{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34372798", "kind": "science-record", "revision": 8, "content_hash": "sha256:5a5778ef1deb8e35c69616980ef5408e3952e3ca225a168b3836ecc5593fa571", "created_at": "2026-11-01T15:41:47Z", "updated_at": "2026-11-01T22:47:18Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Using a machine learning approach to identify key prognostic molecules for esophageal squamous cell carcinoma.", "doi": "10.1186/s12885-021-08647-1", "pmid": "34372798", "authors": ["Meng-Xiang Li", "Xiao-Meng Sun", "Wei-Gang Cheng", "Hao-Jie Ruan", "Ke Liu", "Pan Chen", "Hai-Jun Xu", "She-Gan Gao", "Xiao-Shan Feng", "Yi-Jun Qi"], "journal": "BMC cancer", "year": 2021, "abstract": "BACKGROUND: A plethora of prognostic biomarkers for esophageal squamous cell carcinoma (ESCC) that have hitherto been reported are challenged with low reproducibility due to high molecular heterogeneity of ESCC. The purpose of this study was to identify the optimal biomarkers for ESCC using machine learning algorithms.\nMETHODS: Biomarkers related to clinical survival, recurrence or therapeutic response of patients with ESCC were determined through literature database searching. Forty-eight biomarkers linked to recurrence or prognosis of ESCC were used to construct a molecular interaction network based on NetBox and then to identify the functional modules. Publicably available mRNA transcriptome data of ESCC downloaded from Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) datasets included GSE53625 and TCGA-ESCC. Five machine learning algorithms, including logical regression (LR), support vector machine (SVM), artificial neural network (ANN), random forest (RF) and XGBoost, were used to develop classifiers for prognostic classification for feature selection. The area under ROC curve (AUC) was used to evaluate the performance of the prognostic classifiers. The importances of identified molecules were ranked by their occurrence frequencies in the prognostic classifiers. Kaplan-Meier survival analysis and log-rank test were performed to determine the statistical significance of overall survival.\nRESULTS: A total of 48 clinically proven molecules associated with ESCC progression were used to construct a molecular interaction network with 3 functional modules comprising 17 component molecules. The 131,071 prognostic classifiers using these 17 molecules were built for each machine learning algorithm. Using the occurrence frequencies in the prognostic classifiers with AUCs greater than the mean value of all 131,071 AUCs to rank importances of these 17 molecules, stratifin encoded by SFN was identified as the optimal prognostic biomarker for ESCC, whose performance was further validated in another 2 independent cohorts.\nCONCLUSION: The occurrence frequencies across various feature selection approaches reflect the degree of clinical importance and stratifin is an optimal prognostic biomarker for ESCC.", "claims": [{"id": "claim-method", "statement": "Kaplan-Meier survival analysis and log-rank test were performed to determine the statistical significance of overall survival.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34372798", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Kaplan-Meier survival analysis and log-rank test were performed to determine the statistical significance of overall survival."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data sets of GSE53625 from GEO (https://www.ncbi.nlm.nih.gov/geo/) and 37 ESCC cases with Asian ancestry from TCGA (UCSC Xena, https://xena.ucsc.edu/) are public open and available.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34372798", "locator": "sections[24] \"Availability of data and materials\" paragraph 2", "quote": "The data sets of GSE53625 from GEO (https://www.ncbi.nlm.nih.gov/geo/) and 37 ESCC cases with Asian ancestry from TCGA (UCSC Xena, https://xena.ucsc.edu/) are public open and available."