@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: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: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: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: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: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: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: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}

}