{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32058995", "kind": "science-record", "revision": 8, "content_hash": "sha256:8accf4b722c2ecd030e91991b509988f7ce89fa344fe362f6b3e4e17af22270d", "created_at": "2026-11-01T15:40:56Z", "updated_at": "2026-11-01T22:01:17Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Hub Genes and Pathways in Gastric Adenocarcinoma Based on Bioinformatics Analysis.", "doi": "10.12659/MSM.920261", "pmid": "32058995", "authors": ["Jieping Qiu", "Mengyu Sun", "Yaoqun Wang", "Bo Chen"], "journal": "Medical science monitor : international medical journal of experimental and clinical research", "year": 2020, "abstract": "BACKGROUND Gastric adenocarcinoma accounts for 95% of all gastric malignant tumors. The purpose of this research was to identify differentially expressed genes (DEGs) of gastric adenocarcinoma by use of bioinformatics methods. MATERIAL AND METHODS The gene microarray datasets of GSE103236, GSE79973, and GSE29998 were imported from the GEO database, containing 70 gastric adenocarcinoma samples and 68 matched normal samples. Gene ontology (GO) and KEGG analysis were applied to screened DEGs; Cytoscape software was used for constructing protein-protein interaction (PPI) networks and to perform module analysis of the DEGs. UALCAN was used for prognostic analysis. RESULTS We identified 2909 upregulated DEGs (uDEGs) and 7106 downregulated DEGs (dDEGs) of gastric adenocarcinoma. The GO analysis showed uDEGs were enriched in skeletal system development, cell adhesion, and biological adhesion. KEGG pathway analysis showed uDEGs were enriched in ECM-receptor interaction, focal adhesion, and Cytokine-cytokine receptor interaction. The top 10 hub genes - COL1A1, COL3A1, COL1A2, BGN, COL5A2, THBS2, TIMP1, SPP1, PDGFRB, and COL4A1 - were distinguished from the PPI network. These 10 hub genes were shown to be significantly upregulated in gastric adenocarcinoma tissues in GEPIA. Prognostic analysis of the 10 hub genes via UALCAN showed that the upregulated expression of COL3A1, COL1A2, BGN, and THBS2 significantly reduced the survival time of gastric adenocarcinoma patients. Module analysis revealed that gastric adenocarcinoma was related to 2 pathways: including focal adhesion signaling and ECM-receptor interaction. CONCLUSIONS This research distinguished hub genes and relevant signal pathways, which contributes to our understanding of the molecular mechanisms, and could be used as diagnostic indicators and therapeutic biomarkers for gastric adenocarcinoma.", "claims": [{"id": "claim-method", "statement": "The data were divided into a gastric adenocarcinoma group and a normal group for further analysis by GEO2R.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32058995", "locator": "sections[4] \"Data processing\" paragraph 2", "quote": "The data were divided into a gastric adenocarcinoma group and a normal group for further analysis by GEO2R."}], "state": "complete"}, {"id": "claim-data-access", "statement": "GSE103236 contains 19 samples, including 10 gastric adenocarcinoma samples and 9 matched normal mucosa samples.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32058995", "locator": "sections[3] \"Datasets\" paragraph 2", "quote": "GSE103236 contains 19 samples, including 10 gastric adenocarcinoma samples and 9 matched normal mucosa samples."