@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: 59; 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: 5; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85213041340,

title = {Searching and Using MobiDB Resource 6 to Explore Predictions and Annotations for Intrinsically Disordered Proteins},

author = {Maria Cristina Aspromonte and Federica Quaglia and Alexander Miguel Monzon and Damiano Clementel and Alessio Del Conte and Damiano Piovesan and Silvio C. E. Tosatto},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-85213041340&origin=inward},

doi = {10.1002/cpz1.70077},

year  = {2024},

date = {2024-01-01},

journal = {Current Protocols},

volume = {4},

number = {12},

publisher = {John Wiley and Sons Inc},

abstract = {Current Protocols© 2024 The Author(s). Current Protocols published by Wiley Periodicals LLC.Intrinsically disordered proteins (IDPs) make up around 30% of eukaryotic proteomes and play a crucial role in cellular processes and in pathological conditions such as neurodegenerative disorders and cancers. However, IDPs exhibit dynamic conformational ensembles and are often involved in the formation of biomolecular condensates. Understanding the function of IDPs is critical to research in many areas of science. MobiDB is a unique resource that serves as a comprehensive knowledgebase of IDPs and intrinsically disordered regions (IDRs), combining disorder annotations from experimental evidence and predictions for a broad range of protein sequences. Over the past decade, MobiDB has evolved with a focus on expanding annotation coverage, standardizing annotation provenance, and enhancing database accessibility. The latest MobiDB, version 6, released in July 2024, includes significant improvements, such as the integration of AlphaFoldDB predictions and a new homology transfer pipeline that has substantially increased the number of entries with high-quality annotations. The user interface has also been updated, highlighting annotation features, clarifying the entry page, and providing an immediate overview of disorder, binding, and disorder functions information in the protein sequence. This protocol guides the user through applications of the MobiDB, including disorder prediction, curated data analysis, and exploration of interaction data. This guide covers how to perform a search in MobiDB annotations using the web interface and the MobiDB REST API for programmatic access. The protocols use a step-by-step walkthrough using the human growth hormone receptor to demonstrate MobiDB's functions for visualization and interpretation of protein disorder data. © 2024 The Author(s). Current Protocols published by Wiley Periodicals LLC. Basic Protocol 1: Searching MobiDB query formats. Basic Protocol 2: Searching MobiDB selected datasets and selected proteomes. Basic Protocol 3: Performing a search on the Statistics page in MobiDB. Support Protocol: Programmatic access with MobiDB REST API. Basic Protocol 4: Visualizing and interpreting a MobiDB Entry: The GHR use case.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85145966264,

title = {MobiDB: 10 years of intrinsically disordered proteins},

author = {Damiano Piovesan and Alessio Del Conte and Damiano Clementel and Alexander Miguel Monzon and Martina Bevilacqua and Maria Cristina Aspromonte and Javier A Iserte and Fernando E Orti and Cristina Marino-Buslje and Silvio C. E Tosatto},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-85145966264&origin=inward},

doi = {10.1093/nar/gkac1065},

year  = {2023},

date = {2023-01-01},

journal = {Nucleic Acids Research},

volume = {51},

number = {1 D},

pages = {D438-D444},

publisher = {Oxford University Press},

abstract = {© 2023 The Author(s) 2022. Published by Oxford University Press on behalf of Nucleic Acids Research.The MobiDB database (URL: https://mobidb.org/) is a knowledge base of intrinsically disordered proteins. MobiDB aggregates disorder annotations derived from the literature and from experimental evidence along with predictions for all known protein sequences. MobiDB generates new knowledge and captures the functional significance of disordered regions by processing and combining complementary sources of information. Since its first release 10 years ago, the MobiDB database has evolved in order to improve the quality and coverage of protein disorder annotations and its accessibility. MobiDB has now reached its maturity in terms of data standardization and visualization. Here, we present a new release which focuses on the optimization of user experience and database content. The major advances compared to the previous version are the integration of AlphaFoldDB predictions and the re-implementation of the homology transfer pipeline, which expands manually curated annotations by two orders of magnitude. Finally, the entry page has been restyled in order to provide an overview of the available annotations along with two separate views that highlight structural disorder evidence and functions associated with different binding modes.},

note = {Cited by: 92; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85159553803,

title = {RING-PyMOL: residue interaction networks of structural ensembles and molecular dynamics},

author = {Alessio Del Conte and Alexander Miguel Monzon and Damiano Clementel and Giorgia F. Camagni and Giovanni Minervini and Silvio C. E. Tosatto and Damiano Piovesan},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-85159553803&origin=inward},

