@article{SCOPUS_ID:105030612709,

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/record/display.uri?eid=2-s2.0-105030612709&origin=inward},

doi = {10.1093/bioadv/vbag028},

year  = {2026},

date = {2026-01-01},

journal = {Bioinformatics Advances},

volume = {6},

number = {1},

publisher = {Oxford University Press},

abstract = {© The Author(s) 2026. Published by Oxford University Press.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105014118997,

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

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

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

doi = {10.1002/prot.70045},

year  = {2026},

date = {2026-01-01},

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

volume = {94},

number = {1},

pages = {414-424},

publisher = {John Wiley and Sons Inc},

abstract = {© 2025 The Author(s). PROTEINS: Structure, Function, and Bioinformatics published by Wiley Periodicals LLC.Intrinsic disorder (ID) in proteins is a complex phenomenon, encompassing a continuum from entirely disordered regions to structured domains with flexible segments. The absence of a ground truth for all forms of disorder, combined with the possibility of structural transitions between ordered and disordered states under specific conditions, makes accurate prediction of ID especially challenging. The Critical Assessment of Protein Intrinsic Disorder (CAID) evaluates ID prediction methods using diverse benchmarks derived from DisProt, a manually curated database of experimentally validated annotations. This paper presents findings from the third round (CAID3), in which 24 new methods were assessed along with the predictors from previous rounds. Compared to CAID2, the top-performing methods in CAID3 demonstrated significant gains in average precision: over 31% improvement in predicting linker regions, and 15% in disorder prediction. This round introduces a new binding sub-challenge focused on identifying binding regions within known IDR boundaries. The results indicate that this task remains challenging, highlighting the potential for improvement. The top-performing methods in CAID3 are mostly new and commonly used embeddings from protein language models (pLMs), underscoring the growing impact of pLMs in tackling the complexities of disordered proteins and advancing ID prediction.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105027149057,

title = {Desmoplakin Cardiomyopathy: Gene Dose-Dependent Myocardial Remodeling, Arrhythmias, and Premature Death},

author = {Anna Guazzo and Induja Perumal Vanaja and Anna Di Bona and Riccardo Bariani and Maria C. Disalvo and Mattia Albiero and Nicolas Kuperwasser and Pierre David and Rudy Celeghin and Vittoria Di Mauro and Arianna Scalco and María López-Moreno and Marco Cason and Monica De Gaspari and Mila Della Barbera and Stefania Rizzo and Laura Ventura and Domenico Corrado and Barbara Bauce and Giuseppe Zanotti and Gaetano Thiene and Kalliopi Pilichou and Giovanni Minervini and José Maria Perez Pomares and Mario Pende and Cristina Basso and Marco Mongillo and Tania Zaglia},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105027149057&origin=inward},

doi = {10.1016/j.jacep.2025.10.031},

year  = {2026},

date = {2026-01-01},

journal = {JACC: Clinical Electrophysiology},

publisher = {Elsevier Inc.},

abstract = {© 2025 The AuthorsBackground: Pathogenic variants in DSP cause arrhythmogenic cardiomyopathies with variable inheritance pattern. Recessive mutations underlie syndromic forms such as Carvajal syndrome, whereas dominant variants cause DSP cardiomyopathy, a left-dominant arrhythmogenic cardiomyopathy characterized by early electrical instability, inflammation, and fibrosis. The mechanisms driving these phenotypes remain poorly defined. Objectives: The authors sought to create a clinically relevant platform to investigate disease mechanisms in Desmoplakin Cardiomyopathy. Methods: We generated a knock-in mouse carrying the DspS311A mutation, orthologous to the human pathogenic hotspot S299R. Heterozygous and homozygous mice (n ≥6/group) were longitudinally phenotyped by echocardiography, electrocardiographic telemetry, histology, and ultrastructural and molecular analyses. Moderate treadmill exercise was used as a physiological stressor. Outcomes included cardiac function, arrhythmias, fibrosis, apoptosis, inflammation, and desmosomal integrity. Results: Homozygous DspS311A/S311A mice developed early biventricular dysfunction with subepicardial necrosis, replacement fibrosis, myocardial inflammation, spontaneous arrhythmias, and cutaneous defects, recapitulating Carvajal syndrome. Heterozygous DspWT/S311A mice exhibited hallmarks of dominant DSP cardiomyopathy: patchy left ventricular fibrosis, apoptosis, inflammation, and electrical instability preceding systolic impairment. Desmosomal remodeling occurred in both genotypes, with connexin-43 mislocalization evident from 1 month, whereas β-catenin nuclear translocation and reduced DSP/DSG2 protein were restricted to homozygotes. Of note, spontaneous arrhythmias and electrical instability were already present in both genotypes, temporally preceding structural remodeling. Exercise accelerated apoptosis, fibrosis, arrhythmias, and premature death. Conclusions: This DspS311A knock-in model captures key aspects of recessive and dominant DSP cardiomyopathies, uniquely combining spontaneous arrhythmias, inflammation, and extracardiac features. This model provides a unique in vivo platform to dissect DSP-related arrhythmogenic mechanisms and to test therapies aimed at preventing sudden cardiac death.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105028199071,

