Astrocytoma progression scoring system based on the WHO 2016 criteria.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30643174", "kind": "science-record", "revision": 7, "content_hash": "sha256:84c32b2c9ee4ba5c9c115208501461afc1722ed02505a61135cca1306d59cd64", "created_at": "2026-11-01T15:40:40Z", "updated_at": "2026-11-01T22:00:16Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Astrocytoma progression scoring system based on the WHO 2016 criteria.", "doi": "10.1038/s41598-018-36471-4", "pmid": "30643174", "authors": ["Zhen-Hang Li", "Yan-Lei Guan", "Qiang Liu", "Yao Wang", "Run Cui", "Yun-Jie Wang"], "journal": "Scientific reports", "year": 2019, "abstract": "Diffuse astrocytoma (including glioblastoma) is morbid with a worse prognosis than other types of glioma. Therefore, we sought to build a progression-associated score to improve malignancy and prognostic predictions for astrocytoma. The astrocytoma progression (AP) score was constructed through bioinformatics analyses of the training cohort (TCGA RNA-seq) and included 18 genes representing distinct aspects of regulation during astrocytoma progression. This classifier could successfully discriminate patients with distinct prognoses in the training and validation (REMBRANDT, GSE16011 and TCGA-GBM Microarray) cohorts (P < 0.05 in all cohorts) and in different clinicopathological subgroups. Distinct patterns of somatic mutations and copy number variation were also observed. The bioinformatics analyses suggested that genes associated with a higher AP score were significantly involved in cancer progression-related biological processes, such as the cell cycle and immune/inflammatory responses, whereas genes associated with a lower AP score were associated with relatively normal nervous system biological processes. The analyses indicated that the AP score was a robust predictor of patient survival, and its ability to predict astrocytoma malignancy was well elucidated. Therefore, this bioinformatics-based scoring system suggested that astrocytoma progression could distinguish patients with different underlying biological processes and clinical outcomes, facilitate more precise tumour grading and possibly shed light on future classification strategies and therapeutics for astrocytoma patients.", "claims": [{"id": "claim-method", "statement": "The prognostic differences between patients with high or low expression of a certain gene or score (higher or lower than the median value) were calculated by the Kaplan–Meier method with the two-sided log-rank test using the R “survival” package.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30643174", "locator": "sections[13] \"Statistical analysis\" paragraph 2", "quote": "The prognostic differences between patients with high or low expression of a certain gene or score (higher or lower than the median value) were calculated by the Kaplan–Meier method with the two-sided log-rank test using the R “survival” package."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The expression, CNV, somatic mutation and clinical data from 471 cases (training cohort) and 525 GBM cases belonging to TCGA dataset were retrieved from the website http://cancergenome.nih.gov/. The REMBRANDT dataset was retrieved from the website http://caintegrator.nci.nih.gov/rembrandt. The GSE16011 dataset was retrieved from the Gene Expression Omnibus website (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE16011). The GSE4271 dataset was retrieved from the Gene Expression Omnibus website (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=gse4271).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30643174", "locator": "sections[19] \"Availability of Data and Materials\" paragraph 2", "quote": "The expression, CNV, somatic mutation and clinical data from 471 cases (training cohort) and 525 GBM cases belonging to TCGA dataset were retrieved from the website http://cancergenome.nih.gov/. The REMBRANDT dataset was retrieved from the website http://caintegrator.nci.nih.gov/rembrandt. The GSE16011 dataset was retrieved from the Gene Expression Omnibus website (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE16011). The GSE4271 dataset was retrieved from the Gene Expression Omnibus website (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=gse4271)."