{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33935718", "kind": "science-record", "revision": 7, "content_hash": "sha256:bfd0aa338def86382f6b581987fff4a1596ca449a57adefec7cb7f6f39149415", "created_at": "2026-11-01T15:41:34Z", "updated_at": "2026-11-01T22:03:40Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Transcriptomic and microRNA Expression Profiles Identify Biomarkers for Predicting Neo-Chemoradiotherapy Response in Esophageal Squamous Cell Carcinomas (ESCC).", "doi": "10.3389/fphar.2021.626972", "pmid": "33935718", "authors": ["Jian Wang", "Pengyi Yu", "Judong Luo", "Zhiqiang Sun", "Jingping Yu", "Jianlin Wang"], "journal": "Frontiers in pharmacology", "year": 2021, "abstract": "Neo-chemoradiotherapy (nCRT) before surgery is a standard treatment for locally advanced esophageal cancers. However, the treatment outcome of nCRT varied with different patients. This study aimed to identify potential biomarkers for prediction of nCRT-response in patients with esophageal squamous cell carcinoma (ESCC). Microarray datasets of nCRT responder and non-responder samples (access number GSE45670 and GSE59974) of patients with ESCC were downloaded from Gene Expression Omnibus (GEO) database. The mRNA expression profiles of cancer biopsies from four ESCC patients were analyzed before and after nCRT. Differentially expressed genes (DEGs) and miRNAs were screened between nCRT responder and non-responder ESCC samples. Functional enrichment analysis was conducted for these DEGs followed by construction of protein-protein interaction (PPI) network and miRNA-mRNA regulatory network. Finally, univariate survival analysis was performed to identify candidate biomarkers with prognostic values in ESCC. We identified numerous DEGs and differentially expressed miRNAs from nCRT responder group. GO and KEGG analysis showed that the dysregulated genes were mainly involved in biological processes and pathways, including \"response to stimulus\", \"cellular response to organic substance\", \"regulation of signal transduction\", \"AGE-RAGE signaling pathway in diabetic complications\", and \"steroid hormone biosynthesis\". After integration of PPI network and miRNA-mRNA network analysis, we found eight genes, TNF, AKR1C1, AKR1C2, ICAM1, GPR68, GNB4, SERPINE1 and MMP12, could be candidate genes associated with disease progression. Univariate cox regression analysis showed that there was no significant correlation between dysregulated miRNAs (such as hsa-miR-34b-3p, hsa-miR-127-5p, hsa-miR-144-3p, and hsa-miR-486-5p, et al.) and overall survival of ESCC patients. Moreover, abnormal expression of MMP12 was significantly correlated with pathological degree, TNM stage, lymph nodes metastasis, and overall survival of ESCC patients (p < 0.05). Taken together, our study identified that MMP12 might be a useful tumor biomarker and therapeutic target for ESCC.", "claims": [{"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number can be found below: https://www.ncbi.nlm.nih.gov/,GSE137867.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33935718", "locator": "sections[16] \"Data Availability Statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number can be found below: https://www.ncbi.nlm.nih.gov/,GSE137867."}], "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:33935718"], "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:GSE137867"], "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:GSE137867"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33935718", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fphar.2021.626972", "sha256": "sha256:fb4dd7fe1812aa636d0f60db63cde4b3495ceb550426d6923323848870ec0f5f", "bytes": 43613, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fphar.2021.626972", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8082678", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE137867", "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=GSE137867", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE137867", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number can be found below: https://www.ncbi.nlm.nih.gov/,GSE137867.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number can be found below: https://www.ncbi.nlm.nih.gov/,GSE137867.