}], "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:32058995"], "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:GSE103236"], "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:GSE103236"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32058995", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.12659/MSM.920261", "sha256": "sha256:da496565fc6ffef87dc0b2dbc505deb340da4daf84babf658442965bb0892751", "bytes": 32823, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.12659/MSM.920261", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7034404", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE103236", "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=GSE103236", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE103236", "version": null, "note": "GSE103236 contains 19 samples, including 10 gastric adenocarcinoma samples and 9 matched normal mucosa samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE103236 contains 19 samples, including 10 gastric adenocarcinoma samples and 9 matched normal mucosa samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2758660", "GSM2758661", "GSM2758662", "GSM2758663", "GSM2758664", "GSM2758665", "GSM2758666", "GSM2758667", "GSM2758668", "GSM2758669", "GSM2758670", "GSM2758671", "GSM2758672", "GSM2758673", "GSM2758674", "GSM2758675", "GSM2758676", "GSM2758677", "GSM2758678"], "sample_count": 19, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "Microarray gene expresion analysis for early and advanced gastric adenocarcinoma vs normal adjacent tissue.", "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:GSE29998", "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=GSE29998", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29998", "version": null, "note": "GSE103236 contains 19 samples, including 10 gastric adenocarcinoma samples and 9 matched normal mucosa samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE103236 contains 19 samples, including 10 gastric adenocarcinoma samples and 9 matched normal mucosa samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM742395", "GSM742396", "GSM742397", "GSM742398", "GSM742399", "GSM742400", "GSM742401", "GSM742402", "GSM742403", "GSM742404", "GSM742405", "GSM742406", "GSM742407", "GSM742408", "GSM742409", "GSM742410", "GSM742411", "GSM742412", "GSM742413", "GSM742414", "GSM742415", "GSM742416", "GSM742417", "GSM742418", "GSM742419", "GSM742420", "GSM742421", "GSM742422", "GSM742423", "GSM742424", "GSM742425", "GSM742426", "GSM742427", "GSM742428", "GSM742429", "GSM742430", "GSM742431", "GSM742432", "GSM742433", "GSM742434", "GSM742435", "GSM742436", "GSM742437", "GSM742438", "GSM742439", "GSM742440", "GSM742441", "GSM742442", "GSM742443", "GSM742444", "GSM742445", "GSM742446", "GSM742447", "GSM742448", "GSM742449", "GSM742450", "GSM742451", "GSM742452", "GSM742453", "GSM742454", "GSM742455", "GSM742456", "GSM742457", "GSM742458", "GSM742459", "GSM742460", "GSM742461", "GSM742462", "GSM742463", "GSM742464", "GSM742465", "GSM742466", "GSM742467", "GSM742468", "GSM742469", "GSM742470", "GSM742471", "GSM742472", "GSM742473", "GSM742474", "GSM742475", "GSM742476", "GSM742477", "GSM742478", "GSM742479", "GSM742480", "GSM742481", "GSM742482", "GSM742483", "GSM742484", "GSM742485", "GSM742486", "GSM742487", "GSM742488", "GSM742489", "GSM742490", "GSM742491", "GSM742492", "GSM742493"], "sample_count": 99, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "Deep sequencing of gastric carcinoma reveals somatic mutations relevant to personalized medicine [Illumina mRNA expression array data]", "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:GSE79973", "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=GSE79973", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE79973", "version": null, "note": "GSE103236 contains 19 samples, including 10 gastric adenocarcinoma samples and 9 matched normal mucosa samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE103236 contains 19 samples, including 10 gastric adenocarcinoma samples and 9 matched normal mucosa samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2109532", "GSM2109533", "GSM2109534", "GSM2109535", "GSM2109536", "GSM2109537", "GSM2109538", "GSM2109539", "GSM2109540", "GSM2109541", "GSM2109542", "GSM2109543", "GSM2109544", "GSM2109545", "GSM2109546", "GSM2109547", "GSM2109548", "GSM2109549", "GSM2109550", "GSM2109551"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from