@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: 10; 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: 13; 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: 4; 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},

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: 1; 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},

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: 0; 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: 3; 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: 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: 19; 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: 12; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}