exons X1 and X2 within the β-propeller domain, has remained poorly characterized despite decades of integrin research. Methods: We combined comparative genomics across primates with targeted re-alignment to assess exon conservation and annotation fidelity; analyzed RNA-seq for exon-level usage; applied splice-site prediction to evaluate inclusion potential; surveyed cancer mutation resources for exon-specific variants; and used structural/disorder modeling to infer effects on the β-propeller. Results: Exon X2 is conserved at the genomic level but inconsistently annotated, reflecting the limitations of current annotation pipelines rather than genuine evolutionary loss. RNA-seq analyses reveal low but detectable expression of X2, consistent with weak splice site predictions that suggest strict regulatory control and condition-specific expression. Despite its rarity, recurrent mutations in exon X2 are reported in cancer datasets, implying possible roles in disease. Structural modeling further indicates that X2 contributes to a flexible, disordered region within the β-propeller domain, potentially influencing laminin binding or β-subunit dimerization. Conclusions: Altogether, our results suggest that ITGA6 X1X2 could be a rare, tightly regulated isoform with potential functional and pathological relevance. © 2025 by the authors.},

note = {Cited by: 1; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Aspromonte2025309,

title = {Genetic variants and phenotypic data curated for the CAGI6 intellectual disability panel challenge},

author = {Maria Cristina Aspromonte and Alessio Del Conte and Roberta Polli and Demetrio Baldo and Francesco Benedicenti and Elisa Bettella and Stefania Bigoni and Stefania Boni and Claudia Ciaccio and Stefano D’Arrigo and Ilaria Donati and Elisa Granocchio and Isabella Mammi and Donatella Milani and Susanna Negrin and Margherita Nosadini and Fiorenza Soli and Franco Stanzial and Licia Turolla and Damiano Piovesan and Silvio C. E. Tosatto and Alessandra Murgia and Emanuela Leonardi},

url = {https://www.scopus.com/pages/publications/86000084600?origin=resultslist},

doi = {10.1007/s00439-025-02733-1},

issn = {03406717},

year  = {2025},

date = {2025-01-01},

journal = {Human Genetics},

volume = {144},

number = {2},

pages = {309 - 326},

publisher = {Springer Science and Business Media Deutschland GmbH},

abstract = {Neurodevelopmental disorders (NDDs) are common conditions including clinically diverse and genetically heterogeneous diseases, such as intellectual disability, autism spectrum disorders, and epilepsy. The intricate genetic underpinnings of NDDs pose a formidable challenge, given their multifaceted genetic architecture and heterogeneous clinical presentations. This work delves into the intricate interplay between genetic variants and phenotypic manifestations in neurodevelopmental disorders, presenting a dataset curated for the Critical Assessment of Genome Interpretation (CAGI6) ID Panel Challenge. The CAGI6 competition serves as a platform for evaluating the efficacy of computational methods in predicting phenotypic outcomes from genetic data. In this study, a targeted gene panel sequencing has been used to investigate the genetic causes of NDDs in a cohort of 415 paediatric patients. We identified 60 pathogenic and 49 likely pathogenic variants in 102 individuals that accounted for 25% of NDD cases in the cohort. The most mutated genes were ANKRD11, MECP2, ARID1B, ASH1L, CHD8, KDM5C, MED12 and PTCHD1 The majority of pathogenic variants were de novo, with some inherited from mildly affected parents. Loss-of-function variants were the most common type of pathogenic variant. In silico analysis tools were used to assess the potential impact of variants on splicing and structural/functional effects of missense variants. The study highlights the challenges in variant interpretation especially in cases with atypical phenotypic manifestations. Overall, this study provides valuable insights into the genetic causes of NDDs and emphasises the importance of understanding the underlying genetic factors for accurate diagnosis, and intervention development in neurodevelopmental conditions. © The Author(s) 2025.},

note = {Cited by: 6; All Open Access; Green Open Access; Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Paysan-Lafosse2025D523,

title = {The Pfam protein families database: Embracing AI/ML},

author = {Typhaine Paysan-Lafosse and Antonina Andreeva and Matthias Blum and Sara Rocio Chuguransky and Tiago Grego and Beatriz Lazaro Pinto and Gustavo A Salazar and Maxwell L Bileschi and Felipe Llinares-López and Laetitia Meng-Papaxanthos and Lucy J Colwell and Nick V Grishin and R. Dustin Schaeffer and Damiano Clementel and Silvio C. E Tosatto and Erik Sonnhammer and Valerie Wood and Alex Bateman},

url = {https://www.scopus.com/pages/publications/85214397377?origin=resultslist},

doi = {10.1093/nar/gkae997},

issn = {03051048},

year  = {2025},

date = {2025-01-01},

journal = {Nucleic Acids Research},

volume = {53},

number = {D1},

pages = {D523 - D534},

publisher = {Oxford University Press},

abstract = {The Pfam protein families database is a comprehensive collection of protein domains and families used for genome annotation and protein structure and function analysis (https://www.ebi.ac.uk/interpro/). This update describes major developments in Pfam since 2020, including decommissioning the Pfam website and integration with InterPro, harmonization with the ECOD structural classification, and expanded curation of metagenomic, microprotein and repeat-containing families. We highlight how AlphaFold structure predictions are being leveraged to refine domain boundaries and identify new domains. New families discovered through large-scale sequence similarity analysis of AlphaFold models are described. We also detail the development of Pfam-N, which uses deep learning to expand family coverage, achieving an 8.8% increase in UniProtKB coverage compared to standard Pfam. We discuss plans for more frequent Pfam releases integrated with InterPro and the potential for artificial intelligence to further assist curation. Despite recent advances, many protein families remain to be classified, and Pfam continues working toward comprehensive coverage of the protein universe. © 2025 The Author(s) 2024.},

note = {Cited by: 268; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Blum2025D444,

