Enzyme annotation in UniProtKB using Rhea.

MOTIVATION: To provide high quality computationally tractable enzyme annotation in UniProtKB using Rhea, a comprehensive expert-curated knowledgebase of biochemical reactions which describes reaction participants using the ChEBI (Chemical Entities of Biological Interest) ontology. RESULTS: We replaced existing textual descriptions of biochemical reactions in UniProtKB with their equivalents from Rhea, which is now the standard for annotation of enzymatic reactions in UniProtKB. We developed improved search and query facilities for the UniProt website, REST API and SPARQL endpoint that leverage the chemical structure data, nomenclature and classification that Rhea and ChEBI provide. AVAILABILITY AND IMPLEMENTATION: UniProtKB at https://www.uniprot.org; UniProt REST API at https://www.uniprot.org/help/api; UniProt SPARQL endpoint at https://sparql.uniprot.org/; Rhea at https://www.rhea-db.org.

Scaling up data curation using deep learning: An application to literature triage in genomic variation resources.

Manually curating biomedical knowledge from publications is necessary to build a knowledge based service that provides highly precise and organized information to users. The process of retrieving relevant publications for curation, which is also known as document triage, is usually carried out by querying and reading articles in PubMed. However, this query-based method often obtains unsatisfactory precision and recall on the retrieved results, and it is difficult to manually generate optimal queries. To address this, we propose a machine-learning assisted triage method. We collect previously curated publications from two databases UniProtKB/Swiss-Prot and the NHGRI-EBI GWAS Catalog, and used them as a gold-standard dataset for training deep learning models based on convolutional neural networks. We then use the trained models to classify and rank new publications for curation. For evaluation, we apply our method to the real-world manual curation process of UniProtKB/Swiss-Prot and the GWAS Catalog. We demonstrate that our machine-assisted triage method outperforms the current query-based triage methods, improves efficiency, and enriches curated content. Our method achieves a precision 1.81 and 2.99 times higher than that obtained by the current query-based triage methods of UniProtKB/Swiss-Prot and the GWAS Catalog, respectively, without compromising recall. In fact, our method retrieves many additional relevant publications that the query-based method of UniProtKB/Swiss-Prot could not find. As these results show, our machine learning-based method can make the triage process more efficient and is being implemented in production so that human curators can focus on more challenging tasks to improve the quality of knowledge bases.

On expert curation and scalability: UniProtKB/Swiss-Prot as a case study.

MOTIVATION: Biological knowledgebases, such as UniProtKB/Swiss-Prot, constitute an essential component of daily scientific research by offering distilled, summarized and computable knowledge extracted from the literature by expert curators. While knowledgebases play an increasingly important role in the scientific community, their ability to keep up with the growth of biomedical literature is under scrutiny. Using UniProtKB/Swiss-Prot as a case study, we address this concern via multiple literature triage approaches. RESULTS: With the assistance of the PubTator text-mining tool, we tagged more than 10 000 articles to assess the ratio of papers relevant for curation. We first show that curators read and evaluate many more papers than they curate, and that measuring the number of curated publications is insufficient to provide a complete picture as demonstrated by the fact that 8000-10 000 papers are curated in UniProt each year while curators evaluate 50 000-70 000 papers per year. We show that 90% of the papers in PubMed are out of the scope of UniProt, that a maximum of 2-3% of the papers indexed in PubMed each year are relevant for UniProt curation, and that, despite appearances, expert curation in UniProt is scalable. AVAILABILITY AND IMPLEMENTATION: UniProt is freely available at http://www.uniprot.org/. CONTACT: sylvain.poux@sib.swiss. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

HAMAP in 2015: updates to the protein family classification and annotation system.

