Silvio C. E. Tosatto

@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: 2; 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: 1; 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: 1; 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: 14; 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: 0; 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: 4; 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: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: 1},

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: 0; 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: 0; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}