title = {InterPro: The protein sequence classification resource in 2025},

author = {Matthias Blum and Antonina Andreeva and Laise Cavalcanti Florentino and Sara Rocio Chuguransky and Tiago Grego and Emma Hobbs and Beatriz Lazaro Pinto and Ailsa Orr and Typhaine Paysan-Lafosse and Irina Ponamareva and Gustavo A Salazar and Nicola Bordin and Peer Bork and Alan Bridge and Lucy Colwell and Julian Gough and Daniel H Haft and Ivica Letunic and Felipe Llinares-López and Aron Marchler-Bauer and Laetitia Meng-Papaxanthos and Huaiyu Mi and Darren A Natale and Christine A Orengo and Arun P Pandurangan and Damiano Piovesan and Catherine Rivoire and Christian J. A Sigrist and Narmada Thanki and Françoise Thibaud-Nissen and Paul D Thomas and Silvio C. E Tosatto and Cathy H Wu and Alex Bateman},

url = {https://www.scopus.com/pages/publications/85214359849?origin=resultslist},

doi = {10.1093/nar/gkae1082},

issn = {03051048},

year  = {2025},

date = {2025-01-01},

journal = {Nucleic Acids Research},

volume = {53},

number = {D1},

pages = {D444 - D456},

publisher = {Oxford University Press},

abstract = {InterPro (https://www.ebi.ac.uk/interpro) is a freely accessible resource for the classification of protein sequences into families. It integrates predictive models, known as signatures, from multiple member databases to classify sequences into families and predict the presence of domains and significant sites. The InterPro database provides annotations for over 200 million sequences, ensuring extensive coverage of UniProtKB, the standard repository of protein sequences, and includes mappings to several other major resources, such as Gene Ontology (GO), Protein Data Bank in Europe (PDBe) and the AlphaFold Protein Structure Database. In this publication, we report on the status of InterPro (version 101.0), detailing new developments in the database, associated web interface and software. Notable updates include the increased integration of structures predicted by AlphaFold and the enhanced description of protein families using artificial intelligence. Over the past two years, more than 5000 new InterPro entries have been created. The InterPro website now offers access to 85 000 protein families and domains from its member databases and serves as a long-Term archive for retired databases. InterPro data, software and tools are freely available. © 2025 The Author(s) 2024.},

note = {Cited by: 831; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Aspromonte2025227,

title = {CAGI6 ID panel challenge: assessment of phenotype and variant predictions in 415 children with neurodevelopmental disorders (NDDs)},

author = {Maria Cristina Aspromonte and Alessio Del Conte and Shaowen Zhu and Wuwei Tan and Yang Shen and Yexian Zhang and Qi Li and Maggie Haitian Wang and Giulia Babbi and Samuele Bovo and Pier Luigi Martelli and Rita Casadio and Azza Althagafi and Sumyyah Toonsi and Maxat Kulmanov and Robert Hoehndorf and Panagiotis Katsonis and Amanda Williams and Olivier Lichtarge and Su Xian and Wesley Surento and Vikas Pejaver and Sean D. Mooney and Uma Sunderam and Rajgopal Srinivasan and Alessandra Murgia and Damiano Piovesan and Silvio C. E. Tosatto and Emanuela Leonardi},

url = {https://www.scopus.com/pages/publications/85217180047?origin=resultslist},

doi = {10.1007/s00439-024-02722-w},

issn = {03406717},

year  = {2025},

date = {2025-01-01},

journal = {Human Genetics},

volume = {144},

number = {2},

pages = {227 - 242},

publisher = {Springer Science and Business Media Deutschland GmbH},

abstract = {The Genetics of Neurodevelopmental Disorders Lab in Padua provided a new intellectual disability (ID) Panel challenge for computational methods to predict patient phenotypes and their causal variants in the context of the Critical Assessment of the Genome Interpretation, 6th edition (CAGI6). Eight research teams submitted a total of 30 models to predict phenotypes based on the sequences of 74 genes (VCF format) in 415 pediatric patients affected by Neurodevelopmental Disorders (NDDs). NDDs are clinically and genetically heterogeneous conditions, with onset in infant age. Here, we assess the ability and accuracy of computational methods to predict comorbid phenotypes based on clinical features described in each patient and their causal variants. We also evaluated predictions for possible genetic causes in patients without a clear genetic diagnosis. Like the previous ID Panel challenge in CAGI5, seven clinical features (ID, ASD, ataxia, epilepsy, microcephaly, macrocephaly, hypotonia), and variants (Pathogenic/Likely Pathogenic, Variants of Uncertain Significance and Risk Factors) were provided. The phenotypic traits and variant data of 150 patients from the CAGI5 ID Panel Challenge were provided as training set for predictors. The CAGI6 challenge confirms CAGI5 results that predicting phenotypes from gene panel data is highly challenging, with AUC values close to random, and no method able to predict relevant variants with both high accuracy and precision. However, a significant improvement is noted for the best method, with recall increasing from 66% to 82%. Several groups also successfully predicted difficult-to-detect variants, emphasizing the importance of variants initially excluded by the Padua NDD Lab. © The Author(s) 2025.},

note = {Cited by: 3; All Open Access; Green Open Access; Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Clementel2025D575,

title = {RepeatsDB in 2025: expanding annotations of structured tandem repeats proteins on AlphaFoldDB},

author = {Damiano Clementel and Paula Nazarena Arrías and Soroush Mozaffari and Zarifa Osmanli and Ximena Aixa Castro and RepeatsDB Curators and Carlo Ferrari and Andrey V. Kajava and Silvio C. E. Tosatto and Alexander Miguel Monzon},

url = {https://www.scopus.com/pages/publications/85211995276?origin=resultslist},

doi = {10.1093/nar/gkae965},

issn = {03051048},

year  = {2025},

date = {2025-01-01},

journal = {Nucleic Acids Research},

volume = {53},

number = {D1},

pages = {D575 - D581},

publisher = {Oxford University Press},

abstract = {RepeatsDB (URL: https://repeatsdb.org) stands as a key resource for the classification and annotation of Structured Tandem Repeat Proteins (STRPs), incorporating data from both the Protein Data Bank (PDB) and AlphaFoldDB. This latest release features substantial advancements, including annotations for over 34 000 unique protein sequences from >2000 organisms, representing a fifteenfold increase in coverage. Leveraging state-of-the-art structural alignment tools, RepeatsDB now offers faster and more precise detection of STRPs across both experimental and predicted structures. Key improvements also include a redesigned user interface and enhanced web server, providing an intuitive browsing experience with improved data searchability and accessibility. A new statistics page allows users to explore database metrics based on repeat classifications, while API enhancements support scalability to manage the growing volume of data. These advancements not only refine the understanding of STRPs but also streamline annotation processes, further strengthening RepeatsDB’s role in advancing our understanding of STRP functions. © The Author(s) 2024. Published by Oxford University Press on behalf of Nucleic Acids Research.},

