{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32323746", "kind": "science-record", "revision": 7, "content_hash": "sha256:2ac92a39cabb895a890165433570d9c911474cddbb91d790f55ff580b7c7c853", "created_at": "2026-11-01T15:41:00Z", "updated_at": "2026-11-01T22:01:32Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A novel microRNA signature for pathological grading in lung adenocarcinoma based on TCGA and GEO data.", "doi": "10.3892/ijmm.2020.4526", "pmid": "32323746", "authors": ["Zhiyu Yang", "Hongkun Yin", "Lei Shi", "Xiaohua Qian"], "journal": "International journal of molecular medicine", "year": 2020, "abstract": "Lung adenocarcinoma (LUAD) is one of the most common types of lung cancer and its poor prognosis largely depends on the tumor pathological stage. Critical roles of microRNAs (miRNAs) have been reported in the tumorigenesis and progression of lung cancer. However, whether the differential expression pattern of miRNAs could be used to distinguish early‑stage (stage I) from mid‑late‑stage (stages II‑IV) LUAD tumors is still unclear. In this study, clinical information and miRNA expression profiles of patients with LUAD were downloaded from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus databases. TCGA‑LUAD (n=470) dataset was used for model training and validation, and the GSE62182 (n=94) and GSE83527 (n=36) datasets were used as external independent test datasets. The diagnostic model was created through miRNA feature selection followed by SVM classifier and was confirmed by 5‑fold cross‑validation. A receiver operating characteristic curve was calculated to evaluate the accuracy and robustness of the model. Using the DX score and LIBSVM tool, a 16‑miRNA signature that could distinguish LUAD pathological stages was identified. The area under the curve rates were 0.62 [95% confidence interval (CI): 0.56‑0.67], 0.66 (95% CI: 0.54‑0.76) and 0.63 (95% CI: 0.43‑0.82) in TCGA‑LUAD internal validation dataset, the GSE62182 external validation dataset, and the GSE83527 external validation dataset, respectively. Kyoto Encyclopedia of Genes and Genomes and Gene Ontology enrichment analyses suggested that the target genes of the 16‑miRNA signature were mainly involved in metabolic pathways. The present findings demonstrate that a 16‑miRNA signature could serve as a promising diagnostic biomarker for pathological staging in LUAD.", "claims": [{"id": "claim-method", "statement": "Two-sided Fisher’s exact test was used to analyze the significance of the GO category and KEGG pathway enrichment, and corrected P<0.05 was considered to indicate a statistically significant difference.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32323746", "locator": "sections[5] \"GO and KEGG pathway analyses\" paragraph 2", "quote": "Two-sided Fisher’s exact test was used to analyze the significance of the GO category and KEGG pathway enrichment, and corrected P<0.05 was considered to indicate a statistically significant difference."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data used in this study can be downloaded from TCGA (https://portal.gdc.cancer.gov/) and GEO (https://www.ncbi.nlm.nih.gov/geo) databases.