{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32284764", "kind": "science-record", "revision": 8, "content_hash": "sha256:3961968b8ebe9fa77e5e32e52c1d9bc33a2bd7bb13dc0ab884660d73c9446b8d", "created_at": "2026-11-01T15:40:59Z", "updated_at": "2026-11-01T22:01:29Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Down-regulated Solute Carrier Family 4 Member 4 Predicts Poor Progression in Colorectal Cancer.", "doi": "10.7150/jca.36696", "pmid": "32284764", "authors": ["Hong Yang", "Yao Lu", "Weilan Lan", "Bin Huang", "Jiumao Lin"], "journal": "Journal of Cancer", "year": 2020, "abstract": "Aim: To identify potential key candidate genes, whose expression and clinical significance was further assessed in colorectal cancer (CRC). Methods: Three original microarray datasets (GSE41328, GSE22598, and GSE23878) from NCBI-GEO were used to analyze differentially expressed genes (DEGs) in CRC. Online database analyses through Oncomine and GEIPA were performed to evaluate SLC4A4 expression and explore the prognostic merit of SLC4A4 expression, which was further confirmed by analyses from QPCR based cDNA array and IHC based tissue microarray (TMA). STRING website was used to explore the interaction between SLC4A4 with other DEGs based on the protein-protein interaction (PPI) networks. Results: Analysis of three original microarray datasets from GEO identified 82 shared, differentially expressed genes (28 upregulated and 54 down-regulated) in CRC tissues. Online analyses from Oncomine and GEIPA revealed lower SLC4A4 mRNA expression in CRC tissues compared to adjacent normal tissues, which were further confirmed by QPCR based cDNA array and IHC based TMA analyses on both mRNA and protein levels. Survival analyses through GEIPA and from TMA demonstrated that low SLC4A4 expression is correlated with worse overall survival among patients with CRC. Survival analysis from Kaplan-meier plotter demonstrated that low SLC4A4 expression is significantly associated with poor progression (including relapse-free survival, overall survival, distant metastasis-free survival, post-progression survival) of patients with breast cancer, lung cancer, gastric cancer, and ovarian cancer. PPI analysis found that SLC4A4 is highly correlated with various genes, including SLC9A3, SLC26A6, ENSG00000214921, SLC26A4, SLC9A3R1, and SLC9A1. Conclusion: The mRNA and protein levels of SLC4A4 were decreased in CRC tissues, and low expression of SLC4A4 significantly correlated with shorter survival of CRC patients and poorer progression of patients with breast cancer, lung cancer, gastric cancer and ovarian cancer, suggesting potential role of SLC4A4 on tumor suppression and prognostic prediction in multiple malignancies including CRC.", "claims": [{"id": "claim-method", "statement": "Differentially expressed genes (DEGs) were identified using the classical t-test, and statistically significant DEGs were defined with P < 0.01 and [logFC] > 2 as the cutoff criteria.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32284764", "locator": "sections[3] \"Microarray data information and DEGs identification\" paragraph 3", "quote": "Differentially expressed genes (DEGs) were identified using the classical t-test, and statistically significant DEGs were defined with P < 0.01 and [logFC] > 2 as the cutoff criteria."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The microarray data in GSE22598 included 17 pairs of cancer and non-cancerous tissues from CRC patients (Submission date: December 04, 2011) 13.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32284764", "locator": "sections[3] \"Microarray data information and DEGs identification\" paragraph 2", "quote": "The microarray data in GSE22598 included 17 pairs of cancer and non-cancerous tissues from CRC patients (Submission date: December 04, 2011) 13."