note = {Cited by: 15; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Cesaro2025,

title = {Comprehensive Analysis of the Putative Substratome of FAM20C, the Master Serine Kinase of the Secretory Pathway},

author = {Luca Cesaro and Francesca Noventa and Trinidad De Los Angeles Cordero and Barbara Molon and Valentina Bosello Travain and Maria Cristina Aspromonte and Mauro Salvi},

url = {https://www.scopus.com/pages/publications/105022934716?origin=resultslist},

doi = {10.3390/biom15111582},

issn = {2218273X},

year  = {2025},

date = {2025-01-01},

journal = {Biomolecules},

volume = {15},

number = {11},

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

abstract = {FAM20C, previously known as Golgi casein kinase (GCK), is a serine/threonine kinase localized to the Golgi apparatus and classified within the acidophilic kinase family. Its phosphorylation motif is characterized by a glutamic acid residue at the +2 position relative to the target site. Before its molecular identity was established, analysis of a limited number of phosphosites in secreted proteins showed that around 70% matched the GCK consensus sequence, suggesting that GCK is the principal kinase for secreted proteins. Following the identification of GCK as FAM20C, the generation of FAM20C knockout cell lines and phosphoproteomic data confirmed its role: approximately 80% of serine/threonine phosphosites in the secretome of two different human cell lines were shown to depend on FAM20C. In this study, comparative analysis of in vitro phosphorylation datasets from a broad panel of recombinant Ser/Thr kinases confirmed that the FAM20C consensus sequence is distinct from those of other acidophilic kinases. Examination of experimentally identified human phosphosites within the secretory pathway revealed strong conservation of the FAM20C consensus, firmly establishing this enzyme as the master Ser kinase of the entire pathway. From this dataset, we defined the putative FAM20C substratome, comprising 443 phosphosites across 256 proteins, ~77% of which had not been previously linked to FAM20C. This represents the most extensive FAM20C substratome to date and a valuable resource for functional studies. Notably, enrichment analysis highlights strong links between FAM20C and major extracellular pathways, including collagen fibril organization, complement activation, and blood coagulation, underscoring an underappreciated role for this kinase in regulating hemostasis and innate immunity. © 2025 by the authors.},

note = {Cited by: 2; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Pradelli2025,

title = {Mathematical modeling and simulation of tumor-induced angiogenesis in retinal hemangioblastoma},

author = {Franco Pradelli and Giovanni Minervini and Pradeep Venkatesh and Shorya Azad and Hector Gomez and Silvio C. E. Tosatto},

url = {https://www.scopus.com/pages/publications/105018034228?origin=resultslist},

doi = {10.1371/journal.pcbi.1012799},

issn = {1553734X},

year  = {2025},

date = {2025-01-01},

journal = {PLOS Computational Biology},

volume = {21},

number = {9},

publisher = {Public Library of Science},

abstract = {Retinal Hemangioblastoma (RH) is the most frequent manifestation of the von Hippel-Lindau syndrome (VHL), a rare disease associated with the germline mutation of the von Hippel-Lindau protein (pVHL). An emblematic feature of RH is the high vascularity, which is explained by the overexpression of angiogenic factors (AFs) arising from the pVHL impairment. The introduction of Optical Coherence Tomography Angiography (OCTA) allowed observing this feature with exceptional detail. Here, we combine OCTA images and a mechanistic model to investigate tumor growth and vascular development in a patient-specific way. We derived our model from the agreed pathology for RH and focused on the earliest stages of tumor-induced angiogenesis. Our simulations closely resemble the medical images, supporting the capability of our model to simulate vascular patterning in actual patients. Our results also suggest that angiogenesis in RH occurs upon reaching a critical dimension (around 200 μm), followed by the rapid formation of stable vascular networks. These findings open a new perspective on the crucial role of time in antiangiogenic therapy in RH, which has resulted in ineffective control. Indeed, it might be that when RH is diagnosed, angiogenesis is already too advanced to be effectively targeted with any effective means. Moreover, our simulations suggest that vascularization in RH is not a continuous process but an inconstant development with long, stable phases and rapid episodes of vascular sprouting. Copyright: © 2025 Pradelli et al. This is an open access article distributed under the terms of the Creative Commons Attribution License},

note = {Cited by: 1; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Bellanda2024,

title = {A PDZ scaffolding/CaM-mediated pathway in Cryptochrome signaling},

author = {Massimo Bellanda and Milena Damulewicz and Barbara Zambelli and Elisa Costanzi and Francesco Gregoris and Stefano Mammi and Silvio C. E. Tosatto and Rodolfo Costa and Giovanni Minervini and Gabriella M. Mazzotta},

url = {https://www.scopus.com/pages/publications/85185346556?origin=resultslist},

doi = {10.1002/pro.4914},

issn = {09618368},

year  = {2024},

date = {2024-01-01},

journal = {Protein Science},

volume = {33},

number = {3},

publisher = {John Wiley and Sons Inc},

abstract = {Cryptochromes are cardinal constituents of the circadian clock, which orchestrates daily physiological rhythms in living organisms. A growing body of evidence points to their participation in pathways that have not traditionally been associated with circadian clock regulation, implying that cryptochromes may be subject to modulation by multiple signaling mechanisms. In this study, we demonstrate that human CRY2 (hCRY2) forms a complex with the large, modular scaffolding protein known as Multi-PDZ Domain Protein 1 (MUPP1). This interaction is facilitated by the calcium-binding protein Calmodulin (CaM) in a calcium-dependent manner. Our findings suggest a novel cooperative mechanism for the regulation of mammalian cryptochromes, mediated by calcium ions (Ca^{2+}) and CaM. We propose that this Ca^{2+}/CaM-mediated signaling pathway may be an evolutionarily conserved mechanism that has been maintained from Drosophila to mammals, most likely in relation to its potential role in the broader context of cryptochrome function and regulation. Further, the understanding of cryptochrome interactions with other proteins and signaling pathways could lead to a better definition of its role within the intricate network of molecular interactions that govern circadian rhythms. © 2024 The Protein Society.},

