{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32324791", "kind": "science-record", "revision": 7, "content_hash": "sha256:cbed5b37430e8a0dcf902dadacb5a8b83de7a374ac1bb5686061680bf1a2332f", "created_at": "2026-11-01T15:41:00Z", "updated_at": "2026-11-01T22:01:33Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Normal myeloid progenitor cell subset-associated gene signatures for acute myeloid leukaemia subtyping with prognostic impact.", "doi": "10.1371/journal.pone.0229593", "pmid": "32324791", "authors": ["Anna A Schönherz", "Julie Støve Bødker", "Alexander Schmitz", "Rasmus Froberg Brøndum", "Lasse Hjort Jakobsen", "Anne Stidsholt Roug", "Marianne T Severinsen", "Tarec C El-Galaly", "Paw Jensen", "Hans Erik Johnsen", "Martin Bøgsted", "Karen Dybkær"], "journal": "PloS one", "year": 2020, "abstract": "Acute myeloid leukaemia (AML) is characterised by phenotypic heterogeneity, which we hypothesise is a consequence of deregulated differentiation with transcriptional reminiscence of the normal compartment or cell-of-origin. Here, we propose a classification system based on normal myeloid progenitor cell subset-associated gene signatures (MAGS) for individual assignments of AML subtypes. We generated a MAGS classifier including the progenitor compartments CD34+/CD38- for haematopoietic stem cells (HSCs), CD34+/CD38+/CD45RA- for megakaryocyte-erythroid progenitors (MEPs), and CD34+/CD38+/CD45RA+ for granulocytic-monocytic progenitors (GMPs) using regularised multinomial regression with three discrete outcomes and an elastic net penalty. The regularisation parameters were chosen by cross-validation, and MAGS assignment accuracy was validated in an independent data set (N = 38; accuracy = 0.79) of sorted normal myeloid subpopulations. The prognostic value of MAGS assignment was studied in two clinical cohorts (TCGA: N = 171; GSE6891: N = 520) and had a significant prognostic impact. Furthermore, multivariate Cox regression analysis using the MAGS subtype, FAB subtype, cytogenetics, molecular genetics, and age as explanatory variables showed independent prognostic value. Molecular characterisation of subtypes by differential gene expression analysis, gene set enrichment analysis, and mutation patterns indicated reduced proliferation and overrepresentation of RUNX1 and IDH2 mutations in the HSC subtype; increased proliferation and overrepresentation of CEBPA mutations in the MEP subtype; and innate immune activation and overrepresentation of WT1 mutations in the GMP subtype. We present a differentiation-dependent classification system for AML subtypes with distinct pathogenetic and prognostic importance that can help identify candidates poorly responding to combination chemotherapy and potentially guide alternative treatments.", "claims": [{"id": "claim-method", "statement": "The MAGS classifier for the HSC, MEP, and GMP subsets was obtained from regularised multinomial regression with the cell type as the discrete outcome and the median-centred GEP of the training cohort as the explanatory variable. The model was fitted with an elastic net penalty.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32324791", "locator": "sections[4] \"Statistical analysis\" paragraph 3", "quote": "The MAGS classifier for the HSC, MEP, and GMP subsets was obtained from regularised multinomial regression with the cell type as the discrete outcome and the median-centred GEP of the training cohort as the explanatory variable. The model was fitted with an elastic net penalty."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All relevant data are within the manuscript and its Supporting Information files.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32324791", "locator": "sections[17] \"Data Availability\" paragraph 2", "quote": "All relevant data are within the manuscript and its Supporting Information files."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:32324791"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE17054"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE17054"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32324791", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0229593", "sha256": "sha256:c346b44364cb23b60d9ffb91c2b7f677b363a7db92af6586046c722e4072c4b8", "bytes": 58545, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0229593", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7179860", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE17054", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE17054", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE17054", "version": null, "note": "All relevant data are within the manuscript and its Supporting Information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All relevant data are within the manuscript and its Supporting Information files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM426404", "GSM426405", "GSM426406", "GSM426407", "GSM426408", "GSM426409", "GSM426410", "GSM426411", "GSM426412", "GSM426413", "GSM426414", "GSM426415", "GSM426416"], "sample_count": 13, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Dysregulated gene expression networks in human acute myelogenous leukemia stem