}], "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:34372798"], "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:GSE53625"], "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:GSE53625"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34372798", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12885-021-08647-1", "sha256": "sha256:a71008efbf5729c6b73d3520fffad9111ec13b952e86229413e8de407ed892e1", "bytes": 41500, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12885-021-08647-1", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8351329", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE53625", "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=GSE53625", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53625", "version": null, "note": "The data sets of GSE53625 from GEO (https://www.ncbi.nlm.nih.gov/geo/) and 37 ESCC cases with Asian ancestry from TCGA (UCSC Xena, https://xena.ucsc.edu/) are public open and available.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets of GSE53625 from GEO (https://www.ncbi.nlm.nih.gov/geo/) and 37 ESCC cases with Asian ancestry from TCGA (UCSC Xena, https://xena.ucsc.edu/) are public open and available.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1296956", "GSM1296957", "GSM1296958", "GSM1296959", "GSM1296960", "GSM1296961", "GSM1296962", "GSM1296963", "GSM1296964", "GSM1296965", "GSM1296966", "GSM1296967", "GSM1296968", "GSM1296969", "GSM1296970", "GSM1296971", "GSM1296972", "GSM1296973", "GSM1296974", "GSM1296975", "GSM1296976", "GSM1296977", "GSM1296978", "GSM1296979", "GSM1296980", "GSM1296981", "GSM1296982", "GSM1296983", "GSM1296984", "GSM1296985", "GSM1296986", "GSM1296987", "GSM1296988", "GSM1296989", "GSM1296990", "GSM1296991", "GSM1296992", "GSM1296993", "GSM1296994", "GSM1296995", "GSM1296996", "GSM1296997", "GSM1296998", "GSM1296999", "GSM1297000", "GSM1297001", "GSM1297002", "GSM1297003", "GSM1297004", "GSM1297005", "GSM1297006", "GSM1297007", "GSM1297008", "GSM1297009", "GSM1297010", "GSM1297011", "GSM1297012", "GSM1297013", "GSM1297014", "GSM1297015", "GSM1297016", "GSM1297017", "GSM1297018", "GSM1297019", "GSM1297020", "GSM1297021", "GSM1297022", "GSM1297023", "GSM1297024", "GSM1297025", "GSM1297026", "GSM1297027", "GSM1297028", "GSM1297029", "GSM1297030", "GSM1297031", "GSM1297032", "GSM1297033", "GSM1297034", "GSM1297035", "GSM1297036", "GSM1297037", "GSM1297038", "GSM1297039", "GSM1297040", "GSM1297041", "GSM1297042", "GSM1297043", "GSM1297044", "GSM1297045", "GSM1297046", "GSM1297047", "GSM1297048", "GSM1297049", "GSM1297050", "GSM1297051", "GSM1297052", "GSM1297053", "GSM1297054", "GSM1297055", "GSM1297056", "GSM1297057", "GSM1297058", "GSM1297059", "GSM1297060", "GSM1297061", "GSM1297062", "GSM1297063", "GSM1297064", "GSM1297065", "GSM1297066", "GSM1297067", "GSM1297068", "GSM1297069", "GSM1297070", "GSM1297071", "GSM1297072", "GSM1297073", "GSM1297074", "GSM1297075", "GSM1297076", "GSM1297077", "GSM1297078", "GSM1297079", "GSM1297080", "GSM1297081", "GSM1297082", "GSM1297083", "GSM1297084", "GSM1297085", "GSM1297086", "GSM1297087", "GSM1297088", "GSM1297089", "GSM1297090", "GSM1297091", "GSM1297092", "GSM1297093", "GSM1297094", "GSM1297095", "GSM1297096", "GSM1297097", "GSM1297098", "GSM1297099", "GSM1297100", "GSM1297101", "GSM1297102", "GSM1297103", "GSM1297104", "GSM1297105", "GSM1297106", "GSM1297107", "GSM1297108", "GSM1297109", "GSM1297110", "GSM1297111", "GSM1297112", "GSM1297113", "GSM1297114", "GSM1297115", "GSM1297116", "GSM1297117", "GSM1297118", "GSM1297119", "GSM1297120", "GSM1297121", "GSM1297122", "GSM1297123", "GSM1297124", "GSM1297125", "GSM1297126", "GSM1297127", "GSM1297128", "GSM1297129", "GSM1297130", "GSM1297131", "GSM1297132", "GSM1297133", "GSM1297134", "GSM1297135", "GSM1297136", "GSM1297137", "GSM1297138", "GSM1297139", "GSM1297140", "GSM1297141", "GSM1297142", "GSM1297143", "GSM1297144", "GSM1297145", "GSM1297146", "GSM1297147", "GSM1297148", "GSM1297149", "GSM1297150", "GSM1297151", "GSM1297152", "GSM1297153", "GSM1297154", "GSM1297155", "GSM1297156", "GSM1297157", "GSM1297158", "GSM1297159", "GSM1297160", "GSM1297161", "GSM1297