{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33343487", "kind": "science-record", "revision": 5, "content_hash": "sha256:e82bc25e8c1ace87475f1258e0c9d65848e68e1b86e5d49f701388ab33e1e7f6", "created_at": "2026-11-01T15:41:20Z", "updated_at": "2026-11-01T22:02:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Development and Validation of a Five-Gene Signature to Predict Relapse-Free Survival in Multiple Sclerosis.", "doi": "10.3389/fneur.2020.579683", "pmid": "33343487", "authors": ["Fei Ye", "Jie Liang", "Jiaoxing Li", "Haiyan Li", "Wenli Sheng"], "journal": "Frontiers in neurology", "year": 2020, "abstract": "Background: Multiple sclerosis (MS) is an inflammatory and demyelinating disease of the central nervous system with a variable natural history of relapse and remission. Previous studies have found many differentially expressed genes (DEGs) in the peripheral blood of MS patients and healthy controls, but the value of these genes for predicting the risk of relapse remains elusive. Here we develop and validate an effective and noninvasive gene signature for predicting relapse-free survival (RFS) in MS patients. Methods: Gene expression matrices were downloaded from Gene Expression Omnibus and ArrayExpress. DEGs in MS patients and healthy controls were screened in an integrated analysis of seven data sets. Candidate genes from a combination of protein-protein interaction and weighted correlation network analysis were used to identify key genes related to RFS. An independent data set (GSE15245) was randomized into training and test groups. Univariate and least absolute shrinkage and selection operator-Cox regression analyses were used in the training group to develop a gene signature. A nomogram incorporating independent risk factors was developed via multivariate Cox regression analyses. Kaplan-Meier methods, receiver-operating characteristic (ROC) curves, and Harrell's concordance index (C-index) were used to estimate the performance of the gene signature and nomogram. The test group was used for external validation. Results: A five-gene signature comprising FTH1, GBP2, MYL6, NCOA4, and SRP9 was used to calculate risk scores to predict individual RFS. The risk score was an independent risk factor, and a nomogram incorporating clinical parameters was established. ROC curves and C-indices demonstrated great performance of these predictive tools in both the training and test groups. Conclusions: The five-gene signature may be a reliable tool for assisting physicians in predicting RFS in clinical practice. We anticipate that these findings could not only facilitate personalized treatment for MS patients but also provide insight into the complex molecular mechanism of this disease.", "claims": [{"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33343487", "locator": "sections[21] \"Data Availability Statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."}], "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:33343487"], "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:E-MTAB-4890"], "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:E-MTAB-4890"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33343487", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fneur.2020.579683", "sha256": "sha256:7a6a66a0d94c1881756860b4e4ba7b829764ccf1b19e2ab5812d9ba24512197e", "bytes": 31900, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fneur.2020.579683", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7744728", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:E-MTAB-4890", "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=E-MTAB-4890", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-4890", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:29:01Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:E-MTAB-5151", "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=E-MTAB-5151", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-5151", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:29:01Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:E-MTAB-69", "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=E-MTAB-69", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-69", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:29:02Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE15245", "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