{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31724326", "kind": "science-record", "revision": 8, "content_hash": "sha256:057434ac12270ac3a4b6da6a0ee29c08fc174525169661aed4fd739787740268", "created_at": "2026-11-01T15:40:51Z", "updated_at": "2026-11-01T22:44:19Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A network-based predictive gene expression signature for recurrence risks in stage II colorectal cancer.", "doi": "10.1002/cam4.2642", "pmid": "31724326", "authors": ["Wen-Jing Yang", "Hai-Bo Wang", "Wen-Da Wang", "Peng-Yu Bai", "Hong-Xia Lu", "Chang-He Sun", "Zi-Shen Liu", "Ding-Kun Guan", "Guo-Wang Yang", "Gan-Lin Zhang"], "journal": "Cancer medicine", "year": 2020, "abstract": "The current criteria for defining the recurrence risks of stage II colorectal cancer (CRC) are not robust; therefore, we aimed to explore novel gene signatures to predict recurrence risks and to reveal the underlying mechanisms of stage II CRC. First, the gene expression profiles of 124 patients with stage II CRC from The Cancer Genome Atlas (TCGA) database were obtained to screen differentially expressed genes (DEGs). A total of 202 DEGs, including 128 upregulated and 74 downregulated, were identified in the recurrence group (n = 24) compared to the nonrecurrence group (n = 100). Furthermore, the top 5 DEGs (ZNF561, WFS1, SLC2A1, MFI2, and PTGR1) were identified by random forest variable hunting, and four (ZNF561, WFS1, SLC2A1, and PTGR1) were selected to create a four-gene recurrent model (GRM), with an area under the curve (AUC) of 0.882 according to the receiver operating characteristic curve, and the robust diagnostic effectiveness of the GRM was further validated with another gene expression profiling dataset (GSE12032), with an AUC of 0.943. The diagnostic effectiveness of the GRM regarding recurrence was associated with poor disease-free survival in all stages of CRC. In addition, gene ontology functional annotation and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analyses revealed 18 enriched functions and 6 enriched pathways. Four genes, ABCG2, CACNA1F, CYP19A1, and TF, were identified as hub genes by the protein-protein interaction network, which further validated that these genes were correlated with a poor pathologic stage and overall survival in all stages of CRC. In conclusion, the GRM can effectively classify stage II CRC into groups of high and low risks of recurrence, thereby making up for the prognostic value of the traditional clinicopathological risk factors defined by the National Comprehensive Cancer Network guidelines. The hub genes may be useful therapeutic targets for recurrence. Thus, the GRM and hub genes could offer clinical value in directing individualized and precision therapeutic regimens for stage II CRC patients.", "claims": [{"id": "claim-method", "statement": "edgeR is an R package used for the analysis of DEGs10 and was used in our study to screen the DEGs between the recurrence and nonrecurrence groups.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31724326", "locator": "sections[4] \"Data preprocessing and the identification of DEGs\" paragraph 2", "quote": "edgeR is an R package used for the analysis of DEGs10 and was used in our study to screen the DEGs between the recurrence and nonrecurrence groups."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analyzed in current study can be obtained from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31724326", "locator": "sections[27] \"DATA AVAILABILITY STATEMENT\" paragraph 2", "quote": "The datasets used and/or analyzed in current study can be obtained from the corresponding author on reasonable request."