}], "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:32284764"], "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:GSE22598"], "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:GSE22598"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32284764", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/jca.36696", "sha256": "sha256:7a4cf8b5402d0fe70535c44189f0b415f68fbe016ed9a67a47c72f3ce81eb767", "bytes": 33291, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/jca.36696", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7150457", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE22598", "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=GSE22598", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE22598", "version": null, "note": "The microarray data in GSE22598 included 17 pairs of cancer and non-cancerous tissues from CRC patients (Submission date: December 04, 2011) 13.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data in GSE22598 included 17 pairs of cancer and non-cancerous tissues from CRC patients (Submission date: December 04, 2011) 13.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM452629", "GSM452630", "GSM452631", "GSM452632", "GSM452633", "GSM452634", "GSM452635", "GSM452636", "GSM452637", "GSM452638", "GSM452639", "GSM452640", "GSM452641", "GSM452642", "GSM452643", "GSM452644", "GSM452645", "GSM452646", "GSM452647", "GSM452648", "GSM452649", "GSM452650", "GSM452651", "GSM452652", "GSM452653", "GSM452654", "GSM452655", "GSM452656", "GSM452657", "GSM452658", "GSM452659", "GSM452660", "GSM452661", "GSM452662", "GSM560745", "GSM560746", "GSM560747", "GSM560748"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Clinical significance of UNC5B Expression in Colorectal Cancer", "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:GSE23878", "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=GSE23878", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE23878", "version": null, "note": "The microarray data in GSE22598 included 17 pairs of cancer and non-cancerous tissues from CRC patients (Submission date: December 04, 2011) 13.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data in GSE22598 included 17 pairs of cancer and non-cancerous tissues from CRC patients (Submission date: December 04, 2011) 13.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM588828", "GSM588829", "GSM588830", "GSM588831", "GSM588832", "GSM588833", "GSM588834", "GSM588835", "GSM588836", "GSM588837", "GSM588838", "GSM588839", "GSM588840", "GSM588841", "GSM588842", "GSM588843", "GSM588844", "GSM588845", "GSM588846", "GSM588847", "GSM588848", "GSM588849", "GSM588850", "GSM588851", "GSM588852", "GSM588853", "GSM588854", "GSM588855", "GSM588856", "GSM588857", "GSM588858", "GSM588859", "GSM588860", "GSM588861", "GSM588862", "GSM588863", "GSM588864", "GSM588865", "GSM588866", "GSM588867", "GSM588868", "GSM588869", "GSM588870", "GSM588871", "GSM588872", "GSM588873", "GSM588874", "GSM588875", "GSM588876", "GSM588877", "GSM588878", "GSM588879", "GSM588880", "GSM588881", "GSM588882", "GSM588883", "GSM588884", "GSM588885", "GSM588886"], "sample_count": 59, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genome Wide Expression Analysis of Middle Eastern Colorectal Cancer Reveals FOXM1 as a Novel Target for Cancer Therapy", "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:GSE41328", "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=GSE41328", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE41328", "version": null, "note": "The microarray data in GSE22598 included 17 pairs of cancer and non-cancerous tissues from CRC patients (Submission date: December 04, 2011) 13.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data in GSE22598 included 17 pairs of cancer and non-cancerous tissues from CRC patients (Submission date: December 04, 2011) 13.