{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31173250", "kind": "science-record", "revision": 7, "content_hash": "sha256:6964e0ef260b795840dbf931ff235a754f74e440bb6e070c5a8a4967a9382d6e", "created_at": "2026-11-01T15:40:45Z", "updated_at": "2026-11-01T22:00:35Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Screening key genes and signaling pathways in colorectal cancer by integrated bioinformatics analysis.", "doi": "10.3892/mmr.2019.10336", "pmid": "31173250", "authors": ["Chang Yu", "Fuqiang Chen", "Jianjun Jiang", "Hong Zhang", "Meijuan Zhou"], "journal": "Molecular medicine reports", "year": 2019, "abstract": "The aim of the present study was to identify potential key genes associated with the progression and prognosis of colorectal cancer (CRC). Differentially expressed genes (DEGs) between CRC and normal samples were screened by integrated analysis of gene expression profile datasets, including the Gene Expression Omnibus (GEO) and The Cancer Genome Atlas. Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis was conducted to identify the biological role of DEGs. In addition, a protein‑protein interaction network and survival analysis were used to identify the key genes. The profiles of GSE9348, GSE22598 and GSE113513 were downloaded from the GEO database. A total of 405 common DEGs were identified, including 236 down‑ and 169 upregulated. GO analysis revealed that the downregulated DEGs were mainly enriched in 'detoxification of copper ion' [biological process, (BP)], 'oxidoreductase activity, acting on CH‑OH group of donors, NAD or NADP as acceptor' [molecular function, (MF)] and 'brush border' [cellular component, (CC)]. Upregulated DEGs were mainly involved in 'nuclear division' (BP), 'snoRNA binding' (MF) and 'nucleolar part' (CC). KEGG pathway analysis revealed that DEGs were mainly involved in 'mineral absorption', 'nitrogen metabolism', 'cell cycle' and 'caffeine metabolism'. A PPI network was constructed with 268 nodes and 1,027 edges. The top one module was selected, and it was revealed that module‑related genes were mainly enriched in the GO terms 'sister chromatid segregation' (BP), 'chemokine activity' (MF), and 'condensed chromosome (CC)'. The KEGG pathway was mainly enriched in 'cell cycle', 'progesterone‑mediated oocyte maturation', 'chemokine signaling pathway', 'IL‑17 signaling pathway', 'legionellosis', and 'rheumatoid arthritis'. DNA topoisomerase II‑α (TOP2A), mitotic arrest deficient 2 like 1 (MAD2L1), cyclin B1 (CCNB1), checkpoint kinase 1 (CHEK1), cell division cycle 6 (CDC6) and ubiquitin conjugating enzyme E2 C (UBE2C) were indicated as hub genes. Furthermore, survival analysis revealed that TOP2A, MAD2L1, CDC6 and CHEK1 may serve as prognostic biomarkers in CRC. The present study provided insights into the molecular mechanism of CRC that may be useful in further investigations.", "claims": [{"id": "claim-method", "statement": "Kaplan-Meier analysis was performed based on the expression and clinical data of TCGA, and Perl was used to merge data.