{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32974187", "kind": "science-record", "revision": 4, "content_hash": "sha256:69e1c0ee4099f73c212838b6948d9825a3d3f3c841ea2c2cbb9679f1fde07cd2", "created_at": "2026-11-01T15:41:11Z", "updated_at": "2026-11-01T21:23:50Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Matrix Metallopeptidase 14: A Candidate Prognostic Biomarker for Diffuse Large B-Cell Lymphoma.", "doi": "10.3389/fonc.2020.01520", "pmid": "32974187", "authors": ["Chengliang Yin", "Junyan Zhang", "Ming Shen", "Zhenyang Gu", "Yan Li", "Wanguo Xue", "Jinlong Shi", "Wenrong Huang"], "journal": "Frontiers in oncology", "year": 2020, "abstract": "BACKGROUND: Matrix metallopeptidase 14 (MMP14) is an important gene in the regulation of T-cell function. However, the correlation between MMP14 expression, prognosis, and immune cell infiltration in diffuse large B-cell lymphoma (DLBCL) remains unclear.\nMETHODS: We investigated the influence of MMP14 on clinical prognosis using data obtained from three Gene Expression Omnibus (GEO) database sets (GSE98588, GSE10846, and GSE4475). The expression of MMP14 was analyzed using the Gene Expression Profiling Interactive Analysis (GEPIA). The correlation between MMP14 and immune cell infiltration was investigated using the Cell-type Identification By Estimating Relative Subsets Of RNA Transcripts (CIBERSORT) and Tumor Immune Estimation Resource (TIMER) tools. In addition, the correlation between MMP14 expression and immune gene markers was analyzed by TIMER and GEPIA.\nRESULTS: MMP14 expression positively correlated with favorable progression-free survival (PFS; GSE98588, P = 0.02) and overall survival (OS; GSE98588, P = 0.003; GSE10846, P = 5.517e-05; and GSE4475, P = 9.85e-04). Moreover, MMP14 expression was higher in DLBCL tumors than in normal tissues. Regarding clinical characteristics, high MMP14 expression was found to be correlated with race. MMP14 expression was also correlated with immune cell infiltration and had a remarkable correlation with various immune marker sets. It was found that M0 macrophages were the immune cells most related to survival, decreasing with the increase in Ann Arbor clinical stage. The results especially showed that MMP14 was a prognostic biomarker and related to the macrophages M0.\nCONCLUSION: The results suggest that MMP14 is a novel prognostic molecular marker for DLBCL and is related to the immune cell infiltration, especially related to the macrophages M0. Our study provides insights for understanding the potential roles of MMP14 in tumor immunology and its suitability as a prognosis biomarker in DLBCL.", "claims": [{"id": "claim-method", "statement": "We performed Kaplan–Meier analysis to measure the OS of the 48 patients obtained from TCGA based on the abundance ratio of the 11 identified immune cell types, for which the cut-off level was set at the median value.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32974187", "locator": "sections[7] \"Clinical Relationship With the Immune Cell Most Related to Survival\" paragraph 2", "quote": "We performed Kaplan–Meier analysis to measure the OS of the 48 patients obtained from TCGA based on the abundance ratio of the 11 identified immune cell types, for which the cut-off level was set at the median value."