}], "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:31724326"], "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:GSE12032"], "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:GSE12032"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31724326", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1002/cam4.2642", "sha256": "sha256:5faac053659a5aa22c0108f05f0b0e5b489b9f58e284320eba87efbe8081be60", "bytes": 48403, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1002/cam4.2642", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6943157", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE12032", "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=GSE12032", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE12032", "version": null, "note": "The datasets used and/or analyzed in current study can be obtained from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed in current study can be obtained from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM304101", "GSM304102", "GSM304103", "GSM304104", "GSM304105", "GSM304106", "GSM304107", "GSM304108", "GSM304109", "GSM304110", "GSM304111", "GSM304112", "GSM304113", "GSM304114", "GSM304115", "GSM304116", "GSM304117", "GSM304118", "GSM304119", "GSM304120", "GSM304121", "GSM304122", "GSM304123", "GSM304124", "GSM304125", "GSM304126", "GSM304127", "GSM304128", "GSM304129", "GSM304130", "GSM304131", "GSM304132", "GSM304133", "GSM304134", "GSM304135", "GSM304136", "GSM304137", "GSM304138", "GSM304139", "GSM304140", "GSM304141", "GSM304142", "GSM304143", "GSM304144", "GSM304145", "GSM304146", "GSM304147", "GSM304148", "GSM304149", "GSM304150", "GSM304151", "GSM304152", "GSM304153", "GSM304154", "GSM304155", "GSM304156", "GSM304157", "GSM304158", "GSM304159", "GSM304160", "GSM304161", "GSM304162", "GSM304163", "GSM304164", "GSM304165", "GSM304166", "GSM304167", "GSM304168", "GSM304169", "GSM304170", "GSM304171", "GSM304172", "GSM304173", "GSM304174", "GSM304175", "GSM304176", "GSM304177", "GSM304178", "GSM304179", "GSM304180", "GSM304181", "GSM304182", "GSM304183", "GSM304184", "GSM304185", "GSM304186", "GSM304187", "GSM304188", "GSM304189", "GSM304190", "GSM304191", "GSM304192", "GSM304193", "GSM304194", "GSM304195", "GSM304196", "GSM304197", "GSM304198", "GSM304199", "GSM304200", "GSM304201", "GSM304202", "GSM304203", "GSM304204", "GSM304205", "GSM304206", "GSM304207", "GSM304208", "GSM304209", "GSM304210", "GSM304211", "GSM304212", "GSM304213", "GSM304214", "GSM304215", "GSM304216", "GSM304217", "GSM304218", "GSM304219", "GSM304220", "GSM304221", "GSM304222", "GSM304223", "GSM304224", "GSM304225", "GSM304226", "GSM304227", "GSM304228", "GSM304229", "GSM304230", "GSM304231", "GSM304232", "GSM304233", "GSM304234", "GSM304235", "GSM304236", "GSM304237", "GSM304238", "GSM304239", "GSM304240", "GSM304241", "GSM304242", "GSM304243", "GSM304244", "GSM304245", "GSM304246", "GSM304247", "GSM304248", "GSM304249", "GSM304250", "GSM304251", "GSM304252", "GSM304253", "GSM304254", "GSM304255", "GSM304256", "GSM304257", "GSM304258", "GSM304259", "GSM467732", "GSM467733", "GSM467734", "GSM467735", "GSM467736", "GSM467737", "GSM467738", "GSM467739", "GSM467740", "GSM467741", "GSM467742", "GSM467743", "GSM467744", "GSM467745", "GSM467746", "GSM467747", "GSM467748", "GSM467749", "GSM467750", "GSM467751", "GSM467752", "GSM467753", "GSM467754", "GSM467755", "GSM467756", "GSM467757", "GSM467758", "GSM467759", "GSM467760", "GSM467761", "GSM467762", "GSM467763", "GSM467764", "GSM467765", "GSM467766", "GSM467767", "GSM467768", "GSM467769", "GSM467770"], "sample_count": 198, "group_sizes": null, "group_sizes_basis": null, "platform": "1291", "taxon": "Homo sapiens", "title": "Inherent gene signature of stage II and III colorectal cancer leads in individual recurrence", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31724326:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0a7f7c8421fec162ebb96fa1e7facd15a0f09f6fc5b1052671affbc269c4a906", "bytes": 1421, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#cam42642-tbl-0003", "version": null, "note": "The 18 most significant enriched gene sets for recurrence features of stage II CRC from BP, MF, CC", "structure": {"pmcid": "PMC6943157", "section_index": 9, "section_title": "Functional annotation and pathway enrichment analyses", "row_count": 22, "column_count": 4}, "table": {"label": "Table 3", "caption": "The 18 most significant enriched gene sets for recurrence features of stage II CRC from BP, MF, CC", "rows": [["ID", "Description", "Count", "P‐Value"], ["Molecular Function"], ["GO:0019825", "Oxygen