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31173250", "locator": "sections[8] \"Survival analysis of hub genes\" paragraph 2", "quote": "Kaplan-Meier analysis was performed based on the expression and clinical data of TCGA, and Perl was used to merge data."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data generated or analyzed during the present study are included in this article, and the R codes are available at https://github.com/Yuchang66/CRC-project.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31173250", "locator": "sections[19] \"Availability of data and materials\" paragraph 2", "quote": "All data generated or analyzed during the present study are included in this article, and the R codes are available at https://github.com/Yuchang66/CRC-project."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:31173250"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31173250", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/mmr.2019.10336", "sha256": "sha256:8fb18283fdf1fb06ab0e6ddec69756e5faf755d797331370b3d62598ad61b4f5", "bytes": 36501, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/mmr.2019.10336", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6625394", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:31173250:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d0ad4096143186b44c3fac7c013578c969c6d629630153ba852e0a434e324b9c", "bytes": 721, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#tI-mmr-20-02-1259", "version": null, "note": "Information on the datasets included in the current study.", "structure": {"pmcid": "PMC6625394", "section_index": 4, "section_title": "Gene expression profile data", "row_count": 5, "column_count": 4}, "table": {"label": "Table I.", "caption": "Information on the datasets included in the current study.", "rows": [["Dataset", "Reference", "Platform", "No. of samples (normal/tumor)"], ["GSE9348", "Hong et al, 2010 (8)", "[HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array", "12/12"], ["GSE22598", "Okazaki et al, 2011 (9)", "[HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array", "17/17"], ["GSE113513", "Peng et al, 2018 (unpublished)", "[PrimeView] Affymetrix Human Gene Expression Array", "14/14"], ["TCGA_CRC", "The Cancer Genome Atlas (TCGA) data portal", "IlluminaHiseq (Illumina, San Diego, CA)", "51/647"]], "row_count": 5, "column_count": 4, "numeric_cells": 12, "header_rows": 1, "locator": "section[4]/table-wrap[1]#tI-mmr-20-02-1259"}}, {"id": "asset:table:pmid:31173250:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f92d2fcec5abbfd9854a7b847a31ef45933c71ba03fc8bcfe8b243103a5f15ae", "bytes": 2350, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#tII-mmr-20-02-1259", "version": null, "note": "Top 20 down- and upregulated overlapping DEGs in GSE113513, GSE9348, GSE22598 and TCGA were screened by intersected analysis.", "structure": {"pmcid": "PMC6625394", "section_index": 11, "section_title": "Identification of DEGs in GEO and TCGA", "row_count": 41, "column_count": 6}, "table": {"label": "Table II.", "caption": "Top 20 down- and upregulated overlapping DEGs in GSE113513, GSE9348, GSE22598 and TCGA were screened by intersected