162", "GSM1297163", "GSM1297164", "GSM1297165", "GSM1297166", "GSM1297167", "GSM1297168", "GSM1297169", "GSM1297170", "GSM1297171", "GSM1297172", "GSM1297173", "GSM1297174", "GSM1297175", "GSM1297176", "GSM1297177", "GSM1297178", "GSM1297179", "GSM1297180", "GSM1297181", "GSM1297182", "GSM1297183", "GSM1297184", "GSM1297185", "GSM1297186", "GSM1297187", "GSM1297188", "GSM1297189", "GSM1297190", "GSM1297191", "GSM1297192", "GSM1297193", "GSM1297194", "GSM1297195", "GSM1297196", "GSM1297197", "GSM1297198", "GSM1297199", "GSM1297200", "GSM1297201", "GSM1297202", "GSM1297203", "GSM1297204", "GSM1297205", "GSM1297206", "GSM1297207", "GSM1297208", "GSM1297209", "GSM1297210", "GSM1297211", "GSM1297212", "GSM1297213", "GSM1297214", "GSM1297215", "GSM1297216", "GSM1297217", "GSM1297218", "GSM1297219", "GSM1297220", "GSM1297221", "GSM1297222", "GSM1297223", "GSM1297224", "GSM1297225", "GSM1297226", "GSM1297227", "GSM1297228", "GSM1297229", "GSM1297230", "GSM1297231", "GSM1297232", "GSM1297233", "GSM1297234", "GSM1297235", "GSM1297236", "GSM1297237", "GSM1297238", "GSM1297239", "GSM1297240", "GSM1297241", "GSM1297242", "GSM1297243", "GSM1297244", "GSM1297245", "GSM1297246", "GSM1297247", "GSM1297248", "GSM1297249", "GSM1297250", "GSM1297251", "GSM1297252", "GSM1297253", "GSM1297254", "GSM1297255", "GSM1297256", "GSM1297257", "GSM1297258", "GSM1297259", "GSM1297260", "GSM1297261", "GSM1297262", "GSM1297263", "GSM1297264", "GSM1297265", "GSM1297266", "GSM1297267", "GSM1297268", "GSM1297269", "GSM1297270", "GSM1297271", "GSM1297272", "GSM1297273", "GSM1297274", "GSM1297275", "GSM1297276", "GSM1297277", "GSM1297278", "GSM1297279", "GSM1297280", "GSM1297281", "GSM1297282", "GSM1297283", "GSM1297284", "GSM1297285", "GSM1297286", "GSM1297287", "GSM1297288", "GSM1297289", "GSM1297290", "GSM1297291", "GSM1297292", "GSM1297293", "GSM1297294", "GSM1297295", "GSM1297296", "GSM1297297", "GSM1297298", "GSM1297299", "GSM1297300", "GSM1297301", "GSM1297302", "GSM1297303", "GSM1297304", "GSM1297305", "GSM1297306", "GSM1297307", "GSM1297308", "GSM1297309", "GSM1297310", "GSM1297311", "GSM1297312", "GSM1297313"], "sample_count": 358, "group_sizes": null, "group_sizes_basis": null, "platform": "18109", "taxon": "Homo sapiens", "title": "LncRNA profile study reveals a three-lncRNA signature associated with the survival of esophageal squamous cell carcinoma patients", "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:34372798:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a2620f7c578ad22dd99ed5cd6398f39dc51ffab72cc02da86cba6883cab25c84", "bytes": 8414, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab1", "version": null, "note": "Thirty-eight studies reporting 48 molecules that were associated with clinical survival, recurrence or therapeutic outcome of ESCC patients", "structure": {"pmcid": "PMC8351329", "section_index": 13, "section_title": "Prognostic biomarkers of esophageal squamous cell carcinoma", "row_count": 39, "column_count": 5}, "table": {"label": "Table 1", "caption": "Thirty-eight studies reporting 48 molecules that were associated with clinical survival, recurrence or therapeutic outcome of ESCC patients", "rows": [["Biomarkers", "Prognosis/recurrence/therapeutic outcome", "PMID", "Sample sizes", "Conclusions"], ["BRCA1", "Prognosis and chemoradiotherapy", "23,326,344", "144", "Low BRCA1 expression was an independent prognostic factor in cisplatin-based chemotherapy (HR 0.29, 95% CI 0.12–0.71; P = 0.007) or chemoradiotherapy (HR 0.12, 95% CI 0.04–0.37; P < 0.001) group."], ["CCNA2", "Chemotherapy", "23,205,070", "48", "The expression of cyclin A was an independent prognosis factor in patients with ESCC following paclitaxel-based chemotherapy."], ["CCND1", "Prognosis and radiochemotherapy", "9,988,238", "172", "Patients with cyclin D1-positive carcinomas showed significantly worse overall survival than patients with cyclin D1-negative carcinomas (HR 2.14, 95% CI 1.134–3.42; P = 0.0038)"], ["CD163 & CD68", "Prognosis and neoadjuvant chemotherapy", "25,752,960", "210", "High