{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32802843", "kind": "science-record", "revision": 8, "content_hash": "sha256:5b34b82404cd2a519fb997dcae3b288a1cf9e1a5174a55c29b9539b83e723392", "created_at": "2026-11-01T15:41:08Z", "updated_at": "2026-11-01T22:45:13Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification and Validation of an Energy Metabolism-Related lncRNA-mRNA Signature for Lower-Grade Glioma.", "doi": "10.1155/2020/3708231", "pmid": "32802843", "authors": ["Jingwei Zhao", "Le Wang", "Bo Wei"], "journal": "BioMed research international", "year": 2020, "abstract": "Energy metabolic processes play important roles for tumor malignancy, indicating that related protein-coding genes and regulatory upstream genes (such as long noncoding RNAs (lncRNAs)) may represent potential biomarkers for prognostic prediction. This study will develop a new energy metabolism-related lncRNA-mRNA prognostic signature for lower-grade glioma (LGG) patients. A GSE4290 dataset obtained from Gene Expression Omnibus was used for screening the differentially expressed genes (DEGs) and lncRNAs (DELs). The Cancer Genome Atlas (TCGA) dataset was used as the prognosis training set, while the Chinese Glioma Genome Atlas (CGGA) was for the validation set. Energy metabolism-related genes were collected from the Molecular Signatures Database (MsigDB), and a coexpression network was established between energy metabolism-related DEGs and DELs to identify energy metabolism-related DELs. Least absolute shrinkage and selection operator (LASSO) analysis was performed to filter the prognostic signature which underwent survival analysis and nomogram construction. A total of 1613 DEGs and 37 DELs were identified between LGG and normal brain tissues. One hundred and ten DEGs were overlapped with energy metabolism-related genes. Twenty-seven DELs could coexpress with 67 metabolism-related DEGs. LASSO regression analysis showed that 9 genes in the coexpression network were the optimal signature and used to construct the risk score. Kaplan-Meier curve analysis showed that patients with a high risk score had significantly worse OS than those with a low risk score (TCGA: HR = 3.192, 95%CI = 2.182-4.670; CGGA: HR = 1.922, 95%CI = 1.431-2.583). The predictive accuracy of the risk score was also high according to the AUC of the ROC curve (TCGA: 0.827; CGGA: 0.806). Multivariate Cox regression analyses revealed age, IDH1 mutation, and risk score as independent prognostic factors, and thus, a prognostic nomogram was established based on these three variables. The excellent prognostic performance of the nomogram was confirmed by calibration and discrimination analyses. In conclusion, our findings provided a new biomarker for the stratification of LGG patients with poor prognosis.", "claims": [{"id": "claim-method", "statement": "The Linear Models for Microarray Data (LIMMA) method (version 3.34.7; https://bioconductor.org/packages/release/bioc/html/limma.html) [15] in the Bioconductor R package (version 3.4.1; http://www.R-project.org/) was used to identify differentially expressed genes (DEGs) and lncRNAs (DELs) between LGG and normal controls.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32802843", "locator": "sections[4] \"2.2. Identification of Energy Metabolism-Related Genes\" paragraph 3", "quote": "The Linear Models for Microarray Data (LIMMA) method (version 3.34.7; https://bioconductor.org/packages/release/bioc/html/limma.html) [15] in the Bioconductor R package (version 3.4.1; http://www.R-project.org/) was used to identify differentially expressed genes (DEGs) and lncRNAs (DELs) between LGG and normal controls."