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1014798", "GSM1014799", "GSM1014800", "GSM1014801", "GSM1014802", "GSM1014803", "GSM1014804", "GSM1014805", "GSM1014806", "GSM1014807", "GSM1014808", "GSM1014809", "GSM1014810", "GSM1014811", "GSM1014812", "GSM1014813", "GSM1014814", "GSM1014815", "GSM1014816", "GSM1014817"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Colorectal adenocarcinomas and matched normal colonic tissues", "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:32284764:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6786c0346370751657bb5617c916949ab71844c7902b18443e1491ab7cd6cf22", "bytes": 2354, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#T2", "version": null, "note": "Oncomine Analysis of SLC4A4 mRNA Expression in Colorectal Cancer.", "structure": {"pmcid": "PMC7150457", "section_index": 4, "section_title": "Candidate gene SLC4A4 mRNA expression analysis thorough Oncomine", "row_count": 25, "column_count": 6}, "table": {"label": "Table 2", "caption": "Oncomine Analysis of SLC4A4 mRNA Expression in Colorectal Cancer.", "rows": [["Cohort no.", "Cohort", "Data type", "Sample(n)", "Fold change", "P value"], ["1", "Hong Colorectal", "mRNA", "Colorectal Carcinoma (70) vs Normal (12)", "-76.322", "4.85E-43"], ["2", "Kaiser Colon", "mRNA", "Rectosigmoid Adenocarcinoma (10) vs Normal (5)", "-24.78", "7.11E-09"], ["", "", "mRNA", "Rectal Adenocarcinoma (8) vs Normal (5)", "-27.235", "1.47E-08"], ["", "", "mRNA", "Colon Mucinous Adenocarcinoma (13) vs Normal (5)", "-20.693", "2.18E-09"], ["", "", "mRNA", "Cecum Adenocarcinoma (17) vs Normal (5)", "-24.032", "6.09E-12"], ["", "", "mRNA", "Colon Adenocarcinoma (41) vs Normal (5)", "-21.563", "6.90E-14"], ["", "", "mRNA", "Rectal Mucinous Adenocarcinoma (4) vs Normal (5)", "-2.159", "5.34E-07"], ["3", "Skrzypczak Colorectal", "mRNA", "Colon Adenocarcinoma (45) vs Normal (24)", "-9.951", "2.75E-20"], ["", "", "mRNA", "Colorectal Carcinoma (36) vs Normal (24)", "-9.342", "1.80E-23"], ["4", "Skrzypczak2 Colorectal", "mRNA", "Colorectal Carcinoma (5) vs Normal (10)", "-20.289", "1.07E-09"], ["", "", "mRNA", "Colon Adenoma (5) vs Normal (10)", "-13.821", "3.90E-09"], ["", "", "mRNA", "Colon Adenoma Epithelia (5) vs Normal (10)", "-16.29", "8.16E-11"], ["", "", "mRNA", "Colon Carcinoma Epithelia (5) vs Normal (10)", "-17.805", "7.70E-10"], ["5", "Sabates-Bellver Colon", "mRNA", "Rectal Adenoma (7) vs Normal (32)", "-8.076", "1.88E-05"], ["", "", "mRNA", "Colon Adenoma (25) vs Normal (32)", "-6.33", "5.65E-20"], ["6", "TCGA Colorectal", "mRNA", "Cecum Adenocarcinoma (22) vs Normal (22)", "-24.228", "9.79E-16"], ["", "", "mRNA", "Rectal Adenocarcinoma (60) vs Normal (22)", "-26.086", "2.09E-34"], ["", "", "mRNA", "Colon Adenocarcinoma (101) vs Normal (22)", "-20.712", "1.79E-38"], ["", "", "mRNA", "Colon Mucinous Adenocarcinoma (22) vs Normal (22)", "-14.978", "6.34E-13"], ["", "", "mRNA", "Rectal Mucinous Adenocarcinoma (6) vs Normal (22)", "-11.405", "4.13E-06"], ["", "", "mRNA", "Rectosigmoid Adenocarcinoma (22) vs Normal (3)", "-40.431", "3.79E-06"], ["7", "Gaedcke Colorectal", "mRNA", "Rectal Adenocarcinoma (65) vs Normal (65)", "-3.71", "3.89E-49"], ["8", "Ki Colon", "mRNA", "Colon Adenocarcinoma (50) vs Normal (28)", "-4.786", "3.87E-14"], ["9", "Caspar Colon", "mRNA", "Colon Adenoma Epithelia (56) vs Normal (22)", "-2.957", "3.06E-06"]], "row_count": 25, "column_count": 6, "numeric_cells": 81, "header_rows": 1, "locator": "section[4]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:32284764:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b3534d63fe99d98582d014630e2cf6be0eb28eb7faba6d80cae8e25c3bd352af", "bytes": 989, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T1", "version": null, "note": "82 