HAMAP (High-quality Automated and Manual Annotation of Proteins--available at http://hamap.expasy.org/) is a system for the automatic classification and annotation of protein sequences. HAMAP provides annotation of the same quality and detail as UniProtKB/Swiss-Prot, using manually curated profiles for protein sequence family classification and expert curated rules for functional annotation of family members. HAMAP data and tools are made available through our website and as part of the UniRule pipeline of UniProt, providing annotation for millions of unreviewed sequences of UniProtKB/TrEMBL. Here we report on the growth of HAMAP and updates to the HAMAP system since our last report in the NAR Database Issue of 2013. We continue to augment HAMAP with new family profiles and annotation rules as new protein families are characterized and annotated in UniProtKB/Swiss-Prot; the latest version of HAMAP (as of 3 September 2014) contains 1983 family classification profiles and 1998 annotation rules (up from 1780 and 1720). We demonstrate how the complex logic of HAMAP rules allows for precise annotation of individual functional variants within large homologous protein families. We also describe improvements to our web-based tool HAMAP-Scan which simplify the classification and annotation of sequences, and the incorporation of an improved sequence-profile search algorithm.

HAMAP in 2013, new developments in the protein family classification and annotation system.

HAMAP (High-quality Automated and Manual Annotation of Proteins-available at http://hamap.expasy.org/) is a system for the classification and annotation of protein sequences. It consists of a collection of manually curated family profiles for protein classification, and associated annotation rules that specify annotations that apply to family members. HAMAP was originally developed to support the manual curation of UniProtKB/Swiss-Prot records describing microbial proteins. Here we describe new developments in HAMAP, including the extension of HAMAP to eukaryotic proteins, the use of HAMAP in the automated annotation of UniProtKB/TrEMBL, providing high-quality annotation for millions of protein sequences, and the future integration of HAMAP into a unified system for UniProtKB annotation, UniRule. HAMAP is continuously updated by expert curators with new family profiles and annotation rules as new protein families are characterized. The collection of HAMAP family classification profiles and annotation rules can be browsed and viewed on the HAMAP website, which also provides an interface to scan user sequences against HAMAP profiles.

Genetic variations and diseases in UniProtKB/Swiss-Prot: the ins and outs of expert manual curation.

During the last few years, next-generation sequencing (NGS) technologies have accelerated the detection of genetic variants resulting in the rapid discovery of new disease-associated genes. However, the wealth of variation data made available by NGS alone is not sufficient to understand the mechanisms underlying disease pathogenesis and manifestation. Multidisciplinary approaches combining sequence and clinical data with prior biological knowledge are needed to unravel the role of genetic variants in human health and disease. In this context, it is crucial that these data are linked, organized, and made readily available through reliable online resources. The Swiss-Prot section of the Universal Protein Knowledgebase (UniProtKB/Swiss-Prot) provides the scientific community with a collection of information on protein functions, interactions, biological pathways, as well as human genetic diseases and variants, all manually reviewed by experts. In this article, we present an overview of the information content of UniProtKB/Swiss-Prot to show how this knowledgebase can support researchers in the elucidation of the mechanisms leading from a molecular defect to a disease phenotype.

The UniProt-GO Annotation database in 2011.

The GO annotation dataset provided by the UniProt Consortium (GOA: http://www.ebi.ac.uk/GOA) is a comprehensive set of evidenced-based associations between terms from the Gene Ontology resource and UniProtKB proteins. Currently supplying over 100 million annotations to 11 million proteins in more than 360,000 taxa, this resource has increased 2-fold over the last 2 years and has benefited from a wealth of checks to improve annotation correctness and consistency as well as now supplying a greater information content enabled by GO Consortium annotation format developments. Detailed, manual GO annotations obtained from the curation of peer-reviewed papers are directly contributed by all UniProt curators and supplemented with manual and electronic annotations from 36 model organism and domain-focused scientific resources. The inclusion of high-quality, automatic annotation predictions ensures the UniProt GO annotation dataset supplies functional information to a wide range of proteins, including those from poorly characterized, non-model organism species. UniProt GO annotations are freely available in a range of formats accessible by both file downloads and web-based views. In addition, the introduction of a new, normalized file format in 2010 has made for easier handling of the complete UniProt-GOA data set.