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4090710", "GSM4090711", "GSM4090712", "GSM4090713", "GSM4090714", "GSM4090715", "GSM4090716", "GSM4090717"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "15207", "taxon": "Homo sapiens", "title": "Tissue samples of 4 patients with esophageal cancer before and after radiotherapy", "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:GSE45670", "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=GSE45670", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE45670", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number can be found below: https://www.ncbi.nlm.nih.gov/,GSE137867.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number can be found below: https://www.ncbi.nlm.nih.gov/,GSE137867.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1111662", "GSM1111663", "GSM1111664", "GSM1111665", "GSM1111666", "GSM1111667", "GSM1111668", "GSM1111669", "GSM1111670", "GSM1111671", "GSM1111672", "GSM1111673", "GSM1111674", "GSM1111675", "GSM1111676", "GSM1111677", "GSM1111678", "GSM1111679", "GSM1111680", "GSM1111681", "GSM1111682", "GSM1111683", "GSM1111684", "GSM1111685", "GSM1111686", "GSM1111687", "GSM1111688", "GSM1111689", "GSM1111690", "GSM1111691", "GSM1111692", "GSM1111693", "GSM1111694", "GSM1111695", "GSM1111696", "GSM1111697", "GSM1111698", "GSM1111699"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from esophageal squamous cell carcinomas and normal esophageal epithelia", "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:GSE59974", "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=GSE59974", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE59974", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number can be found below: https://www.ncbi.nlm.nih.gov/,GSE137867.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number can be found below: https://www.ncbi.nlm.nih.gov/,GSE137867.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1462901", "GSM1462902", "GSM1462903", "GSM1462904", "GSM1462905", "GSM1462906", "GSM1462907", "GSM1462908", "GSM1462909", "GSM1462910", "GSM1462911", "GSM1462912", "GSM1462913", "GSM1462914", "GSM1462915", "GSM1462916", "GSM1462917", "GSM1462918", "GSM1462919", "GSM1462920", "GSM1462921", "GSM1462922", "GSM1462923", "GSM1462924", "GSM1462925", "GSM1462926", "GSM1462927", "GSM1462928"], "sample_count": 28, "group_sizes": null, "group_sizes_basis": null, "platform": "19007", "taxon": "Homo sapiens", "title": "MiRNA expression arrays from esophageal squamous cell carcinomas with different neoadjuvant chemoradiotherapy response", "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:33935718:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b290d309861458f5cf6a42233b52623a1b2bd3ccde8009f5c65f0696d1f7a413", "bytes": 613, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T1", "version": null, "note": "Twenty five DEGs were identified from two mRNA profiles (GSE45670 dataset and GSE137867 dataset), including 17 upregulated genes and 8 down-regulated genes in the ESCC responder groups compared with control non-responder groups.", "structure": {"pmcid": "PMC8082678", "section_index": 10, "section_title": "Screening DEGs From nCRT Responders of ESCCs", "row_count": 3, "column_count": 2}, "table": {"label": "TABLE 1", "caption": "Twenty five DEGs were identified from two mRNA profiles (GSE45670 dataset and GSE137867 dataset), including 17 upregulated genes and 8 down-regulated genes in the ESCC responder groups compared with control non-responder groups.", "rows": [["DEGs", "Gene names"], ["Up-regulated", "ANO4, BMP2, DTNB, GADD45A, GAS1, GNB4, GPR68, ICAM1, IL24, MAN1A1, MMP12, NRBF2, SERPINE1, SLC31A2, SNX10, TNF, TNNT1"], ["Down-regulated", "AKR1C1, AKR1C2, PCTP, PER2, RAB40B, TLE2, ZDHHC11, ZNF703"]], "row_count": 3, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33935718:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5c86181d73c70acd71498ef13e00de5384c98f18a3714c0d4622314cb5c9e212", "bytes": 1348, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#T2", "version": null, "note": "Fifety nine differential expressed miRNAs were identified from miRNA profiles (GSE59974 dataset), including 44 upregulated genes and 15 down-regulated genes in the ESCC responder groups compared with control groups.", "structure": {"pmcid": "PMC8082678", "section_index": 10, "section_title": "Screening DEGs From nCRT Responders of ESCCs", "row_count": 3, "column_count": 2}, "table": {"label": "TABLE 2", "caption": "Fifety nine differential expressed miRNAs were identified from miRNA profiles (GSE59974 dataset), including 44 upregulated genes and 15 down-regulated genes in the ESCC responder groups compared with control groups.", "rows": [["miRNAs", "Gene