note = {Cited by: 3; All Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{DelConte2024W306,

title = {RING 4.0: Faster residue interaction networks with novel interaction types across over 35,000 different chemical structures},

author = {Alessio Del Conte and Giorgia F Camagni and Damiano Clementel and Giovanni Minervini and Alexander Miguel Monzon and Carlo Ferrari and Damiano Piovesan and Silvio C. E Tosatto},

url = {https://www.scopus.com/pages/publications/85197788039?origin=resultslist},

doi = {10.1093/nar/gkae337},

issn = {03051048},

year  = {2024},

date = {2024-01-01},

journal = {Nucleic Acids Research},

volume = {52},

number = {W1},

pages = {W306 - W312},

publisher = {Oxford University Press},

abstract = {Residue interaction networks (RINs) are a valuable approach for representing contacts in protein structures. RINs have been widely used in various research areas, including the analysis of mutation effects, domain-domain communication, catalytic activity, and molecular dynamics simulations. The RING server is a powerful tool to calculate non-covalent molecular interactions based on geometrical parameters, providing high-quality and reliable results. Here, we introduce RING 4.0, which includes significant enhancements for identifying both covalent and non-covalent bonds in protein structures. It now encompasses seven different interaction types, with the addition of π-hydrogen, halogen bonds and metal ion coordination sites. The definitions of all available bond types have also been refined and RING can now process the complete PDB chemical component dictionary (over 35000 different molecules) which provides atom names and covalent connectivity information for all known ligands. Optimization of the software has improved execution time by an order of magnitude. The RING web server has been redesigned to provide a more engaging and interactive user experience, incorporating new visualization tools. Users can now visualize all types of interactions simultaneously in the structure viewer and network component. The web server, including extensive help and tutorials, is available from URL: https://ring.biocomputingup.it/. © 2024 The Author(s). Published by Oxford University Press on behalf of Nucleic Acids Research.},

note = {Cited by: 103; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Gregoris2024,

title = {In Silico Exploration of AHR-HIF Pathway Interplay: Implications for Therapeutic Targeting in ccRCC},

author = {Francesco Gregoris and Giovanni Minervini and Silvio C. E. Tosatto},

url = {https://www.scopus.com/pages/publications/85205114282?origin=resultslist},

doi = {10.3390/genes15091167},

issn = {20734425},

year  = {2024},

date = {2024-01-01},

journal = {Genes},

volume = {15},

number = {9},

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

abstract = {The oxygen-sensing pathway is a crucial regulatory circuit that defines cellular conditions and is extensively exploited in cancer development. Pathogenic mutations in the von Hippel–Lindau (VHL) tumour suppressor impair its role as a master regulator of hypoxia-inducible factors (HIFs), leading to constitutive HIF activation and uncontrolled angiogenesis, increasing the risk of developing clear cell renal cell carcinoma (ccRCC). HIF hyperactivation can sequester HIF-1β, preventing the aryl hydrocarbon receptor (AHR) from correctly activating gene expression in response to endogenous and exogenous ligands such as TCDD (dioxins). In this study, we used protein–protein interaction networks and gene expression profiling to characterize the impact of VHL loss on AHR activity. Our findings reveal specific expression patterns of AHR interactors following exposure to 2,3,7,8-tetrachlorodibenzo-p-dioxin (TCDD) and in ccRCC. We identified several AHR interactors significantly associated with poor survival rates in ccRCC patients. Notably, the upregulation of the androgen receptor (AR) and retinoblastoma-associated protein (RB1) by TCDD, coupled with their respective downregulation in ccRCC and association with poor survival rates, suggests novel therapeutic targets. The strategic activation of the AHR via selective AHR modulators (SAhRMs) could stimulate its anticancer activity, specifically targeting RB1 and AR to reduce cell cycle progression and metastasis formation in ccRCC. Our study provides comprehensive insights into the complex interplay between the AHR and HIF pathways in ccRCC pathogenesis, offering novel strategies for targeted therapeutic interventions. © 2024 by the authors.},

note = {Cited by: 5; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Aspromonte2024D434,

title = {DisProt in 2024: improving function annotation of intrinsically disordered proteins},

author = {Maria Cristina Aspromonte and Maria Victoria Nugnes and Federica Quaglia and Adel Bouharoua and Silvio C. E. Tosatto and Damiano Piovesan and Vasileios Sagris and Vasilis J. Promponas and Anastasia Chasapi and Erzsébet Fichó and Galo E. Balatti and Gustavo Parisi and Martín González Buitrón and Gabor Erdos and Matyas Pajkos and Zsuzsanna Dosztányi and Laszlo Dobson and Alessio Del Conte and Damiano Clementel and Edoardo Salladini and Emanuela Leonardi and Fatemeh Kordevani and Hamidreza Ghafouri and Luiggi G. Tenorio Ku and Alexander Miguel Monzon and Carlo Ferrari and Zsófia Kálmán and Juliet F. Nilsson and Jaime Santos and Carlos Pintado-Grima and Salvador Ventura and Veronika Ács and Rita Pancsa and Mariane Goncalves Kulik and Miguel A. Andrade-Navarro and Pedro José Barbosa Pereira and Sonia Longhi and Philippe Le Mercier and Julian Bergier and Peter Tompa and Tamas Lazar},

url = {https://www.scopus.com/pages/publications/85176208048?origin=resultslist},

doi = {10.1093/nar/gkad928},

issn = {03051048},

year  = {2024},

date = {2024-01-01},

journal = {Nucleic Acids Research},

volume = {52},

number = {D1},

pages = {D434 - D441},

publisher = {Oxford University Press},

abstract = {DisProt (URL: https://disprot.org) is the gold standard database for intrinsically disordered proteins and regions, providing valuable information about their functions. The latest version of DisProt brings significant advancements, including a broader representation of functions and an enhanced curation process. These improvements aim to increase both the quality of annotations and their coverage at the sequence level. Higher coverage has been achieved by adopting additional evidence codes. Quality of annotations has been improved by systematically applying Minimum Information About Disorder Experiments (MIADE) principles and reporting all the details of the experimental setup that could potentially influence the structural state of a protein. The DisProt database now includes new thematic datasets and has expanded the adoption of Gene Ontology terms, resulting in an extensive functional repertoire which is automatically propagated to UniProtKB. Finally, we show that DisProt’s curated annotations strongly correlate with disorder predictions inferred from AlphaFold2 pLDDT (predicted Local Distance Difference Test) confidence scores. This comparison highlights the utility of DisProt in explaining apparent uncertainty of certain well-defined predicted structures, which often correspond to folding-upon-binding fragments. Overall, DisProt serves as a comprehensive resource, combining experimental evidence of disorder information to enhance our understanding of intrinsically disordered proteins and their functional implications. © The Author(s) 2023. Published by Oxford University Press on behalf of Nucleic Acids Research.},