cells", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE19429", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE19429", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19429", "version": null, "note": "All relevant data are within the manuscript and its Supporting Information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All relevant data are within the manuscript and its Supporting Information files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM483297", "GSM483298", "GSM483299", "GSM483300", "GSM483301", "GSM483302", "GSM483303", "GSM483304", "GSM483305", "GSM483306", "GSM483307", "GSM483308", "GSM483309", "GSM483310", "GSM483311", "GSM483312", "GSM483313", "GSM483314", "GSM483315", "GSM483316", "GSM483317", "GSM483318", "GSM483319", "GSM483320", "GSM483321", "GSM483322", "GSM483323", "GSM483324", "GSM483325", "GSM483326", "GSM483327", "GSM483328", "GSM483329", "GSM483330", "GSM483331", "GSM483332", "GSM483333", "GSM483334", "GSM483335", "GSM483336", "GSM483337", "GSM483338", "GSM483339", "GSM483340", "GSM483341", "GSM483342", "GSM483343", "GSM483344", "GSM483345", "GSM483346", "GSM483347", "GSM483348", "GSM483349", "GSM483350", "GSM483351", "GSM483352", "GSM483353", "GSM483354", "GSM483355", "GSM483356", "GSM483357", "GSM483358", "GSM483359", "GSM483360", "GSM483361", "GSM483362", "GSM483363", "GSM483364", "GSM483365", "GSM483366", "GSM483367", "GSM483368", "GSM483369", "GSM483370", "GSM483371", "GSM483372", "GSM483373", "GSM483374", "GSM483375", "GSM483376", "GSM483377", "GSM483378", "GSM483379", "GSM483380", "GSM483381", "GSM483382", "GSM483383", "GSM483384", "GSM483385", "GSM483386", "GSM483387", "GSM483388", "GSM483389", "GSM483390", "GSM483391", "GSM483392", "GSM483393", "GSM483394", "GSM483395", "GSM483396", "GSM483397", "GSM483398", "GSM483399", "GSM483400", "GSM483401", "GSM483402", "GSM483403", "GSM483404", "GSM483405", "GSM483406", "GSM483407", "GSM483408", "GSM483409", "GSM483410", "GSM483411", "GSM483412", "GSM483413", "GSM483414", "GSM483415", "GSM483416", "GSM483417", "GSM483418", "GSM483419", "GSM483420", "GSM483421", "GSM483422", "GSM483423", "GSM483424", "GSM483425", "GSM483426", "GSM483427", "GSM483428", "GSM483429", "GSM483430", "GSM483431", "GSM483432", "GSM483433", "GSM483434", "GSM483435", "GSM483436", "GSM483437", "GSM483438", "GSM483439", "GSM483440", "GSM483441", "GSM483442", "GSM483443", "GSM483444", "GSM483445", "GSM483446", "GSM483447", "GSM483448", "GSM483449", "GSM483450", "GSM483451", "GSM483452", "GSM483453", "GSM483454", "GSM483455", "GSM483456", "GSM483457", "GSM483458", "GSM483459", "GSM483460", "GSM483461", "GSM483462", "GSM483463", "GSM483464", "GSM483465", "GSM483466", "GSM483467", "GSM483468", "GSM483469", "GSM483470", "GSM483471", "GSM483472", "GSM483473", "GSM483474", "GSM483475", "GSM483476", "GSM483477", "GSM483478", "GSM483479", "GSM483480", "GSM483481", "GSM483482", "GSM483483", "GSM483484", "GSM483485", "GSM483486", "GSM483487", "GSM483488", "GSM483489", "GSM483490", "GSM483491", "GSM483492", "GSM483493", "GSM483494", "GSM483495", "GSM483496"], "sample_count": 200, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from bone marrow CD34+ cells of MDS patients and healthy controls", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE19599", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE19599", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19599", "version": null, "note": "All relevant data are within the manuscript and its Supporting Information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All relevant data are within the manuscript and its Supporting Information files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM488968", "GSM488969", "GSM488970", "GSM488971", "GSM488972", "GSM488973", "GSM488974", "GSM488975", "GSM488976", "GSM488977", "GSM488978", "GSM488979", "GSM488980", "GSM488981", "GSM488982", "GSM488983"], "sample_count": 16, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data for normal flow sorted hematopietic cell subpopulations", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE42519", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42519", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE42519", "version": null, "note": "All relevant data are within the manuscript and its Supporting Information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All relevant data are within the manuscript and its Supporting Information files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1041380", "GSM1041381", "GSM1041382", "GSM1041383", "GSM1041384", "GSM1041385", "GSM1041386", "GSM1041387", "GSM1041388", "GSM1041389", "GSM1041390", "GSM1041391", "GSM1041392", "GSM1041393", "GSM1041394", "GSM1041395", "GSM1041396", "GSM1041397", "GSM1041398", "GSM1041399", "GSM1041400", "GSM1041401", "GSM1041402", "GSM1041403", "GSM1041404", "GSM1041405", "GSM1041406", "GSM1041407", "GSM1041408", "GSM1041409", "GSM1041410", "GSM1041411", "GSM1041412", "GSM1041413"], "sample_count": 34, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "The Hematopoietic System - Myeloid arm", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE63270", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE63270", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63270", "version": null, "note": "All relevant data