}], "state": "complete"}, {"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:32974187", "locator": "sections[16] \"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:32974187"], "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:GSE10846"], "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:GSE10846"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32974187", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fonc.2020.01520", "sha256": "sha256:f7d6fb41a6cb02b37947deb2eb9f3fab61149795970a7aecb55b9a08fb7cbef7", "bytes": 28620, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fonc.2020.01520", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7473157", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE10846", "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=GSE10846", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10846", "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": ["GSM274895", "GSM274896", "GSM274897", "GSM274898", "GSM274899", "GSM274900", "GSM274901", "GSM274902", "GSM274903", "GSM274904", "GSM274905", "GSM274906", "GSM274907", "GSM274908", "GSM274909", "GSM274910", "GSM274911", "GSM274912", "GSM274913", "GSM274914", "GSM274915", "GSM274916", "GSM274917", "GSM274918", "GSM274919", "GSM274920", "GSM274921", "GSM274922", "GSM274923", "GSM274924", "GSM274925", "GSM274926", "GSM274927", "GSM274928", "GSM274929", "GSM274930", "GSM274931", "GSM274932", "GSM274933", "GSM274934", "GSM274935", "GSM274936", "GSM274937", "GSM274938", "GSM274939", "GSM274940", "GSM274941", "GSM274942", "GSM274943", "GSM274944", "GSM274945", "GSM274946", "GSM274947", "GSM274948", "GSM274949", "GSM274950", "GSM274951", "GSM274952", "GSM274953", "GSM274954", "GSM274955", "GSM274956", "GSM274957", "GSM274958", "GSM274959", "GSM274960", "GSM274961", "GSM274962", "GSM274963", "GSM274964", "GSM274965", "GSM274966", "GSM274967", "GSM274968", "GSM274969", "GSM274970", "GSM274971", "GSM274972", "GSM274973", "GSM274974", "GSM274975", "GSM274976", "GSM274977", "GSM274978", "GSM274979", "GSM274980", "GSM274981", "GSM274982", "GSM274983", "GSM274984", "GSM274985", "GSM274986", "GSM274987", "GSM274988", "GSM274989", "GSM274990", "GSM274991", "GSM274992", "GSM274993", "GSM274994", "GSM274995", "GSM274996", "GSM274997", "GSM274998", "GSM274999", "GSM275000", "GSM275001", "GSM275002", "GSM275003", "GSM275004", "GSM275005", "GSM275006", "GSM275007", "GSM275008", "GSM275009", "GSM275010", "GSM275011", "GSM275012", "GSM275013", "GSM275014", "GSM275015", "GSM275016", "GSM275017", "GSM275018", "GSM275019", "GSM275020", "GSM275021", "GSM275022", "GSM275023", "GSM275024", "GSM275025", "GSM275026", "GSM275027", "GSM275028", "GSM275029", "GSM275030", "GSM275031", "GSM275032", "GSM275033", "GSM275034", "GSM275035", "GSM275036", "GSM275037", "GSM275038", "GSM275039", "GSM275040", "GSM275041", "GSM275042", "GSM275043", "GSM275044", "GSM275045", "GSM275046", "GSM275047", "GSM275048", "GSM275049", "GSM275050", "GSM275051", "GSM275052", "GSM275053", "GSM275054", "GSM275055", "GSM275056", "GSM275057", "GSM275058", "GSM275059", "GSM275060", "GSM275061", "GSM275062", "GSM275063", "GSM275064", "GSM275065", "GSM275066", "GSM275067", "GSM275068", "GSM275069", "GSM275070", "GSM275071", "GSM275072", "GSM275073", "GSM275074", "GSM275075", "GSM275076", "GSM275077", "GSM275078", "GSM275079", "GSM275080", "GSM275081", "GSM275082", "GSM275083", "GSM275084", "GSM275085", "GSM275086", "GSM275087", "GSM275088", "GSM275089", "GSM275090", "GSM275091", "GSM275092", "GSM275093", "GSM275094", "GSM275095", "GSM275096", "GSM275097", "GSM275098", "GSM275099", "GSM275100", "GSM275101", "GSM275102", "GSM275103", "GSM275104", "GSM275105", "GSM275106", "GSM275107", "GSM275108", "GSM275109", "GSM275110", "GSM275111", "GSM275112", "GSM275113", "GSM275114", "GSM275115", "GSM275116", "GSM275117", "GSM275118