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data were collected from GEO (GSE4290; http://www.ncbi.nlm.nih.gov/geo/), TCGA (https://gdc-portal.nci.nih.gov/), and CGGA (http://www.cgga.org.cn) databases.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32802843", "locator": "sections[14] \"Data Availability\" paragraph 2", "quote": "All data were collected from GEO (GSE4290; http://www.ncbi.nlm.nih.gov/geo/), TCGA (https://gdc-portal.nci.nih.gov/), and CGGA (http://www.cgga.org.cn) databases."}], "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:32802843"], "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:GSE4290"], "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:GSE4290"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32802843", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2020/3708231", "sha256": "sha256:317336515a0d42a0776500cff99dddb13ad58c015f6b6fe6352e11640aed20f9", "bytes": 45666, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2020/3708231", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7403901", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE4290", "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=GSE4290", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE4290", "version": null, "note": "All data were collected from GEO (GSE4290; http://www.ncbi.nlm.nih.gov/geo/), TCGA (https://gdc-portal.nci.nih.gov/), and CGGA (http://www.cgga.org.cn) databases.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data were collected from GEO (GSE4290; http://www.ncbi.nlm.nih.gov/geo/), TCGA (https://gdc-portal.nci.nih.gov/), and CGGA (http://www.cgga.org.cn) databases.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM97793", "GSM97794", "GSM97795", "GSM97796", "GSM97797", "GSM97798", "GSM97799", "GSM97800", "GSM97801", "GSM97802", "GSM97803", "GSM97804", "GSM97805", "GSM97806", "GSM97807", "GSM97808", "GSM97809", "GSM97810", "GSM97811", "GSM97812", "GSM97813", "GSM97814", "GSM97815", "GSM97816", "GSM97817", "GSM97818", "GSM97819", "GSM97820", "GSM97821", "GSM97822", "GSM97823", "GSM97824", "GSM97825", "GSM97826", "GSM97827", "GSM97828", "GSM97829", "GSM97830", "GSM97831", "GSM97832", "GSM97833", "GSM97834", "GSM97835", "GSM97836", "GSM97837", "GSM97838", "GSM97839", "GSM97840", "GSM97841", "GSM97842", "GSM97843", "GSM97844", "GSM97845", "GSM97846", "GSM97847", "GSM97848", "GSM97849", "GSM97850", "GSM97851", "GSM97852", "GSM97853", "GSM97854", "GSM97855", "GSM97856", "GSM97857", "GSM97858", "GSM97859", "GSM97860", "GSM97861", "GSM97862", "GSM97863", "GSM97864", "GSM97865", "GSM97866", "GSM97867", "GSM97868", "GSM97869", "GSM97870", "GSM97871", "GSM97872", "GSM97873", "GSM97874", "GSM97875", "GSM97876", "GSM97877", "GSM97878", "GSM97879", "GSM97880", "GSM97881", "GSM97882", "GSM97883", "GSM97884", "GSM97885", "GSM97886", "GSM97887", "GSM97888", "GSM97889", "GSM97890", "GSM97891", "GSM97892", "GSM97893", "GSM97894", "GSM97895", "GSM97896", "GSM97897", "GSM97898", "GSM97899", "GSM97900", "GSM97901", "GSM97902", "GSM97903", "GSM97904", "GSM97905", "GSM97906", "GSM97907", "GSM97908", "GSM97909", "GSM97910", "GSM97911", "GSM97912", "GSM97913", "GSM97914", "GSM97915", "GSM97916", "GSM97917", "GSM97918", "GSM97919", "GSM97920", "GSM97921", "GSM97922", "GSM97923", "GSM97924", "GSM97925", "GSM97926", "GSM97927", "GSM97928", "GSM97929", "GSM97930", "GSM97931", "GSM97932", "GSM97933", "GSM97934", "GSM97935", "GSM97936", "GSM97937", "GSM97938", "GSM97939", "GSM97940", "GSM97941", "GSM97942", "GSM97943", "GSM97944", "GSM97945", "GSM97946", "GSM97947", "GSM97948", "GSM97949", "GSM97950", "GSM97951", "GSM97952", "GSM97953", "GSM97954", "GSM97955", "GSM97956", "GSM97957", "GSM97958", "GSM97959", "GSM97960", "GSM97961", "GSM97962", "GSM97963", "GSM97964", "GSM97965", "GSM97966", "GSM97967", "GSM97968", "GSM97969", "GSM97970", "GSM97971", "GSM97972"], "sample_count": 180, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data of glioma samples from Henry Ford Hospital", "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:32802843:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7b388a6b1fdc31f4ea9eb9a4d03a8c021b2862fa5f007225a351109d0c03484a", "bytes": 3927, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#tab1", "version": null, "note": "Function enrichment.", "structure": {"pmcid": "PMC7403901", "section_index": 9, "section_title": "3.1. Identification of Energy Metabolism-Related DERs", "row_count": 43, "column_count": 4}, "table": {"label": "Table 1", "caption": "Function enrichment.", "rows": [["Category", "Term", "p value", "Genes"], ["Biology process", "GO:0006661~phosphatidylinositol biosynthetic process", "3.380e − 06", "INPP5J, ARF3, SYNJ1, PI4KA, PIP4K2A, MTMR7"], ["GO:0030203~glycosaminoglycan metabolic process", "5.100e − 06", "B3GAT1, GPC2, CHST9, BCAN, VCAN"], ["GO:0030206~chondroitin sulfate biosynthetic process", "1.310e − 04", "CHSY3, CHST9, BCAN, VCAN"], ["GO:0009725~response to hormone", "6.240e − 04", "ME1, OXCT1, FHL2, DHCR24"], ["GO:0035338~long-chain fatty-acyl-CoA biosynthetic process", "6.240e − 04", "ACOT7, ELOVL4, SLC25A1, ACOT4"], ["GO:0030208~dermatan sulfate biosynthetic process", "1.009e − 03", "UST, BCAN, VCAN"], ["GO:0055114~oxidation-reduction process", "2.379e − 03", "ME1, TYRP1, CYP46A1, CYP2C8, QDPR, CBR4, SRD5A1, CRYM, DHCR24"], ["GO:0006699~bile acid biosynthetic process", "3.136e − 03", "CYP46A1, STAR, SLC27A2"], ["GO:0046856~phosphatidylinositol dephosphorylation", "4.090e − 03", "INPP5J, SYNJ1, MTMR7"], ["GO:0008652~cellular amino acid biosynthetic process", "4.792e − 03", "GLS2, ASPA, GOT1"], ["GO:0042493~response to drug", "7.278e − 03", "STAR, BCHE, OXCT1, FABP3, SRD5A1, AACS"], ["GO:0019083~viral transcription", "1.015e − 02", "RPLP0, NUP93, TPR, RPS21"], ["GO:0006486~protein glycosylation", "1.040e − 02", "B3GAT1, B3GALT2, B4GALT6, LRP2"], ["GO:0070859~positive regulation of bile acid biosynthetic process", "1.192e − 02", "NR1D1, STAR"], ["GO:0006024~glycosaminoglycan biosynthetic process", "1.218e − 02", "GPC2, HAS1, HS3ST2"], ["GO:0006094~gluconeogenesis", "1.332e − 02", "GOT1, ENO2, SLC25A1"], ["GO:0006533~aspartate catabolic process", "1.587e − 02", "ASPA, GOT1"], ["GO:0071320~cellular response to cAMP", "1.829e − 02", "STAR, RPLP0, SRD5A1"], ["GO:0016101~diterpenoid metabolic process", "1.979e − 02", "STAR, SRD5A1"], ["GO:0071394~cellular response to testosterone stimulus", "1.979e − 02", "SRD5A1, AACS"], ["GO:0006629~lipid metabolic process", "2.485e − 02", "CPNE6, AACS, LRP2, FABP6"], ["GO:0060992~response to fungicide", "2.760e − 02", "STAR, SRD5A1"], ["GO:0044539~long-chain fatty acid import", "2.760e − 02", "FABP3, SLC27A2"], ["GO:0044321~response to leptin", "2.760e − 02", "NR1D1, STAR"], ["GO:0046951~ketone body biosynthetic process", "3.148e − 02", "HMGCLL1, AACS"], ["GO:0007584~response to nutrient", "3.523e − 02", "STAR, OXCT1, AACS"], ["GO:0035457~cellular response to interferon-alpha", "3.535e − 02", "STAR, TPR"], ["GO:0032869~cellular response to insulin stimulus", "3.788e − 02", "GOT1, STAR, SRD5A1"], ["GO:0046855~inositol phosphate dephosphorylation", "4.304e − 02", "SYNJ1, MTMR7"], ["GO:0046488~phosphatidylinositol metabolic process", "4.304e − 02", "PITPNM3, SYNJ1"], ["GO:0051292~nuclear pore complex assembly", "4.304e − 02", "NUP93, TPR"], ["GO:0071872~cellular response to epinephrine stimulus", "4.686e − 02", "STAR, SRD5A1"], [""], ["KEGG pathway", "hsa01100:metabolic pathways", "9.150e − 06", "ME1, PLD3, TYRP1, HMGCLL1, B3GALT2, CYP2C8, SYNJ1, PI4KA, QDPR, HK1, AGMAT, RIMKLA, ACOT4, GLS2, ASPA, CKMT1A, GOT1, CHSY3, INPP5J, ENO2, B4GALT6, MTMR7, DHCR24"], ["hsa00562:inositol phosphate metabolism", "1.555e − 03", "INPP5J, SYNJ1, PI4KA, PIP4K2A, MTMR7"], ["hsa00250:alanine, aspartate, and glutamate metabolism", "1.894e − 03", "GLS2, ASPA, GOT1, RIMKLA"], ["hsa04070:phosphatidylinositol signaling system", "5.025e − 03", "INPP5J, SYNJ1, PI4KA, PIP4K2A, MTMR7"], ["hsa00330:arginine and proline metabolism", "5.263e − 03", "CKMT1A, GOT1, AGMAT, CARNS1"], ["hsa00062:fatty acid elongation", "1.343e − 02", "ACOT7, ELOVL4, ACOT4"], ["hsa00650:butanoate metabolism", "1.558e − 02", "HMGCLL1, OXCT1, AACS"], ["hsa00280:valine, leucine, and isoleucine degradation", "4.385e − 02", "HMGCLL1, OXCT1, AACS"], ["hsa01200:carbon metabolism", "4.608e − 02", "ME1, GOT1, ENO2, HK1"]], "row_count": 43, "column_count": 4, "numeric_cells": 91, "header_rows": 1, "locator": "section[9]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:32802843:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:86ee9bdec6ec1185d9408e07d6632ac7b6ed2ca8de54e8ff8196e87fd7f846a4", "bytes": 1649, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#tab2", "version": null, "note": "The optimal signature combination.", "structure": {"pmcid": "PMC7403901", "section_index": 10, "section_title": "3.2. Development of Energy Metabolism-Related DER-Based Risk Score", "row_count": 11, "column_count": 11}, "table": {"label": "Table 2", "caption": "The optimal signature combination.", "rows": [["Symbol", "Type", "Expression (LGG vs. CK)", "Expression (GBM vs. LGG)", "Multivariate Cox regression analysis", "LASSO coefficient"], ["logFC", "FDR (GSE4290)", "p value (GSE4290)", "p value (CGGA)", "p value (TCGA)", "HR", "95% CI", "p value"], ["GABPB1-AS1", "lncRNA", "1.07", "2.72e − 07", "7.59e − 03", "6.72e − 06", "8.83e − 289", "0.9946", "0.9899-0.9994", "2.846e − 02", "-0.05468"], ["HAR1A", "lncRNA", "-1.51", "7.65e − 04", "4.31e − 03", "1.65e − 15", "1.62e − 102", "0.9938", "0.988-0.9996", "3.580e − 02", "-0.64387"], ["LINC00599", "lncRNA", "-1.3", "4.80e − 05", "3.64e − 02", "2.36e − 06", "2.62e − 105", "1.0035", "1.0001-1.007", "4.628e − 02", "0.00904"], ["SNAI3-AS1", "lncRNA", "-1.76", "9.51e − 08", "7.96e − 03", "3.12e − 10", "1.71e − 258", "0.9817", "0.9701-0.9934", "2.310e − 03", "-1.81399"], ["SNHG1", "lncRNA", "1.3", "6.06e − 09", "1.28e − 01", "1.28e − 04", "8.19e − 222", "1.0054", "1.0004-1.0104", "3.328e − 02", "0.29846"], ["FABP6", "mRNA", "-2.18", "1.13e − 07", "2.94e − 01", "4.34e − 02", "1.42e − 128", "1.0062", "1.004-1.0085", "6.270e − 08", "0.55872"], ["MBOAT7", "mRNA", "-1.27", "3.92e − 09", "8.01e − 01", "1.11e − 03", "0", "1.0084", "1.0017-1.0152", "1.463e − 02", "0.77305"], ["SLC25A1", "mRNA", "1.03", "2.39e − 09", "4.05e − 03", "5.96e − 12", "0", "0.9955", "0.9911-0.9999", "4.934e − 02", "-0.40797"], ["UST", "mRNA", "1.47", "5.50e − 10", "5.80e − 05", "7.57e − 08", "2.41e − 