title = {Early multimodal behavioral cues in autism: a micro-analytical exploration of actions, gestures and speech during naturalistic parent-child interactions},

author = {Mastrogiuseppe and Famà and Bruschetta and Leonardi and Campisi and Aiello and Carrozza and Ruggeri and Baieli and Campisi and Turriziani and Di Rosa and Lombardo and Tartarisco and Capirci and Pioggia and Ruta},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105028199071&origin=inward},

doi = {10.1016/j.ijchp.2026.100664},

year  = {2026},

date = {2026-01-01},

journal = {International Journal of Clinical and Health Psychology},

volume = {26},

number = {1},

publisher = {Elsevier B.V.},

abstract = {© 2026 The Author(s).Early signs of autism often emerge through distinct developmental pathways, particularly in communication, social interaction, and play. While naturalistic parent-child interactions during free play are ideal for observing spontaneous social behaviors, few autism studies have adopted this ecological and developmental approach. To address this gap, we used a fine-grained microanalytic method to examine motor, gestural, and vocal behaviors in young children, integrating machine learning to explore how combinations of these traits distinguish early autistic neurodivergence. We analyzed video recordings of 58 autistic and non-autistic children (aged 13–40 months) engaged in naturalistic parent-child play. A frame-by-frame micro-coding scheme was applied to capture actions, gestures, speech, and their multimodal integration. Clear differences emerged between neurotypical (NT) and autistic (ASC) children. NT children displayed more gestures, particularly deictic and conventional-interactive, greater gesture–gaze coordination, more functional object play, and more frequent multi-word utterances. In contrast, ASC children showed fewer deictic and conventional-interactive gestures and greater use of instrumental gestures, reduced gesture–gaze coordination, a higher reliance on vocalizations rather than words, and increased object manipulation compared to functional play. Feature selection using ANOVA F-tests identified a core set of key predictors most frequently and independently selected across folds of cross-validation: Alternate Gaze, Reaching, and Instrumental Gesture. Higher values of Alternate Gaze were associated with NT classification, while elevated frequencies of Reaching and Instrumental Gestures were linked to ASC classification. A logistic regression classifier trained on these features achieved over 85% accuracy in distinguishing the two groups. These findings underscore the value of an ecologically valid, and developmentally informed approach to identifying early behavioral markers of autism, supporting earlier recognition and the design of more personalized, strengths-based interventions.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105033505349,

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/record/display.uri?eid=2-s2.0-105033505349&origin=inward},

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

year  = {2026},

date = {2026-01-01},

journal = {Nature Protocols},

publisher = {Springer Nature},

abstract = {© Springer Nature Limited 2026.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.},

note = {Cited by: 0},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105031259193,

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

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

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

doi = {10.3390/genes17020219},

year  = {2026},

date = {2026-01-01},

journal = {Genes},

volume = {17},

number = {2},

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

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

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105029446962,

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/record/display.uri?eid=2-s2.0-105029446962&origin=inward},

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

year  = {2026},

date = {2026-01-01},

journal = {Cell Death and Disease},

volume = {17},

number = {1},

publisher = {Springer Nature},

abstract = {© The Author(s) 2026.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105026115828,

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/record/display.uri?eid=2-s2.0-105026115828&origin=inward},

doi = {10.1002/pro.70426},

year  = {2026},

date = {2026-01-01},

journal = {Protein Science},

volume = {35},

number = {1},

publisher = {John Wiley and Sons Inc},

abstract = {© 2025 The Protein Society.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105024913941,

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/record/display.uri?eid=2-s2.0-105024913941&origin=inward},

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

year  = {2026},

date = {2026-01-01},

journal = {Current Opinion in Structural Biology},

volume = {96},

publisher = {Elsevier Ltd},

abstract = {© 2025 The Author(s).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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105025600452,

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/record/display.uri?eid=2-s2.0-105025600452&origin=inward},

doi = {10.1002/pro.70427},

year  = {2026},

date = {2026-01-01},

journal = {Protein Science},

volume = {35},

number = {1},

publisher = {John Wiley and Sons Inc},

abstract = {© 2025 The Author(s). Protein Science published by Wiley Periodicals LLC on behalf of The Protein Society.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105027748200,