", "GSM275119", "GSM275120", "GSM275121", "GSM275122", "GSM275123", "GSM275124", "GSM275125", "GSM275126", "GSM275127", "GSM275128", "GSM275129", "GSM275130", "GSM275131", "GSM275132", "GSM275133", "GSM275134", "GSM275135", "GSM275136", "GSM275137", "GSM275138", "GSM275139", "GSM275140", "GSM275141", "GSM275142", "GSM275143", "GSM275144", "GSM275145", "GSM275146", "GSM275147", "GSM275148", "GSM275149", "GSM275150", "GSM275151", "GSM275152", "GSM275153", "GSM275154", "GSM275155", "GSM275156", "GSM275157", "GSM275158", "GSM275159", "GSM275160", "GSM275161", "GSM275162", "GSM275163", "GSM275164", "GSM275165", "GSM275166", "GSM275167", "GSM275168", "GSM275169", "GSM275170", "GSM275171", "GSM275172", "GSM275173", "GSM275174", "GSM275175", "GSM275176", "GSM275177", "GSM275178", "GSM275179", "GSM275180", "GSM275181", "GSM275182", "GSM275183", "GSM275184", "GSM275185", "GSM275186", "GSM275187", "GSM275188", "GSM275189", "GSM275190", "GSM275191", "GSM275192", "GSM275193", "GSM275194", "GSM275195", "GSM275196", "GSM275197", "GSM275198", "GSM275199", "GSM275200", "GSM275201", "GSM275202", "GSM275203", "GSM275204", "GSM275205", "GSM275206", "GSM275207", "GSM275208", "GSM275209", "GSM275210", "GSM275211", "GSM275212", "GSM275213", "GSM275214", "GSM275215", "GSM275216", "GSM275217", "GSM275218", "GSM275219", "GSM275220", "GSM275221", "GSM275222", "GSM275223", "GSM275224", "GSM275225", "GSM275226", "GSM275227", "GSM275228", "GSM275229", "GSM275230", "GSM275231", "GSM275232", "GSM275233", "GSM275234", "GSM275235", "GSM275236", "GSM275237", "GSM275238", "GSM275239", "GSM275240", "GSM275241", "GSM275242", "GSM275243", "GSM275244", "GSM275245", "GSM275246", "GSM275247", "GSM275248", "GSM275249", "GSM275250", "GSM275251", "GSM275252", "GSM275253", "GSM275254", "GSM275255", "GSM275256", "GSM275257", "GSM275258", "GSM275259", "GSM275260", "GSM275261", "GSM275262", "GSM275263", "GSM275264", "GSM275265", "GSM275266", "GSM275267", "GSM275268", "GSM275269", "GSM275270", "GSM275271", "GSM275272", "GSM275273", "GSM275274", "GSM275275", "GSM275276", "GSM275277", "GSM275278", "GSM275279", "GSM275280", "GSM275281", "GSM275282", "GSM275283", "GSM275284", "GSM275285", "GSM275286", "GSM275287", "GSM275288", "GSM275289", "GSM275290", "GSM275291", "GSM275292", "GSM275293", "GSM275294", "GSM275295", "GSM275296", "GSM275297", "GSM275298", "GSM275299", "GSM275300", "GSM275301", "GSM275302", "GSM275303", "GSM275304", "GSM275305", "GSM275306", "GSM275307", "GSM275308", "GSM361239", "GSM361240", "GSM361241", "GSM361242", "GSM361243", "GSM361244"], "sample_count": 420, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Prediction of survival in diffuse large B cell lymphoma treated with chemotherapy plus Rituximab", "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:GSE4475", "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=GSE4475", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE4475", "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": ["GSM100454", "GSM100455", "GSM100456", "GSM100457", "GSM100458", "GSM100459", "GSM100460", "GSM100461", "GSM100462", "GSM100463", "GSM100464", "GSM100465", "GSM100466", "GSM100467", "GSM100468", "GSM100469", "GSM100470", "GSM100471", "GSM100472", "GSM100473", "GSM100474", "GSM100475", "GSM100476", "GSM100477", "GSM100478", "GSM100479", "GSM100480", "GSM100481", "GSM100482", "GSM100483", "GSM100484", "GSM100485", "GSM100486", "GSM100487", "GSM100488", "GSM100489", "GSM100490", "GSM100491", "GSM100492", "GSM100493", "GSM100494", "GSM100495", "GSM100496", "GSM100497", "GSM100498", "GSM100499", "GSM100500", "GSM100501", "GSM100502", "GSM100503", "GSM100504", "GSM100505", "GSM100506", "GSM100507", "GSM100508", "GSM100509", "GSM100510", "GSM100511", "GSM100512", "GSM100513", "GSM100514", "GSM100515", "GSM100516", "GSM100517", "GSM100518", "GSM100519", "GSM100520", "GSM100521", "GSM100522", "GSM100523", "GSM100524", "GSM100525", "GSM100526", "GSM100527", "GSM100528", "GSM100529", "GSM100530", "GSM100531", "GSM100532", "GSM100533", "GSM100534", "GSM100535", "GSM100536", "GSM100537", "GSM100538", "GSM100539", "GSM100540", "GSM100541", "GSM100542", "GSM100543", "GSM100544", "GSM100545", "GSM100546", "GSM100547", "GSM100548", "GSM100549", "GSM100550", "GSM100551", "GSM100552", "GSM100553", "GSM100554", "GSM100555", "GSM100556", "GSM100557", "GSM100558", "GSM100559", "GSM100560", "GSM100561", "GSM100562", "GSM100563", "GSM100564", "GSM100565", "GSM100566", "GSM100567", "GSM100568", "GSM100569", "GSM100570", "GSM100571", "GSM100572", "GSM100573", "GSM100574", "GSM100575", "GSM100576", "GSM100577", "GSM100578", "GSM100579", "GSM100580", "GSM100581", "GSM100582", "GSM100583", "GSM100584", "GSM100585", "GSM100586", "GSM100587", "GSM100588", "GSM100589", "GSM100590", "GSM100591", "GSM100592", "GSM100593", "GSM100594", "GSM100595", "GSM100596", "GSM100597", "GSM100598", "GSM100599", "GSM100600", "GSM100601", "GSM100602", "GSM100603", "GSM100604", "GSM100605", "GSM100606", "GSM100607", "GSM100608", "GSM100609", "GSM100610", "GSM100611", "GSM100612", "GSM100613", "GSM100614", "GSM100615", "GSM100616", "GSM100617", "GSM100618", "GSM100619", "GSM100620", "GSM100621", "GSM100622", "GSM100623", "GSM100624", "GSM100625", "GSM100626", "GSM100627", "GSM100628", "GSM100629", "GSM100630", "GSM100631", "GSM100632", "GSM100633", "GSM100634", "GSM100635", "GSM100636", "GSM100637", "GSM100638", "GSM100639", "GSM100640", "GSM100641", "GSM100642", "GSM100643", "GSM100644", "GSM100645", "GSM100646", "GSM100647", "GSM100648", "GSM100649", "GSM100650", "GSM100651", "GSM100652", "GSM100653", "GSM100654", "GSM100655", "GSM100656", "GSM100657", "GSM100658", "GSM100659", "GSM100660", "GSM100661", "GSM100662", "GSM100663", "GSM100664", "GSM100665", "GSM100666", "GSM100667", "GSM100668", "GSM100669", "GSM100670", "GSM100671", "GSM100672", "GSM100673", "GSM100674"], "sample_count": 221, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "A Biologic Definition of Burkitt's Lymphoma from Transcriptional and Genomic Profiling", "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:GSE98588", "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=GSE98588", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE98588", "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": ["GSM2601334", "GSM2601335", "GSM2601336", "GSM2601337", "GSM2601338", "GSM2601339", "GSM2601340", "GSM2601341", "GSM2601342", "GSM2601343", "GSM2601344", "GSM2601345", "GSM2601346", "GSM2601347", "GSM2601348", "GSM2601349", "GSM2601350", "GSM2601351", "GSM2601352", "GSM2601353", "GSM2601354", "GSM2601355", "GSM2601356", "GSM2601357", "GSM2601358", "GSM2601359", "GSM2601360", "GSM2601361", "GSM2601362", "GSM2601363", "GSM2601364", "GSM2601365", "GSM2601366", "GSM2601367", "GSM2601368", "GSM2601369", "GSM2601370", "GSM2601371", "GSM2601372", "GSM2601373", "GSM2601374", "GSM2601375", "GSM2601376", "GSM2601377", "GSM2601378", "GSM2601379", "GSM2601380", "GSM2601381", "GSM2601382", "GSM2601383", "GSM2601384", "GSM2601385", "GSM2601386", "GSM2601387", "GSM2601388", "GSM2601389", "GSM2601390", "GSM2601391", "GSM2601392", "GSM2601393", "GSM2601394", "GSM2601395", "GSM2601396", "GSM2601397", "GSM2601398", "GSM2601399", "GSM2601400", "GSM2601401", "GSM2601402", "GSM2601403", "GSM2601404", "GSM2601405", "GSM2601406", "GSM2601407", "GSM2601408", "GSM2601409", "GSM2601410", "GSM2601411", "GSM2601412", "GSM2601413", "GSM2601414", "GSM2601415", "GSM2601416", "GSM2601417", "GSM2601418", "GSM2601419", "GSM2601420", "GSM2601421", "GSM2601422", "GSM2601423", "GSM2601424", "GSM2601425", "GSM2601426", "GSM2601427", "GSM2601428", "GSM2601429", "GSM2601430", "GSM2601431", "GSM2601432", "GSM2601433", "GSM2601434", "GSM2601435", "GSM2601436", "GSM2601437", "GSM2601438", "GSM2601439", "GSM2601440", "GSM2601441", "GSM2601442", "GSM2601443", "GSM2601444", "GSM2601445", "GSM2601446", "GSM2601447", "GSM2601448", "GSM2601449", "GSM2601450", "GSM2601451", "GSM2601452", "GSM2601453", "GSM2601454", "GSM2601455", "GSM2601456", "GSM2601457", "GSM2601458", "GSM2601459", "GSM2601460", "GSM2601461", "GSM2601462", "GSM2601463", "GSM2601464", "GSM2601465", "GSM2601466", "GSM2601467", "GSM2601468", "GSM2601469", "GSM2601470"], "sample_count": 137, "group_sizes": null, "group_sizes_basis": null, "platform": "23432", "taxon": "Homo sapiens", "title": "Genetically-defined Diffuse Large B-cell Lymphoma Subsets Arise by Distinct Pathogenetic Mechanisms and Predicts Outcome", "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:32974187:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b5e309f083a846f9b1bb43392332abf2c436b7eeb16bbf35a90d92f3701c10b9", "bytes": 1622, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T1", "version": null, "note": "Most significantly correlated signaling pathways with matrix metallopeptidase 14 (MMP14) expression, based on their normalized enrichment score (NES) and P-value (top five modules).", "structure": {"pmcid": "PMC7473157", "section_index": 11, "section_title": "Matrix Metallopeptidase 14 Expression Correlation With Clinical Characteristics and Predicted Biological Functions", "row_count": 24, "column_count": 5}, "table": {"label": "TABLE 1", "caption": "Most significantly correlated signaling pathways with matrix metallopeptidase 14 (MMP14) expression, based on their normalized enrichment score (NES) and P-value (top five modules).", "rows": [["", "GO name", "NES", "NOM p-value", "FDR q-value"], ["Positive", "Regulation of macrophage migration", "2.248", "0", "9.46e-04"], ["", "2.246", "0", "", "4.73e-04"], ["", "2.246", "0", "", "3.15e-04"], ["", "Iron ion homeostasis", "2.202", "0", "4.78e-04"], ["", "Collagen catabolic process", "2.199", "0", "3.82e-04"], ["Negative", "Nuclear-transcribed mRNA catabolic process", "−2.112", "0", "5.89e-023"], ["", "Viral gene expression", "-2.031", "0", "1.19e-02"], ["", "Nuclear-transcribed mRNA catabolic process nonsense-mediated decay", "−2.005", "2.08e-03", "1.39e-02"], ["", "rRNA methylation", "−1.993", "2.07e-03", "1.48e-02"], ["", "Translational initiation", "−1.993", "4.23e-03", "1.19e-02"], [""], ["", "KEGG name", "NES", "NOM p-value", "FDR q-value"], [""], ["Positive", "Lysosome", "2.246", "0", "0"], ["", "Glycosaminoglycan degradation", "2.012", "0", "2.11e-02"], ["", "Ecm receptor interaction", "1.990", "0", "2.00e-02"], ["", "Other glycan degradation", "1.986", "0", "1.76e-02"], ["", "Complement and coagulation cascades", "1.917", "0", "3.47e-02"], ["Negative", "RNA polymerase", "−1.729", "2.35e-02", "2.00e-01"], ["", "Ribosome", "−1.644", "4.55e-02", "2.27 e-01"], ["", "Nucleotide excision repair", "−1.636", "4.58e-02", "1.63 e-01"], ["", "Spliceosome", "−1.633", "5.54e-02", "1.24 e-01"], ["", "Base excision