note = {Cited by: 119; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Mozaffari2024,

title = {STRPsearch: fast detection of structured tandem repeat proteins},

author = {Soroush Mozaffari and Paula Nazarena Arrías and Damiano Clementel and Damiano Piovesan and Carlo Ferrari and Silvio C. E. Tosatto and Alexander Miguel Monzon},

url = {https://www.scopus.com/pages/publications/85211966531?origin=resultslist},

doi = {10.1093/bioinformatics/btae690},

issn = {13674803},

year  = {2024},

date = {2024-01-01},

journal = {Bioinformatics},

volume = {40},

number = {12},

publisher = {Oxford University Press},

abstract = {Motivation: Structured Tandem Repeats Proteins (STRPs) constitute a subclass of tandem repeats characterized by repetitive structural motifs. These proteins exhibit distinct secondary structures that form repetitive tertiary arrangements, often resulting in large molecular assemblies. Despite highly variable sequences, STRPs can perform important and diverse biological functions, maintaining a consistent structure with a variable number of repeat units. With the advent of protein structure prediction methods, millions of 3D models of proteins are now publicly available. However, automatic detection of STRPs remains challenging with current state-of-the-art tools due to their lack of accuracy and long execution times, hindering their application on large datasets. In most cases, manual curation remains the most accurate method for detecting and classifying STRPs, making it impracticable to annotate millions of structures. Results: We introduce STRPsearch, a novel tool for the rapid identification, classification, and mapping of STRPs. Leveraging manually curated entries from RepeatsDB as the known conformational space of STRPs, STRPsearch uses the latest advances in structural alignment for a fast and accurate detection of repeated structural motifs in proteins, followed by an innovative approach to map units and insertions through the generation of TM-score profiles. STRPsearch is highly scalable, efficiently processing large datasets, and can be applied to both experimental structures and predicted models. In addition, it demonstrates superior performance compared to existing tools, offering researchers a reliable and comprehensive solution for STRP analysis across diverse proteomes. © The Author(s) 2024.},

note = {Cited by: 5; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Aspromonte2024,

title = {Searching and Using MobiDB Resource 6 to Explore Predictions and Annotations for Intrinsically Disordered Proteins},

author = {Maria Cristina Aspromonte and Federica Quaglia and Alexander Miguel Monzon and Damiano Clementel and Alessio Del Conte and Damiano Piovesan and Silvio C. E. Tosatto},

url = {https://www.scopus.com/pages/publications/85213041340?origin=resultslist},

doi = {10.1002/cpz1.70077},

issn = {26911299},

year  = {2024},

date = {2024-01-01},

journal = {Current Protocols},

volume = {4},

number = {12},

publisher = {John Wiley and Sons Inc},

abstract = {Intrinsically disordered proteins (IDPs) make up around 30% of eukaryotic proteomes and play a crucial role in cellular processes and in pathological conditions such as neurodegenerative disorders and cancers. However, IDPs exhibit dynamic conformational ensembles and are often involved in the formation of biomolecular condensates. Understanding the function of IDPs is critical to research in many areas of science. MobiDB is a unique resource that serves as a comprehensive knowledgebase of IDPs and intrinsically disordered regions (IDRs), combining disorder annotations from experimental evidence and predictions for a broad range of protein sequences. Over the past decade, MobiDB has evolved with a focus on expanding annotation coverage, standardizing annotation provenance, and enhancing database accessibility. The latest MobiDB, version 6, released in July 2024, includes significant improvements, such as the integration of AlphaFoldDB predictions and a new homology transfer pipeline that has substantially increased the number of entries with high-quality annotations. The user interface has also been updated, highlighting annotation features, clarifying the entry page, and providing an immediate overview of disorder, binding, and disorder functions information in the protein sequence. This protocol guides the user through applications of the MobiDB, including disorder prediction, curated data analysis, and exploration of interaction data. This guide covers how to perform a search in MobiDB annotations using the web interface and the MobiDB REST API for programmatic access. The protocols use a step-by-step walkthrough using the human growth hormone receptor to demonstrate MobiDB's functions for visualization and interpretation of protein disorder data. © 2024 The Author(s). Current Protocols published by Wiley Periodicals LLC. Basic Protocol 1: Searching MobiDB query formats. Basic Protocol 2: Searching MobiDB selected datasets and selected proteomes. Basic Protocol 3: Performing a search on the Statistics page in MobiDB. Support Protocol: Programmatic access with MobiDB REST API. Basic Protocol 4: Visualizing and interpreting a MobiDB Entry: The GHR use case. Current Protocols© 2024 The Author(s). Current Protocols published by Wiley Periodicals LLC.},

note = {Cited by: 0; All Open Access; Green Open Access; Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Quaglia2024,

title = {Best practices for the manual curation of intrinsically disordered proteins in DisProt},

author = {Federica Quaglia and Anastasia Chasapi and Maria Victoria Nugnes and Maria Cristina Aspromonte and Emanuela Leonardi and Damiano Piovesan and Silvio C. E. Tosatto},

url = {https://www.scopus.com/pages/publications/85188297172?origin=resultslist},