are within the manuscript and its Supporting Information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All relevant data are within the manuscript and its Supporting Information files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1544800", "GSM1544801", "GSM1544802", "GSM1544803", "GSM1544804", "GSM1544805", "GSM1544806", "GSM1544807", "GSM1544808", "GSM1544809", "GSM1544810", "GSM1544811", "GSM1544812", "GSM1544813", "GSM1544814", "GSM1544815", "GSM1544816", "GSM1544817", "GSM1544818", "GSM1544819", "GSM1544820", "GSM1544821", "GSM1544822", "GSM1544823", "GSM1544824", "GSM1544825", "GSM1544826", "GSM1544827", "GSM1544828", "GSM1544829", "GSM1544830", "GSM1544831", "GSM1544832", "GSM1544833", "GSM1544834", "GSM1544835", "GSM1544836", "GSM1544837", "GSM1544838", "GSM1544839", "GSM1544840", "GSM1544841", "GSM1544842", "GSM1544843", "GSM1544844", "GSM1544845", "GSM1544846", "GSM1544847", "GSM1544848", "GSM1544849", "GSM1544850", "GSM1544851", "GSM1544852", "GSM1544853", "GSM1544854", "GSM1544855", "GSM1544856", "GSM1544857", "GSM1544858", "GSM1544859", "GSM1544860", "GSM1544861", "GSM1544862", "GSM1544863", "GSM1544864", "GSM1544865", "GSM1544866", "GSM1544867", "GSM1544868", "GSM1544869", "GSM1544870", "GSM1544871", "GSM1544872", "GSM1544873", "GSM1544874", "GSM1544875", "GSM1544876", "GSM1544877", "GSM1544878", "GSM1544879", "GSM1544880", "GSM1544881", "GSM1544882", "GSM1544883", "GSM1544884", "GSM1544885", "GSM1544886", "GSM1544887", "GSM1544888", "GSM1544889", "GSM1544890", "GSM1544891", "GSM1544892", "GSM1544893", "GSM1544894", "GSM1544895", "GSM1544896", "GSM1544897", "GSM1544898", "GSM1544899", "GSM1544900", "GSM1544901", "GSM1544902", "GSM1544903"], "sample_count": 104, "group_sizes": null, "group_sizes_basis": null, "platform": "17810", "taxon": "Homo sapiens", "title": "Expression profiles of normal hematopoietic stem and progenitor cells and acute myeloid leukemia sub-populations", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE6891", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE6891", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6891", "version": null, "note": "All relevant data are within the manuscript and its Supporting Information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All relevant data are within the manuscript and its Supporting Information files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM158711", "GSM158712", "GSM158713", "GSM158714", "GSM158715", "GSM158716", "GSM158717", "GSM158718", "GSM158719", "GSM158720", "GSM158721", "GSM158722", "GSM158723", "GSM158724", "GSM158725", "GSM158726", "GSM158727", "GSM158728", "GSM158729", "GSM158730", "GSM158731", "GSM158732", "GSM158733", "GSM158734", "GSM158735", "GSM158736", "GSM158737", "GSM158738", "GSM158739", "GSM158740", "GSM158741", "GSM158742", "GSM158743", "GSM158744", "GSM158745", "GSM158746", "GSM158747", "GSM158748", "GSM158749", "GSM158750", "GSM158751", "GSM158752", "GSM158753", "GSM158754", "GSM158755", "GSM158756", "GSM158757", "GSM158758", "GSM158759", "GSM158760", "GSM158761", "GSM158762", "GSM158763", "GSM158764", "GSM158765", "GSM158766", "GSM158767", "GSM158768", "GSM158769", "GSM158770", "GSM158771", "GSM158772", "GSM158773", "GSM158774", "GSM158775", "GSM158776", "GSM158777", "GSM158778", "GSM158779", "GSM158780", "GSM158781", "GSM158782", "GSM158783", "GSM158784", "GSM158785", "GSM158786", "GSM158787", "GSM158788", "GSM158789", "GSM158790", "GSM158791", "GSM158792", "GSM158793", "GSM158794", "GSM158795", "GSM158796", "GSM158797", "GSM158798", "GSM158799", "GSM158800", "GSM158801", "GSM158802", "GSM158803", "GSM158804", "GSM158805", "GSM158806", "GSM158807", "GSM158808", "GSM158809", "GSM158810", "GSM158811", "GSM158812", "GSM158813", "GSM158814", "GSM158815", "GSM158816", "GSM158817", "GSM158818", "GSM158819", "GSM158820", "GSM158821", "GSM158822", "GSM158823", "GSM158824", "GSM158825", "GSM158826", "GSM158827", "GSM158828", "GSM158829", "GSM158830", "GSM158831", "GSM158832", "GSM158833", "GSM158834", "GSM158835", "GSM158836", "GSM158837", "GSM158838", "GSM158839", "GSM158840", "GSM158841", "GSM158842", "GSM158843", "GSM158844", "GSM158845", "GSM158846", "GSM158847", "GSM158848", "GSM158849", "GSM158850", "GSM158851", "GSM158852", "GSM158853", "GSM158854", "GSM158855", "GSM158856", "GSM158857", "GSM158858", "GSM158859", "GSM158860", "GSM158861", "GSM158862", "GSM158863", "GSM158864", "GSM158865", "GSM158866", "GSM158867", "GSM158868", "GSM158869", "GSM158870", "GSM158871", "GSM158872", "GSM158873", "GSM158874", "GSM158875", "GSM158876", "GSM158877", "GSM158878", "GSM158879", "GSM158880", "GSM158881", "GSM158882", "GSM158883", "GSM158884", "GSM158885", "GSM158886", "GSM158887", "GSM158888", "GSM158889", "GSM158890", "GSM158891", "GSM158892", "GSM158893", "GSM158894", "GSM158895", "GSM158896", "GSM158897", "GSM158898", "GSM158899", "GSM158900", "GSM158901", "GSM158902", "GSM158903", "GSM158904", "GSM158905", "GSM158906", "GSM158907", "GSM158908", "GSM158909", "GSM158910", "GSM158911", "GSM158912", "GSM158913", "GSM158914", "GSM158915", "GSM158916", "GSM158917", "GSM158918", "GSM158919", "GSM158920", "GSM158921", "GSM158922", "GSM158923", "GSM158924", "GSM158925", "GSM158926", "GSM158927", "GSM158928", "GSM158929", "GSM158