repair", "−1.584", "6.11e-02", "1.46 e-01"]], "row_count": 24, "column_count": 5, "numeric_cells": 60, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:32974187:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:52bf77de626b784a7896676d691bf1356ff4d2baa42012965d0e5c764a1026f1", "bytes": 3304, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T2", "version": null, "note": "Correlation analysis between MMP14 and immune cell-related genes and markers, as assessed with Tumor Immune Estimation Resource (TIMER).", "structure": {"pmcid": "PMC7473157", "section_index": 12, "section_title": "Matrix Metallopeptidase 14 Expression Is Correlated With Immune Cell Infiltration in Diffuse Large B-Cell Lymphoma", "row_count": 55, "column_count": 6}, "table": {"label": "TABLE 2", "caption": "Correlation analysis between MMP14 and immune cell-related genes and markers, as assessed with Tumor Immune Estimation Resource (TIMER).", "rows": [["Description", "Gene markers", "DLBCL"], ["", "", "No adjustment", "Purity adjusted"], ["", "", "Cor", "P", "Cor", "P"], ["B cell", "CD19", "-0.254", "8.19e-02", "−0.259", "1.02e-01"], ["", "CD79A", "−0.147", "3.18e-01", "−0.161", "3.15e-01"], ["Monocyte", "CD86", "0.253", "8.24e-02", "0.319", "4.20e-02"], ["", "CD115 (CSF1R)", "0.636", "2.2e-06", "0.589", "5.07e-05"], ["TAM", "CCL2", "0.281", "5.32e-02", "0.265", "9.43e-02"], ["", "CD68", "0.782", "0e-00", "0.786", "1.18e-09"], ["", "IL10", "0.359", "1.26e-02", "0.276", "8.05e-02"], ["Macrophage M0", "MMP9", "0.716", "5.92e-08", "0.66", "2.73e-06"], ["", "NCF2", "0.601", "9.70e-08", "0.556", "1.59e-04"], ["", "ACP5", "0.633", "2.50e-06", "0.558", "1.49e-04"], ["", "PLA2G7", "0.687", "2.27e-07", "0.668", "1.85e-06"], ["Macrophage M1", "INOS (NOS2)", "0.292", "4.44e-02", "0.181", "2.57e-01"], ["", "IRF5", "0.197", "1.79e-01", "0.037", "8.16e-01"], ["", "COX2(PTGS2)", "0.246", "9.2e-02", "0.061", "3.14e-01"], ["Macrophage M2", "CD163", "0.465", "9.84e-04", "0.488", "1.21e-03"], ["", "VSIG4", "0.502", "8.36e-04", "0.532", "3.48e-04"], ["", "MS4A4A", "0.281", "5.3e-02", "0.253", "1.10e-01"], ["Neutrophils", "CD66b (CEACAM8)", "0.252", "8.35e-02", "0.223", "1.61e-01"], ["", "CD11b (ITGAM)", "0.765", "0e-00", "0.765", "5.55e-09"], ["", "CCR7", "0.018", "9.05e-01", "−0.141", "3.79e-01"], ["Dendritic cells", "HLA-DPB1", "0.047", "7.48e-01", "0.058", "7.16e-01"], ["", "HLA-DQB1", "−0.038", "7.95e-01", "0.055", "7.33e-01"], ["", "HLA-DRA", "0.117", "4.25e-01", "0.072", "6.55e-01"], ["", "HLA-DPA1", "0.132", "3.72e-01", "0.101", "5.30e-01"], ["", "BDCA-1(CD1C)", "−0.153", "2.97e-01", "−0.203", "2.03e-01"], ["", "BDCA-4(NRP1)", "0.536", "1.13e-04", "0.421", "6.15e-03"], ["", "CD11c (ITGAX)", "0.443", "1.79e-03", "0.345", "2.72e-02"], ["CD8 + T cell", "CD8A", "0.205", "1.62e-01", "0.061", "7.05e-01"], ["", "CD8B", "0.125", "3.95e-01", "0.021", "8.94e-01"], ["T cell (general)", "CD3D", "−0.022", "8.8e-01", "0.282", "7.37e-02"], ["", "CD3E", "0.115", "4.36e-01", "−0.065", "6.85e-01"], ["", "CD2", "0.166", "2.58e-01", "0.031", "8.48e-01"], ["Natural killer cell", "KIR2DL1", "0.048", "7.48e-01", "−0.1", "5.33e-01"], ["", "KIR2DL3", "0.15", "3.08e-01", "0.063", "6.96e-01"], ["", "KIR2DL4", "0.324", "2.48e-02", "0.204", "2.02e-01"], ["", "KIR3DL1", "0.087", "5.58e-01", "0.056", "7028e-01"], ["", "KIR3DL2", "0.047", "7.49e-01", "−0.062", "7.00e-01"], ["", "KIR3DL3", "-0.117", "4.27e-01", "−0.112", "4.87e-01"], ["", "KIR2DS4", "0.09", "5.44e-01", "0.013", "9.37e-01"], ["Th1", "T-bet (TBX21)", "0.233", "1.11e-01", "0.14", "3.81e-01"], ["", "STAT4", "0.16", "2.76e-01", "-0.052", "7.45e-01"], ["", "STAT1", "0.472", "8.19e-04", "0.442", "3.85e-03"], ["", "IFN-γ (IFNG)", "0.532", "2.15e-02", "0.291", "6.52e-02"], ["", "TNF-α (TNF)", "0.338", "1.92e-02", "0.265", "9.38e-02"], ["", "GATA3", "0.183", "2.13e-01", "0.035", "8.27e-01"], ["", "STAT6", "0.146", "3.2e-01", "0.076", "6.39e-01"], ["", "STAT5A", "0.224", "1.26e-01", "0.225", "1.58e-01"], ["", "IL13", "0.067", "9.63e-01", "−0.026", "8.58e-01"], ["Tfh", "BCL6", "-0.134", "3.61e-01", "-0.033", "8.38e-01"], ["", "IL21", "0.167", "2.58e-01", "0.072", "6.57e-01"], ["Th17", "STAT3", "0.402", "4.89e-03", "0.315", "4.48e-02"], ["", "IL17A", "0.081", "5.83e-01", "0.024", "8.82e-01"]], "row_count": 55, "column_count": 6, "numeric_cells": 225, "header_rows": 3, "locator": "section[12]/table-wrap[1]#T2"}}], "gaps": ["asset:data:geo:GSE10846 not downloaded", "asset:data:geo:GSE10846 licence not read", "asset:data:geo:GSE4475 not downloaded", "asset:data:geo:GSE4475 licence not read", "asset:data:geo:GSE98588 not downloaded", "asset:data:geo:GSE98588 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Kaplan–Meier survival analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We performed Kaplan–Meier analysis to measure the OS of the 48 patients obtained from TCGA based on the abundance ratio of the 11 identified immune cell types, for which the cut-off level was set at the median value."}}], "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": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Kaplan–Meier survival analysis), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["GSE98588", "GSE10846", "GSE4475"], "resolved_accessions": ["GSE98588", "GSE10846", "GSE4475"], "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 GSE98588, GSE10846, GSE4475 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": [], "assets": ["source:pmid:32974187", "data:geo:GSE10846", "asset:table:pmid:32974187:1", "asset:table:pmid:32974187:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE10846"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:22:45Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 20354, "completion_tokens": 2049, "cached_tokens": 792}}, "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:32974187", "type": "paper", "label": "pmid:32974187"}, {"id": "source:pmid:32974187", "type": "manuscript", "label": "PMID 32974187 full text"}, {"id": "data:geo:GSE10846", "type": "dataset", "label": "GEO GSE10846"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32974187", "type": "paper", "label": "pmid:32974187"}, {"id": "source:pmid:32974187", "type": "manuscript", "label": "PMID 32974187 full text"}, {"id": "data:geo:GSE10846", "type": "dataset", "label": "GEO GSE10846"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32974187", "type": "extraction", "used": ["source:pmid:32974187"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE10846", "type": "accession_resolution", "used": ["data:geo:GSE10846"], "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:32974187", "parent_hash": "sha256:9f570cdbb526c4e8bd08f52b1dd09d8356952ae1ead5c5cf76afb1881ab58319", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE10846 licence not read", "asset:data:geo:GSE10846 not downloaded", "asset:data:geo:GSE4475 licence not read", "asset:data:geo:GSE4475 not downloaded", "asset:data:geo:GSE98588 licence not read", "asset:data:geo:GSE98588 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]},"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":"2026-11-04T02:53:55+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}}}