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

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

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

doi = {10.1093/nar/gkaf1175},

year  = {2026},

date = {2026-01-01},

journal = {Nucleic Acids Research},

volume = {54},

number = {D1},

pages = {D383-D392},

publisher = {Oxford University Press},

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

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105033513263,

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/record/display.uri?eid=2-s2.0-105033513263&origin=inward},

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

year  = {2026},

date = {2026-01-01},

journal = {Scientific data},

volume = {13},

number = {1},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105027746750,

title = {The Gene Ontology knowledgebase in 2026},

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

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

doi = {10.1093/nar/gkaf1292},

year  = {2026},

date = {2026-01-01},

journal = {Nucleic Acids Research},

volume = {54},

number = {D1},

pages = {D1779-D1792},

publisher = {Oxford University Press},

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

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105012381789,

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/record/display.uri?eid=2-s2.0-105012381789&origin=inward},

doi = {10.1093/bioinformatics/btaf395},

year  = {2025},

date = {2025-01-01},

journal = {Bioinformatics},

volume = {41},

number = {7},

publisher = {Oxford University Press},

abstract = {© 2025 The Author(s). 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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105022934716,

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/record/display.uri?eid=2-s2.0-105022934716&origin=inward},

doi = {10.3390/biom15111582},

year  = {2025},

date = {2025-01-01},

journal = {Biomolecules},

volume = {15},

number = {11},

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

abstract = {© 2025 by the authors.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, textasciitilde 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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85191992890,

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/record/display.uri?eid=2-s2.0-85191992890&origin=inward},

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

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{SCOPUS_ID:105015207644,

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/record/display.uri?eid=2-s2.0-105015207644&origin=inward},

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

year  = {2025},

date = {2025-01-01},

journal = {Trends in Biochemical Sciences},

volume = {50},

number = {12},

pages = {1072-1085},

publisher = {Elsevier Ltd},

abstract = {© 2025 The Author(s)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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105011353218,

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/record/display.uri?eid=2-s2.0-105011353218&origin=inward},

doi = {10.3389/fbinf.2025.1586744},

year  = {2025},

date = {2025-01-01},

journal = {Frontiers in Bioinformatics},

volume = {5},

publisher = {Frontiers Media SA},

abstract = {Copyright © 2025 Clementel, Del Conte, Monzon and Tosatto.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).},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105008238034,

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/record/display.uri?eid=2-s2.0-105008238034&origin=inward},

doi = {10.1093/bioadv/vbaf112},

year  = {2025},

date = {2025-01-01},

journal = {Bioinformatics Advances},

volume = {5},

number = {1},

publisher = {Oxford University Press},

abstract = {© 2025 The Author(s).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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105007010286,

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/record/display.uri?eid=2-s2.0-105007010286&origin=inward},

doi = {10.1093/bioinformatics/btaf297},

year  = {2025},

date = {2025-01-01},

journal = {Bioinformatics},

volume = {41},

number = {5},

publisher = {Oxford University Press},

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

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:86000084600,

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/record/display.uri?eid=2-s2.0-86000084600&origin=inward},

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

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 = {© The Author(s) 2025.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85217180047,

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/record/display.uri?eid=2-s2.0-85217180047&origin=inward},

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

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 Author(s) 2025.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85214397377,

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/record/display.uri?eid=2-s2.0-85214397377&origin=inward},

doi = {10.1093/nar/gkae997},

year  = {2025},

date = {2025-01-01},

journal = {Nucleic Acids Research},

volume = {53},

number = {D1},

pages = {D523-D534},

publisher = {Oxford University Press},

abstract = {© 2025 The Author(s) 2024.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.},

note = {Cited by: 124; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85214359849,

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/record/display.uri?eid=2-s2.0-85214359849&origin=inward},

doi = {10.1093/nar/gkae1082},

year  = {2025},

date = {2025-01-01},

journal = {Nucleic Acids Research},

volume = {53},

number = {D1},

pages = {D444-D456},

publisher = {Oxford University Press},

abstract = {© 2025 The Author(s) 2024.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.},

note = {Cited by: 446; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85211995276,

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/record/display.uri?eid=2-s2.0-85211995276&origin=inward},

doi = {10.1093/nar/gkae965},

year  = {2025},

date = {2025-01-01},

journal = {Nucleic Acids Research},

volume = {53},

number = {D1},

pages = {D575-D581},

publisher = {Oxford University Press},

abstract = {© The Author(s) 2024. Published by Oxford University Press on behalf of Nucleic Acids Research.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85213063415,

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/record/display.uri?eid=2-s2.0-85213063415&origin=inward},

doi = {10.1093/nar/gkae969},

year  = {2025},

date = {2025-01-01},

journal = {Nucleic Acids Research},

volume = {53},

number = {D1},

pages = {D495-D503},

publisher = {Oxford University Press},

abstract = {© The Author(s) 2024. Published by Oxford University Press on behalf of Nucleic Acids Research.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.},

note = {Cited by: 34; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105016106568,