binding", "7", "6.14E‐06"], ["GO:0005506", "Iron ion binding", "10", "1.96E‐05"], ["GO:0020037", "Heme binding", "9", "6.04E‐05"], ["GO:0004497", "Monooxygenase activity", "6", "2.53E‐04"], ["GO:0016712", "Oxidoreductase activity", "4", "3.83E‐04"], ["GO:0008395", "Steroid hydroxylase activity", "4", ".00202095"], ["GO:0004930", "G‐protein coupled receptor activity", "16", ".00415544"], ["GO:0005344", "Oxygen transporter activity", "3", ".00799984"], ["GO:0005200", "Structural constituent of cytoskeleton", "5", ".02284408"], ["GO:0070330", "Aromatase activity", "3", ".02840488"], ["Biological Process"], ["GO:0008202", "Steroid metabolic process", "5", "7.68E‐04"], ["GO:0015671", "Oxygen transport", "3", ".00894403"], ["GO:0007186", "G protein‐coupled receptor signaling pathway", "17", ".01335430"], ["GO:0007608", "Sensory perception of smell", "6", ".01900123"], ["GO:0017144", "Drug metabolic process", "3", ".02772735"], ["GO:0008544", "Epidermis development", "4", ".04905401"], ["Cellular Component"], ["GO:0005833", "Hemoglobin complex", "3", ".00574369"], ["GO:0031090", "Organelle membrane", "5", ".01005061"]], "row_count": 22, "column_count": 4, "numeric_cells": 54, "header_rows": 1, "locator": "section[17]/table-wrap[1]#cam42642-tbl-0003"}}, {"id": "asset:table:pmid:31724326:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:86b9d788014be0db296cb5d82cc32b6ee18f9a3651d073d37a795048d5719113", "bytes": 676, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[2]#cam42642-tbl-0004", "version": null, "note": "The 6 most significant enriched pathways for recurrence features of stage II CRC from KEGG", "structure": {"pmcid": "PMC6943157", "section_index": 9, "section_title": "Functional annotation and pathway enrichment analyses", "row_count": 7, "column_count": 4}, "table": {"label": "Table 4", "caption": "The 6 most significant enriched pathways for recurrence features of stage II CRC from KEGG", "rows": [["KEGG pathway id", "Description", "Count", "P‐Value"], ["hsa00982", "Drug metabolism—cytochrome P450", "4", ".04376667"], ["hsa00983", "Drug metabolism—other enzymes", "4", ".01587008"], ["hsa05204", "Chemical carcinogenesis", "5", ".01355137"], ["hsa00980", "Metabolism of xenobiotics by cytochrome P450", "5", ".0103847"], ["hsa00830", "Retinol metabolism", "5", ".00660703"], ["hsa00140", "Steroid hormone biosynthesis", "8", "4.00E‐06"]], "row_count": 7, "column_count": 4, "numeric_cells": 20, "header_rows": 1, "locator": "section[17]/table-wrap[2]#cam42642-tbl-0004"}}, {"id": "asset:table:pmid:31724326:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:98e61ee4ab1729ab8862c00d08fe13a5b873fce04b98075ad45241fbd4f0b7d3", "bytes": 541, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#cam42642-tbl-0001", "version": null, "note": "The TCGA top 5 DEGs for ROC construction were ranked by MDG with random forest method", "structure": {"pmcid": "PMC6943157", "section_index": 14, "section_title": "Acquisition of the classified DEGs by the random forest classifier", "row_count": 6, "column_count": 3}, "table": {"label": "Table 1", "caption": "The TCGA top 5 DEGs for ROC construction were ranked by MDG with random forest method", "rows": [["Gene", "Description", "Mean Decrease Gini (MDG)"], ["ZNF561", "Zinc finger protein 561", "17.608"], ["WFS1", "Wolframin ER transmembrane glycoprotein", "13.193"], ["SLC2A1", "Solute carrier family 2 member 1", "11.726"], ["MFI2", "Melanotransferrin", "9.878"], ["PTGR1", "Prostaglandin reductase 1", "9.510"]], "row_count": 6, "column_count": 3, "numeric_cells": 9, "header_rows": 1, "locator": "section[14]/table-wrap[1]#cam42642-tbl-0001"}}, {"id": "asset:table:pmid:31724326:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:add838113982b12bea0dcbde533f5f666489932bc8fc3e15d21ab108f856f618", "bytes": 797, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#cam42642-tbl-0002", "version": null, "note": "The top 10 DEGs of GSE12032 were ranked by MDG with random forest method", "structure": {"pmcid": "PMC6943157", "section_index": 15, "section_title": "Construction of a four‐GRM and further validation", "row_count": 11, "column_count": 