=GSE15245", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15245", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM380715", "GSM380716", "GSM380717", "GSM380718", "GSM380719", "GSM380720", "GSM380721", "GSM380722", "GSM380723", "GSM380724", "GSM380725", "GSM380726", "GSM380727", "GSM380728", "GSM380729", "GSM380730", "GSM380731", "GSM380732", "GSM380733", "GSM380734", "GSM380735", "GSM380736", "GSM380737", "GSM380738", "GSM380739", "GSM380740", "GSM380741", "GSM380742", "GSM380743", "GSM380744", "GSM380745", "GSM380746", "GSM380747", "GSM380748", "GSM380749", "GSM380750", "GSM380751", "GSM380752", "GSM380753", "GSM380754", "GSM380755", "GSM380756", "GSM380757", "GSM380758", "GSM380759", "GSM380760", "GSM380761", "GSM380762", "GSM380763", "GSM380764", "GSM380765", "GSM380766", "GSM380767", "GSM380768", "GSM380769", "GSM380770", "GSM380771", "GSM380772", "GSM380773", "GSM380774", "GSM380775", "GSM380776", "GSM380777", "GSM380778", "GSM380779", "GSM380780", "GSM380781", "GSM380782", "GSM380783", "GSM380784", "GSM380785", "GSM380786", "GSM380787", "GSM380788", "GSM380789", "GSM380790", "GSM380791", "GSM380792", "GSM380793", "GSM380794", "GSM380795", "GSM380796", "GSM380797", "GSM380798", "GSM380799", "GSM380800", "GSM380801", "GSM380802", "GSM380803", "GSM380804", "GSM380805", "GSM380806", "GSM380807", "GSM380808"], "sample_count": 94, "group_sizes": null, "group_sizes_basis": null, "platform": "571;96", "taxon": "Homo sapiens", "title": "Prediction of acute multiple sclerosis relapses by transcription levels of peripheral blood 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:GSE17048", "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=GSE17048", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE17048", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM426595", "GSM426596", "GSM426597", "GSM426598", "GSM426599", "GSM426600", "GSM426601", "GSM426602", "GSM426603", "GSM426604", "GSM426605", "GSM426606", "GSM426607", "GSM426608", "GSM426609", "GSM426610", "GSM426611", "GSM426612", "GSM426613", "GSM426614", "GSM426615", "GSM426616", "GSM426617", "GSM426618", "GSM426619", "GSM426620", "GSM426621", "GSM426622", "GSM426623", "GSM426624", "GSM426625", "GSM426626", "GSM426627", "GSM426628", "GSM426629", "GSM426630", "GSM426631", "GSM426632", "GSM426633", "GSM426634", "GSM426635", "GSM426636", "GSM426637", "GSM426638", "GSM426639", "GSM426640", "GSM426641", "GSM426642", "GSM426643", "GSM426644", "GSM426645", "GSM426646", "GSM426647", "GSM426648", "GSM426649", "GSM426650", "GSM426651", "GSM426652", "GSM426653", "GSM426654", "GSM426655", "GSM426656", "GSM426657", "GSM426658", "GSM426659", "GSM426660", "GSM426661", "GSM426662", "GSM426663", "GSM426664", "GSM426665", "GSM426666", "GSM426667", "GSM426668", "GSM426669", "GSM426670", "GSM426671", "GSM426672", "GSM426673", "GSM426674", "GSM426675", "GSM426676", "GSM426677", "GSM426678", "GSM426679", "GSM426680", "GSM426681", "GSM426682", "GSM426683", "GSM426684", "GSM426685", "GSM426686", "GSM426687", "GSM426688", "GSM426689", "GSM426690", "GSM426691", "GSM426692", "GSM426693", "GSM426694", "GSM426695", "GSM426696", "GSM426697", "GSM426698", "GSM426699", "GSM426700", "GSM426701", "GSM426702", "GSM426703", "GSM426704", "GSM426705", "GSM426706", "GSM426707", "GSM426708", "GSM426709", "GSM426710", "GSM426711", "GSM426712", "GSM426713", "GSM426714", "GSM426715", "GSM426716", "GSM426717", "GSM426718", "GSM426719", "GSM426720", "GSM426721", "GSM426722", "GSM426723", "GSM426724", "GSM426725", "GSM426726", "GSM426727", "GSM426728", "GSM426729", "GSM426730", "GSM426731", "GSM426732", "GSM426733", "GSM426734", "GSM426735", "GSM426736", "GSM426737", "GSM426738"], "sample_count": 144, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "Multiple Sclerosis Blood Cell mRNA Transcriptome", "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:GSE21942", "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=GSE21942", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21942", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM545818", "GSM545819", "GSM545820", "GSM545821", "GSM545822", "GSM545823", "GSM545824", "GSM545825", "GSM545826", "GSM545827", "GSM545828", "GSM545829", "GSM545830", "GSM545831", "GSM545832", "GSM545833", "GSM545834", "GSM545835", "GSM545836", "GSM545837", "GSM545838", "GSM545839", "GSM545840", "GSM545841", "GSM545842", "GSM545843", "GSM545844", "GSM545845", "GSM545846"], "sample_count": 29, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from peripheral blood mononuclear cells in multiple sclerosis patients and 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:GSE41890", "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=GSE41890", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE41890", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1026993", "GSM1026994", "GSM1026995", "GSM1026996", "GSM1026997", "GSM1026998", "GSM1026999", "GSM1027000", "GSM1027001", "GSM1027002", "GSM1027003", "GSM1027004", "GSM1027005", "GSM1027006", "GSM1027007", "GSM1027008", "GSM1027009", "GSM1027010", "GSM1027011", "GSM1027012", "GSM1027013", "GSM1027014", "GSM1027015", "GSM1027016", "GSM1027017", "GSM1027018", "GSM1027019", "GSM1027020", "GSM1027021", "GSM1027022", "GSM1027023", "GSM1027024", "GSM1027025", "GSM1027026", "GSM1027027", "GSM1027028", "GSM1027029", "GSM1027030", "GSM1027031", "GSM1027032", "GSM1027033", "GSM1027034", "GSM1027035", "GSM1027036", "GSM1027037", "GSM1027038", "GSM1027039", "GSM1027040", "GSM1027041", "GSM1027042", "GSM1027043", "GSM1027044", "GSM1027045", "GSM1027046", "GSM1027047", "GSM1027048", "GSM1027049", "GSM1027050", "GSM1027051", "GSM1027052", "GSM1027053", "GSM1027054", "GSM1027055", "GSM1027056", "GSM1027057", "GSM1027058", "GSM1027059", "GSM1027060"], "sample_count": 68, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Expression data from multiple sclerosis patients in remission and relapse", "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:GSE59085", "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=GSE59085", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE59085", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1426343", "GSM1426344", "GSM1426345", "GSM1426346", "GSM1426347", "GSM1426348", "GSM1426349", "GSM1426350", "GSM1426351", "GSM1426352", "GSM1426353", "GSM1426354", "GSM1426355", "GSM1426356", "GSM1426357", "GSM1426358", "GSM1426359", "GSM1426360", "GSM1426361", "GSM1426362", "GSM1426363", "GSM1426364"], "sample_count": 22, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "The Role of Interleukin-11 in the Development of the Autoimmune Response in Multiple Sclerosis", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33343487:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:49f99e16aa3e9f8f41193970f0fe263870ed0ce3676cf56c36d5936bb0c634a7", "bytes": 842, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Summary of seven microarray data sets that met the inclusive criteria in this study.", "structure": {"pmcid": "PMC7744728", "section_index": 3, "section_title": "Data Downloading and Processing", "row_count": 9, "column_count": 6}, "table": {"label": "Table 1", "caption": "Summary of seven microarray data sets that met the inclusive criteria in this study.", "rows": [["Accession", "Released date", "Platform", "Source", "Samples"], ["", "", "", "", "Healthy control", "Multiple sclerosis"], ["E-MTAB-69", "Dec 2, 2009", "A-AFFY-44", "PBMC", "18", "26"], ["E-MTAB-4890", "Sep 30, 2017", "A-MEXP-931", "PBMC", "40", "142 (49 RRMS, 21 SPMS, 23 PPMS, 49 CIS)"], ["E-MTAB-5151", "Sep 30, 2017", "A-MEXP-931", "PBMC", "27", "49 (21 RRMS, 13 SPMS, 23 PPMS)"], ["GSE17048", "Jul 10, 2009", "GPL6947", "Blood", "45", "99 (36 RRMS, 20 SPMS, 43 PPMS)"], ["GSE21942", "May 20, 2010", "GPL570", "PBMC", "15", "14"], ["GSE41890", "Oct 28, 2012", "GPL6244", "PBMC", "24", "44"], ["GSE59085", "Jul 3, 2014", "GPL570", "PBMC", "7", "15 (15 CIS)"]], "row_count": 9, "column_count": 6, "numeric_cells": 35, "header_rows": 2, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33343487:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2b2db0e578d611335f1ea4d5f8203ec92f43320c5cbdc62eed669bd6a03eba55", "bytes": 648, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#T2", "version": null, "note": "The clinical features of MS patients in the training group and test group.", "structure": {"pmcid": "PMC7744728", "section_index": 15, "section_title": "Identification of Key Genes Related to RFS and Construction of a Predictive Gene Signature", "row_count": 11, "column_count": 4}, "table": {"label": "Table 2", "caption": "The clinical features of MS patients in the training group and test group.", "rows": [["Feature", "Training (n = 63)", "Test (n = 