930", "GSM158931", "GSM158932", "GSM158933", "GSM158934", "GSM158935", "GSM158936", "GSM158937", "GSM158938", "GSM158939", "GSM158940", "GSM158941", "GSM158942", "GSM158943", "GSM158944", "GSM158945", "GSM158946", "GSM158947", "GSM158948", "GSM158949", "GSM158950", "GSM158951", "GSM158952", "GSM158953", "GSM158954", "GSM158955", "GSM158956", "GSM158957", "GSM158958", "GSM158959", "GSM158960", "GSM158961", "GSM158962", "GSM158963", "GSM158964", "GSM158965", "GSM158966", "GSM158967", "GSM158968", "GSM158969", "GSM158970", "GSM158971", "GSM158972", "GSM158973", "GSM158974", "GSM158975", "GSM158976", "GSM158977", "GSM158978", "GSM158979", "GSM158980", "GSM158981", "GSM158982", "GSM158983", "GSM158984", "GSM158985", "GSM158986", "GSM158987", "GSM158988", "GSM158989", "GSM158990", "GSM158991", "GSM158992", "GSM158993", "GSM158994", "GSM158995", "GSM158996", "GSM158997", "GSM158998", "GSM158999", "GSM159000", "GSM159001", "GSM159002", "GSM159003", "GSM159004", "GSM159005", "GSM159006", "GSM159007", "GSM159008", "GSM159009", "GSM159010", "GSM159011", "GSM159012", "GSM159013", "GSM159014", "GSM159015", "GSM159016", "GSM159017", "GSM159018", "GSM159019", "GSM159020", "GSM159021", "GSM159022", "GSM159023", "GSM159024", "GSM159025", "GSM159026", "GSM159027", "GSM159028", "GSM159029", "GSM159030", "GSM159031", "GSM159032", "GSM159033", "GSM159034", "GSM159035", "GSM159036", "GSM159037", "GSM159038", "GSM159039", "GSM159040", "GSM159041", "GSM159042", "GSM159043", "GSM159044", "GSM159045", "GSM159046", "GSM159047", "GSM159048", "GSM159049", "GSM159050", "GSM159051", "GSM159052", "GSM159053", "GSM159054", "GSM159055", "GSM159056", "GSM159057", "GSM159058", "GSM159059", "GSM159060", "GSM159061", "GSM159062", "GSM159063", "GSM159064", "GSM159065", "GSM159066", "GSM159067", "GSM159068", "GSM159069", "GSM159070", "GSM159071", "GSM159072", "GSM159073", "GSM159074", "GSM159075", "GSM159076", "GSM159077", "GSM159078", "GSM159079", "GSM159080", "GSM159081", "GSM159082", "GSM159083", "GSM159084", "GSM159085", "GSM159086", "GSM159087", "GSM159088", "GSM159089", "GSM159090", "GSM159091", "GSM159092", "GSM159093", "GSM159094", "GSM159095", "GSM159096", "GSM159097", "GSM159098", "GSM159099", "GSM159100", "GSM159101", "GSM159102", "GSM159103", "GSM159104", "GSM159105", "GSM159106", "GSM159107", "GSM159108", "GSM159109", "GSM159110", "GSM159111", "GSM159112", "GSM159113", "GSM159114", "GSM159115", "GSM159116", "GSM159117", "GSM159118", "GSM159119", "GSM159120", "GSM159121", "GSM159122", "GSM159123", "GSM159124", "GSM159125", "GSM159126", "GSM159127", "GSM159128", "GSM159129", "GSM159130", "GSM159131", "GSM159132", "GSM159133", "GSM159134", "GSM159135", "GSM159136", "GSM159137", "GSM159138", "GSM159139", "GSM159140", "GSM159141", "GSM159142", "GSM159143", "GSM159144", "GSM159145", "GSM159146", "GSM159147", "GSM159148", "GSM159149", "GSM159150", "GSM159151", "GSM159152", "GSM159153", "GSM159154", "GSM159155", "GSM159156", "GSM159157", "GSM159158", "GSM159159", "GSM159160", "GSM159161", "GSM159162", "GSM159163", "GSM159164", "GSM159165", "GSM159166", "GSM159167", "GSM159168", "GSM159169", "GSM159170", "GSM159171", "GSM768679", "GSM768680", "GSM768681", "GSM768682", "GSM768683", "GSM768684", "GSM768685", "GSM768686", "GSM768687", "GSM768688", "GSM768689", "GSM768690", "GSM768691", "GSM768692", "GSM768693", "GSM768694", "GSM768695", "GSM768696", "GSM768697", "GSM768698", "GSM768699", "GSM768700", "GSM768701", "GSM768702", "GSM768703", "GSM768704", "GSM768705", "GSM768706", "GSM768707", "GSM768708", "GSM768709", "GSM768710", "GSM768711", "GSM768712", "GSM768713", "GSM768714", "GSM768715", "GSM768716", "GSM768717", "GSM768718", "GSM768719", "GSM768720", "GSM768721", "GSM768722", "GSM768723", "GSM768724", "GSM768725", "GSM768726", "GSM768727", "GSM768728", "GSM768729", "GSM768730", "GSM768731", "GSM768732", "GSM768733", "GSM768734", "GSM768735", "GSM768736", "GSM768737", "GSM768738", "GSM768739", "GSM768740", "GSM768741", "GSM768742", "GSM768743", "GSM768744", "GSM768745", "GSM768746", "GSM768747", "GSM768748", "GSM768749", "GSM768750", "GSM768751", "GSM768752", "GSM768753", "GSM768754"], "sample_count": 537, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Acute myeloid leukemia samples of samples =< 60yrs on HG-U133 plus 2", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32324791:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e9d46dab0d6bbf697c2de554520b4f2f9c8abfb03a57c9e8fa7dec7736a588de", "bytes": 871, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#pone.0229593.t001", "version": null, "note": "MAGS prediction accuracy assigning 100% (A) or 85% (B) of the samples to the defined MAGS subtypes HSC, GMP, MEP, and an additional UC subtype.", "structure": {"pmcid": "PMC7179860", "section_index": 10, "section_title": "Generation and validation of MAGS", "row_count": 10, "column_count": 6}, "table": {"label": "Table 1", "caption": "MAGS prediction accuracy assigning 100% (A) or 85% (B) of the samples to the defined MAGS subtypes HSC, GMP, MEP, and an additional UC subtype.", "rows": [["A)", "", "Predicted", "Invalid Prediction (%)"], ["Observed", "", "HSC (%)", "MEP (%)", "GMP (%)", "UC (%)"], ["HSC (N = 26)", "18 (69.2)", "4 (15.4)", "4 (15.4)", "-", "8 (30.8)"], ["MEP (N = 5)", "0 (0)", "5 (100)", "0 (0)", "-", "0 (0)"], ["GMP (N = 7)", "0 (0)", "0 (0)", "7 (100)", "-", "0 (0)"], ["B)", "", "Predicted", "Invalid Prediction (%)"], ["Observed", "", "HSC (%)", "MEP (%)", "GMP (%)", "UC (%)"], ["HSC (N = 26)", "17 (65.4)", "3 (11.5)", "0 (0)", "6 (23.1)", "9 (34.6)"], ["MEP (N = 5)", "0 (0)", "5 (100)", "0 (0)", "0 (0)", "0 (0)"], ["GMP (N = 7)", "0 (0)", "0 (0)", "7 (100)", "0 (0)", "0 (0)"]], "row_count": 10, "column_count": 6, "numeric_cells": 33, "header_rows": 0, "locator": "section[10]/table-wrap[1]#pone.0229593.t001"}}, {"id": "asset:table:pmid:32324791:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:41ae1ff84260f8a631edb61f04f046e5df3119baf943f0230b416270d02f7d09", "bytes": 610, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#pone.0229593.t002", "version": null, "note": "Distributions and frequencies of assigned MAGS subtypes across two clinical cohorts: TCGA (N = 182) and GSE6891 (N = 520).Two-sided Fishers exact tests were used to determine significantly different distributions across data sets (p = 0.99).", "structure": {"pmcid": "PMC7179860", "section_index": 11, "section_title": "MAGS assignment of clinical samples and prognostic impact", "row_count": 3, "column_count": 6}, "table": {"label": "Table 2", "caption": "Distributions and frequencies of assigned MAGS subtypes across two clinical cohorts: TCGA (N = 182) and GSE6891 (N = 520).Two-sided Fishers exact tests were used to determine significantly different distributions across data sets (p = 0.99).", "rows": [["Cohort", "HSC (%)", "MEP (%)", "GMP (%)", "UC (%)", "Total (%)"], ["TCGA", "50 (27.5)", "48 (26.4)", "56 (30.8)", "28 (15.4)", "182 (100)"], ["GSE6891", "146 (28.1)", "134 (25.8)", "162 (31.2)", "78 (15.0)", "520 (100)"]], "row_count": 3, "column_count": 6, "numeric_cells": 11, "header_rows": 1, "locator": "section[11]/table-wrap[1]#pone.0229593.t002"}}, {"id": "asset:table:pmid:32324791:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e1435be04c29712a8ccb4c73782a04ff5a4a1c9775aa00f2df517802c4133e73", "bytes": 1403, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#pone.0229593.t003", "version": null, "note": "Univariate Cox regression analysis for MAGS-assigned clinical cohorts (GSE6891 cohort: N = 520; TCGA-cohort: N = 171) and the corresponding AML meta-cohort (N = 691) that included both clinical cohorts.Analyses were performed for overall survival. Samples with missing survival information (TCGA cohort: N = 11) were excluded. Table columns indicate the total sample size (N), the number of patients that died (Events) per MAGS subtype, the associated hazards ration (HR), the 95% lower and upper confidence intervals (CI), and the estimated p-value (P).", "structure": {"pmcid": "PMC7179860", "section_index": 11, "section_title": "MAGS assignment of clinical samples and prognostic impact", "row_count": 16, "column_count": 6}, "table": {"label": "Table 3", "caption": "Univariate Cox regression analysis for MAGS-assigned clinical cohorts (GSE6891 cohort: N = 520; TCGA-cohort: N = 171) and the corresponding AML meta-cohort (N = 691) that included both clinical cohorts.Analyses were performed for overall survival. Samples with missing survival information (TCGA cohort: N = 11) were excluded. Table columns indicate the total sample size (N), the number of patients that died (Events) per MAGS subtype, the associated hazards ration (HR), the 95% lower and upper confidence intervals (CI), and the estimated p-value (P).", "rows": [["", "N", "Events", "HR", "95% CI", "P"], ["TCGA cohort", "", "", "", "", ""], ["HSC", "48", "40", "1", "", ""], ["MEP", "44", "22", "0.44", "0.26–0.74", "1.90e-03**"], ["GMP", "52", "34", "0.68", "0.43–1.08", "0.1"], ["UC", "27", "14", "0.37", "0.20–0.69", "1.63e-03**"], ["GSE6891 cohort", "", "", "", "", ""], ["HSC", "146", "115", "1", "", ""], ["MEP", "134", "77", "0.53", "0.40–0.71", "2.13e-05***"], ["GMP", "162", "101", "0.63", "0.48–0.83", "7.86e-04***"], ["UC", "78", "52", "0.70", "0.51–0.98", "0.03"], ["Meta-cohorta", "", "", "", "", ""], ["HSC", "194", "155", "1", "", ""], ["MEP", "178", "99", "0.51", "0.40–0.65", "1.46e-07***"], ["GMP", "214", "135", "0.64", "0.51–0.81", "1.64e-04***"], ["UC", "105", "66", "0.60", "0.45–0.80", "5.32e-04***"]], "row_count": 16, "column_count": 6, "numeric_cells": 56, "header_rows": 1, "locator": "section[11]/table-wrap[2]#pone.0229593.t003"}}, {"id": "asset:table:pmid:32324791:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d616118d0c6f505e19ab2e800a7ed0eff0b4edc69f33f7b696a02a58395ded1c", "bytes": 8121, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[3]#pone.0229593.t004", "version": null, "note": "Cox regression analysis of potential confounding variables conducted for the TCGA (N = 122), GSE6891 (N = 439), and meta-cohort (N = 561).Cohorts were limited to samples with complete records for all explanatory variables investigated. Results are shown for the (A) univariate Cox regression analysis per explanatory variable and (B) associated multivariate Cox regression analyses limited to confounding variables tested significant in univariate Cox regression analyses. Table columns are as described in Table 3. Analyses were performed for overall