infiltration of CD68+ macrophages and CD163+ macrophages was significantly associated with poor prognosis for patients undergoing neoadjuvant chemotherapy (P = 0.057, P = 0.003)."], ["CD274", "Prognosis and chemoradiotherapy", "26,623,522", "45", "The higher PD-L1 H-scores had poorer overall survival (median 16.7 versus 32.9 months, P = 0.02) than those with lower H-scores. (HR 2.29, 95% CI 1.12–4.69; P = 0.023)"], ["CD44 & PROM1", "Prognosis", "27,748,881", "47", "Patients with strong expression of CD44 or CD133 and those with a high ratio of CD133-positive tumor cells showed significantly poor prognosis regardless of the effect of chemotherapy. PROM1 (HR 5.05, 95% CI 1.12–4.69; P = 0.023)"], ["CDKN2A", "neoadjuvant chemotherapy", "26,514,506", "101", "ESCC tumors that were found positive for p16 expression appeared to fall into responders group rather than non responders (P = 0.008) and reported with less mortality (P = 0.048)."], ["CEA & KRT19", "Chemoradiotherapy", "19,863,186", "84", "CEA may be helpful in predicting the responsiveness in ESCC of primary lesions to CRT, with the effective rates (CR + PR) in CEA high and low groups of 58.3% (14/24) and 93.3% (56/60), respectively (P = 0.013 and 0.013)."], ["EGFR", "Chemoradiotherapy", "17,940,077", "62", "The difference in the CR rate between EGFR positive and -negative groups was significant (CR rate: 62% vs. 34%; P = 0.037)."], ["CRP", "Chemoradiotherapy", "21,224,533", "36", "Serum CRP can predict of CRT response with an accuracy of 75%."], ["ERCC1", "Chemotherapy", "23,263,828", "46", "Patients with ERCC1 negative tumors had a higher treatment response than the ERCC1 positive group (radiological response rates; 92.3% vs.50%, P = 0.013)."], ["FAM84B", "Neoadjuvant chemoradiation", "25,980,316", "21", "The fold-change of circulating FAM84B mRNA expression can predict the pCR with an AUC of 0.73."], ["FDXR", "Prognosis and Neoadjuvant chemoradiation", "26,637,858", "50", "Fdxr was significantly correlated with postoperative outcomes and an independent prognostic factor (HR 4.950, 95% CI 1.603–15.38; 0.012)."], ["HOXC6 & HOXC8", "Prognosis", "24,525,058", "274", "HOXC6 and HOXC8 were independent prognostic factors in patients with ESCC. HOXC6: (HR 1.341, 95% CI 0.895–2.010; P = 0.045); HOXC8: (HR 1.657, 95% CI 1.146–2.395; P = 0.007)."], ["IL6R", "Prognosis", "23,648,090", "218", "The sIL6R level was one of several significant independent predictors of an unfavorable outcome. (HR 3.20, 95% CI 1.34–7.53; P = 0.008)"], ["MDM2 & MKI67", "Prognosis and chemoradiotherapy", "25,880,782", "79", "MDM2 and p16 are predictive markers for chemoradioresistance in cStageIII ESCC and Ki-67 is a prognostic marker following dCRT in cStageIII ESCC."], ["MLH1", "Prognosis", "18,053,639", "51", "The expression of hMLH1 is a potential marker of tumor response and survival."], ["MMS19", "Chemoradiotherapy", "25,892,874", "103", "High cytoplasmic MMS19 expression was associated with a good response to chemoradiotherapy (OR 11.5, 95% CI: 3.0–44.5; P < 0.001)."], ["MT3", "Prognosis", "16,351,731", "64", "Esophageal squamous cell carcinomas with negative p53, positive CDC25B, and negative MT expressions respond well to CRT."], ["MUC13 & MUC20", "Prognosis and neoadjuvant chemotherapy", "26,323,930", "186", "The median survival time of patients with low MUC13/high MUC20 expression was significantly shorter than that of patients with high MUC13/low MUC20 expression (27.7 months vs. 59.5 months, P = 0.021; HR 0.531, 95% CI: 0.299–0.944; P = 0.031)."], ["MUC4", "neoadjuvant chemotherapy", "26,673,820", "186", "Low expression of MUC4 and MUC20 in resection samples was significantly correlated with better TRG (tumor regression grade). MUC4 and MUC20 were identified as potential biomarkers for predicting the efficacy of neoadjuvant chemotherapy in ESCC patients."], ["NOTCH1 & PIK3CA", "Prognosis and Chemotherapy", "26,528,858", "104", "NOTCH1 mutations was correlated with shorter survival times and failed to respond to chemotherapy, whereas