doi = {10.1093/bioinformatics/btad260},

year  = {2023},

date = {2023-01-01},

journal = {Bioinformatics},

volume = {39},

number = {5},

publisher = {Oxford University Press},

abstract = {© The Author(s) 2023. Published by Oxford University Press.RING-PyMOL is a plugin for PyMOL providing a set of analysis tools for structural ensembles and molecular dynamic simulations. RING-PyMOL combines residue interaction networks, as provided by the RING software, with structural clustering to enhance the analysis and visualization of the conformational complexity. It combines precise calculation of non-covalent interactions with the power of PyMOL to manipulate and visualize protein structures. The plugin identifies and highlights correlating contacts and interaction patterns that can explain structural allostery, active sites, and structural heterogeneity connected with molecular function. It is easy to use and extremely fast, processing and rendering hundreds of models and long trajectories in seconds. RING-PyMOL generates a number of interactive plots and output files for use with external tools. The underlying RING software has been improved extensively. It is 10 times faster, can process mmCIF files and it identifies typed interactions also for nucleic acids.},

note = {Cited by: 13; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85163958831,

title = {CAID prediction portal: A comprehensive service for predicting intrinsic disorder and binding regions in proteins},

author = {Alessio Del Conte and Adel Bouhraoua and Mahta Mehdiabadi and Damiano Clementel and Alexander Miguel Monzon and Silvio C. E. Tosatto and Damiano Piovesan and Alex S. Holehouse and Daniel Griffith and Ryan J. Emenecker and Ashwini Patil and Ronesh Sharma and Tatsuhiko Tsunoda and Alok Sharma and Yi Jun Tang and Bin Liu and Claudio Mirabello and Björn Wallner and Burkhard Rost and Dagmar Ilzhöfer and Maria Littmann and Michael Heinzinger and Lea I. M. Krautheimer and Michael Bernhofer and Liam J. McGuffin and Isabelle Callebaut and Tristan Bitard Feildel and Jian Liu and Jianlin Cheng and Zhiye Guo and Jinbo Xu and Sheng Wang and Nawar Malhis and Jörg Gsponer and Chol-Song Kim and Kun-Sop Han and Myong-Chol Ma and Lukasz Kurgan and Sina Ghadermarzi and Akila Katuwawala and Bi Zhao and Zhenling Peng and Zhonghua Wu and Gang Hu and Kui Wang and Md Tamjidul Hoque and Md Wasi Ul Kabir and Michele Vendruscolo and Pietro Sormanni and Min Li and Fuhao Zhang and Pengzhen Jia and Yida Wang and Michail Yu Lobanov and Oxana V. Galzitskaya and Wim Vranken and Adrián Díaz and Thomas Litfin and Yaoqi Zhou and Jack Hanson and Kuldip Paliwal and Zsuzsanna Dosztányi and Gábor Erdős},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-85163958831&origin=inward},

doi = {10.1093/nar/gkad430},

year  = {2023},

date = {2023-01-01},

journal = {Nucleic Acids Research},

volume = {51},

number = {W1},

pages = {W62-W69},

publisher = {Oxford University Press},

abstract = {© 2023 The Author(s). Published by Oxford University Press on behalf of Nucleic Acids Research.Intrinsic disorder (ID) in proteins is well-established in structural biology, with increasing evidence for its involvement in essential biological processes. As measuring dynamic ID behavior experimentally on a large scale remains difficult, scores of published ID predictors have tried to fill this gap. Unfortunately, their heterogeneity makes it difficult to compare performance, confounding biologists wanting to make an informed choice. To address this issue, the Critical Assessment of protein Intrinsic Disorder (CAID) benchmarks predictors for ID and binding regions as a community blind-test in a standardized computing environment. Here we present the CAID Prediction Portal, a web server executing all CAID methods on user-defined sequences. The server generates standardized output and facilitates comparison between methods, producing a consensus prediction highlighting high-confidence ID regions. The website contains extensive documentation explaining the meaning of different CAID statistics and providing a brief description of all methods. Predictor output is visualized in an interactive feature viewer and made available for download in a single table, with the option to recover previous sessions via a private dashboard. The CAID Prediction Portal is a valuable resource for researchers interested in studying ID in proteins. The server is available at the URL: https://caid.idpcentral.org.},

note = {Cited by: 37; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85165364940,

title = {The repetitive structure of DNA clamps: An overlooked protein tandem repeat},

author = {Paula Nazarena Arrías and Alexander Miguel Monzon and Damiano Clementel and Soroush Mozaffari and Damiano Piovesan and Andrey V. Kajava and Silvio C. E. Tosatto},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-85165364940&origin=inward},