survival.", "structure": {"pmcid": "PMC7179860", "section_index": 11, "section_title": "MAGS assignment of clinical samples and prognostic impact", "row_count": 69, "column_count": 17}, "table": {"label": "Table 4", "caption": "Cox regression analysis of potential confounding variables conducted for the TCGA (N = 122), GSE6891 (N = 439), and meta-cohort (N = 561).Cohorts were limited to samples with complete records for all explanatory variables investigated. Results are shown for the (A) univariate Cox regression analysis per explanatory variable and (B) associated multivariate Cox regression analyses limited to confounding variables tested significant in univariate Cox regression analyses. Table columns are as described in Table 3. Analyses were performed for overall survival.", "rows": [["A) Simple Cox Regression", "", ""], ["", "TCGA cohort (N = 122)", "GSE6891 cohort (N = 439)", "AML meta-cohort (N = 561)"], ["", "", "N", "Events", "HR", "95% CI", "P", "N", "Events", "HR", "95% CI", "P", "N", "Events", "HR", "95% CI", "P"], ["MAGS", "HSC", "37", "32", "1", "", "", "120", "93", "1", "", "", "157", "125", "1", "", ""], ["MEP", "26", "15", "0.523", "0.282–0.971", "0.040*", "108", "56", "0.491", "0.352–0.685", "2.75E-05***", "134", "71", "0.486", "0.363–0.650", "1.26E-06***"], ["GMP", "40", "26", "0.595", "0.353–1.005", "0.052", "147", "89", "0.632", "0.472–0.846", "0.002**", "187", "115", "0.622", "0.483–0.802", "2.50E-04***"], ["UC", "19", "9", "0.309", "0.146–0.652", "0.002**", "64", "40", "0.666", "0.460–0.965", "0.032*", "83", "49", "0.580", "0.417–0.807", "0.001**"], ["Cytogenetic riska", "GOOD", "24", "10", "1", "", "", "97", "40", "1", "", "", "NA", "NA", "NA", "NA", "NA"], ["INTER", "60", "42", "2.636", "1.319–5.268", "0.006**", "247", "160", "1.900", "1.341–2.690", "3.02E-04***", "NA", "NA", "NA", "NA", "NA"], ["POOR", "35", "27", "2.828", "1.362–5.872", "0.005**", "85", "69", "3.222", "2.173–4.778", "5.84E-09***", "NA", "NA", "NA", "NA", "NA"], ["UC", "3", "3", "8.159", "2.188–30.431", "0.002**", "10", "9", "3.801", "1.839–7.857", "3.14E-04***", "NA", "NA", "NA", "NA", "NA"], ["FABb", "M0", "13", "9", "1", "", "", "16", "13", "1", "", "", "29", "22", "1", "", ""], ["M1", "28", "21", "1.773", "0.805–3.904", "0.155", "94", "60", "0.646", "0.355–1.177", "0.153", "122", "81", "0.772", "0.481–1.236", "0.281"], ["M2", "27", "17", "1.156", "0.520–2.659", "0.697", "104", "64", "0.629", "0.346–1.142", "0.128", "131", "81", "0.698", "0.435–1.119", "0.135"], ["M3", "6", "3", "0.542", "0.146–2.013", "0.360", "24", "11", "0.469", "0.210–1.048", "0.065", "30", "14", "0.492", "0.251–0.962", "0.038*"], ["M4", "27", "16", "0.861", "0.379–1.955", "0.720", "79", "48", "0.635", "0.344–1.173", "0.147", "106", "64", "0.683", "0.420–1.108", "0.123"], ["M4E", "NA", "NA", "NA", "NA", "NA", "5", "2", "0.325", "0.073–1.444", "0.140", "5", "2", "0.330", "0.077–1.403", "0.133"], ["M5", "14", "10", "1.957", "0.785–4.879", "0.150", "103", "72", "0.780", "0.432–1.407", "0.408", "117", "82", "0.846", "0.528–1.356", "0.488"], ["M6", "3", "3", "2.452", "0.649–9.272", "0.186", "6", "3", "0.415", "0.118–1.456", "0.170", "9", "6", "0.702", "0.284–1.731", "0.442"], ["M7", "3", "3", "2.311", "0.615–8.679", "0.215", "0", "0", "NA", "NA", "NA", "3", "3", "1.920", "0.573–6.429", "0.290"], ["UC", "1", "0", "2.751", "NA", "0.996", "8", "5", "0.869", "0.310–2.438", "0.790", "9", "5", "0.865", "0.328–2.286", "0.771"], ["CEBPA", "NEG", "119", "80", "1", "", "", "406", "262", "1", "", "", "525", "342", "1", "", ""], ["POS", "3", "2", "1.184", "0.289–4.851", "0.815", "29", "13", "0.555", "0.318–0.968", "0.038*", "32", "15", "0.556", "0.332–0.933", "0.026*"], ["FLT3-ITD", "NEG", "121", "81", "1", "", "", "315", "187", "1", "", "", "436", "268", "1", "", ""], ["POS", "1", "1", "5.724", "0.766–42.766", "0.089", "124", "91", "1.665", "1.294–2.141", "7.18E-05***", "125", "92", "1.428", "1.127–1.811", "0.003**"], ["FLT3-TKD", "NEG", "107", "71", "1", "", "", "390", "254", "1", "", "", "497", "325", "1", "", ""], ["POS", "15", "11", "1.478", "0.778–2.810", "0.233", "48", "24", "0.699", "0.460–1.062", "0.093", "63", "35", "0.820", "0.579–1.163", "0.265"], ["IDH1", "NEG", "116", "78", "1", "", "", "405", "256", "1", "", "", "521", "334", "1", "", ""], ["POS", "6", "4", "0.772", "0.282–2.114", "0.614", "31", "19", "0.901", "0.565–1.436", "0.661", "37", "23", "0.863", "0.565–1.316", "0.493"], ["IDH2", "NEG", "113", "78", "1", "", "", "400", "254", "1", "", "", "513", "332", "1", "", ""], ["POS", "9", "4", "0.509", "0.186–1.394", "0.189", "36", "21", "0.849", "0.544–1.324", "0.470", "45", "25", "0.765", "0.509–1.148", "0.196"], ["KRAS", "NEG", "116", "78", "1", "", "", "436", "276", "1", "", "", "552", "354", "1", "", ""], ["POS", "6", "4", "0.669", "0.244–1.836", "0.435", "3", "2", "1.028", "0.256–4.132", "0.970", "9", "6", "1.031", "0.460–2.311", "0.941"], ["NMP1", "NEG", "109", "73", "1", "", "", "303", "198", "1", "", "", "412", "271", "1", "", ""], ["POS", "13", "9", "1.739", "0.864–3.501", "0.121", "136", "80", "0.874", "0.674–1.133", "0.310", "149", "89", "0.845", "0.665–1.074", "0.169"], ["NRAS", "NEG", "115", "77", "1", "", "", "396", "253", "1", "", "", "511", "330", "1", "", ""], ["POS", "7", "5", "1.435", "0.578–3.563", "0.436", "42", "25", "0.826", "0.548–1.246", "0.362", "49", "30", "0.843", "0.580–1.225", "0.370"], ["WBC", "WBC", "122", "82", "1.002", "0.998–1.006", "0.402", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA"], ["Age", "Age", "122", "82", "1.041", "1.022–1.060", "1.44E-05***", "439", "278", "1.015", "1.005–1.026", "0.003**", "561", "360", "1.025", "1.017–1.033", "2.64E-09***"], ["Cohort", "TCGA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "122", "82", "1", "", ""], ["GSE6891", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "439", "278", "0.579", "0.451–0.744", "1.99E-05***"], ["B) Multivariate