PIK3CA mutations pointed to better responses to chemotherapy and longer survival times than patients without PIK3CA mutations."], ["PTGS2", "Prognosis and Chemoradiotherapy", "21,437,756", "58", "Negative or weak expression of PTGS2 was correlated significantly with CRT response (OR 6.296, 95% CI 1.58–25.096; P = 0.010)."], ["PTPN6", "Prognosis", "32,536,826", "184", "Elevated PTPN6 expression indicated longer OS (HR 1.123, 95% CI: 0.565–2.230; P = 0.741)."], ["RAD51", "Prognosis and recurrence", "24,065,387", "89", "Rad51 expression in ESCC was associated with poor survival (P = 0.0324) and recurrence (P = 0.0171)."], ["REG1A", "Prognosis", "23,645,481", "177", "REG1A expression was a significant prognostic factor (HR 3.095, 95% CI: 1.569–5.943; P = 0.0015)."], ["SFN", "Chemoradiation therapy", "15,999,354", "62", "SFN-positive expressions were closely related to the response to CRT."], ["Prognosis", "24,743,601", "278", "Downregulation of 14–3-3σpredicts poor survival, suggesting that 14–3-3σmay be a biomarker for early detection of high-risk subjects and diagnosis of ESCC. (HR 0.466, 95% CI 0.251–0.866; P = 0.016)."], ["Prognosis", "20,108,042", "148", "Reduced stratifin expression, T4 stage, lymph node metastasis, and distant metastasis were independent risk factors for worse prognosis in ESCC patients."], ["SGTA", "Prognosis", "23,939,810", "120", "SGTA expression indicated poor prognosis (RR 3.513, 95% CI: 2.161–9.791; P = 0.016)."], ["TGFB1 & VEGFA", "Prognosis", "24,623,035", "79", "VEGFA and TGFB1 were significantly associated with pathological response and/or DFS, and may be used to predict pathological response and survivals for ESCC patients receiving combined modality therapy."], ["TP53 & RRM2B", "Prognosis and chemoradiotherapy", "15,655,547", "62", "p53 or p53R2 (RRM2B) expression was correlated with a favorable response to CRT (P = 0.0001 or 0.041 clinical, P = 0.016 or 0.0018 histological, respectively; TP53, RR 2.688, 95% CI: 1.157–6.250; P = 0.0011. RRM2B, RR 2.469, 95% CI: 1.164–5.235; P = 0.0057)."], ["Prognosis", "25,135,238", "36", "The median tumor associated survival was 34.2 months for patients with normal TP53, compared with 8.9 months for those with mutant TP53. The latter had a 3-fold higher risk of death (HR 3.01, 95% CI 1.359–6.86; P = 0.005)."], ["Prognosis", "10,414,702", "42", "The current study indicated that p53 mutation of tumor tissues might be a prognostic factor for esophageal squamous cell carcinoma cases and one of the risk factors for its recurrence."], ["Chemotherapy", "19,941,080", "97", "Patients with mutations in p53 therefore showed significantly poorer prognosis than those without mutant p53."], ["RAC3 & TRAM1", "Prognosis and chemoradiotherapy", "19,552,757", "98", "Overexpression of AIB1/RAC3/ TRAM1 is a useful predictor of CRT resistance and an independent molecular marker of poor prognosis for ESCC patients."], ["ALDH1A1, ALDH1A2, ALDH1A3, ALDH1B1, ALDH1L1, ALDH1L2", "Prognosis and recurrence", "22,847,125", "152", "ALDH1 was a predictor of postoperative recurrence and prognosis in ESCC, and CD44 might be a predictor of recurrence and prognosis."], ["PITX2", "Prognosis and chemoradiotherapy", "23,132,660", "454", "High expression of PITX2 was associated with poor disease-specific survival (HR 1.732, 95% CI 1.133–2.646; P = 0.011) in ESCC."]], "row_count": 39, "column_count": 5, "numeric_cells": 117, "header_rows": 1, "locator": "section[13]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:34372798:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dcbaf7bb4d3876419e4ac99adfd6e21caceb3ca5cf42354a1a2ed2ae3aaddbbc", "bytes": 528, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#Tab2", "version": null, "note": "The top 5 important molecules identified by each machine learning algorithm", "structure": {"pmcid": "PMC8351329", "section_index": 15, "section_title": "Prognostic classification using 5 machine learning algorithms", "row_count": 7, "column_count": 6}, "table": {"label": "Table 2", "caption": "The