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/record/display.uri?eid=2-s2.0-105016106568&origin=inward},

doi = {10.12688/openreseurope.20628.1},

year  = {2025},

date = {2025-01-01},

journal = {Open Research Europe},

volume = {5},

publisher = {F1000 Research Ltd},

abstract = {Copyright: © 2025 Longhi S et al.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105017879475,

title = {Mapping cryptic phosphorylation sites in the human proteome},

author = {Dino Gasparotto and Annarita Zanon and Valerio Bonaldo and Elisa Marchiori and Massimo Casagranda and Erika Di Domenico and Laura Copat and Tommaso Fortunato Asquini and Marta Rigoli and Sirio Vittorio Feltrin and Nuria Lopez Lorenzo and Graziano Lolli and Maria Pennuto and Jesùs R Requena and Omar Rota Stabelli and Giovanni Minervini and Cristian Micheletti and Giovanni Spagnolli and Pietro Faccioli and Emiliano Biasini},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105017879475&origin=inward},

doi = {10.1038/s44318-025-00567-1},

year  = {2025},

date = {2025-01-01},

journal = {EMBO Journal},

volume = {44},

number = {22},

pages = {6704-6731},

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

abstract = {© The Author(s) 2025.Advances in computational and experimental methods have revealed the existence of transient, non-native protein folding intermediates that could play roles in disparate biological processes, from regulation of protein expression to disease-relevant misfolding mechanisms. Here, we tested the possibility that specific post-translational modifications may involve residues exposed during the folding process by assessing the solvent accessibility of 87,138 post-translationally modified amino acids in the human proteome. Unexpectedly, we found that one-third of phosphorylated proteins present at least one phosphosite completely buried within the protein’s inner core. Computational and experimental analyses suggest that these cryptic phosphosites may become exposed during the folding process, where their modification could destabilize native structures and trigger protein degradation. Phylogenetic investigation also reveals that cryptic phosphosites are more conserved than surface-exposed phosphorylated residues. Finally, cross-referencing with cancer mutation databases suggests that phosphomimetic mutations in cryptic phosphosites can increase tumor fitness by inactivating specific onco-suppressors. These findings define a novel role for co-translational phosphorylation in shaping protein folding and expression, laying the groundwork for exploring the implications of cryptic phosphorylation in health and disease.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105023126850,

title = {RYR1-Related Myopathies Involve More than Calcium Dysregulation: Insights from Transcriptomic Profiling},

author = {Daniele Sabbatini and Domenico Gorgoglione and Giovanni Minervini and Aurora Fusto and Matteo Suman and Chiara Romualdi and Sara Vianello and Giuliana Capece and Gianni Sorarù and Caterina Marchioretti and Maria Pennuto and Luca Vedovelli and Gyorgy Szabadkai and Luca Bello and Elena Pegoraro},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105023126850&origin=inward},

doi = {10.3390/biom15111599},

year  = {2025},

date = {2025-01-01},

journal = {Biomolecules},

volume = {15},

number = {11},

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

abstract = {© 2025 by the authors.Ryanodine receptor 1-related myopathies (RYR1-RM) are caused by RYR1 gene variants and comprise a wide spectrum of histopathological manifestations. Here, we focus on patients carrying RYR1 variants and muscle histopathology consistent with central core disease (CCD) or multi-minicore disease (MmD). RNA-sequencing analyses of skeletal muscle biopsies obtained from both CCD and MmD patients and from healthy controls were performed to better understand the molecular pathways activated by RYR1 variants. Our analyses revealed that, beyond the well-established role of RYR1 in calcium homeostasis, broader cellular pathways are implicated. In CCD, differentially expressed genes were enriched for pathways related to oxidative stress response, SMAD signalling, and apoptosis, consistent with the role of intracellular calcium dysregulation in promoting mitochondrial dysfunction and cell death. In contrast, MmD patients exhibited enrichment of pathways related to immune activation. This was corroborated by the upregulation of GTPase-regulating genes and the down-regulation of transcriptional repressors such as ZFP36 and ATN1. When considering all RYR1-RM patients collectively, Wnt signalling, immune-related pathways, and oxidative phosphorylation emerged as shared enriched pathways, indicating possible convergent mechanisms across histopathological phenotypes. Our study suggests that complex gene regulation driven by RYR1 variants may be a unifying feature in CCD and MmD, offering new insight into potential therapeutic targets.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105025851995,