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32323746", "locator": "sections[13] \"Availability of data and materials\" paragraph 2", "quote": "All data used in this study can be downloaded from TCGA (https://portal.gdc.cancer.gov/) and GEO (https://www.ncbi.nlm.nih.gov/geo) 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:32323746"], "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:GSE62182"], "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:GSE62182"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32323746", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/ijmm.2020.4526", "sha256": "sha256:a970a84cd96ec5844a85e49e71b9811f90bbfaa0674ddaf1f772568350b5d389", "bytes": 38187, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/ijmm.2020.4526", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7138293", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE62182", "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=GSE62182", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62182", "version": null, "note": "All data used in this study can be downloaded from TCGA (https://portal.gdc.cancer.gov/) and GEO (https://www.ncbi.nlm.nih.gov/geo) databases.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data used in this study can be downloaded from TCGA (https://portal.gdc.cancer.gov/) and GEO (https://www.ncbi.nlm.nih.gov/geo) databases.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1521159", "GSM1521160", "GSM1521161", "GSM1521162", "GSM1521163", "GSM1521164", "GSM1521165", "GSM1521166", "GSM1521167", "GSM1521168", "GSM1521169", "GSM1521170", "GSM1521171", "GSM1521172", "GSM1521173", "GSM1521174", "GSM1521175", "GSM1521176", "GSM1521177", "GSM1521178", "GSM1521179", "GSM1521180", "GSM1521181", "GSM1521182", "GSM1521183", "GSM1521184", "GSM1521185", "GSM1521186", "GSM1521187", "GSM1521188", "GSM1521189", "GSM1521190", "GSM1521191", "GSM1521192", "GSM1521193", "GSM1521194", "GSM1521195", "GSM1521196", "GSM1521197", "GSM1521198", "GSM1521199", "GSM1521200", "GSM1521201", "GSM1521202", "GSM1521203", "GSM1521204", "GSM1521205", "GSM1521206", "GSM1521207", "GSM1521208", "GSM1521209", "GSM1521210", "GSM1521211", "GSM1521212", "GSM1521213", "GSM1521214", "GSM1521215", "GSM1521216", "GSM1521217", "GSM1521218", "GSM1521219", "GSM1521220", "GSM1521221", "GSM1521222", "GSM1521223", "GSM1521224", "GSM1521225", "GSM1521226", "GSM1521227", "GSM1521228", "GSM1521229", "GSM1521230", "GSM1521231", "GSM1521232", "GSM1521233", "GSM1521234", "GSM1521235", "GSM1521236", "GSM1521237", "GSM1521238", "GSM1521239", "GSM1521240", "GSM1521241", "GSM1521242", "GSM1521243", "GSM1521244", "GSM1521245", "GSM1521246", "GSM1521247", "GSM1521248", "GSM1521249", "GSM1521250", "GSM1521251", "GSM1521252", "GSM1521253", "GSM1521254", "GSM1521255", "GSM1521256", "GSM1521257", "GSM1521258", "GSM1521259", "GSM1521260", "GSM1521261", "GSM1521262", "GSM1521263", "GSM1521264", "GSM1521265", "GSM1521266", "GSM1521267", "GSM1521268", "GSM1521269", "GSM1521270", "GSM1521271", "GSM1521272", "GSM1521273", "GSM1521274", "GSM1521275", "GSM1521276", "GSM1521277", "GSM1521278", "GSM1521279", "GSM1521280", "GSM1521281", "GSM1521282", "GSM1521283", "GSM1521284", "GSM1521285", "GSM1521286", "GSM1521287", "GSM1521288", "GSM1521289", "GSM1521290", "GSM1521291", "GSM1521292", "GSM1521293", "GSM1521294", "GSM1521295", "GSM1521296", "GSM1521297", "GSM1521298", "GSM1521299", "GSM1521300", "GSM1521301", "GSM1521302", "GSM1521303", "GSM1521304", "GSM1521305", "GSM1521306", "GSM1521307", "GSM1521308", "GSM1521309", "GSM1521310", "GSM1521311", "GSM1521312", "GSM1521313", "GSM1521314", "GSM1521315", "GSM1521316", "GSM1521317", "GSM1521318", "GSM1521319", "GSM1521320", "GSM1521321", "GSM1521322", "GSM1521323", "GSM1521324", "GSM1521325", "GSM1521326", "GSM1521327", "GSM1521328", "GSM1521329", "GSM1521330", "GSM1521331", "GSM1521332", "GSM1521333", "GSM1521334", "GSM1521335", "GSM1521336", "GSM1521337", "GSM1521338", "GSM1521339", "GSM1521340", "GSM1521341", "GSM1521342", "GSM1521343", "GSM1521344", "GSM1521345", "GSM1521346"], "sample_count": 188, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Smoking Status Impacts microRNA Mediated Prognosis and Lung Adenocarcinoma Biology", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE83527", "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=GSE83527", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE83527", "version": null, "note": "All data used in this study can be downloaded from TCGA (https://portal.gdc.cancer.gov/) and GEO (https://www.ncbi.nlm.nih.gov/geo) databases.