names"], ["Up-regulated", "hsa-miR-106b-3p, hsa-miR-122-5p, hsa-miR-1252, hsa-miR-127-5p, hsa-miR-1295a, hsa-miR-1343, hsa-miR-137, hsa-miR-155-3p, hsa-miR-18a-3p, hsa-miR-195-3p, hsa-miR-196a-5p, hsa-miR-206, hsa-miR-222-5p, hsa-miR-299-3p, hsa-miR-3144-5p, hsa-miR-323b-5p, hsa-miR-330-3p, hsa-miR-34b-3p, hsa-miR-3617-5p, hsa-miR-363-5p, hsa-miR-373-3p, hsa-miR-3975, hsa-miR-3978, hsa-miR-424-5p, hsa-miR-4448, hsa-miR-4528, hsa-miR-4645-3p, hsa-miR-4670-5p, hsa-miR-4704-5p, hsa-miR-4709-3p, hsa-miR-4715-5p, hsa-miR-4717-5p, hsa-miR-4773, hsa-miR-4774-5p, hsa-miR-4789-5p, hsa-miR-4798-5p, hsa-miR-503-5p, hsa-miR-504, hsa-miR-5189, hsa-miR-539-3p, hsa-miR-5579-3p, hsa-miR-637, hsa-miR-7-5p, hsa-miR-924"], ["Down-regulated", "hsa-miR-138-1-3p, hsa-miR-144-3p, hsa-miR-144-5p, hsa-miR-192-3p, hsa-miR-3145-5p, hsa-miR-3972, hsa-miR-486-5p, hsa-miR-489, hsa-miR-499a-5p, hsa-miR-550b-2-5p, hsa-miR-551b-3p, hsa-miR-5585-5p, hsa-miR-5690, hsa-miR-640, hsa-miR-675-3p"]], "row_count": 3, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[10]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:33935718:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c15ee0835ecc8627718c6e8c2cf850f00f434c3882780c498290980344156829", "bytes": 1184, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T3", "version": null, "note": "Gene Ontology analysis of differentially expressed genes associated with ESCC (Top ten biological process terms).", "structure": {"pmcid": "PMC8082678", "section_index": 11, "section_title": "GO and KEGG Analysis for These Candidate Genes", "row_count": 11, "column_count": 5}, "table": {"label": "TABLE 3", "caption": "Gene Ontology analysis of differentially expressed genes associated with ESCC (Top ten biological process terms).", "rows": [["Category", "Description", "Count", "p value", "FDR"], ["BP", "GO:0071396∼cellular_response_to_lipid", "6", "2.80e−06", "0.001617666"], ["BP", "GO:0050896∼response_to_stimulus", "18", "2.84e−06", "0.001617666"], ["BP", "GO:0071395∼cellular_response_to_jasmonic_acid_stimulus", "2", "3.63e−06", "0.001617666"], ["BP", "GO:0023051∼regulation_of_signaling", "12", "6.06e−06", "0.001658521"], ["BP", "GO:0010033∼response_to_organic_substance", "11", "7.33e−06", "0.001658521"], ["BP", "GO:0071310∼cellular_response_to_organic_substance", "10", "7.44e−06", "0.001658521"], ["BP", "GO:0009966∼regulation_of_signal_transduction", "11", "1.32e−05", "0.002048231"], ["BP", "GO:0071222∼cellular_response_to_lipopolysaccharide", "4", "1.46e−05", "0.002048231"], ["BP", "GO:0030155∼regulation_of_cell_adhesion", "6", "1.46−-05", "0.002048231"], ["BP", "GO:2000351∼regulation_of_endothelial_cell_apoptotic_process", "3", "1.54e−05", "0.002048231"]], "row_count": 11, "column_count": 5, "numeric_cells": 40, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:33935718:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:404b99413d5c49e10984051479f524323e97e0524ae23f033762c5b2ad3d3162", "bytes": 1401, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#T4", "version": null, "note": "KEGG pathway analysis of differentially expressed genes in ESCC.", "structure": {"pmcid": "PMC8082678", "section_index": 11, "section_title": "GO and KEGG Analysis for These Candidate Genes", "row_count": 11, "column_count": 6}, "table": {"label": "TABLE 4", "caption": "KEGG pathway analysis of differentially expressed genes in ESCC.", "rows": [["Category", "Description", "Count", "p value", "FDR", "Genes"], ["KEGG", "hsa04933∼AGE-RAGE_signaling_pathway_in_diabetic_complications Homo_sapiens_(human)", "3", "5.23e−04", "0.058021807", "ICAM1/SERPINE1/TNF"], ["KEGG", "hsa05143∼African_trypanosomiasis Homo_sapiens_(human)", "2", "1.63e−03", "0.08638883", "ICAM1/TNF"], ["KEGG", "hsa05144∼Malaria Homo_sapiens_(human)", "2", "2.85e−03", "0.08638883", "ICAM1/TNF"], ["KEGG", "hsa05169∼Epstein-Barr_virus_infection Homo_sapiens_(human)", "3", "3.91e−03", "0.08638883", "GADD45A/ICAM1/TNF"], ["KEGG", "hsa00140∼Steroid_hormone_biosynthesis Homo_sapiens_(human)", "2", "4.24e−03", "0.08638883", "AKR1C1/AKR1C2"], ["KEGG", "hsa05217∼Basal_cell_carcinoma Homo_sapiens_(human)", "2", "4.67e−03", "0.08638883", "BMP2/GADD45A"], ["KEGG", "hsa04115∼p53_signaling_pathway Homo_sapiens_(human)", "2", "6.06e−03", "0.095935394", "GADD45A/SERPINE1"], ["KEGG", "hsa05323∼Rheumatoid_arthritis Homo_sapiens_(human)", "2", "9.54e−03", "0.095935394", "ICAM1/TNF"], ["KEGG", "hsa04350∼TGF-beta_signaling_pathway Homo_sapiens_(human)", "2", "0.01", "0.095935394", "BMP2/TNF"], ["KEGG", "hsa04713∼Circadian_entrainment Homo_sapiens_(human)", "2", "0.01", "0.095935394", "GNB4/PER2"]], "row_count": 11, "column_count": 6, "numeric_cells": 43, "header_rows": 