Cox Regression", "", ""], ["", "", "TCGA cohort (N = 122)", "GSE6891 cohort (N = 439)", "AML meta-cohort (N = 561)"], ["", "", "N", "Events", "HR", "95% CI", "P", "N", "Events", "HR", "95% CI", "P", "N", "Events", "HR", "95% CI", "P"], ["MAGS", "HSC", "37", "32", "1", "", "", "120", "93", "1", "", "", "157", "125", "1", "", ""], ["MEP", "26", "15", "0.781", "0.404–1.511", "0.464", "108", "56", "0.600", "0.419–0.862", "0.006**", "134", "71", "0.524", "0.374–0.734", "1.69E-04***"], ["GMP", "40", "26", "0.780", "0.445–1.365", "0.383", "147", "89", "0.723", "0.537–0.973", "0.032*", "187", "115", "0.593", "0.443–0.793", "4.32E-04***"], ["UC", "19", "9", "0.467", "0.213–1.025", "0.058*", "64", "40", "0.742", "0.508–1.084", "0.123", "83", "49", "0.561", "0.398–0.791", "9.55E-04***"], ["Cytogenetic riska", "GOOD", "24", "10", "1", "", "", "97", "40", "1", "", "", "-", "-", "-", "-", "-"], ["INTER", "60", "42", "1.996", "0.964–4.129", "0.063", "247", "160", "1.529", "1.045–2.239", "0.029", "-", "-", "-", "-", "-"], ["POOR", "35", "27", "1.911", "0.870–4.195", "0.107", "85", "69", "2.751", "1.825–4.147", "1.36E-06***", "-", "-", "-", "-", "-"], ["UC", "3", "3", "7.440", "1.928–28,712", "0.004**", "10", "9", "3.036", "1.445–6.379", "0.003**", "-", "-", "-", "-", "-"], ["FABb", "M0", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-", "29", "22", "1", "", ""], ["M1", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-", "122", "81", "1.267", "0.769–2.087", "0.353"], ["M2", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-", "131", "81", "1.266", "0.766–2.094", "0.358"], ["M3", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-", "30", "14", "1.089", "0.531–2.233", "0.816"], ["M4", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-", "106", "64", "1.143", "0.684–1.911", "0.610"], ["M4E", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-", "5", "2", "0.861", "0.196–3.790", "0.844"], ["M5", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-", "117", "82", "1.595", "0.934–2.723", "0.087"], ["M6", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-", "9", "6", "1.140", "0.418–3.112", "0.798"], ["M7", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-", "3", "3", "2.006", "0.573–7.021", "0.276"], ["UC", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-", "9", "5", "1.186", "0.442–3.181", "0.735"], ["CEBPA", "NEG", "-", "-", "-", "-", "-", "406", "262", "1", "", "", "525", "342", "1", "", ""], ["POS", "-", "-", "-", "-", "-", "29", "13", "0.703", "0.386–1.283", "0.251", "32", "15", "0.759", "0.433–1.331", "0.336"], ["FLT3-ITD", "NEG", "-", "-", "-", "-", "-", "315", "187", "1", "", "", "436", "268", "1", "", ""], ["POS", "-", "-", "-", "-", "-", "124", "91", "1.621", "1.230–2.135", "6.04E-04***", "125", "92", "1.542", "1.193–1.994", "9.52E-04***"], ["Age", "Age", "122", "82", "1.035", "1.017–1.054", "1.71E-04***", "435", "275", "1.011", "1.001–1.022", "0.036*", "557", "357", "1.021", "1.012–1.030", "4.56E-06***"], ["Cohort", "TCGA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "122", "82", "1", "", ""], ["GSE6891", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "439", "278", "0.640", "0.472–0.869", "0.005**"]], "row_count": 69, "column_count": 17, "numeric_cells": 652, "header_rows": 0, "locator": "section[11]/table-wrap[3]#pone.0229593.t004"}}, {"id": "asset:table:pmid:32324791:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d728a681f3957405306352a241379871e30665639209dff220b9db24770e2d5d", "bytes": 1382, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#pone.0229593.t005", "version": null, "note": "Overview of enrichment patterns detected using gene set enrichment analysis (GSEA) in the reduced assignment probability meta-cohort (N = 573: NGSE6891 = 423, NTCGA = 150), investigating the Hallmark, the C2-CP, and the C3-TFT gene set collections retrieved from the MSigDB.GSEA analysis was conducted for three comparisons: (A) HSC vs. Rest, (B) MEP vs. Rest, and (C) GMP vs. Rest. The total number of enriched gene sets (Total) with p-value ≤ 0.01 and FDR ≤ 0.25, and the numbers of enriched gene sets detected per group within each comparison are presented.", "structure": {"pmcid": "PMC7179860", "section_index": 12, "section_title": "DGE and functional annotation of enriched gene sets", "row_count": 15, "column_count": 4}, "table": {"label": "Table 5", "caption": "Overview of enrichment patterns detected using gene set enrichment analysis (GSEA) in the reduced assignment probability meta-cohort (N = 573: NGSE6891 = 423, NTCGA = 150), investigating the Hallmark, the C2-CP, and the C3-TFT gene set collections