gastric cancer and paried normal tissues", "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:32058995:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:04e4a5b3e5433f696b555f4879637d6edf51abcbbecc4e7628882c555ae33e61", "bytes": 2098, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#t1-medscimonit-26-e920261", "version": null, "note": "DEGs in gastric adenocarcinoma shared in 3 microarrays.", "structure": {"pmcid": "PMC7034404", "section_index": 9, "section_title": "Screening of DEGs", "row_count": 3, "column_count": 3}, "table": {"label": "Table 1", "caption": "DEGs in gastric adenocarcinoma shared in 3 microarrays.", "rows": [["DEGS", "Total", "Elements"], ["uDEGs", "92", "IGF2BP3, CDC25B, C5AR1, ZMYND15, COL1A1, GDPD5, ANLN, CHRNA5, FNDC1, COL18A1, PRRX1, PDGFRB, COL5A2, KIF4A, THY1, ASCL2, ANTXR1, SPP1, WNT5A, OLR1, MSR1, MELK, CDH11, TIMP1, BGN, COL8A1, TEAD4, ECT2, MMP11, KRT80, DDX31, FSCN1, SRPX2, WNT2, LRP8, CEMIP, BMP1, DIO2, ARPC1B, MFAP2, WISP1, VMO1, COL4A1, SLC1A3, SULF1, CLDN1, COL11A1, TREM1, COL1A2, APOC1, COL12A1, ESM1, ARHGAP11A, PLAU, RFC3, TGM2, OSMR, FOXC1, CHEK1, TNFRSF11B, VSNL1, IGFBP7, CST1, RCC2, LEF1, IL13RA2, LZTS1, SPHK1, KIF2C, AGPAT4, BUB1, TNFRSF12A, TROAP, ANGPT2, COL3A1, TMEM158, SERPINH1, FAP, INHBA, CDCA3, SLC5A6, CKAP2, THBS2, OLFML2B, S100A10, COL6A3, CSF2RA, HSD11B1, PMEPA1, CTHRC1, GAD1, NCAPG"], ["dDEGs", "158", "EPB41L4B, COL4A5, ZNF385B, NRG4, IRX3, KLF4, NDRG2, IGFBP2, SLC9A2, SCNN1B, ESRRB, HTR4, F13A1, CNTD1, ADHFE1, CELA3B, OSBPL7, ADGRG2, MYOC, GIF, GPER1, HBB, GNG7, COL4A6, ERO1B, SOSTDC1, SBSPON, TMED6, ARHGAP24, CKMT2, KCNJ16, SLC26A7, ADAMTSL1, SYT4, PTGER3, ATP4A, DNASE1L3, CKB, MAL, AQP4, ESRRG, STOX2, CPA2, OXCT1, ABCA8, TTLL7, AXDND1, FXYD4, PER3, SHMT1, ETNPPL, DPT, PACRG, CAPN13, SLC5A5, FGA, NTN1, LGI1, ATP4B, EPM2A, SLC2A4, ADH1A, KLF15, SCUBE2, GPX3, KCNMB2, MAMDC2, SELENBP1, GPAT3, CLIC6, HAPLN1, TRIM50, B3GAT1, MS4A2, BHMT, GHRL, PNOC, GPRC5C, KCNJ13, DGKD, BMP6, GC, ALDH6A1, PDGFD, HTR1E, KIT, ADH1C, TOX, GCNT2, SST, PLCXD3, XYLT2, SLC6A16, CWH43, PDK4, GFRA2, GPR155, GREM2, NR3C2, PLA2G1B, MUC6, LINGO2, RNASE1, MYZAP, GUCA1C, AKR1C1, ACACB, PNPLA7, FXYD1, BAALC, PPP2R3A, BMP5, CKM, FBXL13, COBLL1, RGMB, FBP2, FAM150B, HIF3A, GSTA4, FGG, CHGA, RAB26, CAPN9, MT1M, SGSM1, ASPA, SCGN, SULT2A1, GAMT, CDHR3, CCKBR, ADRB2, GRIA3, SCGB2A1, SLC7A8, DUOX1, SORCS1, ARHGEF37, SCARA5, PACSIN1, LIFR, FNDC5, GLUL, CHIA, METTL7A, FAM189A2, SSTR1, PAIP2B, ACER2, ADH1B, MYRIP, KCNE2, PPP1R3C, TCEA3, PDE8B, SIGLEC11, KBTBD12"]], "row_count": 3, "column_count": 3, "numeric_cells": 4, "header_rows": 1, "locator": "section[9]/table-wrap[1]#t1-medscimonit-26-e920261"}}, {"id": "asset:table:pmid:32058995:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:488171f4b74c285b7339b52ca757f468dec53e14b80b59cc0b0397f53b82c865", "bytes": 5784, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#t2-medscimonit-26-e920261", "version": null, "note": "Gene ontology analysis of DEGs related to gastric adenocarcinoma.", "structure": {"pmcid": "PMC7034404", "section_index": 10, "section_title": "GO term enrichment analysis", "row_count": 55, "column_count": 7}, "table": {"label": "Table 2", "caption": "Gene ontology analysis of DEGs related to gastric adenocarcinoma.", "rows": [["Expression", "Category", "Term", "Count", "%", "P value", "FDR"], ["Upregulated", "GOTERM_BP_FAT", "GO: 0001501~skeletal system development", "19", "3.140495868", "6.25E-17", "1.67E-13"], ["GOTERM_BP_FAT", "GO: 0007155~cell adhesion", "20", "3.305785124", "4.39E-12", "6.55E-09"], ["GOTERM_BP_FAT", "GO: 0022610~biological adhesion", "20", "3.305785124", "4.50E-12", "6.72E-09"], ["GOTERM_BP_FAT", "GO: 0030199~collagen fibril organization", "8", "1.32231405", "1.19E-11", "1.78E-08"], ["GOTERM_BP_FAT", "GO: 