doi = {10.1093/database/baae009},

issn = {17580463},

year  = {2024},

date = {2024-01-01},

journal = {Database},

volume = {2024},

publisher = {Oxford University Press},

abstract = {The DisProt database is a resource containing manually curated data on experimentally validated intrinsically disordered proteins (IDPs) and intrinsically disordered regions (IDRs) from the literature. Developed in 2005, its primary goal was to collect structural and functional information into proteins that lack a fixed three-dimensional structure.Today, DisProt has evolved into a major repository that not only collects experimental data but also contributes to our understanding of the IDPs/IDRs roles in various biological processes, such as autophagy or the life cycle mechanisms in viruses or their involvement in diseases (such as cancer and neurodevelopmental disorders). DisProt offers detailed information on the structural states of IDPs/IDRs, including state transitions, interactions and their functions, all provided as curated annotations. One of the central activities of DisProt is the meticulous curation of experimental data from the literature. For this reason, to ensure that every expert and volunteer curator possesses the requisite knowledge for data evaluation, collection and integration, training courses and curation materials are available. However, biocuration guidelines concur on the importance of developing robust guidelines that not only provide critical information about data consistency but also ensure data acquisition.This guideline aims to provide both biocurators and external users with best practices for manually curating IDPs and IDRs in DisProt. It describes every step of the literature curation process and provides use cases of IDP curation within DisProt. © The Author(s) 2024. Published by Oxford University Press.},

note = {Cited by: 5; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{MacDonagh2024,

title = {Structured Tandem Repeats in Protein Interactions},

author = {Juan Mac Donagh and Abril Marchesini and Agostina Spiga and Maximiliano José Fallico and Paula Nazarena Arrías and Alexander Miguel Monzon and Aimilia-Christina Vagiona and Mariane Gonçalves-Kulik and Pablo Mier and Miguel A. Andrade-Navarro},

url = {https://www.scopus.com/pages/publications/85187783312?origin=resultslist},

doi = {10.3390/ijms25052994},

issn = {16616596},

year  = {2024},

date = {2024-01-01},

journal = {International Journal of Molecular Sciences},

volume = {25},

number = {5},

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

abstract = {Tandem repeats (TRs) in protein sequences are consecutive, highly similar sequence motifs. Some types of TRs fold into structural units that pack together in ensembles, forming either an (open) elongated domain or a (closed) propeller, where the last unit of the ensemble packs against the first one. Here, we examine TR proteins (TRPs) to see how their sequence, structure, and evolutionary properties favor them for a function as mediators of protein interactions. Our observations suggest that TRPs bind other proteins using large, structured surfaces like globular domains; in particular, open-structured TR ensembles are favored by flexible termini and the possibility to tightly coil against their targets. While, intuitively, open ensembles of TRs seem prone to evolve due to their potential to accommodate insertions and deletions of units, these evolutionary events are unexpectedly rare, suggesting that they are advantageous for the emergence of the ancestral sequence but are early fixed. We hypothesize that their flexibility makes it easier for further proteins to adapt to interact with them, which would explain their large number of protein interactions. We provide insight into the properties of open TR ensembles, which make them scaffolds for alternative protein complexes to organize genes, RNA and proteins. © 2024 by the authors.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Attafi2024,

title = {DOME Registry: implementing community-wide recommendations for reporting supervised machine learning in biology},

author = {Omar Abdelghani Attafi and Damiano Clementel and Konstantinos Kyritsis and Emidio Capriotti and Gavin Farrell and Styliani-Christina Fragkouli and Leyla Jael Castro and András Hatos and Tom Lenaerts and Stanislav Mazurenko and Soroush Mozaffari and Franco Pradelli and Patrick Ruch and Castrense Savojardo and Paola Turina and Federico Zambelli and Damiano Piovesan and Alexander Miguel Monzon and Fotis Psomopoulos and Silvio C. E. Tosatto},

url = {https://www.scopus.com/pages/publications/85212459848?origin=resultslist},

doi = {10.1093/gigascience/giae094},

issn = {2047217X},

year  = {2024},

date = {2024-01-01},

journal = {GigaScience},

volume = {13},

publisher = {Oxford University Press},

abstract = {Supervised machine learning (ML) is used extensively in biology and deserves closer scrutiny. The Data Optimization Model Evaluation (DOME) recommendations aim to enhance the validation and reproducibility of ML research by establishing standards for key aspects such as data handling and processing, optimization, evaluation, and model interpretability. The recommendations help to ensure that key details are reported transparently by providing a structured set of questions. Here, we introduce the DOME registry (URL: registry.dome-ml.org), a database that allows scientists to manage and access comprehensive DOME-related information on published ML studies. The registry uses external resources like ORCID, APICURON, and the Data Stewardship Wizard to streamline the annotation process and ensure comprehensive documentation. By assigning unique identifiers and DOME scores to publications, the registry fosters a standardized evaluation of ML methods. Future plans include continuing to grow the registry through community curation, improving the DOME score definition and encouraging publishers to adopt DOME standards, and promoting transparency and reproducibility of ML in the life sciences. © The Author(s) 2024. Published by Oxford University Press GigaScience.},

note = {Cited by: 5; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Piovesan2024,

title = {CAFA-evaluator: a Python tool for benchmarking ontological classification methods},

author = {Damiano Piovesan and Davide Zago and Parnal Joshi and M. Clara De Paolis Kaluza and Mahta Mehdiabadi and Rashika Ramola and Alexander Miguel Monzon and Walter Reade and Iddo Friedberg and Predrag Radivojac and Silvio C. E. Tosatto},

url = {https://www.scopus.com/pages/publications/85188993912?origin=resultslist},

doi = {10.1093/bioadv/vbae043},

issn = {26350041},

year  = {2024},

date = {2024-01-01},

journal = {Bioinformatics Advances},

volume = {4},

number = {1},

publisher = {Oxford University Press},

abstract = {We present CAFA-evaluator, a powerful Python program designed to evaluate the performance of prediction methods on targets with hierarchical concept dependencies. It generalizes multi-label evaluation to modern ontologies where the prediction targets are drawn from a directed acyclic graph and achieves high efficiency by leveraging matrix computation and topological sorting. The program requirements include a small number of standard Python libraries, making CAFA-evaluator easy to maintain. The code replicates the Critical Assessment of protein Function Annotation (CAFA) benchmarking, which evaluates predictions of the consistent subgraphs in Gene Ontology. Owing to its reliability and accuracy, the organizers have selected CAFA-evaluator as the official CAFA evaluation software. © 2024 The Author(s). Published by Oxford University Press.},

note = {Cited by: 11; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Arrías2024,

title = {Diversity and structural-functional insights of alpha-solenoid proteins},

author = {Paula Nazarena Arrías and Zarifa Osmanli and Estefanía Peralta and Patricio Manuel Chinestrad and Alexander Miguel Monzon and Silvio C. E. Tosatto},

