{"doi":"10.1371/journal.pcbi.1009757","title":"Ten simple rules for large-scale data processing","abstract":"Exabytes of images, sequences, tabular data, and unstructured data are now available for analysis to advance science. These data support efforts to visualize the image of the black hole [1], characterize the spectrum of mutations across cancer types [2], create a sophisticated language model [3], and many other tasks. Defining a data analysis as large scale or not is likely to be a moving target as computing and data transfer technologies advance. We consider an analysis large scale when the data size exceeds the capacity of local resources or when the amount of time spent waiting for high-performance computing (HPC) compute capacity would disrupt the pace of the research project. For example, the recount2 [4] analysis processed petabytes of data, so we consider it to be large-scale data processing for the current day standard.","journal":"PLoS Computational Biology","year":2022,"id":281123,"datarank":0.4406354931354932,"base_score":2.1972245773362196,"endowment":2.1972245773362196,"self_citation_contribution":0.32958368660043297,"citation_network_contribution":0.11105180653506024,"self_endowment_contribution":0.32958368660043297,"citer_contribution":0.11105180653506024,"corpus_percentile":null,"corpus_rank":null,"citation_count":8,"citer_count":8,"citers_with_citation_signal":6,"citers_with_endowment":6,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.8805,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2022-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":452,"name":"Alexandra J. Lee","orcid":"0000-0002-0208-3730","position":1,"is_corresponding":false},{"id":2967,"name":"Jaclyn N. Taroni","orcid":"0000-0003-4734-4508","position":2,"is_corresponding":false},{"id":37322,"name":"K. Wheeler","orcid":"0000-0002-0640-2903","position":3,"is_corresponding":false},{"id":2121,"name":"Chen-Shan Chin","orcid":"0000-0003-4394-2455","position":4,"is_corresponding":false},{"id":6971,"name":"Sean Davis","orcid":"0000-0002-8991-6458","position":5,"is_corresponding":false},{"id":308,"name":"Casey S. Greene","orcid":"0000-0001-8713-9213","position":6,"is_corresponding":false},{"id":49023,"name":"Arkarachai Fungtammasan","orcid":"0000-0003-2398-0358","position":0,"is_corresponding":true}],"reference_count":17,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T00:29:07.472902Z","pmid":"35143491","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}