retrieved from the MSigDB.GSEA analysis was conducted for three comparisons: (A) HSC vs. Rest, (B) MEP vs. Rest, and (C) GMP vs. Rest. The total number of enriched gene sets (Total) with p-value ≤ 0.01 and FDR ≤ 0.25, and the numbers of enriched gene sets detected per group within each comparison are presented.", "rows": [["A) HSC vs. Rest"], ["MSigDB collection", "Total", "Enriched in HSC (%)", "Enriched in Rest (%)"], ["Hallmark", "31", "10 (32.3)", "21 (67.7)"], ["C2-CP", "256", "30 (11.7)", "226 (88.3)"], ["C3-TFT", "222", "173 (77.9)", "49 (22.1)"], ["B) MEP vs. Rest"], ["MSigDB collection", "Total", "Enriched in GMP (%)", "Enriched in Rest (%)"], ["Hallmark", "25", "11 (44.0)", "14 (56.0)"], ["C2-CP", "360", "59 (16.4)", "301 (83.6)"], ["C3-TFT", "101", "32 (31.7)", "69 (68.3)"], ["C) GMP vs. Rest"], ["MsigDB collection", "Total", "Enriched in MEP (%)", "Enriched in Rest (%)"], ["Hallmark", "21", "20 (95.2)", "1 (4.8)"], ["C2-CP", "254", "252 (99.2)", "301 (0.8)"], ["C3-TFT", "22", "9 (40.9)", "69 (59.1)"]], "row_count": 15, "column_count": 4, "numeric_cells": 27, "header_rows": 0, "locator": "section[12]/table-wrap[1]#pone.0229593.t005"}}], "gaps": ["asset:data:geo:GSE17054 not downloaded", "asset:data:geo:GSE17054 licence not read", "asset:data:geo:GSE19429 not downloaded", "asset:data:geo:GSE19429 licence not read", "asset:data:geo:GSE19599 not downloaded", "asset:data:geo:GSE19599 licence not read", "asset:data:geo:GSE42519 not downloaded", "asset:data:geo:GSE42519 licence not read", "asset:data:geo:GSE63270 not downloaded", "asset:data:geo:GSE63270 licence not read", "asset:data:geo:GSE6891 not downloaded", "asset:data:geo:GSE6891 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Cox regression"}}, {"id": "method-3", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-4", "family": "contingency_analysis", "specific": "fisher_exact", "label": "Categorical (contingency table) analysis", "dsl_operations": ["contingency_table", "chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "Fishers exact"}}, {"id": "method-5", "family": null, "specific": null, "label": "Regularised multinomial regression with an elastic net penalty", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The MAGS classifier for the HSC, MEP, and GMP subsets was obtained from regularised multinomial regression with the cell type as the discrete outcome and the median-centred GEP of the training cohort as the explanatory variable. The model was fitted with an elastic net penalty."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE63270", "GSE42519", "GSE19599", "GSE17054", "GSE19429", "GSE6891"], "resolved_accessions": ["GSE63270", "GSE42519", "GSE19599", "GSE17054", "GSE19429", "GSE6891"], "statements": ["All relevant data are within the manuscript and its Supporting Information files."], "basis": "The paper names GSE63270, GSE42519, GSE19599, GSE17054, GSE19429, GSE6891 in Gene Expression Omnibus Database (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:32324791", "data:geo:GSE17054", "asset:table:pmid:32324791:1", "asset:table:pmid:32324791:2", "asset:table:pmid:32324791:3", "asset:table:pmid:32324791:4", "asset:table:pmid:32324791:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE17054"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:19:28Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 44779, "completion_tokens": 2029, "cached_tokens": 784}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:32324791", "type": "paper", "label": "pmid:32324791"}, {"id": "source:pmid:32324791", "type": "manuscript", "label": "PMID 32324791 full text"}, {"id": "data:geo:GSE17054", "type": "dataset", "label": "GEO GSE17054"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32324791", "type": "paper", "label": "pmid:32324791"}, {"id": "source:pmid:32324791", "type": "manuscript", "label": "PMID 32324791 full text"}, {"id": "data:geo:GSE17054", "type": "dataset", "label": "GEO GSE17054"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32324791", "type": "extraction", "used": ["source:pmid:32324791"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE17054", "type": "accession_resolution", "used": ["data:geo:GSE17054"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:32324791", "parent_hash": "sha256:78a9748bbab7fa64b43ac994dc8d67bb5a6f0dee308ecdf1c93a299f90cb699a", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE17054 licence not read", "asset:data:geo:GSE17054 not downloaded", "asset:data:geo:GSE19429 licence not read", "asset:data:geo:GSE19429 not downloaded", "asset:data:geo:GSE19599 licence not read", "asset:data:geo:GSE19599 not downloaded", "asset:data:geo:GSE42519 licence not read", "asset:data:geo:GSE42519 not downloaded", "asset:data:geo:GSE63270 licence not read", "asset:data:geo:GSE63270 not downloaded", "asset:data:geo:GSE6891 licence not read", "asset:data:geo:GSE6891 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["level using a Brainarray custom CDF for the Affymetrix Human Genome U133 Plus 2.0 GeneChip (version"], "order_basis": "paper_text_order:2561", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Kaplan-Meier"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:50:12+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}