3}, "table": {"label": "Table 2", "caption": "The top 10 DEGs of GSE12032 were ranked by MDG with random forest method", "rows": [["Gene", "Description", "Mean Decrease Gini (MDG)"], ["ABCB5", "Zinc finger protein 561", "1.405"], ["SLC2A1", "Solute carrier family 2 member 1", "1.300"], ["CLDN6", "Claudin 6", "0.924"], ["ZNF561", "Zinc finger protein 561", "0.808"], ["HIST1H4H", "Histone cluster 1 H4 family member h", "0.773"], ["TMEM63A", "Transmembrane protein 63A", "0.725"], ["PTGR1", "Prostaglandin reductase 1", "0.615"], ["BCAR3", "BCAR3 adaptor protein, NSP family member", "0.551"], ["WFS1", "Wolframin ER transmembrane glycoprotein", "0.517"], ["C3orf42", "Long intergenic nonprotein coding RNA 852", "0.475"]], "row_count": 11, "column_count": 3, "numeric_cells": 21, "header_rows": 1, "locator": "section[15]/table-wrap[1]#cam42642-tbl-0002"}}, {"id": "asset:table:pmid:31724326:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0a7f7c8421fec162ebb96fa1e7facd15a0f09f6fc5b1052671affbc269c4a906", "bytes": 1421, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#cam42642-tbl-0003", "version": null, "note": "The 18 most significant enriched gene sets for recurrence features of stage II CRC from BP, MF, CC", "structure": {"pmcid": "PMC6943157", "section_index": 17, "section_title": "Functional annotation and pathway enrichment analyses", "row_count": 22, "column_count": 4}, "table": {"label": "Table 3", "caption": "The 18 most significant enriched gene sets for recurrence features of stage II CRC from BP, MF, CC", "rows": [["ID", "Description", "Count", "P‐Value"], ["Molecular Function"], ["GO:0019825", "Oxygen binding", "7", "6.14E‐06"], ["GO:0005506", "Iron ion binding", "10", "1.96E‐05"], ["GO:0020037", "Heme binding", "9", "6.04E‐05"], ["GO:0004497", "Monooxygenase activity", "6", "2.53E‐04"], ["GO:0016712", "Oxidoreductase activity", "4", "3.83E‐04"], ["GO:0008395", "Steroid hydroxylase activity", "4", ".00202095"], ["GO:0004930", "G‐protein coupled receptor activity", "16", ".00415544"], ["GO:0005344", "Oxygen transporter activity", "3", ".00799984"], ["GO:0005200", "Structural constituent of cytoskeleton", "5", ".02284408"], ["GO:0070330", "Aromatase activity", "3", ".02840488"], ["Biological Process"], ["GO:0008202", "Steroid metabolic process", "5", "7.68E‐04"], ["GO:0015671", "Oxygen transport", "3", ".00894403"], ["GO:0007186", "G protein‐coupled receptor signaling pathway", "17", ".01335430"], ["GO:0007608", "Sensory perception of smell", "6", ".01900123"], ["GO:0017144", "Drug metabolic process", "3", ".02772735"], ["GO:0008544", "Epidermis development", "4", ".04905401"], ["Cellular Component"], ["GO:0005833", "Hemoglobin complex", "3", ".00574369"], ["GO:0031090", "Organelle membrane", "5", ".01005061"]], "row_count": 22, "column_count": 4, "numeric_cells": 54, "header_rows": 1, "locator": "section[17]/table-wrap[1]#cam42642-tbl-0003"}}, {"id": "asset:table:pmid:31724326:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:86b9d788014be0db296cb5d82cc32b6ee18f9a3651d073d37a795048d5719113", "bytes": 676, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[2]#cam42642-tbl-0004", "version": null, "note": "The 6 most significant enriched pathways for recurrence features of stage II CRC from KEGG", "structure": {"pmcid": "PMC6943157", "section_index": 17, "section_title": "Functional annotation and pathway enrichment analyses", "row_count": 7, "column_count": 4}, "table": {"label": "Table 4", "caption": "The 6 most significant enriched pathways for recurrence features of stage II CRC from KEGG", "rows": [["KEGG pathway id", "Description", "Count", "P‐Value"], ["hsa00982", "Drug metabolism—cytochrome P450", "4", ".04376667"], ["hsa00983", "Drug metabolism—other enzymes", "4", ".01587008"], ["hsa05204", "Chemical carcinogenesis", "5", ".01355137"], ["hsa00980", "Metabolism of xenobiotics by cytochrome P450", "5", ".0103847"], ["hsa00830", "Retinol metabolism", "5", ".00660703"], ["hsa00140", "Steroid hormone biosynthesis", "8", "4.00E‐06"]], "row_count": 7, "column_count": 4, "numeric_cells": 20, "header_rows": 