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data used in this study can be downloaded from TCGA (https://portal.gdc.cancer.gov/) and GEO (https://www.ncbi.nlm.nih.gov/geo) databases.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2207991", "GSM2207992", "GSM2207993", "GSM2207994", "GSM2207995", "GSM2207996", "GSM2207997", "GSM2207998", "GSM2207999", "GSM2208000", "GSM2208001", "GSM2208002", "GSM2208003", "GSM2208004", "GSM2208005", "GSM2208006", "GSM2208007", "GSM2208008", "GSM2208009", "GSM2208010", "GSM2208011", "GSM2208012", "GSM2208013", "GSM2208014", "GSM2208015", "GSM2208016", "GSM2208017", "GSM2208018", "GSM2208019", "GSM2208020", "GSM2208021", "GSM2208022", "GSM2208023", "GSM2208024", "GSM2208025", "GSM2208026", "GSM2208027", "GSM2208028", "GSM2208029", "GSM2208030", "GSM2208031", "GSM2208032", "GSM2208033", "GSM2208034", "GSM2208035", "GSM2208036", "GSM2208037", "GSM2208038", "GSM2208039", "GSM2208040", "GSM2208041", "GSM2208042", "GSM2208043", "GSM2208044", "GSM2208045", "GSM2208046", "GSM2208047", "GSM2208048", "GSM2208049", "GSM2208050", "GSM2208051", "GSM2208052", "GSM2208053", "GSM2208054", "GSM2208055", "GSM2208056", "GSM2208057", "GSM2208058", "GSM2208059", "GSM2208060", "GSM2208061", "GSM2208062", "GSM2208063", "GSM2208064", "GSM2208065", "GSM2208066", "GSM2208067"], "sample_count": 77, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Developmental transcription factor NFIB is a putative target of oncofetal miRNAs and is associated with tumour aggressiveness in lung adenocarcinoma", "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:32323746:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a7505fc4cd5877ee11cc213cd8e9347c950daf579a1d0ba77dde0ff8f2a65de7", "bytes": 791, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#tI-ijmm-45-05-1397", "version": null, "note": "Demographic and histopathological data of patients from TCGA and GEO databases.", "structure": {"pmcid": "PMC7138293", "section_index": 3, "section_title": "miRNA expression data collection and preprocessing", "row_count": 12, "column_count": 4}, "table": {"label": "Table I", "caption": "Demographic and histopathological data of patients from TCGA and GEO databases.", "rows": [["Variable", "TCGA-LUAD (n=470) Training and validation dataset", "GSE62182 (n=94) Test dataset 1", "GSE83527 (n=36) Test dataset 2"], ["Sex, n (%)"], ["Female", "255 (54.3)", "65 (69.1)", "15 (41.7)"], ["Male", "215 (45.7)", "29 (30.9)", "21 (58.3)"], ["Smoking, n (%)"], ["Current or former", "320 (68.1)", "67 (71.3)", "33 (91.7)"], ["Never", "150 (31.9)", "27 (28.7)", "3 (8.3)"], ["Stage, n (%)"], ["I", "260 (55.3)", "58 (61.7)", "15 (41.6)"], ["II", "109 (23.2)", "23 (24.5)", "15 (41.6)"], ["III", "78 (16.6)", "10 (10.6)", "5 (13.9)"], ["IV", "23 (4.9)", "3 (3.2)", "1 (2.8)"]], "row_count": 12, "column_count": 4, "numeric_cells": 27, "header_rows": 1, "locator": "section[3]/table-wrap[1]#tI-ijmm-45-05-1397"}}, {"id": "asset:table:pmid:32323746:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:31f7bff8be80e875e14f3fc6498a3c303bfa8a43f99b864f8188c4d8406ca682", "bytes": 1022, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#tII-ijmm-45-05-1397", "version": null, "note": "List of the 16 miRNAs in the