256", "0.9951", "0.9914-0.9989", "1.177e − 02", "-0.55501"]], "row_count": 11, "column_count": 11, "numeric_cells": 86, "header_rows": 2, "locator": "section[10]/table-wrap[1]#tab2"}}, {"id": "asset:table:pmid:32802843:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b293a1107da2f526985f027cc024de83ca2695075467fa9cd4d1d84da16f1653", "bytes": 2009, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#tab3", "version": null, "note": "Univariate and multivariate Cox regression analyses of clinical pathologic features for overall survival.", "structure": {"pmcid": "PMC7403901", "section_index": 10, "section_title": "3.2. Development of Energy Metabolism-Related DER-Based Risk Score", "row_count": 17, "column_count": 8}, "table": {"label": "Table 3", "caption": "Univariate and multivariate Cox regression analyses of clinical pathologic features for overall survival.", "rows": [["Variables", "TCGA (N = 520)", "Univariate analysis", "Multivariate analysis"], ["HR", "95% CI", "p value", "HR", "95% CI", "p value"], ["Age (years, mean ± SD)", "42.84 ± 13.39", "1.057", "1.043-1.072", "2.78e − 15", "1.049", "1.003-1.096", "3.59e − 02"], ["Gender (male/female)", "286/234", "1.145", "0.811-1.617", "4.40e − 01", "—", "—", "—"], ["Animal insect allergy history (yes/no/-)", "16/289/215", "0.831", "0.202-3.428", "7.92e − 01", "—", "—", "—"], ["Asthma history (yes/no/-)", "22/346/152", "0.894", "0.409-1.956", "7.76e − 01", "—", "—", "—"], ["Food allergy history (yes/no/-)", "20/290/210", "1.008", "0.363-2.801", "9.87e − 01", "—", "—", "—"], ["Hay fever history (yes/no/-)", "38/304/178", "0.488", "0.177-1.347", "1.24e − 01", "—", "—", "—"], ["Headache history (yes/no/-)", "174/297/49", "0.841", "0.576-1.227", "3.64e − 01", "—", "—", "—"], ["Histological type (astrocytoma/oligoastrocytoma/oligodendroglioma)", "194/132/194", "0.756", "0.620-0.921", "5.25e − 03", "0.529", "0.244-1.149", "1.08e − 01"], ["IDH1 mutation (yes/no/-)", "91/34/395", "0.181", "0.0675-0.484", "4.14e − 04", "0.226", "0.0729-0.701", "9.98e − 03"], ["Neoplasm histologic grade (G2/G3/-)", "254/265/1", "3.416", "2.341-4.985", "1.84e − 11", "0.949", "0.294-3.063", "9.30e − 01"], ["Radiation therapy (yes/no/-)", "294/181/45", "1.847", "1.209-2.820", "2.83e − 03", "1.981", "0.584-6.722", "2.73e − 01"], ["Targeted molecular therapy", "268/200/52", "1.389", "0.955-2.019", "8.08e − 02", "—", "—", "—"], ["Risk score (high/low)", "260/260", "3.192", "2.182 -4.670", "1.99e − 10", "5.041", "1.272-19.97", "2.13e − 02"], ["Death (dead/alive)", "133/387", "—", "—", "—", "—", "—", "—"], ["Overall survival days (months, mean ± SD)", "32.97 ± 32.78", "—", "—", "—", "—", "—", "—"]], "row_count": 17, "column_count": 8, "numeric_cells": 75, "header_rows": 2, "locator": "section[10]/table-wrap[2]#tab3"}}, {"id": "asset:table:pmid:32802843:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:10a1b2ff7a123ece51f3268165d8acf3a1a3277dd0b6cb767dac31716774aa2c", "bytes": 688, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[3]#tab4", "version": null, "note": "The performance of the nomogram assessed by discrimination parameters.", "structure": {"pmcid": "PMC7403901", "section_index": 10, "section_title": "3.2. Development of Energy Metabolism-Related DER-Based Risk Score", "row_count": 8, "column_count": 6}, "table": {"label": "Table 4", "caption": "The performance of the nomogram assessed by discrimination parameters.", "rows": [["Model", "AUC", "C-index", "p value", "Specificity", "Sensitivity"], ["Age", "0.564", "0.743", "0", "0.889", "0.278"], ["IDH1 