}], "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:30643174"], "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:GSE16011"], "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:GSE16011"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30643174", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-018-36471-4", "sha256": "sha256:1fb8b21a1accc1c03d2f3f451af0d6ced874ded661acea1e615c0ce7e0dccb6d", "bytes": 37345, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-018-36471-4", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6331604", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE16011", "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=GSE16011", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE16011", "version": null, "note": "The expression, CNV, somatic mutation and clinical data from 471 cases (training cohort) and 525 GBM cases belonging to TCGA dataset were retrieved from the website http://cancergenome.nih.gov/. The REMBRANDT dataset was retrieved from the website http://caintegrator.nci.nih.gov/rembrandt. The GSE16011 dataset was retrieved from the Gene Expression Omnibus website (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE16011). The GSE4271 dataset was retrieved from the Gene Expression Omnibus website (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=gse4271).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The expression, CNV, somatic mutation and clinical data from 471 cases (training cohort) and 525 GBM cases belonging to TCGA dataset were retrieved from the website http://cancergenome.nih.gov/. The REMBRANDT dataset was retrieved from the website http://caintegrator.nci.nih.gov/rembrandt. The GSE16011 dataset was retrieved from the Gene Expression Omnibus website (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE16011). The GSE4271 dataset was retrieved from the Gene Expression Omnibus website (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=gse4271).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM405200", "GSM405201", "GSM405202", "GSM405203", "GSM405204", "GSM405205", "GSM405206", "GSM405207", "GSM405208", "GSM405209", "GSM405210", "GSM405211", "GSM405212", "GSM405213", "GSM405214", "GSM405215", "GSM405216", "GSM405217", "GSM405218", "GSM405219", "GSM405220", "GSM405221", "GSM405222", "GSM405223", "GSM405224", "GSM405225", "GSM405226", "GSM405227", "GSM405228", "GSM405229", "GSM405230", "GSM405231", "GSM405232", "GSM405233", "GSM405234", "GSM405235", "GSM405236", "GSM405237", "GSM405238", "GSM405239", "GSM405240", "GSM405241", "GSM405242", "GSM405243", "GSM405244", "GSM405245", "GSM405246", "GSM405247", "GSM405248", "GSM405249", "GSM405250", "GSM405251", "GSM405252", "GSM405253", "GSM405254", "GSM405255", "GSM405256", "GSM405257", "GSM405258", "GSM405259", "GSM405260", "GSM405261", "GSM405262", "GSM405263", "GSM405264", "GSM405265", "GSM405266", "GSM405267", "GSM405268", "GSM405269", "GSM405270", "GSM405271", "GSM405272", "GSM405273", "GSM405274", "GSM405275", "GSM405276", "GSM405277", "GSM405278", "GSM405279", "GSM405280", "GSM405281", "GSM405282", "GSM405283", "GSM405284", "GSM405285", "GSM405286", "GSM405287", "GSM405288", "GSM405289", "GSM405290", "GSM405291", "GSM405292", "GSM405293", "GSM405294", "GSM405295", "GSM405296", "GSM405297", "GSM405298", "GSM405299", "GSM405300", "GSM405301", "GSM405302", "GSM405303", "GSM405304", "GSM405305", "GSM405306", "GSM405307", "GSM405308", "GSM405309", "GSM405310", "GSM405311", "GSM405312", "GSM405313", "GSM405314", "GSM405315", "GSM405316", "GSM405317", "GSM405318", "GSM405319", "GSM405320", "GSM405321", "GSM405322", "GSM405323", "GSM405324", "GSM405325", "GSM405326", "GSM405327", "GSM405328", "GSM405329", "GSM405330", "GSM405331", "GSM405332", "GSM405333", "GSM405334", "GSM405335", "GSM405336", "GSM405337", "GSM405338", "GSM405339", "GSM405340", "GSM405341", "GSM405342", "GSM405343", "GSM405344", "GSM405345", "GSM405346", "GSM405347", "GSM405348", "GSM405349", "GSM405350", "GSM405351", "GSM405352", "GSM405353", "GSM405354", "GSM405355", "GSM405356", "GSM405357", "GSM405358", "GSM405359", "GSM405360", "GSM405361", "GSM405362", "GSM405363", "GSM405364", "GSM405365", "GSM405366", "GSM405367", "GSM405368", "GSM405369", "GSM405370", "GSM405371", "GSM405372", "GSM405373", "GSM405374", "GSM405375", "GSM405376", "GSM405377", "GSM405378", "GSM405379", "GSM405380", "GSM405381", "GSM405382", "GSM405383", "GSM405384", "GSM405385", "GSM405386", "GSM405387", "GSM405388", "GSM405389", "GSM405390", "GSM405391", "GSM405392", "GSM405393", "GSM405394", "GSM405395", "GSM405396", "GSM405397", "GSM405398", "GSM405399", "GSM405400", "GSM405401", "GSM405402", "GSM405403", "GSM405404", "GSM405405", "GSM405406", "GSM405407", "GSM405408", "GSM405409", "GSM405410", "GSM405411", "GSM405412", "GSM405413", "GSM405414", "GSM405415", "GSM405416", "GSM405417", "GSM405418", "GSM405419", "GSM405420", "GSM405421", "GSM405422", "GSM405423", "GSM405424", "GSM405425", "GSM405426", "GSM405427", "GSM405428", "GSM405429", "GSM405430", "GSM405431", "GSM405432", "GSM405433", "GSM405434", "GSM405435", "GSM405436", "GSM405437", "GSM405438", "GSM405439", "GSM405440", "GSM405441", "GSM405442", "GSM405443", "GSM405444", "GSM405445", "GSM405446", "GSM405447", "GSM405448", "GSM405449", "GSM405450", "GSM405451", "GSM405452", "GSM405453", "GSM405454", "GSM405455", "GSM405456", "GSM405457", "GSM405458", "GSM405459", "GSM405460", "GSM405461", "GSM405462", "GSM405463", "GSM405464", "GSM405465", "GSM405466", "GSM405467", "GSM405468", "GSM405469", "GSM405470", "GSM405471", "GSM405472", "GSM405473", "GSM405474", "GSM405475", "GSM405476", "GSM405477", "GSM405478", "GSM405479", "GSM405480", "GSM405481", "GSM405482", "GSM405483"], "sample_count": 284, "group_sizes": null, "group_sizes_basis": null, "platform": "8542", "taxon": "Homo sapiens", "title": "Intrinsic Gene Expression Profiles of Gliomas are a Better Predictor of Survival than Histology", "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:GSE4271", "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=GSE4271", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE4271", "version": null, "note": "The expression, CNV, somatic mutation and clinical data from 471 cases (training cohort) and 525 GBM cases belonging to TCGA dataset were retrieved from the website http://cancergenome.nih.gov/. The REMBRANDT dataset was retrieved from the website http://caintegrator.nci.nih.gov/rembrandt. The GSE16011 dataset was retrieved from the Gene Expression Omnibus website (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE16011). The GSE4271 dataset was retrieved from the Gene Expression Omnibus website (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=gse4271).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The expression, CNV, somatic mutation and clinical data from 471 cases (training cohort) and 525 GBM cases belonging to TCGA dataset were retrieved from the website http://cancergenome.nih.gov/. The REMBRANDT dataset was retrieved from the website http://caintegrator.nci.nih.gov/rembrandt. The GSE16011 dataset was retrieved from the Gene Expression Omnibus website (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE16011). The GSE4271 dataset was retrieved from the Gene Expression Omnibus website (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=gse4271).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM96950", "GSM96951", "GSM96952", "GSM96953", "GSM96954", "GSM96955", "GSM96956", "GSM96957", "GSM96958", "GSM96959", "GSM96960", "GSM96961", "GSM96962", "GSM96963", "GSM96964", "GSM96965", "GSM96966", "GSM96967", "GSM96968", "GSM96969", "GSM96970", "GSM96971", "GSM96972", "GSM96973", "GSM96974", "GSM96975", "GSM96976", "GSM96977", "GSM96978", "GSM96979", "GSM96980", "GSM96981", "GSM96982", "GSM96983", "GSM96984", "GSM96985", "GSM96986", "GSM96987", "GSM96988", "GSM96989", "GSM96990", "GSM96991", "GSM96992", "GSM96993", "GSM96994", "GSM96995", "GSM96996", "GSM96997", "GSM96998", "GSM96999", "GSM97000", "GSM97001", "GSM97002", "GSM97003", "GSM97004", "GSM97005", "GSM97006", "GSM97007", "GSM97008", "GSM97009", "GSM97010", "GSM97011", "GSM97012", "GSM97013", "GSM97014", "GSM97015", "GSM97016", "GSM97017", "GSM97018", "GSM97019", "GSM97020", "GSM97021", "GSM97022", "GSM97023", "GSM97024", "GSM97025", "GSM97026", "GSM97027", "GSM97028", "GSM97029", "GSM97030", "GSM97031", "GSM97032", "GSM97033", "GSM97034", "GSM97035", "GSM97036", "GSM97037", "GSM97038", "GSM97039", "GSM97040", "GSM97041", "GSM97042