1, "locator": "section[11]/table-wrap[2]#T4"}}, {"id": "asset:table:pmid:33935718:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2958abfdc62fc9f125a1ec3c3dfe93dd40677d83884cefd8d4df2840efa17c73", "bytes": 415, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T5", "version": null, "note": "Protein-protein interaction network analysis for differential expressed genes in ESCC samples based on connectivity degrees evaluation.", "structure": {"pmcid": "PMC8082678", "section_index": 12, "section_title": "PPI Network Analysis and Prediction of miRNA-Gene Interactions", "row_count": 9, "column_count": 2}, "table": {"label": "TABLE 5", "caption": "Protein-protein interaction network analysis for differential expressed genes in ESCC samples based on connectivity degrees evaluation.", "rows": [["Gene", "Degree"], ["TNF", "3"], ["AKR1C1", "1"], ["AKR1C2", "1"], ["ICAM1", "1"], ["GPR68", "1"], ["GNB4", "1"], ["SERPINE1", "1"], ["MMP12", "1"]], "row_count": 9, "column_count": 2, "numeric_cells": 10, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T5"}}], "gaps": ["asset:data:geo:GSE137867 not downloaded", "asset:data:geo:GSE137867 licence not read", "asset:data:geo:GSE45670 not downloaded", "asset:data:geo:GSE45670 licence not read", "asset:data:geo:GSE59974 not downloaded", "asset:data:geo:GSE59974 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "reordered", "quote": "“Univariate cox regression analysis and survival analysis were performed to identify crucial genes and miRNAs related to ESCC survival based on the TCGA datasets.”"}}, {"id": "method-2", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "Principal Components Analysis"}}, {"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"}}], "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": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE45670", "GSE59974", "GSE137867"], "resolved_accessions": ["GSE45670", "GSE59974", "GSE137867"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number can be found below: https://www.ncbi.nlm.nih.gov/,GSE137867."], "basis": "The paper names GSE45670, GSE59974, GSE137867 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": ["cox_ph"], "assets": ["source:pmid:33935718", "data:geo:GSE137867", "asset:table:pmid:33935718:1", "asset:table:pmid:33935718:2", "asset:table:pmid:33935718:3", "asset:table:pmid:33935718:4", "asset:table:pmid:33935718:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE137867"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:29:35Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 36007, "completion_tokens": 1520, "cached_tokens": 12040}}, "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:33935718", "type": "paper", "label": "pmid:33935718"}, {"id": "source:pmid:33935718", "type": "manuscript", "label": "PMID 33935718 full text"}, {"id": "data:geo:GSE137867", "type": "dataset", "label": "GEO GSE137867"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33935718", "type": "paper", "label": "pmid:33935718"}, {"id": "source:pmid:33935718", "type": "manuscript", "label": "PMID 33935718 full text"}, {"id": "data:geo:GSE137867", "type": "dataset", "label": "GEO GSE137867"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33935718", "type": "extraction", "used": ["source:pmid:33935718"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE137867", "type": "accession_resolution", "used": ["data:geo:GSE137867"], "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:33935718", "parent_hash": "sha256:62ec50826db43004d8d2eb7008a3e75dadfa93b4bf5878aba41976396baba457", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE137867 licence not read", "asset:data:geo:GSE137867 not downloaded", "asset:data:geo:GSE45670 licence not read", "asset:data:geo:GSE45670 not downloaded", "asset:data:geo:GSE59974 licence not read", "asset:data:geo:GSE59974 not downloaded", "execution.not_run", "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": ["h esophageal squamous cell carcinoma (ESCC). Microarray datasets of nCRT responder and non-responder", ". Data normalization was performed for these microarray data. We extracted the gene expression value", "et were tested on platform of hg-u133_plus_2 Affymetrix Human Genome U133 Plus 2.0 and GSE45670 was"], "order_basis": "paper_text_order:438", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["“Univariate cox regression analysis and survival analysis were performed to identify crucial genes and miRNAs related to ESCC survival based on the TCGA datasets.”"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T04:27:10+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}}}