31)", "p"], ["Age (years)"], ["18–50", "53 (84.1%)", "28 (90.3%)", "0.413"], [">50", "10 (15.9%)", "3 (9.7%)", ""], ["Female", "41 (65.1%)", "19 (61.3%)", "0.719"], ["Type"], ["CIS", "19 (30.2%)", "13 (41.9%)", "0.257"], ["MS", "44 (69.8%)", "18 (58.1%)", ""], ["DMT", "16 (25.4%)", "13 (41.9%)", "0.103"], ["Follow-up (years)", "2.0 ± 1.3", "1.9 ± 1.3", "0.182"], ["Relapse", "43 (68.3%)", "21 (67.7%)", "0.960"]], "row_count": 11, "column_count": 4, "numeric_cells": 26, "header_rows": 1, "locator": "section[15]/table-wrap[1]#T2"}}], "gaps": ["asset:data:geo:E-MTAB-4890 not downloaded", "asset:data:geo:E-MTAB-4890 licence not read", "asset:data:geo:E-MTAB-5151 not downloaded", "asset:data:geo:E-MTAB-5151 licence not read", "asset:data:geo:E-MTAB-69 not downloaded", "asset:data:geo:E-MTAB-69 licence not read", "asset:data:geo:GSE15245 not downloaded", "asset:data:geo:GSE15245 licence not read", "asset:data:geo:GSE17048 not downloaded", "asset:data:geo:GSE17048 licence not read", "asset:data:geo:GSE21942 not downloaded", "asset:data:geo:GSE21942 licence not read", "asset:data:geo:GSE41890 not downloaded", "asset:data:geo:GSE41890 licence not read", "asset:data:geo:GSE59085 not downloaded", "asset:data:geo:GSE59085 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": 0.7, "band": "medium", "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": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-4", "family": null, "specific": null, "label": "Batch normalization", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "“An integrated data set was obtained with batch normalization.”"}}], "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": ["GSE17048", "GSE21942", "GSE41890", "GSE59085", "E-MTAB-69", "E-MTAB-4890", "E-MTAB-5151", "GSE15245"], "resolved_accessions": ["GSE17048", "GSE21942", "GSE41890", "GSE59085", "E-MTAB-69", "E-MTAB-4890", "E-MTAB-5151", "GSE15245"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."], "basis": "The paper names GSE17048, GSE21942, GSE41890, GSE59085, E-MTAB-69, E-MTAB-4890, E-MTAB-5151, GSE15245 in Gene Expression Omnibus (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:33343487", "data:geo:E-MTAB-4890", "asset:table:pmid:33343487:1", "asset:table:pmid:33343487:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:E-MTAB-4890"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:25:38Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 22756, "completion_tokens": 3044, "cached_tokens": 7688}}, "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:33343487", "type": "paper", "label": "pmid:33343487"}, {"id": "source:pmid:33343487", "type": "manuscript", "label": "PMID 33343487 full text"}, {"id": "data:geo:E-MTAB-4890", "type": "dataset", "label": "GEO E-MTAB-4890"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33343487", "type": "paper", "label": "pmid:33343487"}, {"id": "source:pmid:33343487", "type": "manuscript", "label": "PMID 33343487 full text"}, {"id": "data:geo:E-MTAB-4890", "type": "dataset", "label": "GEO E-MTAB-4890"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33343487", "type": "extraction", "used": ["source:pmid:33343487"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-E-MTAB-4890", "type": "accession_resolution", "used": ["data:geo:E-MTAB-4890"], "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:33343487", "parent_hash": "sha256:31920e36b7baba766bbafc84559a1fb3df63a441ce281e6ae0759a9e2e8a2beb", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:E-MTAB-4890 licence not read", "asset:data:geo:E-MTAB-4890 not downloaded", "asset:data:geo:E-MTAB-5151 licence not read", "asset:data:geo:E-MTAB-5151 not downloaded", "asset:data:geo:E-MTAB-69 licence not read", "asset:data:geo:E-MTAB-69 not downloaded", "asset:data:geo:GSE15245 licence not read", "asset:data:geo:GSE15245 not downloaded", "asset:data:geo:GSE17048 licence not read", "asset:data:geo:GSE17048 not downloaded", "asset:data:geo:GSE21942 licence not read", "asset:data:geo:GSE21942 not downloaded", "asset:data:geo:GSE41890 licence not read", "asset:data:geo:GSE41890 not downloaded", "asset:data:geo:GSE59085 licence not read", "asset:data:geo:GSE59085 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": 0.7, "evidence": ["Kaplan-Meier"], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T01:25:48+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}}}