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/record/display.uri?eid=2-s2.0-105025851995&origin=inward},

doi = {10.12688/f1000research.168288.1},

year  = {2025},

date = {2025-01-01},

journal = {F1000Research},

volume = {14},

publisher = {F1000 Research Ltd},

abstract = {Copyright: © 2025 Garrard C et al.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105023334728,

title = {Cryptochrome interaction networks across different tissues in Drosophila melanogaster},

author = {Milena Damulewicz and Francesco Gregoris and Davide Colaianni and Filippo Cendron and Alberto Biscontin and Giovanni Minervini and Gabriella M. Mazzotta},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105023334728&origin=inward},

doi = {10.1186/s13062-025-00696-x},

year  = {2025},

date = {2025-01-01},

journal = {Biology Direct},

volume = {20},

number = {1},

publisher = {BioMed Central Ltd},

abstract = {© The Author(s) 2025.Background: Drosophila CRYPTOCHROME (dCRY) is a blue light-sensitive protein involved in various biological processes, including photoreception, circadian rhythm regulation, synaptic plasticity, and magnetoreception. Its circadian function is strictly connected with light: upon light exposure, dCRY undergoes a conformational change, becoming active and binding to various proteins. However, it can also form complexes in the absence of light, with its function varying depending on the cell type in which it is expressed. Results: Here, we use an experimental approach based on co-immunoprecipitation followed by mass spectrometry analysis, obtaining the in vivo interactome of dCRY in two distinct cell populations - retina photoreceptors and glial cells - at two specific time points: just before lights-on (ZT0) and one hour after lights-on (ZT1). To gain deeper insights into the functional dynamics of dCRY, we constructed reliable protein-protein interaction networks in both cell types and across the two experimental conditions, revealing a complex landscape of interactions. Additionally, we explored the biological pathways associated with the identified dCRY interactors, highlighting several tissue- and time-specific enrichments. We focused on RNA-related pathways, indicating that dCRY and its interactors are involved in regulating RNA metabolism in photoreceptors at ZT0 and in glial cells at ZT1. Finally, as a case study, we further investigated the functions of the RNA-binding protein SQUID, found to interact with dCRY in both tissues. Notably, the impaired circadian locomotor behavior exhibited by Squid mutant flies accounts for the involvement of this hnRNP in the generation of the circadian rhythmicity. Conclusions: In conclusion, our work provides the first tissue- and time-specific dCRY interactome, offering valuable insights into previously unrecognized biological processes in which it may be involved. Specifically, its potential role in the regulation of RNA metabolism contributes crucial evidence concerning the relationship between the circadian clock and RNA metabolism, thereby laying the groundwork for future research in this area.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105018034228,

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/record/display.uri?eid=2-s2.0-105018034228&origin=inward},

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

year  = {2025},

date = {2025-01-01},

journal = {PLOS Computational Biology},

volume = {21},

number = {9},

publisher = {Public Library of Science},

abstract = {Copyright: © 2025 Pradelli et al. This is an open access article distributed under the terms of the Creative Commons Attribution LicenseRetinal 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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105020094912,

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/record/display.uri?eid=2-s2.0-105020094912&origin=inward},

doi = {10.3390/genes16101134},

year  = {2025},

date = {2025-01-01},

journal = {Genes},

volume = {16},

number = {10},

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

abstract = {© 2025 by the authors.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85194767977,

title = {Catechol-induced covalent modifications modulate the aggregation tendency of α-synuclein: An in-solution and in-silico study},

author = {Ilenia Inciardi and Elena Rizzotto and Francesco Gregoris and Benedetta Fongaro and Alice Sosic and Giovanni Minervini and Patrizia Polverino Laureto},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-85194767977&origin=inward},

doi = {10.1002/biof.2086},

year  = {2025},

date = {2025-01-01},

journal = {BioFactors},

volume = {51},

number = {1},

publisher = {John Wiley and Sons Inc},

abstract = {© 2024 International Union of Biochemistry and Molecular Biology.Parkinson's disease (PD) stands as a challenging neurodegenerative condition characterized by the emergence of Lewy Bodies (LBs), intracellular inclusions within dopaminergic neurons. These LBs harbor various proteins, prominently including α-Synuclein (Syn) aggregates, implicated in disease pathology. A promising avenue in PD treatment involves targeting Syn aggregation. Recent findings from our research have shown that 3,4-dihydroxyphenylacetic acid (DOPAC) and 3,4-dihydroxyphenylethanol (DOPET) possess the ability to impede the formation of Syn fibrils by disrupting the aggregation process. Notably, these compounds primarily engage in noncovalent interactions with the protein, leading to the formation of off-pathway oligomers that deter fibril growth. Through proteolysis studies and mass spectrometry (MS) analysis, we have identified potential covalent modifications of Syn in the presence of DOPAC, although the exact site remains elusive. Employing molecular dynamics simulations, we delved into how DOPAC-induced covalent alterations might affect the mechanism of Syn aggregation. Our findings indicate that the addition of a covalent adduct on certain residues enhances fibril flexibility without compromising its secondary structure stability. Furthermore, in the monomeric state, the modified residue fosters novel bonding interactions, thereby influencing long-range interactions between the N- and C-termini of the protein.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85210122158,