0030198~extracellular matrix organization", "8", "1.32231405", "1.30E-07", "1.95E-04"], ["GOTERM_BP_FAT", "GO: 0001503~ossification", "8", "1.32231405", "2.60E-07", "3.89E-04"], ["GOTERM_BP_FAT", "GO: 0060348~bone development", "8", "1.32231405", "4.12E-07", "6.16E-04"], ["GOTERM_BP_FAT", "GO: 0043062~extracellular structure organization", "8", "1.32231405", "2.75E-06", "0.0041046"], ["GOTERM_BP_FAT", "GO: 0032963~collagen metabolic process", "5", "0.826446281", "3.71E-06", "0.005542186"], ["GOTERM_BP_FAT", "GO: 0043588~skin development", "5", "0.826446281", "4.29E-06", "0.006410681"], ["GOTERM_CC_FAT", "GO: 0005578~proteinaceous extracellular matrix", "25", "4.132231405", "1.86E-24", "2.10E-21"], ["GOTERM_CC_FAT", "GO: 0031012~extracellular matrix", "25", "4.132231405", "1.14E-23", "1.28E-20"], ["GOTERM_CC_FAT", "GO: 0005576~extracellular region", "40", "6.611570248", "6.86E-20", "7.75E-17"], ["GOTERM_CC_FAT", "GO: 0044421~extracellular region part", "30", "4.958677686", "8.27E-19", "9.34E-16"], ["GOTERM_CC_FAT", "GO: 0044420~extracellular matrix part", "14", "2.314049587", "1.64E-15", "1.88E-12"], ["GOTERM_CC_FAT", "GO: 0005581~collagen", "9", "1.487603306", "1.49E-12", "1.68E-09"], ["GOTERM_CC_FAT", "GO: 0005583~fibrillar collagen", "5", "0.826446281", "1.48E-07", "1.67E-04"], ["GOTERM_CC_FAT", "GO: 0005604~basement membrane", "6", "0.991735537", "2.04E-05", "0.023013251"], ["GOTERM_CC_FAT", "GO: 0031093~platelet alpha granule lumen", "5", "0.826446281", "2.76E-05", "0.031185256"], ["GOTERM_CC_FAT", "GO: 0060205~cytoplasmic membrane-bounded vesicle lumen", "5", "0.826446281", "3.67E-05", "0.041403378"], ["GOTERM_MF_FAT", "GO: 0005201~extracellular matrix structural constituent", "11", "1.818181818", "5.06E-13", "5.90E-10"], ["GOTERM_MF_FAT", "GO: 0005198~structural molecule activity", "14", "2.314049587", "3.15E-07", "3.67E-04"], ["GOTERM_MF_FAT", "GO: 0005518~collagen binding", "5", "0.826446281", "8.88E-06", "0.010355681"], ["GOTERM_MF_FAT", "GO: 0005539~glycosaminoglycan binding", "7", "1.157024793", "1.19E-05", "0.013923194"], ["GOTERM_MF_FAT", "GO: 0001871~pattern binding", "7", "1.157024793", "2.05E-05", "0.023961179"], ["GOTERM_MF_FAT", "GO: 0030247~polysaccharide binding", "7", "1.157024793", "2.05E-05", "0.023961179"], ["GOTERM_MF_FAT", "GO: 0008201~heparin binding", "6", "0.991735537", "3.72E-05", "0.043401787"], ["GOTERM_MF_FAT", "GO: 0050840~extracellular matrix binding", "4", "0.661157025", "1.30E-04", "0.151895387"], ["GOTERM_MF_FAT", "GO: 0005509~calcium ion binding", "12", "1.983471074", "4.20E-04", "0.488103889"], ["GOTERM_MF_FAT", "GO: 0008237~metallopeptidase activity", "6", "0.991735537", "5.52E-04", "0.641829759"], ["Downregulated", "GOTERM_BP_FAT", "GO: 0007586~digestion", "12", "1.038062284", "7.45E-12", "1.09E-08"], ["GOTERM_BP_FAT", "GO: 0055114~oxidation reduction", "15", "1.297577855", "3.07E-05", "0.045029161"], ["GOTERM_BP_FAT", "GO: 0006081~cellular aldehyde metabolic process", "4", "0.346020761", "6.53E-04", "0.952399247"], ["GOTERM_BP_FAT", "GO: 0030001~metal ion transport", "10", "0.865051903", "0.00213818", "3.08666015"], ["GOTERM_BP_FAT", "GO: 0006812~cation transport", "10", "0.865051903", "0.006666616", "9.333089916"], ["GOTERM_BP_FAT", "GO: 0006811~ion transport", "12", "1.038062284", "0.007065784", "9.865306976"], ["GOTERM_BP_FAT", "GO: 0046903~secretion", "7", "0.605536332", "0.010249221", "14.00683938"], ["GOTERM_BP_FAT", "GO: 0015672~monovalent inorganic cation transport", "7", "0.605536332", "0.01337189", "17.89646714"], ["GOTERM_BP_FAT", "GO: 0006813~potassium ion transport", "5", "0.432525952", "0.016821807", "22.00279704"], ["GOTERM_BP_FAT", "GO: 0022600~digestive system process", "3", "0.259515571", "0.018374485", "23.78773935"], ["GOTERM_CC_FAT", "GO: 0005576~extracellular