1, "locator": "section[17]/table-wrap[2]#cam42642-tbl-0004"}}, {"id": "asset:table:pmid:31724326:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:494089641410f25a96c7c3fbd9c3159ffef4e783e9e6792b62fcddd822f24125", "bytes": 531, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#cam42642-tbl-0005", "version": null, "note": "The four hub genes in the protein‐protein interaction network", "structure": {"pmcid": "PMC6943157", "section_index": 18, "section_title": "PPI network construction and hub gene identification", "row_count": 5, "column_count": 4}, "table": {"label": "Table 5", "caption": "The four hub genes in the protein‐protein interaction network", "rows": [["Gene", "Description", "Degree", "Betweenness"], ["ABCG2", "ATP ‐binding cassette subfamily G member 2", "4.0", "477.4"], ["CACNA1F", "Calcium voltage‐gated channel subunit alpha1 F", "4.0", "242.0"], ["CYP19A1", "Cytochrome P450 family 19 subfamily A member 1", "10.0", "899.3"], ["TF", "Transferrin", "6.0", "680.8"]], "row_count": 5, "column_count": 4, "numeric_cells": 11, "header_rows": 1, "locator": "section[18]/table-wrap[1]#cam42642-tbl-0005"}}], "gaps": ["asset:data:geo:GSE12032 not downloaded", "asset:data:geo:GSE12032 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "edger", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "edgeR is an R package used for the analysis of DEGs10 and was used in our study to screen the DEGs between the recurrence and nonrecurrence groups."}}, {"id": "method-2", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {"auc": "nt model (GRM), with an area under the curve (AUC) of 0"}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "random forest"}}, {"id": "method-3", "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-4", "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": 0.7, "band": "medium", "quote": "pathway enrichment"}}, {"id": "method-5", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC analysis"}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: edger."}, "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": ["GSE12032"], "resolved_accessions": ["GSE12032"], "statements": ["The datasets used and/or analyzed in current study can be obtained from the corresponding author on reasonable request."], "basis": "The paper names GSE12032 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:31724326", "data:geo:GSE12032", "asset:table:pmid:31724326:1", "asset:table:pmid:31724326:2", "asset:table:pmid:31724326:3", "asset:table:pmid:31724326:4", "asset:table:pmid:31724326:5", "asset:table:pmid:31724326:6", "asset:table:pmid:31724326:7"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE12032"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:17:43Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 37040, "completion_tokens": 1360, "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:31724326", "type": "paper", "label": "pmid:31724326"}, {"id": "source:pmid:31724326", "type": "manuscript", "label": "PMID 31724326 full text"}, {"id": "data:geo:GSE12032", "type": "dataset", "label": "GEO GSE12032"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31724326", "type": "paper", "label": "pmid:31724326"}, {"id": "source:pmid:31724326", "type": "manuscript", "label": "PMID 31724326 full text"}, {"id": "data:geo:GSE12032", "type": "dataset", "label": "GEO GSE12032"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31724326", "type": "extraction", "used": ["source:pmid:31724326"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE12032", "type": "accession_resolution", "used": ["data:geo:GSE12032"], "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:31724326", "parent_hash": "sha256:cdcf077c57f3f4aecea12404c52afbeb185f8f09c56ab1858eb01e5dbfbfe1b9", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE12032 licence not read", "asset:data:geo:GSE12032 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["edgeR is an R package used for the analysis of DEGs10 and was used in our study to screen the DEGs between the recurrence and nonrecurrence groups."], "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":"2026-11-04T02:59:10+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}}}