signature.", "structure": {"pmcid": "PMC7138293", "section_index": 8, "section_title": "miRNA selection, model training and validation", "row_count": 17, "column_count": 3}, "table": {"label": "Table II", "caption": "List of the 16 miRNAs in the signature.", "rows": [["miRNA ID", "miRNA region", "Mature miRNA"], ["hsa-mir-2116", "MIMAT0011161", "hsa-miR-2116-3p"], ["hsa-mir-4661", "MIMAT0019729", "hsa-miR-4661-5p"], ["hsa-mir-3942", "MIMAT0018358", "hsa-miR-3942-5p"], ["hsa-mir-4435", "MIMAT0018951", "hsa-miR-4435"], ["hsa-mir-1307", "MIMAT0005951", "hsa-miR-1307-3p"], ["hsa-mir-1254", "MIMAT0005905", "hsa-miR-1254"], ["hsa-mir-582", "MIMAT0004797", "hsa-miR-582-3p"], ["hsa-mir-5690", "MIMAT0022482", "hsa-miR-5690"], ["hsa-mir-4713", "MIMAT0019821", "hsa-miR-4713-3p"], ["hsa-mir-1293", "MIMAT0005883", "hsa-miR-1293"], ["hsa-mir-939", "MIMAT0004982", "hsa-miR-939-5p"], ["hsa-mir-421", "MIMAT0003339", "hsa-miR-421"], ["hsa-mir-335", "MIMAT0000765", "hsa-miR-335-5p"], ["hsa-mir-4677", "MIMAT0019760", "hsa-miR-4677-5p"], ["hsa-mir-4754", "MIMAT0019894", "hsa-miR-4754"], ["hsa-mir-4746", "MIMAT0019880", "hsa-miR-4746-5p"]], "row_count": 17, "column_count": 3, "numeric_cells": 48, "header_rows": 1, "locator": "section[8]/table-wrap[1]#tII-ijmm-45-05-1397"}}, {"id": "asset:table:pmid:32323746:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9b4fdee822eb20c7b404b90ab82266f794b80da3618eed56fd5e01cabb5a3e4d", "bytes": 689, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#tIII-ijmm-45-05-1397", "version": null, "note": "Enriched biological pathways identified in a KEGG pathway analysis.", "structure": {"pmcid": "PMC7138293", "section_index": 9, "section_title": "KEGG and GO analyses", "row_count": 7, "column_count": 5}, "table": {"label": "Table III", "caption": "Enriched biological pathways identified in a KEGG pathway analysis.", "rows": [["No.", "KEGG pathway", "P-value", "Genes", "miRNAs"], ["1", "Fatty acid biosynthesis (hsa00061)", "<1x10−325", "1", "4"], ["2", "Fatty acid metabolism (hsa01212)", "<1x10−325", "6", "4"], ["3", "Other glycan degradation (hsa00511)", "9.86x10−06", "3", "2"], ["4", "Steroid biosynthesis (hsa00100)", "6.13x10−05", "13", "2"], ["5", "Biosynthesis of unsaturated fatty acids (hsa01040)", "0.01643741", "4", "2"], ["6", "ECM-receptor interaction (hsa04512)", "0.04934272", "26", "1"]], "row_count": 7, "column_count": 5, "numeric_cells": 30, "header_rows": 1, "locator": "section[9]/table-wrap[1]#tIII-ijmm-45-05-1397"}}, {"id": "asset:table:pmid:32323746:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:68b15d1fbc7611c91f149e6cdba87c8cc60c48b84aca25e4876cc7a8c26fb4e8", "bytes": 2568, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[2]#tIV-ijmm-45-05-1397", "version": null, "note": "List of significant GO terms in the biological process category.", "structure": {"pmcid": "PMC7138293", "section_index": 9, "section_title": "KEGG and GO analyses", "row_count": 31, "column_count": 5}, "table": {"label": "Table IV", "caption": "List of significant GO terms in the biological process category.", "rows": [["No.", "GO Term (Biological Process)", "P-value", "Genes", "miRNAs"], ["1", "Biological process (GO:0008150)", "<1x10−325", "1,353", "5"], ["2", "Symbiosis, encompassing mutualism through parasitism (GO:0044403)", "<1x10−325", "94", "5"], ["3", "Gene expression (GO:0010467)", "<1x10−325", "125", "6"], ["4", "Biosynthetic process (GO:0009058)", "<1x10−325", "450", "7"], ["5", "Cellular protein modification process (GO:0006464)", "<1x10−325", "562", "8"], ["6", "Cellular nitrogen compound metabolic process (GO:0034641)", "<1x10−325", "612", "10"], ["7", "Viral process (GO:0016032)", "1.11x10−16", "85", "5"], ["8", "Small molecule metabolic process (GO:0044281)", "1.18x10−14", "552", "5"], ["9", "Neurotrophin TRK receptor signaling pathway (GO:0048011)", "3.90x10−13", "99", "6"], ["10", "Nucleobase-containing compound catabolic process (GO:0034655)", "1.04x10−12", "126", "5"], ["11", "Catabolic process (GO:0009056)", "1.24x10−12", "446", "5"], ["12", "Cellular protein metabolic process (GO:0044267)", "2.49x10−08", "131", "5"], ["13", "Response to stress (GO:0006950)", "7.59x10−08", "511", "5"], ["14", "Blood coagulation (GO:0007596)", "1.66x10−06", "115", "3"], ["15", "Cell death (GO:0008219)", "1.79x10−06", "81", "3"], ["16", "Mitotic cell cycle (GO:0000278)", "1.87x10−06", "60", "5"], ["17", "Membrane organization (GO:0061024)", "1.99x10−06", "93", "5"], ["18", "Fc-epsilon receptor signaling pathway (GO:0038095)", "5.15x10−06", "49", "3"], ["19", "mRNA metabolic process (GO:0016071)", "6.09E-05", "40", "5"], ["20", "Epidermal growth factor receptor signaling pathway (GO:0007173)", "0.000209601", "59", "3"], ["21", "Immune system process (GO:0002376)", "0.000331715", "319", "3"], ["22", "RNA metabolic process (GO:0016070)", "0.000428269", "38", "4"], ["23", "Cellular component assembly (GO:0022607)", "0.000625565", "124", "4"], ["24", "RNA splicing (GO:0008380)", "0.002480079", "35", "2"], ["25", "mRNA processing (GO:0006397)", "0.002624066", "61", "4"], ["26", "Activation of signaling protein activity involved in unfolded protein response (GO:0006987)", "0.01328594", "22", "1"], ["27", "DNA metabolic process (GO:0006259)", "0.02118011", "54", "2"], ["28", "Post-translational protein modification (GO:0043687)", "0.02692964", "40", "1"], ["29", "Transcription, DNA-templated (GO:0006351)", "0.02971434", "131", "2"], ["30", "Fibroblast growth factor receptor signaling pathway (GO:0008543)", "0.04102542", "50", "3"]], "row_count": 31, "column_count": 5, "numeric_cells": 150, "header_rows": 1, "locator": "section[9]/table-wrap[2]#tIV-ijmm-45-05-1397"}}, {"id": "asset:table:pmid:32323746:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1dbf38b0e6fbd04df289bb09a48052c376407eff9a9aeb455e09f3990dec53ec", "bytes": 589, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[3]#tV-ijmm-45-05-1397", "version": null, "note": "List of significant GO terms in the cellular component category.", "structure": {"pmcid": "PMC7138293", "section_index": 9, "section_title": "KEGG and GO analyses", "row_count": 6, "column_count": 5}, "table": {"label": "Table V", "caption": "List of significant GO terms in the cellular component category.", "rows": [["No.", "GO Term (Cellular Component)", "P-value", "Genes", "miRNAs"], ["1", "Cellular component (GO:0005575)", "<1x10−325", "1,497", "6"], ["2", "Cytosol (GO:0005829)", "<1x10−325", "336", "6"], ["3", "Protein complex (GO:0043234)", "<1x10−325", "444", "7"], ["4", "Organelle (GO:0043226)", "<1x10−325", "2,361", "10"], ["5", "Nucleoplasm (GO:0005654)", "1.99x10−13", "158", "5"]], "row_count": 6, "column_count": 5, "numeric_cells": 25, "header_rows": 1, "locator": "section[9]/table-wrap[3]#tV-ijmm-45-05-1397"}}, {"id": "asset:table:pmid:32323746:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d3190530d75bba5e4ec058bdaee8ff29acb202176188989190b6f2de1f547407", "bytes": 765, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[4]#tVI-ijmm-45-05-1397", "version": null, "note": "List of significant GO terms in the molecular function category.", "structure": {"pmcid": "PMC7138293", "section_index": 9, "section_title": "KEGG and GO analyses", "row_count": 8, "column_count": 5}, "table": {"label": "Table VI", "caption": "List of significant GO terms in the molecular