{"doi":"10.1093/database/bat029","title":"The MetaboLights repository: curation challenges in metabolomics","abstract":"MetaboLights is the first general-purpose open-access curated repository for metabolomic studies, their raw experimental data and associated metadata, maintained by one of the major open-access data providers in molecular biology. Increases in the number of depositions, number of samples per study and the file size of data submitted to MetaboLights present a challenge for the objective of ensuring high-quality and standardized data in the context of diverse metabolomic workflows and data representations. Here, we describe the MetaboLights curation pipeline, its challenges and its practical application in quality control of complex data depositions. Database URL: http://www.ebi.ac.uk/metabolights.","journal":"Database","year":2013,"id":11406,"datarank":2.2290716105535457,"base_score":4.007333185232471,"endowment":4.007333185232471,"self_citation_contribution":0.6010999777848708,"citation_network_contribution":1.627971632768675,"self_endowment_contribution":0.6010999777848708,"citer_contribution":1.627971632768675,"corpus_percentile":90.423145354684,"corpus_rank":1239,"citation_count":54,"citer_count":41,"citers_with_citation_signal":36,"citers_with_endowment":36,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.9562,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2013-01-01","fair_score":59.1667,"fair_percentile":42.7,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":7597,"name":"Kenneth Haug","orcid":"0000-0003-3168-4145","position":1,"is_corresponding":false},{"id":22181,"name":"Pablo Conesa","orcid":"0000-0003-0575-7718","position":2,"is_corresponding":false},{"id":71,"name":"Janna Hastings","orcid":"0000-0002-3469-4923","position":3,"is_corresponding":false},{"id":22183,"name":"Mark Williams","orcid":"0000-0002-1294-1110","position":4,"is_corresponding":false},{"id":22182,"name":"Tejasvi Mahendraker","orcid":null,"position":5,"is_corresponding":false},{"id":284,"name":"Eamonn Maguire","orcid":"0000-0002-7277-7834","position":6,"is_corresponding":false},{"id":5765,"name":"Philippe Rocca-Serra","orcid":null,"position":8,"is_corresponding":false},{"id":73,"name":"Christoph Steinbeck","orcid":"0000-0001-6966-0814","position":10,"is_corresponding":false},{"id":286,"name":"Alejandra Noemí González Beltrán","orcid":"0000-0003-3499-8262","position":11,"is_corresponding":false},{"id":289,"name":"Rocca-Serra, Philippe","orcid":"0000-0001-9853-5668","position":12,"is_corresponding":false},{"id":290,"name":"Susanna‐Assunta Sansone","orcid":"0000-0001-5306-5690","position":13,"is_corresponding":false},{"id":22184,"name":"Reza M. Salek","orcid":"0000-0001-8604-1732","position":0,"is_corresponding":true}],"reference_count":23,"raw_metadata":null,"created_at":"2026-03-01T18:20:47.508186Z","pmid":"23630246","pmcid":"PMC3638156","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":0.0,"fair_r":66.6667,"fair_zscore":0.4888,"fair_rationale":{"fair_score":59.17,"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=0, 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":"12 OA location(s)","rationale":null}]},"I":{"name":"Interoperable","score":0.0,"criteria":[{"key":"i_linked_data","label":"Linked datasets / DataCite relations","kind":"deterministic","weight":1.0,"fraction":0.0,"signal":"linked_datasets=0, datacite=0","rationale":null},{"key":"i_standard_ids","label":"References data via standard accessions","kind":"deterministic","weight":1.0,"fraction":0.0,"signal":"accessions=0, 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":["Link the underlying datasets via DOIs / DataCite relations.","Reference data using standard accessions (e.g. GEO, PDB, ClinicalTrials.gov).","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":"2026-07-06T15:14:09.120996Z","clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}