mutation", "0.646", "0.733", "8.138e − 05", "0.849", "0.442"], ["Multiclinical", "0.779", "0.8", "1.278e − 06", "0.877", "0.632"], ["lncRNA alone", "0.747", "0.702", "9.97e − 14", "0.832", "0.662"], ["mRNA alone", "0.739", "0.737", "0", "0.778", "0.662"], ["Multi-RNA based", "0.827", "0.812", "0", "0.798", "0.827"], ["Multi-RNA combined", "0.845", "0.928", "0", "0.863", "0.782"]], "row_count": 8, "column_count": 6, "numeric_cells": 35, "header_rows": 1, "locator": "section[10]/table-wrap[3]#tab4"}}], "gaps": ["asset:data:geo:GSE4290 not downloaded", "asset:data:geo:GSE4290 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The Linear Models for Microarray Data (LIMMA) method (version 3.34.7; https://bioconductor.org/packages/release/bioc/html/limma.html) [15] in the Bioconductor R package (version 3.4.1; http://www.R-project.org/) was used to identify differentially expressed genes (DEGs) and lncRNAs (DELs) between LGG and normal controls."}}, {"id": "method-2", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "a low risk score (TCGA: HR = 3"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-3", "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-4", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.7, "band": "medium", "quote": "ROC curve"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE4290"], "resolved_accessions": ["GSE4290"], "statements": ["All data were collected from GEO (GSE4290; http://www.ncbi.nlm.nih.gov/geo/), TCGA (https://gdc-portal.nci.nih.gov/), and CGGA (http://www.cgga.org.cn) databases."], "basis": "The paper names GSE4290 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:32802843", "data:geo:GSE4290", "asset:table:pmid:32802843:1", "asset:table:pmid:32802843:2", "asset:table:pmid:32802843:3", "asset:table:pmid:32802843:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE4290"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:57Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 37506, "completion_tokens": 2005, "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:32802843", "type": "paper", "label": "pmid:32802843"}, {"id": "source:pmid:32802843", "type": "manuscript", "label": "PMID 32802843 full text"}, {"id": "data:geo:GSE4290", "type": "dataset", "label": "GEO GSE4290"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32802843", "type": "paper", "label": "pmid:32802843"}, {"id": "source:pmid:32802843", "type": "manuscript", "label": "PMID 32802843 full text"}, {"id": "data:geo:GSE4290", "type": "dataset", "label": "GEO GSE4290"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32802843", "type": "extraction", "used": ["source:pmid:32802843"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE4290", "type": "accession_resolution", "used": ["data:geo:GSE4290"], "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:32802843", "parent_hash": "sha256:446ad6510dfc3c0e0d0c2ff01791ddae8e4912342ba31078c1c787b900c32b35", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE4290 licence not read", "asset:data:geo:GSE4290 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The Linear Models for Microarray Data (LIMMA) method (version 3.34.7; https://bioconductor.org/packages/release/bioc/html/limma.html) [15] in the Bioconductor R package (version 3.4.1; http://www.R-project.org/) was used to identify differentially expressed genes (DEGs) and lncRNAs (DELs) between LGG and normal controls."], "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":"2026-11-04T01:34:21+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}}}