analysis.", "rows": [["Genes", "GSE113513", "GSE9348", "GSE22598", "TCGA", "Regulation"], ["AQP8", "−4.00", "−6.74", "−2.75", "−6.87", "Down"], ["CLCA4", "−2.30", "−7.61", "−4.91", "−5.35", "Down"], ["GUCA2B", "−4.82", "−5.08", "−3.37", "−6.06", "Down"], ["MS4A12", "−3.68", "−6.04", "−3.54", "−5.36", "Down"], ["GUCA2A", "−4.10", "−5.00", "−3.72", "−5.11", "Down"], ["CA2", "−3.68", "−5.32", "−3.76", "−4.81", "Down"], ["ABCG2", "−2.39", "−6.03", "−3.93", "−4.68", "Down"], ["CLDN8", "−3.69", "−4.40", "−3.65", "−5.07", "Down"], ["GCG", "−4.57", "−3.92", "−4.15", "−4.13", "Down"], ["ZG16", "−3.18", "−4.70", "−4.45", "−4.44", "Down"], ["PKIB", "−3.21", "−4.99", "−3.85", "−3.95", "Down"], ["CA4", "−3.39", "−4.54", "−3.07", "−4.76", "Down"], ["BEST4", "−3.50", "−2.72", "−3.66", "−5.85", "Down"], ["CA1", "−3.33", "−3.20", "−1.94", "−6.51", "Down"], ["MT1M", "−3.29", "−3.90", "−3.35", "−4.30", "Down"], ["CD177", "−2.84", "−4.29", "−2.35", "−5.22", "Down"], ["HSD17B2", "−2.63", "−5.14", "−3.04", "−3.39", "Down"], ["INSL5", "−3.31", "−2.03", "−3.00", "−5.82", "Down"], ["ADH1C", "−3.26", "−3.50", "−3.10", "−4.01", "Down"], ["CLCA1", "−3.45", "−3.77", "−3.62", "−2.54", "Down"], ["FOXQ1", "4.47", "5.16", "5.55", "6.47", "Up"], ["KRT23", "3.69", "4.25", "4.28", "7.37", "Up"], ["LY6G6D", "3.50", "4.09", "3.63", "5.42", "Up"], ["MMP7", "3.15", "3.11", "2.38", "7.03", "Up"], ["CDH3", "2.77", "2.31", "2.76", "5.77", "Up"], ["MMP3", "2.91", "2.94", "2.77", "4.83", "Up"], ["CST1", "1.25", "2.42", "1.00", "8.33", "Up"], ["CRNDE", "3.17", "2.36", "2.73", "4.60", "Up"], ["DPEP1", "2.97", "3.06", "4.14", "2.61", "Up"], ["MMP1", "2.46", "2.59", "3.14", "4.56", "Up"], ["EPHX4", "3.01", "2.32", "2.95", "4.43", "Up"], ["CTHRC1", "1.21", "4.47", "3.15", "3.78", "Up"], ["CLDN1", "2.18", "2.81", "2.74", "4.84", "Up"], ["CEL", "1.56", "2.53", "2.37", "6.10", "Up"], ["CLDN2", "1.54", "2.57", "2.75", "5.57", "Up"], ["SLC35D3", "1.79", "2.97", "3.24", "4.35", "Up"], ["COL11A1", "1.59", "2.49", "1.93", "6.33", "Up"], ["CXCL3", "3.22", "3.60", "2.34", "2.92", "Up"], ["SLCO1B3", "1.43", "1.64", "2.55", "6.44", "Up"], ["CKMT2", "3.33", "2.55", "2.68", "3.46", "Up"]], "row_count": 41, "column_count": 6, "numeric_cells": 170, "header_rows": 1, "locator": "section[11]/table-wrap[1]#tII-mmr-20-02-1259"}}, {"id": "asset:table:pmid:31173250:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:abb9655c6126fc9d411112c656352136c5436d4e2b1877af7a332f0dad8a4eaf", "bytes": 4114, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tIII-mmr-20-02-1259", "version": null, "note": "GO analysis of down- and upregulated overlapping DEGs associated with CRC.", "structure": {"pmcid": "PMC6625394", "section_index": 12, "section_title": "GO and KEGG enrichment analysis", "row_count": 31, "column_count": 6}, "table": {"label": "Table III.", "caption": "GO analysis of down- and upregulated overlapping DEGs associated with CRC.", "rows": [["Expression", "Terms", "ID", "Description", "q-value", "Genes"], ["Upregulated", "BP", "GO:0000280", "Nuclear division", "4.33×10−7", "RRS1/CKS2/TRIP13/CCND1/FIGNL1/TPX2/ANLN/UBE2C/CHEK1/NUF2/RAD54B/DLGAP5/CDC6/MAD2L1/TOP2A/TTK/CCNB1/ASPM/BUB1B/AURKA"], ["", "BP", "GO:0048285", "Organelle