", "GSM97043", "GSM97044", "GSM97045", "GSM97046", "GSM97047", "GSM97048", "GSM97049", "GSM97050", "GSM97051", "GSM97052", "GSM97053", "GSM97054", "GSM97055", "GSM97056", "GSM97057", "GSM97058", "GSM97059", "GSM97060", "GSM97061", "GSM97062", "GSM97063", "GSM97064", "GSM97065", "GSM97066", "GSM97067", "GSM97068", "GSM97069", "GSM97070", "GSM97071", "GSM97072", "GSM97073", "GSM97074", "GSM97075", "GSM97076", "GSM97077", "GSM97078", "GSM97079", "GSM97080", "GSM97081", "GSM97082", "GSM97083", "GSM97084", "GSM97085", "GSM97086", "GSM97087", "GSM97088", "GSM97089", "GSM97090", "GSM97091", "GSM97092", "GSM97093", "GSM97094", "GSM97095", "GSM97096", "GSM97097", "GSM97098", "GSM97099", "GSM97100", "GSM97101", "GSM97102", "GSM97103", "GSM97104", "GSM97105", "GSM97106", "GSM97107", "GSM97108", "GSM97109", "GSM97110", "GSM97111", "GSM97112", "GSM97113", "GSM97114", "GSM97115", "GSM97116", "GSM97117", "GSM97118", "GSM97119", "GSM97120", "GSM97121", "GSM97122", "GSM97123", "GSM97124", "GSM97125", "GSM97126", "GSM97127", "GSM97128", "GSM97129", "GSM97130", "GSM97131", "GSM97132", "GSM97133", "GSM97134", "GSM97135", "GSM97136", "GSM97137", "GSM97138", "GSM97139", "GSM97140", "GSM97141", "GSM97142", "GSM97143", "GSM97144", "GSM97145", "GSM97146", "GSM97147", "GSM97148", "GSM97149"], "sample_count": 200, "group_sizes": null, "group_sizes_basis": null, "platform": "96;97", "taxon": "Homo sapiens", "title": "Molecular subclasses of high-grade glioma: prognosis, disease progression, and neurogenesis", "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:30643174:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3fc2b84d9a56d90a548fe574a152109d1a249f60f2ae5f6a3fd127cfa3b1749e", "bytes": 773, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#Tab1", "version": null, "note": "Univariate and multivariate Cox regression analyses in the training cohort.", "structure": {"pmcid": "PMC6331604", "section_index": 5, "section_title": "Distribution and prognostic value of the AP score among the astrocytoma subgroups", "row_count": 10, "column_count": 5}, "table": {"label": "Table 1", "caption": "Univariate and multivariate Cox regression analyses in the training cohort.", "rows": [["Variables", "Univariate COX", "Multivariate COX"], ["HR", "P", "HR", "P"], ["AP score(High vs Low)", "7.87", "<0.0001", "2.68", "<0.0001"], ["Disease(GBM vs LGG)", "7.40", "<0.0001", "1.98", "0.0004"], ["Age(≥60 vs <60)", "4.38", "<0.0001", "1.50", "0.0310"], ["Gender(Male vs Female)", "1.19", "0.2295", "—", "—"], ["MGMT(Unmethylated vs Methylated)", "2.93", "<0.0001", "1.32", "0.0996"], ["IDH1(Wild type vs Mutant)", "10.39", "<0.0001", "3.54", "<0.0001"], ["Chemotherapy(Yes vs No)", "0.68", "0.0206", "0.98", "0.9239"], ["Radiotherapy(Yes vs No)", "0.92", "0.5906", "—", "—"]], "row_count": 10, "column_count": 5, "numeric_cells": 29, "header_rows": 2, "locator": "section[5]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:30643174:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:54dcd6ecbf34b781ac5252fbddb86b4241c107899702acb2b754cfa55069f744", "bytes": 1172, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#Tab2", "version": null, "note": "Correlation and prognostic value of each immune cell in the training cohort.", "structure": {"pmcid": "PMC6331604", "section_index": 9, "section_title": "Association between the AP score and immune cells", "row_count": 25, "column_count": 4}, "table": {"label": "Table 2", "caption": "Correlation and prognostic value of each immune cell in the training cohort.", "rows": [["Immune cell", "Log-rank test", "Correlation with AP score (Pearson correlation)"], ["P", "r value", "P"], ["Macrophages", "<0.001", "0.712", "<0.001"], ["aDC", "<0.001", "0.640", "<0.001"], ["NK_CD56dim", "<0.001", "0.543", "<0.001"], ["NK", "<0.001", "0.449", "<0.001"], ["Th2", "<0.001", "0.408", "<0.001"], ["Eosinophils", "<0.001", "0.385", "<0.001"], ["iDC", "0.012", "0.356", "<0.001"], ["Neutrophils", "<0.001", "0.337", "<0.001"], ["T_cell", "<0.001", "0.321", "<0.001"], ["DC", "0.029", "0.271", "<0.001"], ["Th17", "0.385", "0.182", "<0.001"], ["TReg", "0.161", "0.164", "<0.001"], ["T_helper", "0.042", "0.163", "<0.001"], ["Th1", "0.023", "0.104", "0.024"], ["Cytotoxic", "0.551", "0.048", "0.301"], ["CD8", "0.001", "−0.003", "0.950"], ["pDC", "<0.001", "−0.083", "0.072"], ["Mast", "0.841", "−0.107", "0.021"], ["NK_CD56bright", "0.614", "−0.219", "<0.001"], ["Tem", "<0.001", "−0.303", "<0.001"], ["B", "0.005", "−0.309", "<0.001"], ["Tgd", "<0.001", "−0.316", "<0.001"], ["Tcm", "<0.001", "−0.418", "<0.001"]], "row_count": 