differentially expressed genes (DEGs) were identified from three profile datasets, including 28 up-regulated genes and 54 down-regulated genes in the colorectal cancer tissues, compared to normal tissues.", "structure": {"pmcid": "PMC7150457", "section_index": 12, "section_title": "Identification of differentially expressed genes in CRC", "row_count": 3, "column_count": 2}, "table": {"label": "Table 1", "caption": "82 differentially expressed genes (DEGs) were identified from three profile datasets, including 28 up-regulated genes and 54 down-regulated genes in the colorectal cancer tissues, compared to normal tissues.", "rows": [["DEGs", "Genes Name"], ["Up-regulated", "CDH3, SLCO4A1, LY6G6F, COL11A1, NFE2L3, CEMIP, AZGP1, MMP7, CTHRC1, TRIB3, TACSTD2, FOXQ1, MMP3, TESC, KLK10, CLDN2, CXCL5, ASCL2, INHBA, AJUBA, MMP1, SLC7A5, CXCL8, CRNDE, CLDN1, EPHX4, KRT23, DPEP1"], ["Down-regulated", "LGALS2, NR3C2, SPIB, HSD17B2, ABCG2, GUCA2B, CHP2, SCARA5, CLCA4, DHRS11, AKR1B10, ARL14, CA4, TRPM6, NXPE4, PYY, SCIN, B3GALT5, TSPAN7, CA2, FCGBP, PKIB, ANPEP, CEACAM7, PADI2, ADTRP, KLF4, ABCA8, SLC51B, ADH1B, GCG, GBA3, MS4A12, PCK1, CPM, VSIG2, ADH1C, GCNT2, LRRC19, SST, SCNN1B, C2orf88, HPGD, LAMA1, CWH43, BEST4, CA1, MUC4, SLC4A4, CA12, GUCA2A, UGT1A3, DHRS9, CA7"]], "row_count": 3, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:32284764:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:22894346b2d18481ca84fdcc1ba788bb597b0ba77bc08ed280b7df6e62ca7e8f", "bytes": 1370, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T3", "version": null, "note": "Correlation between SLCA4A expression and clinicopathological characteristics", "structure": {"pmcid": "PMC7150457", "section_index": 14, "section_title": "Lower SLC4A4 expression associated with shorter survival of CRC patients", "row_count": 27, "column_count": 5}, "table": {"label": "Table 3", "caption": "Correlation between SLCA4A expression and clinicopathological characteristics", "rows": [["", "Total (N=97)", "SLCA4A protein expression", "P-value"], ["Low expression (n=16)", "High expression (n=81)"], ["Age", "", "", "", ""], ["≤ 65", "43 (44.3%)", "4 (25.0%)", "39 (48.1%)", "0.090"], ["> 65", "54 (55.7%)", "12 (72.0%)", "42 (41.9%)"], ["Gender", "", "", "", ""], ["Male", "53 (54.6%)", "11 (68.8%)", "42 (41.9%)", "0.219"], ["Female", "44 (45.4%)", "5 (31.2%)", "39 (48.1%)"], ["Pathology stage", "", "", ""], ["Ⅰ", "0 (0%)", "0 (0%)", "0 (0%)", "0.751"], ["Ⅱ", "51 (52.6%)", "9 (56.3%)", "42 (41.9%)"], ["Ⅲ", "46 (47.4%)", "7 (43.7%)", "39 (48.1%)"], ["Tumor size", "", "", "", ""], ["≤ 5 cm", "50 (51.5%)", "10 (62.5%)", "40 (49.4%)", "0.343"], [">5 cm", "47 (48.5%)", "6 (37.5%)", "41 (50.6%)"], ["T stage", "", "", "", ""], ["T1", "1 (1.0%)", "0 (0%)", "1 (1.2%)", "0.852"], ["T2", "5 (5.2%)", "0 (0%)", "5 (6.2%)"], ["T3", "74 (76.3%)", "14 (87.5%)", "60 (74.1%)"], ["T4", "17 (17.5%)", "2 (12.5%)", "15 (18.5%)"], ["N stage", "", "", "", ""], ["N0", "57 (58.8%)", "9 (56.3%)", "48 (59.3%)", "0.872"], ["N1", "29 (29.9%)", "6 (37.5%)", "23 (28.4%)"], ["N2", "11 (11.3%)", "1 (6.2%)", "10 (12.3%)"], ["M stage", "", "", "", ""], ["M0", "94 (96.9%)", "15 (93.8%)", "79 (97.5%)", "0.430"], ["M1", "3 (3.1%)", "1 (6.2%)", "2 (2.5%)"]], "row_count": 27, "column_count": 5, "numeric_cells": 68, "header_rows": 2, "locator": "section[14]/table-wrap[1]#T3"}}], "gaps": ["asset:data:geo:GSE22598 not downloaded", "asset:data:geo:GSE22598 licence not read", "asset:data:geo:GSE23878 not downloaded", "asset:data:geo:GSE23878 licence not read", "asset:data:geo:GSE41328 not downloaded", "asset:data:geo:GSE41328 licence not read"]}, "analysis": {"state": "partial", "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": 0.7, "band": "medium", "quote": "Kaplan-meier"}}, {"id": "method-2", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log rank"}}, {"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": null, "specific": null, "label": "Classical t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Differentially expressed genes (DEGs) were identified using the classical t-test, and statistically significant DEGs were defined with P < 0.01 and [logFC] > 2 as the cutoff criteria."