fission", "1.16×10−6", "RRS1/CKS2/TRIP13/CCND1/FIGNL1/TPX2/ANLN/UBE2C/CHEK1/NUF2/RAD54B/DLGAP5/CDC6/MAD2L1/TOP2A/TTK/CCNB1/ASPM/BUB1B/AURKA"], ["", "BP", "GO:0140014", "Mitotic nuclear division", "6.51×10−6", "RRS1/TRIP13/CCND1/TPX2/ANLN/UBE2C/CHEK1/NUF2/DLGAP5/CDC6/MAD2L1/TTK/CCNB1/BUB1B/AURKA"], ["", "BP", "GO:0007088", "Regulation of mitotic nuclear division", "1.18×10−5", "TRIP13/CCND1/ANLN/UBE2C/CHEK1/DLGAP5/CDC6/MAD2L1/TTK/CCNB1/BUB1B/AURKA"], ["", "BP", "GO:0000075", "Cell cycle checkpoint", "1.18×10−5", "TRIP13/CCND1/ARID3A/CHEK1/CDC6/MAD2L1/TOP2A/TTK/CCNB1/SOX4/BUB1B/AURKA/PROX1"], ["", "CC", "GO:0044452", "Nucleolar part", "4.66×10−5", "TAF1D/DKC1/UTP4/WDR43/NOP58/RRS1/RPP40/NUFIP1/ORC6/POLR1D/E2F5"], ["", "CC", "GO:0000793", "Condensed chromosome", "4.66×10−5", "RRS1/SKA3/CHEK1/NUF2/CENPA/MAD2L1/TOP2A/CCNB1/SPC25/ERCC6L/BUB1B/AURKA"], ["", "CC", "GO:0000779", "Condensed chromosome, centromeric region", "5.94×10−5", "SKA3/NUF2/CENPA/MAD2L1/CCNB1/SPC25/ERCC6L/BUB1B/AURKA"], ["", "CC", "GO:0000780", "Condensed nuclear Chromosome, centromeric region", "1.13×10−4", "NUF2/CENPA/CCNB1/BUB1B/AURKA"], ["", "CC", "GO:0000776", "Kinetochore", "1.13×10−4", "SKA3/NUF2/CENPA/MAD2L1/TTK/CCNB1/SPC25/ERCC6L/BUB1B"], ["", "MF", "GO:0030515", "snoRNA binding", "2.99×10−3", "DKC1/NOP58/DDX21/NUFIP1"], ["", "MF", "GO:0009982", "Pseudouridine synthase activity", "3.70×10−3", "PUS1/PUS7/DKC1"], ["", "MF", "GO:0035173", "Histone kinase activity", "7.05×10−3", "CHEK1/CCNB1/AURKA"], ["", "MF", "GO:0001664", "G protein-coupled receptor binding", "8.09×10−3", "CXCL3/RNF43/HOMER1/NMU/CXCL8/ZNRF3/CXCL1/CTHRC1/CXCL5"], ["", "MF", "GO:0140098", "Catalytic activity, acting on RNA", "1.15×10−2", "NOB1/PUS1/EXOSC5/NOP2/RPP40/DDX21/RNASEH2A/POLR1D/RAD54B/AZGP1"], ["Downregulated", "BP", "GO:0010273", "Detoxification of copper ion", "1.22×10−5", "MT1M/MT1X/MT1E/MT1H/MT1F/MT1G"], ["", "BP", "GO:1990169", "Stress response to copper ion", "1.22×10−5", "MT1M/MT1X/MT1E/MT1H/MT1F/MT1G"], ["", "BP", "GO:0061687", "Detoxification of inorganic compound", "1.22×10−5", "MT1M/MT1X/MT1E/MT1H/MT1F/MT1G"], ["", "BP", "GO:0071280", "Cellular response to copper ion", "1.22×10−5", "MT1M/MT1X/MT1E/MT1H/MT1F/MT1G/AOC1"], ["", "BP", "GO:0097501", "Stress response to metal ion", "1.35×10−5", "MT1M/MT1X/MT1E/MT1H/MT1F/MT1G"], ["", "CC", "GO:0005903", "Brush border", "6.96×10−5", "CDHR5/TRPM6/SCIN/CDHR2/CA4/LIMA1/CYBRD1/MYO1A/SLC26A3/SI"], ["", "CC", "GO:0045177", "Apical part of cell", "3.15×10−4", "ABCG2/CA2/RAB27A/CDHR5/PTPRH/TRPM6/AQP8/CDHR2/CA4/SCNN1B/CLCA4/CEACAM1/FABP1/CEACAM7/MYO1A/SLC26A3/SI"], ["", "CC", "GO:0031526", "Brush border membrane", "3.15×10−4", "CDHR5/TRPM6/CDHR2/CA4/LIMA1/CYBRD1/SLC26A3"], ["", "CC", "GO:0005902", "Microvillus", "6.78×10−4", "CA2/CDHR5/PTPRH/CDHR2/CEACAM1/CLCA1/AOC3/MYO1A"], ["", "CC", "GO:0098862", "Cluster of actin-based cell projections", "8.31×10−4", "CDHR5/TRPM6/SCIN/CDHR2/CA4/LIMA1/CYBRD1/MYO1A/SLC26A3/SI"], ["", "MF", "GO:0016616", "Oxidoreductase activity, acting on the CH-OH group of donors, NAD or NADP as