doi = {10.1016/j.jsb.2023.108001},

year  = {2023},

date = {2023-01-01},

journal = {Journal of Structural Biology},

volume = {215},

number = {3},

publisher = {Academic Press Inc.},

abstract = {© 2023Structured tandem repeats proteins (STRPs) are a specific kind of tandem repeat proteins characterized by a modular and repetitive three-dimensional structure arrangement. The majority of STRPs adopt solenoid structures, but with the increasing availability of experimental structures and high-quality predicted structural models, more STRP folds can be characterized. Here, we describe “Box repeats”, an overlooked STRP fold present in the DNA sliding clamp processivity factors, which has eluded classification although structural data has been available since the late 1990s. Each Box repeat is a β⍺βββ module of about 60 residues, which forms a class V “beads-on-a-string” type STRP. The number of repeats present in processivity factors is organism dependent. Monomers of PCNA proteins in both Archaea and Eukarya have 4 repeats, while the monomers of bacterial beta-sliding clamps have 6 repeats. This new repeat fold has been added to the RepeatsDB database, which now provides structural annotation for 66 Box repeat proteins belonging to different organisms, including viruses.},

note = {Cited by: 4; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85169818438,

title = {A STRP-ed definition of Structured Tandem Repeats in Proteins},

author = {Alexander Miguel Monzon and Paula Nazarena Arrías and Arne Elofsson and Pablo Mier and Miguel A. Andrade-Navarro and Martina Bevilacqua and Damiano Clementel and Alex Bateman and Layla Hirsh and Maria Silvina Fornasari and Gustavo Parisi and Damiano Piovesan and Andrey V. Kajava and Silvio C. E. Tosatto},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-85169818438&origin=inward},

doi = {10.1016/j.jsb.2023.108023},

year  = {2023},

date = {2023-01-01},

journal = {Journal of Structural Biology},

volume = {215},

number = {4},

publisher = {Academic Press Inc.},

abstract = {© 2023Tandem Repeat Proteins (TRPs) are a class of proteins with repetitive amino acid sequences that have been studied extensively for over two decades. Different features at the level of sequence, structure, function and evolution have been attributed to them by various authors. And yet many of its salient features appear only when looking at specific subclasses of protein tandem repeats. Here, we attempt to rationalize the existing knowledge on Tandem Repeat Proteins (TRPs) by pointing out several dichotomies. The emerging picture is more nuanced than generally assumed and allows us to draw some boundaries of what is not a “proper” TRP. We conclude with an operational definition of a specific subset, which we have denominated STRPs (Structural Tandem Repeat Proteins), which separates a subclass of tandem repeats with distinctive features from several other less well-defined types of repeats. We believe that this definition will help researchers in the field to better characterize the biological meaning of this large yet largely understudied group of proteins.},

note = {Cited by: 6; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:85159198884,

title = {Combining Protein Conformational Diversity and Phylogenetic Information Using CoDNaS and CoDNaS-Q},

author = {Nahuel Escobedo and Alexander Miguel Monzon and María Silvina Fornasari and Nicolas Palopoli and Gustavo Parisi},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-85159198884&origin=inward},

doi = {10.1002/cpz1.764},

year  = {2023},

date = {2023-01-01},

journal = {Current Protocols},

volume = {3},

number = {5},

publisher = {John Wiley and Sons Inc},

abstract = {© 2023 Wiley Periodicals LLC.CoDNaS (http://ufq.unq.edu.ar/codnas/) and CoDNaS-Q (http://ufq.unq.edu.ar/codnasq) are repositories of proteins with different degrees of conformational diversity. Following the ensemble nature of the native state, conformational diversity represents the structural differences between the conformers in the ensemble. Each entry in CoDNaS and CoDNaS-Q contains a redundant collection of experimentally determined conformers obtained under different conditions. These conformers represent snapshots of the protein dynamism. While CoDNaS contains examples of conformational diversity at the tertiary level, a recent development, CoDNaS-Q, contains examples at the quaternary level. In the emerging age of accurate protein structure prediction by machine learning approaches, many questions remain open regarding the characterization of protein dynamism. In this context, most bioinformatics resources take advantage of distinct features derived from protein alignments, however, the complexity and heterogeneity of information makes it difficult to recover reliable biological signatures. Here we present five protocols to explore tertiary and quaternary conformational diversity at the individual protein level as well as for the characterization of the distribution of conformational diversity at the protein family level in a phylogenetic context. These protocols can provide curated protein families with experimentally known conformational diversity, facilitating the exploration of sequence determinants of protein dynamism. © 2023 Wiley Periodicals LLC. Basic Protocol 1: Assessing conformational diversity with CoDNaS. Alternate Protocol 1: Assessing conformational diversity at the quaternary level with CoDNaS-Q. Basic Protocol 2: Exploring conformational diversity in a protein family. Alternate Protocol 2: Exploring quaternary conformational diversity in a protein family. Basic Protocol 3: Representing conformational diversity in a phylogenetic context.},

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: 52; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}