region", "31", "2.6816609", "1.26E-05", "0.014253173"], ["GOTERM_CC_FAT", "GO: 0045177~apical part of cell", "7", "0.605536332", "0.001371031", "1.545706714"], ["GOTERM_CC_FAT", "GO: 0016324~apical plasma membrane", "6", "0.519031142", "0.002113034", "2.373127171"], ["GOTERM_CC_FAT", "GO: 0005624~membrane fraction", "11", "0.951557093", "0.047644803", "42.55171216"], ["GOTERM_MF_FAT", "GO: 0031420~alkali metal ion binding", "7", "0.605536332", "0.004013875", "5.198242704"], ["GOTERM_MF_FAT", "GO: 0004033~aldo-keto reductase activity", "3", "0.259515571", "0.004305787", "5.566366984"], ["GOTERM_MF_FAT", "GO: 0004198~calcium-dependent cysteine-type endopeptidase activity", "3", "0.259515571", "0.004899806", "6.31139254"], ["GOTERM_MF_FAT", "GO: 0008289~lipid binding", "9", "0.778546713", "0.009796998", "12.2496158"], ["GOTERM_MF_FAT", "GO: 0016620~oxidoreductase activity, acting on the aldehyde or oxo group of donors, NAD or NADP as acceptor", "3", "0.259515571", "0.010025001", "12.51741656"], ["GOTERM_MF_FAT", "GO: 0030955~potassium ion binding", "5", "0.432525952", "0.010277041", "12.81257072"], ["GOTERM_MF_FAT", "GO: 0008233~peptidase activity", "10", "0.865051903", "0.013517076", "16.52574449"], ["GOTERM_MF_FAT", "GO: 0015267~channel activity", "8", "0.692041522", "0.019316845", "22.80964632"], ["GOTERM_MF_FAT", "GO: 0022803~passive transmembrane transporter activity", "8", "0.692041522", "0.01954695", "23.04969236"], ["GOTERM_MF_FAT", "GO: 0008900~hydrogen: potassium-exchanging ATPase activity", "2", "0.173010381", "0.019742308", "23.25294859"]], "row_count": 55, "column_count": 7, "numeric_cells": 270, "header_rows": 1, "locator": "section[10]/table-wrap[1]#t2-medscimonit-26-e920261"}}, {"id": "asset:table:pmid:32058995:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:15af2e14966e65e06014d3fd8192675b3b62fad37c7579b4c39bde7e34f9b1f1", "bytes": 1056, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#t3-medscimonit-26-e920261", "version": null, "note": "KEGG pathway analysis of DEGs associated with gastric adenocarcinoma.", "structure": {"pmcid": "PMC7034404", "section_index": 11, "section_title": "KEGG signal pathway analysis", "row_count": 10, "column_count": 6}, "table": {"label": "Table 3", "caption": "KEGG pathway analysis of DEGs associated with gastric adenocarcinoma.", "rows": [["Expression", "Term", "Count", "%", "P value", "FDR"], ["Upregulated", "hsa04512: ECM-receptor interaction", "11", "1.818181818", "2.66E-13", "2.14E-10"], ["hsa04510: Focal adhesion", "11", "1.818181818", "1.80E-09", "1.44E-06"], ["hsa04350: TGF-beta signaling pathway", "4", "0.661157025", "0.005149174", "4.056689024"], ["Downregulated", "hsa00982: Drug metabolism", "8", "0.692041522", "1.46E-07", "1.41E-04"], ["hsa00830: Retinol metabolism", "7", "0.605536332", "1.38E-06", "0.001338048"], ["hsa00980: Metabolism of xenobiotics by cytochrome P450", "7", "0.605536332", "2.60E-06", "0.002518197"], ["hsa00010: Glycolysis/Gluconeogenesis", "4", "0.346020761", "0.007818033", "7.311759835"], ["hsa00591: Linoleic acid metabolism", "3", "0.259515571", "0.015552893", "14.070282"], ["hsa00350: Tyrosine metabolism", "3", "0.259515571", "0.036348334", "30.10544025"]], "row_count": 10, "column_count": 6, "numeric_cells": 45, "header_rows": 1, "locator": "section[11]/table-wrap[1]#t3-medscimonit-26-e920261"}}, {"id": "asset:table:pmid:32058995:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d1a1f89c744662e5e1f505771fcad971687f4aaa0004bffd55aba2cf766459d6", "bytes": 788, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#t4-medscimonit-26-e920261", "version": null, "note": "Connectivity and regulation of the top 10 hub genes.", "structure": {"pmcid": "PMC7034404", "section_index": 12, "section_title": "PPI network construction, module analysis and hub genes determination", "row_count": 11, "column_count": 4}, "table": {"label": "Table 