acceptor", "6.48×10−5", "UGDH/ADH1B/HPGD/LDHD/ADH1C/DHRS11/DHRS9/HSD17B2/AKR1B10/HSD11B2/BMP2"], ["", "MF", "GO:0016614", "Oxidoreductase activity, acting on CH-OH group of donors", "1.09×10−4", "UGDH/ADH1B/HPGD/LDHD/ADH1C/DHRS11/DHRS9/HSD17B2/AKR1B10/HSD11B2/BMP2"], ["", "MF", "GO:0004089", "Carbonate dehydratase activity", "1.26×10−4", "CA7/CA2/CA12/CA1/CA4"], ["", "MF", "GO:0048038", "Quinone binding", "4.90×10−3", "ETFDH/TP53I3/AOC3/AOC1"], ["", "MF", "GO:0033764", "Steroid dehydrogenase activity, acting on the CH-OH group of donors, NAD or NADP as acceptor", "1.52×10−2", "DHRS11/DHRS9/HSD17B2/HSD11B2"]], "row_count": 31, "column_count": 6, "numeric_cells": 81, "header_rows": 1, "locator": "section[12]/table-wrap[1]#tIII-mmr-20-02-1259"}}, {"id": "asset:table:pmid:31173250:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:aad2bbd6518e1938069d4f053360e8ebae7e5cf2cc2b17cda81a78db54e1c691", "bytes": 1961, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#tIV-mmr-20-02-1259", "version": null, "note": "GO analysis of selected module-associated DEGs.", "structure": {"pmcid": "PMC6625394", "section_index": 13, "section_title": "PPI network and module selection", "row_count": 15, "column_count": 5}, "table": {"label": "Table IV.", "caption": "GO analysis of selected module-associated DEGs.", "rows": [["ID", "GO Terms", "Ontology", "q-value", "Genes"], ["GO:0000819", "Sister chromatid segregation", "BP", "5.54×10−13", "BUB1B/CCNB1/CDC6/CENPA/DLGAP5/ERCC6L/MAD2L1/NUF2/SPC25/TOP2A/TRIP13/TTK/UBE2C"], ["GO:0007088", "Regulation of mitotic nuclear division", "BP", "8.77×10−12", "ANLN/AURKA/BUB1B/CCNB1/CDC6/CHEK1/DLGAP5/MAD2L1/TRIP13/TTK/UBE2C"], ["GO:0098813", "Nuclear chromosome", "BP", "1.24×10−11 segregation", "BUB1B/CCNB1/CDC6/CENPA/DLGAP5/ERCC6L/MAD2L1/NUF2/SPC25/TOP2A/TRIP13/TTK/UBE2C"], ["GO:0051304", "Chromosome separation", "BP", "1.37×10−11", "BUB1B/CCNB1/CDC6/DLGAP5/MAD2L1/TOP2A/TRIP13/TTK/UBE2C"], ["GO:0030071", "Regulation of mitotic metaphase/anaphase transition", "BP", "1.46×10−11", "BUB1B/CCNB1/CDC6/DLGAP5/MAD2L1/TRIP13/TTK/UBE2C"], ["GO:0000793", "Condensed chromosome", "CC", "2.53×10−10", "AURKA/BUB1B/CCNB1/CENPA/CHEK1/ERCC6L/MAD2L1/NUF2/SKA3/SPC25/TOP2A"], ["GO:0000779", "Condensed chromosome/centromeric region", "CC", "5.40×10−10", "AURKA/BUB1B/CCNB1/CENPA/ERCC6L/MAD2L1/NUF2/SKA3/SPC25"], ["GO:0000775", "Chromosome/centromeric region", "CC", "1.59×10−9", "AURKA/BUB1B/CCNB1/CENPA/ERCC6L/MAD2L1/NUF2/SKA3/SPC25/TTK"], ["GO:0000776", "Kinetochore", "CC", "1.80×10−9", "BUB1B/CCNB1/CENPA/ERCC6L/MAD2L1/NUF2/SKA3/SPC25/TTK"], ["GO:0000777", "Condensed chromosome kinetochore", "CC", "8.17×10−9", "BUB1B/CCNB1/CENPA/ERCC6L/MAD2L1/NUF2/SKA3/SPC25"], ["GO:0008009", "Chemokine activity", "MF", "1.41×10−9", "CCL19/CCL28/CXCL1/CXCL12/CXCL3/CXCL5/CXCL8"], ["GO:0042379", "Chemokine receptor binding", "MF", "8.09×10−9", "CCL19/CCL28/CXCL1/CXCL12/CXCL3/CXCL5/CXCL8"], ["GO:0045236", "CXCR chemokine receptor binding", "MF", "1.46×10−8", "CXCL1/CXCL12/CXCL3/CXCL5/CXCL8"], ["GO:0035173", "Histone kinase activity", "MF", "1.99×10−4", "AURKA/CCNB1/CHEK1"]], "row_count": 15, "column_count": 5, "numeric_cells": 