function category.", "rows": [["No.", "GO Term (Molecular Function)", "P-value", "Genes", "miRNAs"], ["1", "Molecular function (GO:0003674)", "<1x10−325", "1,491", "6"], ["2", "Ion binding (GO:0043167)", "<1x10−325", "1,414", "7"], ["3", "Poly(A) RNA binding (GO:0044822)", "<1x10−325", "242", "7"], ["4", "RNA binding (GO:0003723)", "<1x10−325", "297", "8"], ["5", "Enzyme binding (GO:0019899)", "3.22x10−15", "337", "8"], ["6", "Protein binding transcription factor activity (GO:0000988)", "1.03x10−07", "131", "6"], ["7", "Enzyme regulator activity (GO:0030234)", "0.02094084", "169", "2"]], "row_count": 8, "column_count": 5, "numeric_cells": 35, "header_rows": 1, "locator": "section[9]/table-wrap[4]#tVI-ijmm-45-05-1397"}}], "gaps": ["asset:data:geo:GSE62182 not downloaded", "asset:data:geo:GSE62182 licence not read", "asset:data:geo:GSE83527 not downloaded", "asset:data:geo:GSE83527 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "SVM"}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "Two-sided Fisher’s exact test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Two-sided Fisher’s exact test was used to analyze the significance of the GO category and KEGG pathway enrichment, and corrected P<0.05 was considered to indicate a statistically significant difference."}}], "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": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: support_vector_machine."}, "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": ["GSE62182", "GSE83527"], "resolved_accessions": ["GSE62182", "GSE83527"], "statements": ["All data used in this study can be downloaded from TCGA (https://portal.gdc.cancer.gov/) and GEO (https://www.ncbi.nlm.nih.gov/geo) databases."], "basis": "The paper names GSE62182, GSE83527 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": ["train_classifier", "cross_validate", "roc_auc"], "assets": ["source:pmid:32323746", "data:geo:GSE62182", "asset:table:pmid:32323746:1", "asset:table:pmid:32323746:2", "asset:table:pmid:32323746:3", "asset:table:pmid:32323746:4", "asset:table:pmid:32323746:5", "asset:table:pmid:32323746:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE62182"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:19:25Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 30597, "completion_tokens": 1583, "cached_tokens": 776}}, "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:32323746", "type": "paper", "label": "pmid:32323746"}, {"id": "source:pmid:32323746", "type": "manuscript", "label": "PMID 32323746 full text"}, {"id": "data:geo:GSE62182", "type": "dataset", "label": "GEO GSE62182"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32323746", "type": "paper", "label": "pmid:32323746"}, {"id": "source:pmid:32323746", "type": "manuscript", "label": "PMID 32323746 full text"}, {"id": "data:geo:GSE62182", "type": "dataset", "label": "GEO GSE62182"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32323746", "type": "extraction", "used": ["source:pmid:32323746"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE62182", "type": "accession_resolution", "used": ["data:geo:GSE62182"], "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:32323746", "parent_hash": "sha256:7d63f018297385bfaa239b033ad872ae66162d2bc91f51e4362b4bc5afa7438d", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE62182 licence not read", "asset:data:geo:GSE62182 not downloaded", "asset:data:geo:GSE83527 licence not read", "asset:data:geo:GSE83527 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["SVM"], "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":"2026-11-04T00:35:24+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}}}