title = {PredIDR: Accurate prediction of protein intrinsic disorder regions using deep convolutional neural network},

author = {Kun-Sop Han and Se-Ryong Song and Myong-hyon Pak and Chol-Song Kim and Chol-Pyok Ri and Alessio Del Conte and Damiano Piovesan},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-85210122158&origin=inward},

doi = {10.1016/j.ijbiomac.2024.137665},

year  = {2025},

date = {2025-01-01},

journal = {International Journal of Biological Macromolecules},

volume = {284},

publisher = {Elsevier B.V.},

abstract = {© 2024 Elsevier B.V.The involvement of protein intrinsic disorder in essential biological processes, it is well known in structural biology. However, experimental methods for detecting intrinsic structural disorder and directly measuring highly dynamic behavior of protein structure are limited. To address this issue, several computational methods to predict intrinsic disorder from protein sequences were developed and their performance is evaluated by the Critical Assessment of protein Intrinsic Disorder (CAID). In this paper, we describe a new computational method, PredIDR, which provides accurate prediction of intrinsically disordered regions in proteins, mimicking experimental X-ray missing residues. Indeed, missing residues in Protein Data Bank (PDB) were used as positive examples to train a deep convolutional neural network which produces two types of output for short and long regions. PredIDR took part in the second round of CAID and was as accurate as the top state-of-the-art IDR prediction methods. PredIDR can be freely used through the CAID Prediction Portal available at https://caid.idpcentral.org/portal or downloaded as a Singularity container from https://biocomputingup.it/shared/caid-predictors/.},

note = {Cited by: 3},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85176208048,

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/record/display.uri?eid=2-s2.0-85176208048&origin=inward},

doi = {10.1093/nar/gkad928},

year  = {2024},

date = {2024-01-01},

journal = {Nucleic Acids Research},

volume = {52},

number = {D1},

pages = {D434-D441},

publisher = {Oxford University Press},

abstract = {© The Author(s) 2023. Published by Oxford University Press on behalf of Nucleic Acids Research.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.},

note = {Cited by: 94; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85207813713,

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/record/display.uri?eid=2-s2.0-85207813713&origin=inward},

doi = {10.1002/pro.5189},

year  = {2024},

date = {2024-01-01},

journal = {Protein Science},

volume = {33},

number = {11},

publisher = {John Wiley and Sons Inc},

abstract = {© 2024 The Author(s). Protein Science published by Wiley Periodicals LLC on behalf of The Protein Society.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85188993912,

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/record/display.uri?eid=2-s2.0-85188993912&origin=inward},

doi = {10.1093/bioadv/vbae043},

year  = {2024},

date = {2024-01-01},

journal = {Bioinformatics Advances},

volume = {4},

number = {1},

publisher = {Oxford University Press},

abstract = {© 2024 The Author(s). Published by Oxford University Press.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85188297172,

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/record/display.uri?eid=2-s2.0-85188297172&origin=inward},

doi = {10.1093/database/baae009},

year  = {2024},

date = {2024-01-01},

journal = {Database},

volume = {2024},

publisher = {Oxford University Press},

abstract = {© The Author(s) 2024. Published by Oxford University Press.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85212459848,

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/record/display.uri?eid=2-s2.0-85212459848&origin=inward},

doi = {10.1093/gigascience/giae094},

year  = {2024},

date = {2024-01-01},

journal = {GigaScience},

volume = {13},

publisher = {Oxford University Press},

abstract = {© The Author(s) 2024. Published by Oxford University Press GigaScience.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85211966531,

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/record/display.uri?eid=2-s2.0-85211966531&origin=inward},

doi = {10.1093/bioinformatics/btae690},

year  = {2024},

date = {2024-01-01},

journal = {Bioinformatics},

volume = {40},

number = {12},

publisher = {Oxford University Press},

abstract = {© The Author(s) 2024.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85213041340,

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/record/display.uri?eid=2-s2.0-85213041340&origin=inward},

doi = {10.1002/cpz1.70077},

year  = {2024},

date = {2024-01-01},

journal = {Current Protocols},

volume = {4},

number = {12},

publisher = {John Wiley and Sons Inc},

abstract = {Current Protocols© 2024 The Author(s). Current Protocols published by Wiley Periodicals LLC.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85197788039,