url = {https://www.scopus.com/pages/publications/85207813713?origin=resultslist},

doi = {10.1002/pro.5189},

issn = {09618368},

year  = {2024},

date = {2024-01-01},

journal = {Protein Science},

volume = {33},

number = {11},

publisher = {John Wiley and Sons Inc},

abstract = {Alpha-solenoids are a significant and diverse subset of structured tandem repeat proteins (STRPs) that are important in various domains of life. This review examines their structural and functional diversity and highlights their role in critical cellular processes such as signaling, apoptosis, and transcriptional regulation. Alpha-solenoids can be classified into three geometric folds: low curvature, high curvature, and corkscrew, as well as eight subfolds: ankyrin repeats; Huntingtin, elongation factor 3, protein phosphatase 2A, and target of rapamycin; armadillo repeats; tetratricopeptide repeats; pentatricopeptide repeats; Pumilio repeats; transcription activator-like; and Sel-1 and Sel-1-like repeats. These subfolds represent distinct protein families with unique structural properties and functions, highlighting the versatility of alpha-solenoids. The review also discusses their association with disease, highlighting their potential as therapeutic targets and their role in protein design. Advances in state-of-the-art structure prediction methods provide new opportunities and challenges in the functional characterization and classification of this kind of fold, emphasizing the need for continued development of methods for their identification and proper data curation and deposition in the main databases. © 2024 The Author(s). Protein Science published by Wiley Periodicals LLC on behalf of The Protein Society.},

note = {Cited by: 9; All Open Access; Green Open Access; Hybrid Gold Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ghafouri2024D536,

title = {PED in 2024: improving the community deposition of structural ensembles for intrinsically disordered proteins},

author = {Hamidreza Ghafouri and Tamas Lazar and Alessio Del Conte and Luiggi G. Tenorio Ku and Peter Tompa and Silvio C. E. Tosatto and Alexander Miguel Monzon and Maria C. Aspromonte and Pau Bernadó and Belén Chaves-Arquero and Lucia Beatriz Chemes and Damiano Clementel and Tiago N. Cordeiro and Carlos A. Elena-Real and Michael Feig and Isabella C. Felli and Carlo Ferrari and Julie D. Forman-Kay and Tiago Gomes and Frank Gondelaud and Claudiu C. Gradinaru and Tâp Ha-Duong and Teresa Head-Gordon and Pétur O. Heidarsson and Giacomo Janson and Gunnar Jeschke and Emanuela Leonardi and Zi Hao Liu and Sonia Longhi and Xamuel L. Lund and Maria J. Macias and Pau Martin-Malpartida and Davide Mercadante and Assia Mouhand and Gabor Nagy and María Victoria Nugnes and José Manuel Pérez-Cañadillas and Giulia Pesce and Roberta Pierattelli and Damiano Piovesan and Federica Quaglia and Sylvie Ricard-Blum and Paul Robustelli and Amin Sagar and Edoardo Salladini and Lucile Sénicourt and Nathalie Sibille and João M. C. Teixeira and Thomas E. Tsangaris and Mihaly Varadi},

url = {https://www.scopus.com/pages/publications/85181761325?origin=resultslist},

doi = {10.1093/nar/gkad947},

issn = {03051048},

year  = {2024},

date = {2024-01-01},

journal = {Nucleic Acids Research},

volume = {52},

number = {D1},

pages = {D536 - D544},

publisher = {Oxford University Press},

abstract = {The Protein Ensemble Database (PED) (URL: https://proteinensemble.org) is the primary resource for depositing structural ensembles of intrinsically disordered proteins. This updated version of PED reflects advancements in the field, denoting a continual expansion with a total of 461 entries and 538 ensembles, including those generated without explicit experimental data through novel machine learning (ML) techniques. With this significant increment in the number of ensembles, a few yet-unprecedented new entries entered the database, including those also determined or refined by electron paramagnetic resonance or circular dichroism data. In addition, PED was enriched with several new features, including a novel deposition service, improved user interface, new database cross-referencing options and integration with the 3D-Beacons network—all representing efforts to improve the FAIRness of the database. Foreseeably, PED will keep growing in size and expanding with new types of ensembles generated by accurate and fast ML-based generative models and coarse-grained simulations. Therefore, among future efforts, priority will be given to further develop the database to be compatible with ensembles modeled at a coarse-grained level. © The Author(s) 2023. Published by Oxford University Press on behalf of Nucleic Acids Research.},

note = {Cited by: 59; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Leonardi2023202,

title = {Expanding the genetics and phenotypic spectrum of Lysine-specific demethylase 5C (KDM5C): a report of 13 novel variants},

author = {Emanuela Leonardi and Maria Cristina Aspromonte and Denise Drongitis and Elisa Bettella and Lucia Verrillo and Roberta Polli and Meriel McEntagart and Laura Licchetta and Robertino Dilena and Stefano D’Arrigo and Claudia Ciaccio and Silvia Esposito and Vincenzo Leuzzi and Annalaura Torella and Demetrio Baldo and Fortunato Lonardo and Giulia Bonato and Serena Pellegrin and Franco Stanzial and Renata Posmyk and Ewa Kaczorowska and Miryam Carecchio and Monika Gos and Sylwia Rzońca-Niewczas and Maria Giuseppina Miano and Alessandra Murgia},

url = {https://www.scopus.com/pages/publications/85142646250?origin=resultslist},

doi = {10.1038/s41431-022-01233-4},

issn = {10184813},

year  = {2023},

date = {2023-01-01},

journal = {European Journal of Human Genetics},

volume = {31},

number = {2},

pages = {202 - 215},

publisher = {Springer Nature},

abstract = {Lysine-specific demethylase 5C (KDM5C) has been identified as an important chromatin remodeling gene, contributing to X-linked neurodevelopmental disorders (NDDs). The KDM5C gene, located in the Xp22 chromosomal region, encodes the H3K4me3-me2 eraser involved in neuronal plasticity and dendritic growth. Here we report 30 individuals carrying 13 novel and one previously identified KDM5C variants. Our cohort includes the first reported case of somatic mosaicism in a male carrying a KDM5C nucleotide substitution, and a dual molecular finding in a female carrying a homozygous truncating FUCA1 alteration together with a de novo KDM5C variant. With the use of next generation sequencing strategies, we detected 1 frameshift, 1 stop codon, 2 splice-site and 10 missense variants, which pathogenic role was carefully investigated by a thorough bioinformatic analysis. The pattern of X-chromosome inactivation was found to have an impact on KDM5C phenotypic expression in females of our cohort. The affected individuals of our case series manifested a neurodevelopmental condition characterized by psychomotor delay, intellectual disability with speech disorders, and behavioral features with particular disturbed sleep pattern; other observed clinical manifestations were short stature, obesity and hypertrichosis. Collectively, these findings expand the current knowledge about the pathogenic mechanisms leading to dysfunction of this important chromatin remodeling gene and contribute to a refinement of the KDM5C phenotypic spectrum. © 2022, This is a U.S. Government work and not under copyright protection in the US; foreign copyright protection may apply.},