top 5 important molecules identified by each machine learning algorithm", "rows": [["Moleculerank", "Weak classifiers", "Strong classifiers"], ["LR", "SVM", "ANN", "RF", "XGBoost"], ["1", "CD44", "CD44", "SFN", "SFN", "SFN"], ["2", "RAC3", "TRAM1", "CCND1", "PTGS2", "PIK3CA"], ["3", "TP53", "SFN", "CD44", "MDM2", "CD44"], ["4", "EGFR", "PTGS2", "PTGS2", "PIK3CA", "VEGFA"], ["5", "SFN", "VEGFA", "MDM2", "RAC3", "PTGS2"]], "row_count": 7, "column_count": 6, "numeric_cells": 10, "header_rows": 2, "locator": "section[15]/table-wrap[1]#Tab2"}}], "gaps": ["asset:data:geo:GSE53625 not downloaded", "asset:data:geo:GSE53625 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": 1.0, "band": "verbatim", "quote": "Kaplan-Meier survival analysis and log-rank test were performed to determine the statistical significance of overall survival."}}, {"id": "method-2", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Student t-test"}}, {"id": "method-3", "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": 0.7, "band": "medium", "quote": "log-rank"}}, {"id": "method-4", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "random forest"}}, {"id": "method-5", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "support vector machine"}}, {"id": "method-6", "family": "machine_learning", "specific": "gradient_boosting", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "XGBoost"}}, {"id": "method-7", "family": "regression_modelling", "specific": "ols", "label": "Regression modelling", "dsl_operations": ["ols_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "linear regression"}}, {"id": "method-8", "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": 0.7, "band": "medium", "quote": "ROC curve"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["GSE53625"], "resolved_accessions": ["GSE53625"], "statements": ["The data sets of GSE53625 from GEO (https://www.ncbi.nlm.nih.gov/geo/) and 37 ESCC cases with Asian ancestry from TCGA (UCSC Xena, https://xena.ucsc.edu/) are public open and available."], "basis": "The paper names GSE53625 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": ["survival_km"], "assets": ["source:pmid:34372798", "data:geo:GSE53625", "asset:table:pmid:34372798:1", "asset:table:pmid:34372798:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE53625"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:33:33Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 33410, "completion_tokens": 1456, "cached_tokens": 776}}, "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:34372798", "type": "paper", "label": "pmid:34372798"}, {"id": "source:pmid:34372798", "type": "manuscript", "label": "PMID 34372798 full text"}, {"id": "data:geo:GSE53625", "type": "dataset", "label": "GEO GSE53625"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34372798", "type": "paper", "label": "pmid:34372798"}, {"id": "source:pmid:34372798", "type": "manuscript", "label": "PMID 34372798 full text"}, {"id": "data:geo:GSE53625", "type": "dataset", "label": "GEO GSE53625"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34372798", "type": "extraction", "used": ["source:pmid:34372798"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE53625", "type": "accession_resolution", "used": ["data:geo:GSE53625"], "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:34372798", "parent_hash": "sha256:2a0570ed67a6f9c16bda0b77d9f53380f0b4a06617fb7a5e68ddb181b24cac6c", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE53625 licence not read", "asset:data:geo:GSE53625 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["t. The relationship between the abundance of western blot and the expression level of SFN was analyzed"], "order_basis": "paper_text_order:2819", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Kaplan-Meier survival analysis and log-rank test were performed to determine the statistical significance of overall survival."], "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":"2026-11-04T01:45:48+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}}}