}}], "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": ["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": "R1", "reachable": true, "accessions": ["GSE22598", "GSE23878", "GSE41328"], "resolved_accessions": ["GSE22598", "GSE23878", "GSE41328"], "statements": ["The microarray data in GSE22598 included 17 pairs of cancer and non-cancerous tissues from CRC patients (Submission date: December 04, 2011) 13."], "basis": "The paper names GSE22598, GSE23878, GSE41328 in NCBI-Gene Expression Omnibus (NCBI-GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:32284764", "data:geo:GSE22598", "asset:table:pmid:32284764:1", "asset:table:pmid:32284764:2", "asset:table:pmid:32284764:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE22598"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:19:19Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 27829, "completion_tokens": 2153, "cached_tokens": 9480}}, "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:32284764", "type": "paper", "label": "pmid:32284764"}, {"id": "source:pmid:32284764", "type": "manuscript", "label": "PMID 32284764 full text"}, {"id": "data:geo:GSE22598", "type": "dataset", "label": "GEO GSE22598"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32284764", "type": "paper", "label": "pmid:32284764"}, {"id": "source:pmid:32284764", "type": "manuscript", "label": "PMID 32284764 full text"}, {"id": "data:geo:GSE22598", "type": "dataset", "label": "GEO GSE22598"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32284764", "type": "extraction", "used": ["source:pmid:32284764"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE22598", "type": "accession_resolution", "used": ["data:geo:GSE22598"], "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:32284764", "parent_hash": "sha256:51496082c74c7d745ae2f3b72350340080995c4c91496111b3f5fd094b2324e0", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE22598 licence not read", "asset:data:geo:GSE22598 not downloaded", "asset:data:geo:GSE23878 licence not read", "asset:data:geo:GSE23878 not downloaded", "asset:data:geo:GSE41328 licence not read", "asset:data:geo:GSE41328 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": 0.99, "evidence": ["rectal cancer (CRC). Methods: Three original microarray datasets (GSE41328, GSE22598, and GSE23878)", "m QPCR based cDNA array and IHC based tissue microarray (TMA). STRING website was used to explore th", "etworks. Results: Analysis of three original microarray datasets from GEO identified 82 shared, diff"], "order_basis": "paper_text_order:215", "id": "assay:1"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["which was further confirmed by analyses from QPCR based cDNA array and IHC based tissue microa", "mal tissues, which were further confirmed by QPCR based cDNA array and IHC based TMA analyses"], "order_basis": "paper_text_order:548", "id": "assay:2"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["d by analyses from QPCR based cDNA array and IHC based tissue microarray (TMA). STRING websit", "rther confirmed by QPCR based cDNA array and IHC based TMA analyses on both mRNA and protein"], "order_basis": "paper_text_order:574", "id": "assay:3"}, {"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": 0.7, "evidence": ["Kaplan-meier"], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"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":"2026-11-04T04:26:33+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}}}