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/record/display.uri?eid=2-s2.0-85197788039&origin=inward},

doi = {10.1093/nar/gkae337},

year  = {2024},

date = {2024-01-01},

journal = {Nucleic Acids Research},

volume = {52},

number = {W1},

pages = {W306-W312},

publisher = {Oxford University Press},

abstract = {© 2024 The Author(s). Published by Oxford University Press on behalf of Nucleic Acids Research.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/.},

note = {Cited by: 75; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85185346556,

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/record/display.uri?eid=2-s2.0-85185346556&origin=inward},

doi = {10.1002/pro.4914},

year  = {2024},

date = {2024-01-01},

journal = {Protein Science},

volume = {33},

number = {3},

publisher = {John Wiley and Sons Inc},

abstract = {© 2024 The Protein Society.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 (Ca2+) and CaM. We propose that this Ca2+/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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85181761325,

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/record/display.uri?eid=2-s2.0-85181761325&origin=inward},

doi = {10.1093/nar/gkad947},

year  = {2024},

date = {2024-01-01},

journal = {Nucleic Acids Research},

volume = {52},

number = {D1},

pages = {D536-D544},

publisher = {Oxford University Press},

abstract = {© The Author(s) 2023. Published by Oxford University Press on behalf of Nucleic Acids Research.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.},

note = {Cited by: 44; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85205114282,

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/record/display.uri?eid=2-s2.0-85205114282&origin=inward},

doi = {10.3390/genes15091167},

year  = {2024},

date = {2024-01-01},

journal = {Genes},

volume = {15},

number = {9},

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

abstract = {© 2024 by the authors.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85187783312,

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/record/display.uri?eid=2-s2.0-85187783312&origin=inward},

doi = {10.3390/ijms25052994},

year  = {2024},

date = {2024-01-01},

journal = {International Journal of Molecular Sciences},

volume = {25},

number = {5},

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

abstract = {© 2024 by the authors.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.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85187866396,

title = {CAGI, the Critical Assessment of Genome Interpretation, establishes progress and prospects for computational genetic variant interpretation methods},

author = {Shantanu Jain and Constantina Bakolitsa and Steven E. Brenner and Predrag Radivojac and John Moult and Susanna Repo and Roger A. Hoskins and Gaia Andreoletti and Daniel Barsky and Ajithavalli Chellapan and Hoyin Chu and Navya Dabbiru and Naveen K. Kollipara and Melissa Ly and Andrew J. Neumann and Lipika R. Pal and Eric Odell and Gaurav Pandey and Robin C. Peters-Petrulewicz and Rajgopal Srinivasan and Stephen F. Yee and Sri Jyothsna Yeleswarapu and Maya Zuhl and Ogun Adebali and Ayoti Patra and Michael A. Beer and Raghavendra Hosur and Jian Peng and Brady M. Bernard and Michael Berry and Shengcheng Dong and Alan P. Boyle and Aashish Adhikari and Jingqi Chen and Zhiqiang Hu and Robert Wang and Yaqiong Wang and Maximilian Miller and Yanran Wang and Yana Bromberg and Paola Turina and Emidio Capriotti and James J. Han and Kivilcim Ozturk and Hannah Carter and Giulia Babbi and Samuele Bovo and Pietro Di Lena and Pier Luigi Martelli and Castrense Savojardo and Rita Casadio and Melissa S. Cline and Greet De Baets and Sandra Bonache and Orland Díez and Sara Gutiérrez-Enríquez and Alejandro Fernández and Gemma Montalban and Lars Ootes and Selen Özkan and Natàlia Padilla and Casandra Riera and Xavier De Cruz and Mark Diekhans and Peter J. Huwe and Qiong Wei and Qifang Xu and Roland L. Dunbrack and Valer Gotea and Laura Elnitski and Gennady Margolin and Piero Fariselli and Ivan V. Kulakovskiy and Vsevolod J. Makeev and Dmitry D. Penzar and Ilya E. Vorontsov and Alexander V. Favorov and Julia R. Forman and Marcia Hasenahuer and Maria S. Fornasari and Gustavo Parisi and Ziga Avsec and Muhammed H. Çelik and Thi Yen Duong Nguyen and Julien Gagneur and Fang-Yuan Shi and Matthew D. Edwards and Yuchun Guo and Kevin Tian and Haoyang Zeng and David K. Gifford and Jonathan Göke and Jan Zaucha and Julian Gough and Graham R. S. Ritchie and Adam Frankish and Jonathan M. Mudge and Jennifer Harrow and Erin L. Young and Yao Yu and ...},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-85187866396&origin=inward},