note = {Cited by: 14; All Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Paysan-Lafosse2023D418,

title = {InterPro in 2022},

author = {Typhaine Paysan-Lafosse and Matthias Blum and Sara Chuguransky and Tiago Grego and Beatriz Lázaro Pinto and Gustavo A. Salazar and Maxwell L. Bileschi and Peer Bork and Alan Bridge and Lucy Colwell and Julian Gough and Daniel H. Haft and Ivica Letunić and Aron Marchler-Bauer and Huaiyu Mi and Darren A. Natale and Christine A. Orengo and Arun P. Pandurangan and Catherine Rivoire and Christian J. A. Sigrist and Ian Sillitoe and Narmada Thanki and Paul D. Thomas and Silvio C. E. Tosatto and Cathy H. Wu and Alex Bateman},

url = {https://www.scopus.com/pages/publications/85159577204?origin=resultslist},

doi = {10.1093/nar/gkac993},

issn = {03051048},

year  = {2023},

date = {2023-01-01},

journal = {Nucleic Acids Research},

volume = {51},

number = {D1},

pages = {D418 - D427},

publisher = {Oxford University Press},

abstract = {The InterPro database (https://www.ebi.ac.uk/ interpro/) provides an integrative classification of protein sequences into families, and identifies functionally important domains and conserved sites. Here, we report recent developments with InterPro (version 90.0) and its associated software, including updates to data content and to the website. These developments extend and enrich the information provided by InterPro, and provide a more user friendly access to the data. Additionally, we have worked on adding Pfam website features to the InterPro website, as the Pfam website will be retired in late 2022. We also show that InterPro’s sequence coverage has kept pace with the growth of UniProtKB. Moreover, we report the development of a card game as a method of engaging the non-scientific community. Finally, we discuss the benefits and challenges brought by the use of artificial intelligence for protein structure prediction. © The Author(s) 2022. Published by Oxford University Press on behalf of Nucleic Acids Research.},

note = {Cited by: 2046; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{DelConte2023,

title = {RING-PyMOL: residue interaction networks of structural ensembles and molecular dynamics},

author = {Alessio Del Conte and Alexander Miguel Monzon and Damiano Clementel and Giorgia F. Camagni and Giovanni Minervini and Silvio C. E. Tosatto and Damiano Piovesan},

url = {https://www.scopus.com/pages/publications/85159553803?origin=resultslist},

doi = {10.1093/bioinformatics/btad260},

issn = {13674803},

year  = {2023},

date = {2023-01-01},

journal = {Bioinformatics},

volume = {39},

number = {5},

publisher = {Oxford University Press},

abstract = {RING-PyMOL is a plugin for PyMOL providing a set of analysis tools for structural ensembles and molecular dynamic simulations. RING-PyMOL combines residue interaction networks, as provided by the RING software, with structural clustering to enhance the analysis and visualization of the conformational complexity. It combines precise calculation of non-covalent interactions with the power of PyMOL to manipulate and visualize protein structures. The plugin identifies and highlights correlating contacts and interaction patterns that can explain structural allostery, active sites, and structural heterogeneity connected with molecular function. It is easy to use and extremely fast, processing and rendering hundreds of models and long trajectories in seconds. RING-PyMOL generates a number of interactive plots and output files for use with external tools. The underlying RING software has been improved extensively. It is 10 times faster, can process mmCIF files and it identifies typed interactions also for nucleic acids. © The Author(s) 2023. Published by Oxford University Press.},

note = {Cited by: 32; All Open Access; Gold Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Vos2023351,

title = {DNA methylation episignatures are sensitive and specific biomarkers for detection of patients with KAT6A/KAT6B variants},

author = {Niels Vos and Jack Reilly and Mariet W Elting and Philippe M Campeau and David Coman and Zornitza Stark and Tiong Yang Tan and David J Amor and Simran Kaur and Miya Stjohn and Angela T Morgan and Benjamin A Kamien and Chirag Patel and Matthew L Tedder and Giuseppe Merla and Paolo Prontera and Marco Castori and Kai Muru and Felicity Collins and John Christodoulou and Janine Smith and Bruria Ben Zeev and Alessandra Murgia and Emanuela Leonardi and Natacha Esber and Antonio Martinez-Monseny and Didac Casas-Alba and Matthew Wallis and Marcel Mannens and Michael A Levy and Raissa Relator and Marielle Alders and Bekim Sadikovic},

url = {https://www.scopus.com/pages/publications/85160965403?origin=resultslist},

doi = {10.2217/epi-2023-0079},

issn = {17501911},

year  = {2023},

date = {2023-01-01},

journal = {Epigenomics},

volume = {15},

number = {6},

pages = {351 - 367},

publisher = {Newlands Press Ltd},

abstract = {Accurate diagnosis for patients living with neurodevelopmental disorders is often met with numerous challenges, related to the ambiguity of findings and lack of specificity in genetic variants leading to pathology. Genome-wide DNA methylation analysis has been used to develop highly sensitive and specific 'episignatures' as biomarkers capable of differentiating and classifying complex neurodevelopmental disorders. In this study we describe distinct episignatures for KAT6A syndrome, caused by pathogenic variants in the lysine acetyltransferase A gene (KAT6A), and for the two neurodevelopmental disorders associated with lysine acetyl transferase B (KAT6B). We demonstrate the ability of our models to differentiate between highly overlapping episignatures, increasing the ability to effectively identify and diagnose these conditions. © 2023 Future Medicine Ltd.},

note = {Cited by: 8; All Open Access; Green Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}