{"doi":"10.1093/nar/gkx967","title":"EBI Metagenomics in 2017: enriching the analysis of microbial communities, from sequence reads to assemblies","abstract":"EBI metagenomics (http://www.ebi.ac.uk/metagenomics) provides a free to use platform for the analysis and archiving of sequence data derived from the microbial populations found in a particular environment. Over the past two years, EBI metagenomics has increased the number of datasets analysed 10-fold. In addition to increased throughput, the underlying analysis pipeline has been overhauled to include both new or updated tools and reference databases. Of particular note is a new workflow for taxonomic assignments that has been extended to include assignments based on both the large and small subunit RNA marker genes and to encompass all cellular micro-organisms. We also describe the addition of metagenomic assembly as a new analysis service. Our pilot studies have produced over 2400 assemblies from datasets in the public domain. From these assemblies, we have produced a searchable, non-redundant protein database of over 50 million sequences. To provide improved access to the data stored within the resource, we have developed a programmatic interface that provides access to the analysis results and associated sample metadata. Finally, we have integrated the results of a series of statistical analyses that provide estimations of diversity and sample comparisons.","journal":"Nucleic Acids Research","year":2017,"id":3162,"datarank":6.893147119388016,"base_score":5.476463551931511,"endowment":5.476463551931511,"self_citation_contribution":0.8214695327897268,"citation_network_contribution":6.071677586598289,"self_endowment_contribution":0.8214695327897268,"citer_contribution":6.071677586598289,"corpus_percentile":97.31569583043243,"corpus_rank":348,"citation_count":238,"citer_count":100,"citers_with_citation_signal":100,"citers_with_endowment":100,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.9235,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2017-10-23","fair_score":84.1667,"fair_percentile":93.59823399558499,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":29847,"name":"Maxim Scheremetjew","orcid":"0000-0002-7458-3072","position":1,"is_corresponding":false},{"id":29836,"name":"Hubert Denise","orcid":"0000-0001-9862-5890","position":2,"is_corresponding":false},{"id":34531,"name":"Simon Potter","orcid":"0000-0003-4208-4102","position":3,"is_corresponding":false},{"id":34532,"name":"Aleksandra Tarkowska","orcid":"0000-0002-3392-3691","position":4,"is_corresponding":false},{"id":34533,"name":"Matloob Qureshi","orcid":"0000-0003-2208-4236","position":5,"is_corresponding":false},{"id":34534,"name":"Gustavo A Salazar","orcid":"0000-0001-9208-4966","position":6,"is_corresponding":false},{"id":29845,"name":"Sebastien Pesseat","orcid":"0000-0003-3245-7921","position":7,"is_corresponding":false},{"id":34535,"name":"Miguel A Boland","orcid":"0000-0002-2703-8936","position":8,"is_corresponding":false},{"id":34537,"name":"Petra ten Hoopen","orcid":"0000-0003-4242-4015","position":10,"is_corresponding":false},{"id":34538,"name":"Blaise Alako","orcid":"0000-0001-6859-4421","position":11,"is_corresponding":false},{"id":18876,"name":"Clara Amid","orcid":"0000-0001-6534-7425","position":12,"is_corresponding":false},{"id":34539,"name":"Darren J. Wilkinson","orcid":"0000-0003-0736-802X","position":13,"is_corresponding":false},{"id":34540,"name":"Thomas P. Curtis","orcid":"0000-0002-9009-1748","position":14,"is_corresponding":false},{"id":11687,"name":"Guy Cochrane","orcid":"0000-0001-7954-7057","position":15,"is_corresponding":false},{"id":36329,"name":"Juan S. Escobar","orcid":"0000-0001-7304-917X","position":16,"is_corresponding":false},{"id":29842,"name":"Alex Mitchell","orcid":"0000-0001-8655-7966","position":17,"is_corresponding":false},{"id":34541,"name":"Fiona Hunter","orcid":"0000-0001-7160-1880","position":18,"is_corresponding":false}],"reference_count":44,"raw_metadata":null,"created_at":"2026-03-01T18:20:47.508186Z","pmid":"29069476","pmcid":"PMC5753268","fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":"gold","license":"cc-by","views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":100.0,"fair_a":70.0,"fair_i":100.0,"fair_r":66.6667,"fair_zscore":2.0352,"fair_rationale":{"fair_score":84.17,"has_llm":false,"dimensions":{"F":{"name":"Findable","score":100.0,"criteria":[{"key":"f_has_doi","label":"Has a persistent DOI","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"DOI present","rationale":null},{"key":"f_repository_presence","label":"Indexed in repositories / literature DBs","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"datacite=25, pmcid=True, pmid=True","rationale":null},{"key":"f_persistent_ids","label":"Resolvable scholarly identifiers (OpenAlex)","kind":"deterministic","weight":0.5,"fraction":1.0,"signal":"OpenAlex id present","rationale":null}]},"A":{"name":"Accessible","score":70.0,"criteria":[{"key":"a_open_access","label":"Open Access / files deposited","kind":"deterministic","weight":1.5,"fraction":0.5,"signal":"files/OA location present but not flagged OA","rationale":null},{"key":"a_retrievable","label":"Free full text retrievable","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"13 OA location(s)","rationale":null}]},"I":{"name":"Interoperable","score":100.0,"criteria":[{"key":"i_linked_data","label":"Linked datasets / DataCite relations","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"linked_datasets=25, datacite=25","rationale":null},{"key":"i_standard_ids","label":"References data via standard accessions","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"accessions=2, trials=0","rationale":null}]},"R":{"name":"Reusable","score":66.67,"criteria":[{"key":"r_license","label":"Clear, open reuse license","kind":"deterministic","weight":1.5,"fraction":1.0,"signal":"open license (cc-by)","rationale":null},{"key":"r_downloads","label":"Demonstrated reuse (downloads)","kind":"deterministic","weight":0.5,"fraction":0.0,"signal":"downloads=0","rationale":null},{"key":"r_version","label":"Versioned / maintained","kind":"deterministic","weight":0.5,"fraction":0.0,"signal":"no version chain","rationale":null},{"key":"r_dataset","label":"Classified as a data resource","kind":"deterministic","weight":0.5,"fraction":1.0,"signal":"is_dataset","rationale":null}]}},"suggestions":["Maintain explicit versioning for the dataset.","Make the paper/data Open Access or deposit the files in an open repository."],"model":null,"agent_version":"fair_agent_v3","fulltext_source":"epmc_xml"},"fair_model":null,"fair_agent_version":"fair_agent_v3","fair_fulltext_source":"epmc_xml","fair_has_llm":false,"fair_computed_at":"2026-06-26T22:07:33.842994Z","clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}