doi = {10.1186/s13059-023-03113-6},

year  = {2024},

date = {2024-01-01},

journal = {Genome Biology},

volume = {25},

number = {1},

publisher = {BioMed Central Ltd},

abstract = {© The Author(s) 2024.Background: The Critical Assessment of Genome Interpretation (CAGI) aims to advance the state-of-the-art for computational prediction of genetic variant impact, particularly where relevant to disease. The five complete editions of the CAGI community experiment comprised 50 challenges, in which participants made blind predictions of phenotypes from genetic data, and these were evaluated by independent assessors. Results: Performance was particularly strong for clinical pathogenic variants, including some difficult-to-diagnose cases, and extends to interpretation of cancer-related variants. Missense variant interpretation methods were able to estimate biochemical effects with increasing accuracy. Assessment of methods for regulatory variants and complex trait disease risk was less definitive and indicates performance potentially suitable for auxiliary use in the clinic. Conclusions: Results show that while current methods are imperfect, they have major utility for research and clinical applications. Emerging methods and increasingly large, robust datasets for training and assessment promise further progress ahead.},

note = {Cited by: 16; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85164785564,

title = {The Gene Ontology knowledgebase in 2023},

author = {Suzi A. Aleksander and James Balhoff and Seth Carbon and J. Michael Cherry and Harold J. Drabkin and Dustin Ebert and Marc Feuermann and Pascale Gaudet and Nomi L. Harris and David P. Hill and Raymond Lee and Huaiyu Mi and Sierra Moxon and Christopher J. Mungall and Anushya Muruganugan and Tremayne Mushayahama and Paul W. Sternberg and Paul D. Thomas and Kimberly Van Auken and Jolene Ramsey and Deborah A. Siegele and Rex L. Chisholm and Petra Fey and Maria Cristina Aspromonte and Maria Victoria Nugnes and Federica Quaglia and Silvio Tosatto and Michelle Giglio and Suvarna Nadendla and Giulia Antonazzo and Helen Attrill and Gil Dos Santos and Steven Marygold and Victor Strelets and Christopher J. Tabone and Jim Thurmond and Pinglei Zhou and Saadullah H. Ahmed and Praoparn Asanitthong and Diana Luna Buitrago and Meltem N. Erdol and Matthew C. Gage and Mohamed Ali Kadhum and Kan Yan Chloe Li and Miao Long and Aleksandra Michalak and Angeline Pesala and Armalya Pritazahra and Shirin C. C. Saverimuttu and Renzhi Su and Kate E. Thurlow and Ruth C Lovering and Colin Logie and Snezhana Oliferenko and Judith Blake and Karen Christie and Lori Corbani and Mary E. Dolan and Li Ni and Dmitry Sitnikov and Cynthia Smith and Alayne Cuzick and James Seager and Laurel Cooper and Justin Elser and Pankaj Jaiswal and Parul Gupta and Sushma Naithani and Manuel Lera-Ramirez and Kim Rutherford and Valerie Wood 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 Stacia R. Engel and Kalpana Karra and Stuart R. Miyasato and Robert S. Nash and Marek S. Skrzypek and Shuai Weng and Edith D. Wong 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 ...},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-85164785564&origin=inward},

doi = {10.1093/genetics/iyad031},

year  = {2023},

date = {2023-01-01},

journal = {Genetics},

volume = {224},

number = {1},

publisher = {Oxford University Press},

abstract = {© 2023 The Author(s). Published by Oxford University Press on behalf of The Genetics Society of America.The Gene Ontology (GO) knowledgebase (http://geneontology.org) is a comprehensive resource concerning the functions of genes and gene products (proteins and noncoding RNAs). GO annotations cover genes from organisms across the tree of life as well as viruses, though most gene function knowledge currently derives from experiments carried out in a relatively small number of model organisms. Here, we provide an updated overview of the GO knowledgebase, as well as the efforts of the broad, international consortium of scientists that develops, maintains, and updates the GO knowledgebase. The GO knowledgebase consists of three components: (1) the GO - a computational knowledge structure describing the functional characteristics of genes; (2) GO annotations - evidence-supported statements asserting that a specific gene product has a particular functional characteristic; and (3) GO Causal Activity Models (GO-CAMs) - mechanistic models of molecular "pathways"(GO biological processes) created by linking multiple GO annotations using defined relations. Each of these components is continually expanded, revised, and updated in response to newly published discoveries and receives extensive QA checks, reviews, and user feedback. For each of these components, we provide a description of the current contents, recent developments to keep the knowledgebase up to date with new discoveries, and guidance on how users can best make use of the data that we provide. We conclude with future directions for the project.},

note = {Cited by: 1923; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85159553803,

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/record/display.uri?eid=2-s2.0-85159553803&origin=inward},

doi = {10.1093/bioinformatics/btad260},

year  = {2023},

date = {2023-01-01},

journal = {Bioinformatics},

volume = {39},

number = {5},

publisher = {Oxford University Press},

abstract = {© The Author(s) 2023. Published by Oxford University Press.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.},

note = {Cited by: 22; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}