@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: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: 29; 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: 8; 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: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},

volume = {144},

number = {2},

pages = {309-326},

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: 1; 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: 137; Open Access},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SCOPUS_ID:105014118997,

title = {Critical Assessment of Protein Intrinsic Disorder Round 3 - Predicting Disorder in the Era of Protein Language Models},

author = {Mahta Mehdiabadi and Alessio Del Conte and Maria Victoria Nugnes and Maria Cristina Aspromonte and Silvio C. E. Tosatto and Damiano Piovesan},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105014118997&origin=inward},

doi = {10.1002/prot.70045},

year  = {2025},

date = {2025-01-01},

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

publisher = {John Wiley and Sons Inc},

abstract = {© 2025 The Author(s). PROTEINS: Structure, Function, and Bioinformatics published by Wiley Periodicals LLC.Intrinsic disorder (ID) in proteins is a complex phenomenon, encompassing a continuum from entirely disordered regions to structured domains with flexible segments. The absence of a ground truth for all forms of disorder, combined with the possibility of structural transitions between ordered and disordered states under specific conditions, makes accurate prediction of ID especially challenging. The Critical Assessment of Protein Intrinsic Disorder (CAID) evaluates ID prediction methods using diverse benchmarks derived from DisProt, a manually curated database of experimentally validated annotations. This paper presents findings from the third (CAID3), in which 24 new methods were assessed along with the predictors from previous rounds. Compared to CAID2, the top-performing methods in CAID3 demonstrated significant gains in average precision: over 31% improvement in predicting linker regions, and 15% in disorder prediction. This round introduces a new binding sub-challenge focused on identifying binding regions within known IDR boundaries. The results indicate that this task remains challenging, highlighting the potential for improvement. The top-performing methods in CAID3 are mostly new and commonly used embeddings from protein language models (pLMs), underscoring the growing impact of pLMs in tackling the complexities of disordered proteins and advancing ID prediction.},

note = {Cited by: 0; 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},

volume = {144},

number = {2},

pages = {227-242},

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: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:105015207644,

title = {Decoding protein structures with residue interaction networks},

author = {Sol C. Begue and Emanuela Leonardi and Silvio C. E. Tosatto},

url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-105015207644&origin=inward},

doi = {10.1016/j.tibs.2025.08.006},

year  = {2025},

date = {2025-01-01},

journal = {Trends in Biochemical Sciences},

publisher = {Elsevier Ltd},

abstract = {© 2025 The Author(s)The rise of AlphaFold and similar structure predictors has made it possible to determine the 3D structure of almost any protein from its amino acid sequence. Residue interaction networks (RINs), graphs where residues are represented as nodes and interactions as edges, provide a powerful framework for analyzing and interpreting this surge in structural data. Here, we provide a comprehensive introduction to RINs, exploring different approaches to constructing and analyzing them, including their integration with molecular dynamics (MD) simulations and artificial intelligence (AI). To illustrate their versatility, we present different case studies where RINs have been applied to investigate thermostability, allosterism, post-translational modifications (PTMs), homology, and evolution. Finally, we discuss future directions for RINs, emphasizing opportunities for refinement and broader integration into structural biology.},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}