EnzChemRED, a rich enzyme chemistry relation extraction dataset.

Expert curation is essential to capture knowledge of enzyme functions from the scientific literature in FAIR open knowledgebases but cannot keep pace with the rate of new discoveries and new publications. In this work we present EnzChemRED, for Enzyme Chemistry Relation Extraction Dataset, a new training and benchmarking dataset to support the development of Natural Language Processing (NLP) methods such as (large) language models that can assist enzyme curation. EnzChemRED consists of 1,210 expert curated PubMed abstracts where enzymes and the chemical reactions they catalyze are annotated using identifiers from the protein knowledgebase UniProtKB and the chemical ontology ChEBI. We show that fine-tuning language models with EnzChemRED significantly boosts their ability to identify proteins and chemicals in text (86.30% F1 score) and to extract the chemical conversions (86.66% F1 score) and the enzymes that catalyze those conversions (83.79% F1 score). We apply our methods to abstracts at PubMed scale to create a draft map of enzyme functions in literature to guide curation efforts in UniProtKB and the reaction knowledgebase Rhea.

EnzChemRED, a rich enzyme chemistry relation extraction dataset.

Expert curation is essential to capture knowledge of enzyme functions from the scientific literature in FAIR open knowledgebases but cannot keep pace with the rate of new discoveries and new publications. In this work we present EnzChemRED, for Enzyme Chemistry Relation Extraction Dataset, a new training and benchmarking dataset to support the development of Natural Language Processing (NLP) methods such as (large) language models that can assist enzyme curation. EnzChemRED consists of 1,210 expert curated PubMed abstracts in which enzymes and the chemical reactions they catalyze are annotated using identifiers from the UniProt Knowledgebase (UniProtKB) and the ontology of Chemical Entities of Biological Interest (ChEBI). We show that fine-tuning pre-trained language models with EnzChemRED can significantly boost their ability to identify mentions of proteins and chemicals in text (Named Entity Recognition, or NER) and to extract the chemical conversions in which they participate (Relation Extraction, or RE), with average F1 score of 86.30% for NER, 86.66% for RE for chemical conversion pairs, and 83.79% for RE for chemical conversion pairs and linked enzymes. We combine the best performing methods after fine-tuning using EnzChemRED to create an end-to-end pipeline for knowledge extraction from text and apply this to abstracts at PubMed scale to create a draft map of enzyme functions in literature to guide curation efforts in UniProtKB and the reaction knowledgebase Rhea. The EnzChemRED corpus is freely available at https://ftp.expasy.org/databases/rhea/nlp/.

Diverse Taxonomies for Diverse Chemistries: Enhanced Representation of Natural Product Metabolism in UniProtKB.

The UniProt Knowledgebase UniProtKB is a comprehensive, high-quality, and freely accessible resource of protein sequences and functional annotation that covers genomes and proteomes from tens of thousands of taxa, including a broad range of plants and microorganisms producing natural products of medical, nutritional, and agronomical interest. Here we describe work that enhances the utility of UniProtKB as a support for both the study of natural products and for their discovery. The foundation of this work is an improved representation of natural product metabolism in UniProtKB using Rhea, an expert-curated knowledgebase of biochemical reactions, that is built on the ChEBI (Chemical Entities of Biological Interest) ontology of small molecules. Knowledge of natural products and precursors is captured in ChEBI, enzyme-catalyzed reactions in Rhea, and enzymes in UniProtKB/Swiss-Prot, thereby linking chemical structure data directly to protein knowledge. We provide a practical demonstration of how users can search UniProtKB for protein knowledge relevant to natural products through interactive or programmatic queries using metabolite names and synonyms, chemical identifiers, chemical classes, and chemical structures and show how to federate UniProtKB with other data and knowledge resources and tools using semantic web technologies such as RDF and SPARQL. All UniProtKB data are freely available for download in a broad range of formats for users to further mine or exploit as an annotation source, to enrich other natural product datasets and databases.