4", "caption": "Connectivity and regulation of the top 10 hub genes.", "rows": [["Gene symbol", "Gene title", "Connectivity", "Regulation"], ["COL1A1", "Collagen type I alpha 1 chain", "34", "Up"], ["COL3A1", "Collagen type III alpha 1 chain", "30", "Up"], ["COL1A2", "Collagen type I alpha 2 chain", "29", "Up"], ["BGN", "Biglycan", "29", "Up"], ["COL5A2", "Collagen type V alpha 2 chain", "23", "Up"], ["THBS2", "Thrombospondin 2", "23", "Up"], ["TIMP1", "TIMP metallopeptidase inhibitor 1", "21", "Up"], ["SPP1", "Secreted phosphoprotein 1", "20", "Up"], ["PDGFRB", "Platelet-derived growth factor receptor beta", "20", "Up"], ["COL4A1", "Collagen type IV alpha 1 chain", "19", "Up"]], "row_count": 11, "column_count": 4, "numeric_cells": 18, "header_rows": 1, "locator": "section[12]/table-wrap[1]#t4-medscimonit-26-e920261"}}], "gaps": ["asset:data:geo:GSE103236 not downloaded", "asset:data:geo:GSE103236 licence not read", "asset:data:geo:GSE29998 not downloaded", "asset:data:geo:GSE29998 licence not read", "asset:data:geo:GSE79973 not downloaded", "asset:data:geo:GSE79973 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-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": "GO enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "GEO2R", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The data were divided into a gastric adenocarcinoma group and a normal group for further analysis by GEO2R."}}], "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": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE103236", "GSE79973", "GSE29998"], "resolved_accessions": ["GSE103236", "GSE79973", "GSE29998"], "statements": ["GSE103236 contains 19 samples, including 10 gastric adenocarcinoma samples and 9 matched normal mucosa samples."], "basis": "The paper names GSE103236, GSE79973, GSE29998 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": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:32058995", "data:geo:GSE103236", "asset:table:pmid:32058995:1", "asset:table:pmid:32058995:2", "asset:table:pmid:32058995:3", "asset:table:pmid:32058995:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE103236"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:18:25Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 27165, "completion_tokens": 1494, "cached_tokens": 784}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:32058995", "type": "paper", "label": "pmid:32058995"}, {"id": "source:pmid:32058995", "type": "manuscript", "label": "PMID 32058995 full text"}, {"id": "data:geo:GSE103236", "type": "dataset", "label": "GEO GSE103236"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32058995", "type": "paper", "label": "pmid:32058995"}, {"id": "source:pmid:32058995", "type": "manuscript", "label": "PMID 32058995 full text"}, {"id": "data:geo:GSE103236", "type": "dataset", "label": "GEO GSE103236"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32058995", "type": "extraction", "used": ["source:pmid:32058995"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE103236", "type": "accession_resolution", "used": ["data:geo:GSE103236"], "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:32058995", "parent_hash": "sha256:553a8385bc3dcb8be8acbdd53425ec4ac7e8fa22af2c0094de8644374a338459", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE103236 licence not read", "asset:data:geo:GSE103236 not downloaded", "asset:data:geo:GSE29998 licence not read", "asset:data:geo:GSE29998 not downloaded", "asset:data:geo:GSE79973 licence not read", "asset:data:geo:GSE79973 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["atics methods. MATERIAL AND METHODS The gene microarray datasets of GSE103236, GSE79973, and GSE2999"], "order_basis": "paper_text_order:313", "id": "assay:1"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:12:33+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}}}