Alexander Miguel Monzon

@article{SCOPUS_ID:105034672381,

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

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

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105034672381&origin=inward},

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

year  = {2026},

date = {2026-01-01},

journal = {Journal of Molecular Biology},

publisher = {Academic Press},

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

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105034198426,

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

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

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105034198426&origin=inward},

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

year  = {2026},

date = {2026-01-01},

journal = {Nature Methods},

publisher = {Nature Research},

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

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: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:105034187048,

title = {Toward a unified framework for determining conformational ensembles of disordered proteins},

author = {Hamidreza Ghafouri and Pavel Kadeřávek and Ana M. Melo and Maria Cristina Aspromonte and Pau Bernadó and Juan Cortés and Zsuzsanna Dosztányi and Gábor Erdős and Michael Feig and Giacomo Janson and Kresten Lindorff-Larsen and Frans A. A. Mulder and Peter Nagy and Richard Pestell and Damiano Piovesan and Marco Schiavina and Benjamin Schuler and Nathalie Sibille and Giulio Tesei and Peter Tompa and Michele Vendruscolo and Jiri Vondrasek and Wim Vranken and Lukas Zidek and Silvio C. E. Tosatto and Alexander Miguel Monzon},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105034187048&origin=inward},

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

year  = {2026},

date = {2026-01-01},

journal = {Nature Methods},

volume = {23},

number = {4},

pages = {705-719},

publisher = {Nature Research},

abstract = {© Springer Nature America, Inc. 2026.Disordered proteins play essential roles in myriad cellular processes, yet their structural characterization remains a major challenge due to their dynamic and heterogeneous nature. Here we present a community-driven initiative to address this problem by advocating a unified framework for determining conformational ensembles of disordered proteins. Our aim is to integrate state-of-the-art experimental techniques with advanced computational methods, including knowledge-based sampling, enhanced molecular dynamics and machine learning models. The modular framework comprises three interconnected components: experimental data acquisition, computational ensemble generation and validation. The systematic development of this framework will ensure the accurate and reproducible determination of conformational ensembles of disordered proteins. We highlight the open challenges necessary to achieve this goal, including force-field accuracy, efficient sampling, and environmental dependence, advocating for collaborative benchmarking and standardized protocols.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105033760847,

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

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

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105033760847&origin=inward},

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

year  = {2026},

date = {2026-01-01},

journal = {Trends in Biochemical Sciences},

publisher = {Elsevier Ltd},

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

note = {Cited by: 0},

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: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: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: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: 12; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}