41, "header_rows": 1, "locator": "section[13]/table-wrap[1]#tIV-mmr-20-02-1259"}}, {"id": "asset:table:pmid:31173250:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:89b33939fc06e24d639ffa14a5c7aa91ac45a40ea10149ff01807f900ec78908", "bytes": 724, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#tV-mmr-20-02-1259", "version": null, "note": "KEGG pathway analysis of selected module-associated DEGs.", "structure": {"pmcid": "PMC6625394", "section_index": 13, "section_title": "PPI network and module selection", "row_count": 7, "column_count": 4}, "table": {"label": "Table V.", "caption": "KEGG pathway analysis of selected module-associated DEGs.", "rows": [["KEGG", "Count", "q-value", "Genes"], ["Cell cycle", "6", "1.88×10−5", "BUB1B/CCNB1/CDC6/CHEK1/MAD2L1/TTK"], ["Progesterone-mediated oocyte maturation", "4", "7.64×10−4", "AURKA/CCNB1/GNAI1/MAD2L1"], ["Chemokine signaling pathway", "9", "4.69×10−8", "CCL19/CCL28/CXCL1/CXCL12/CXCL3/CXCL5/CXCL8/GNAI1/GNG4"], ["IL-17 signaling pathway", "4", "9.02×10−4", "CXCL1/CXCL3/CXCL5/CXCL8"], ["Legionellosis", "3", "9.37×10−4", "CXCL1/CXCL3/CXCL8"], ["Rheumatoid arthritis", "4", "1.06×10−3", "CXCL1/CXCL12/CXCL5/CXCL8"]], "row_count": 7, "column_count": 4, "numeric_cells": 15, "header_rows": 1, "locator": "section[13]/table-wrap[2]#tV-mmr-20-02-1259"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Kaplan-Meier analysis was performed based on the expression and clinical data of TCGA, and Perl was used to merge data."}}, {"id": "method-2", "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": "PPI"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["All data generated or analyzed during the present study are included in this article, and the R codes are available at https://github.com/Yuchang66/CRC-project."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:31173250", "asset:table:pmid:31173250:1", "asset:table:pmid:31173250:2", "asset:table:pmid:31173250:3", "asset:table:pmid:31173250:4", "asset:table:pmid:31173250:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:14:54Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 30737, "completion_tokens": 1293, "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:31173250", "type": "paper", "label": "pmid:31173250"}, {"id": "source:pmid:31173250", "type": "manuscript", "label": "PMID 31173250 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31173250", "type": "paper", "label": "pmid:31173250"}, {"id": "source:pmid:31173250", "type": "manuscript", "label": "PMID 31173250 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31173250", "type": "extraction", "used": ["source:pmid:31173250"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:31173250", "parent_hash": "sha256:65793dd651b21d65eafc40b2871a1a8c064f138f1cbcd861140158dc5dcc60e9", "fork_of": null, "generation": 6}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Kaplan-Meier analysis was performed based on the expression and clinical data of TCGA, and Perl was used to merge data."], "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":"2026-11-04T03:37:02+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}}}