25, "column_count": 4, "numeric_cells": 72, "header_rows": 2, "locator": "section[9]/table-wrap[1]#Tab2"}}], "gaps": ["asset:data:geo:GSE16011 not downloaded", "asset:data:geo:GSE16011 licence not read", "asset:data:geo:GSE4271 not downloaded", "asset:data:geo:GSE4271 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The prognostic differences between patients with high or low expression of a certain gene or score (higher or lower than the median value) were calculated by the Kaplan–Meier method with the two-sided log-rank test using the R “survival” package."}}, {"id": "method-2", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Analysis of variance"}}, {"id": "method-3", "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": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-4", "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": 0.8, "band": "high", "quote": "COX regression"}}, {"id": "method-5", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC analysis"}}, {"id": "method-6", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "Chi-square"}}], "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": ["logrank_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: log_rank_test."}, "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": ["GSE16011", "GSE4271"], "resolved_accessions": ["GSE16011", "GSE4271"], "statements": ["The expression, CNV, somatic mutation and clinical data from 471 cases (training cohort) and 525 GBM cases belonging to TCGA dataset were retrieved from the website http://cancergenome.nih.gov/. The REMBRANDT dataset was retrieved from the website http://caintegrator.nci.nih.gov/rembrandt. The GSE16011 dataset was retrieved from the Gene Expression Omnibus website (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE16011). The GSE4271 dataset was retrieved from the Gene Expression Omnibus website (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=gse4271)."], "basis": "The paper names GSE16011, GSE4271 in Gene Expression Omnibus and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["logrank_test"], "assets": ["source:pmid:30643174", "data:geo:GSE16011", "asset:table:pmid:30643174:1", "asset:table:pmid:30643174:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE16011"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:13:23Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 28586, "completion_tokens": 2575, "cached_tokens": 784}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:30643174", "type": "paper", "label": "pmid:30643174"}, {"id": "source:pmid:30643174", "type": "manuscript", "label": "PMID 30643174 full text"}, {"id": "data:geo:GSE16011", "type": "dataset", "label": "GEO GSE16011"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30643174", "type": "paper", "label": "pmid:30643174"}, {"id": "source:pmid:30643174", "type": "manuscript", "label": "PMID 30643174 full text"}, {"id": "data:geo:GSE16011", "type": "dataset", "label": "GEO GSE16011"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30643174", "type": "extraction", "used": ["source:pmid:30643174"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE16011", "type": "accession_resolution", "used": ["data:geo:GSE16011"], "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:30643174", "parent_hash": "sha256:4c1ce697bf95f9057d9a28ef8220b5a79b7e0e881b9cc3321a10325df60f8f90", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE16011 licence not read", "asset:data:geo:GSE16011 not downloaded", "asset:data:geo:GSE4271 licence not read", "asset:data:geo:GSE4271 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["logrank_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The prognostic differences between patients with high or low expression of a certain gene or score (higher or lower than the median value) were calculated by the Kaplan–Meier method with the two-sided log-rank test using the R “survival” package."], "order_basis": "analysis_only", "id": "assay:1"}]}