Alexander Miguel Monzon

@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: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: 13; 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: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: 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: 3; 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: 1; 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: 20; 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: 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}

}

@article{SCOPUS_ID:85169117009,

title = {Critical assessment of protein intrinsic disorder prediction (CAID) - Results of round 2},

author = {Alessio Del Conte and Mahta Mehdiabadi and Adel Bouhraoua and Alexander Miguel Monzon and Silvio C. E. Tosatto and Damiano Piovesan},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-85169117009&origin=inward},

doi = {10.1002/prot.26582},

year  = {2023},

date = {2023-01-01},

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

volume = {91},

number = {12},

pages = {1925-1934},

publisher = {John Wiley and Sons Inc},

abstract = {© 2023 The Authors. Proteins: Structure, Function, and Bioinformatics published by Wiley Periodicals LLC.Protein intrinsic disorder (ID) is a complex and context-dependent phenomenon that covers a continuum between fully disordered states and folded states with long dynamic regions. The lack of a ground truth that fits all ID flavors and the potential for order-to-disorder transitions depending on specific conditions makes ID prediction challenging. The CAID2 challenge aimed to evaluate the performance of different prediction methods across different benchmarks, leveraging the annotation provided by the DisProt database, which stores the coordinates of ID regions when there is experimental evidence in the literature. The CAID2 challenge demonstrated varying performance of different prediction methods across different benchmarks, highlighting the need for continued development of more versatile and efficient prediction software. Depending on the application, researchers may need to balance performance with execution time when selecting a predictor. Methods based on AlphaFold2 seem to be good ID predictors but they are better at detecting absence of order rather than ID regions as defined in DisProt. The CAID2 predictors can be freely used through the CAID Prediction Portal, and CAID has been integrated into OpenEBench, which will become the official platform for running future CAID challenges.},

note = {Cited by: 26; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}