{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30816530", "kind": "science-record", "revision": 7, "content_hash": "sha256:526ae01c763b530c399e33d3143b93eb40005a2e8acc5945f1f1155df54e00ee", "created_at": "2026-11-01T15:40:42Z", "updated_at": "2026-11-01T22:00:24Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "In silico analysis identified miRNA‑based therapeutic agents against glioblastoma multiforme.", "doi": "10.3892/or.2019.7022", "pmid": "30816530", "authors": ["Dan-Dan Xiong", "Wen-Qing Xu", "Rong-Quan He", "Yi-Wu Dang", "Gang Chen", "Dian-Zhong Luo"], "journal": "Oncology reports", "year": 2019, "abstract": "MicroRNAs (miRNAs or miRs) contribute to the development of various malignant neoplasms, including glioblastoma multiforme (GBM). The present study aimed to explore the pathogenesis of GBM and to identify latent therapeutic agents for patients with GBM, based on an in silico analysis. Gene chips that provide miRNA expression profiling in GBM were obtained from the Gene Expression Omnibus (GEO) database. Differentially expressed miRNAs (DEMs) were also determined via the RobustRankAggreg algorithm. The target genes of DEMs were predicted and then intersected with GBM‑associated genes that were collected from the Gene Expression Profiling Interactive Analysis. Gene Oncology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses of the overlapping genes were then performed. Simultaneously, a connectivity map (CMap) analysis was performed to screen for potential therapeutic agents for GBM. A total of 10 DEMs (hsa‑miR‑196a, hsa‑miR‑10b, hsa‑miR‑196b, hsa‑miR‑18b, hsa‑miR‑542‑3p, hsa‑miR‑129‑3p, hsa‑miR‑1224‑5p, hsa‑miR‑876‑3p and hsa‑miR‑770‑5p) were obtained from three GEO gene chips (GSE25631, GSE42657 and GSE61710). Then, 1,720 target genes of the 10 miRNAs and 4,185 differently expressed genes in GBM were collected. By intersecting the aforementioned gene clusters, the present study identified 390 overlapping genes. GO and KEGG analyses of the 390 genes demonstrated that these genes were involved in certain cancer‑associated biological functions and pathways. Eight genes [(GTPase NRas (NRAS), calcium/calmodulin‑dependent protein kinase type II subunit Gamma (CAMK2G), platelet‑derived growth factor receptor alpha (PDGFRA), calmodulin 3 (CALM3), cyclin‑dependent kinase 6 (CDK6), calcium/calmodulin‑dependent protein kinase type II subunit beta (CAMK2B), retinoblastoma‑associated protein (RB1) and protein kinase C beta type (PRKCB)] that were centralized in the glioma pathway were selected for CMap analysis. Three chemicals (W‑13, gefitinib and exemestane) were identified as putative therapeutic agents for GBM. In summary, the present study identified three miRNA‑based chemicals for use as a therapy for GBM. However, more experimental data are needed to verify the therapeutic properties of these latent drugs in GBM.", "claims": [{"id": "claim-data-access", "statement": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30816530", "locator": "sections[22] \"Availability of data and materials\" paragraph 2", "quote": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:30816530"], "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:GSE25631"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:student_t", "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:GSE25631"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:student_t"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30816530", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/or.2019.7022", "sha256": "sha256:3c66613f8d2d37b6a743fa9053c68bfe89104eb7c0c659a2a0af2dc2bfec196b", "bytes": 48858, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/or.2019.7022", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6412522", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE25631", "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=GSE25631", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE25631", "version": null, "note": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM629768", "GSM629769", "GSM629770", "GSM629771", "GSM629772", "GSM629773", "GSM629774", "GSM629775", "GSM629776", "GSM629777", "GSM629778", "GSM629779", "GSM629780", "GSM629781", "GSM629782", "GSM629783", "GSM629784", "GSM629785", "GSM629786", "GSM629787", "GSM629788", "GSM629789", "GSM629790", "GSM629791", "GSM629792", "GSM629793", "GSM629794", "GSM629795", "GSM629796", "GSM629797", "GSM629798", "GSM629799", "GSM629800", "GSM629801", "GSM629802", "GSM629803", "GSM629804", "GSM629805", "GSM629806", "GSM629807", "GSM629808", "GSM629809", "GSM629810", "GSM629811", "GSM629812", "GSM629813", "GSM629814", "GSM629815", "GSM629816", "GSM629817", "GSM629818", "GSM629819", "GSM629820", "GSM629821", "GSM629822", "GSM629823", "GSM629824", "GSM629825", "GSM629826", "GSM629827", "GSM629828", "GSM629829", "GSM629830", "GSM629831", "GSM629832", "GSM629833", "GSM629834", "GSM629835", "GSM629836", "GSM629837", "GSM629838", "GSM629839", "GSM629840", "GSM629841", "GSM629842", "GSM629843", "GSM629844", "GSM629845", "GSM629846", "GSM629847", "GSM629848", "GSM629849", "GSM629850", "GSM629851", "GSM629852", "GSM629853", "GSM629854"], "sample_count": 87, "group_sizes": null, "group_sizes_basis": null, "platform": "8179", "taxon": "Homo sapiens", "title": "Genome-wide analysis of microRNA expression in surgical specimens of primary glioblastoma multiform", "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:GSE42657", "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=GSE42657", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE42657", "version": null, "note": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1047468", "GSM1047469", "GSM1047470", "GSM1047471", "GSM1047472", "GSM1047473", "GSM1047474", "GSM1047475", "GSM1047476", "GSM1047477", "GSM1047478", "GSM1047479", "GSM1047480", "GSM1047481", "GSM1047482", "GSM1047483", "GSM1047484", "GSM1047485", "GSM1047486", "GSM1047487", "GSM1047488", "GSM1047489", "GSM1047490", "GSM1047491", "GSM1047492", "GSM1047493", "GSM1047494", "GSM1047495", "GSM1047496", "GSM1047497", "GSM1047498", "GSM1047499", "GSM1047500", "GSM1047501", "GSM1047502", "GSM1047503", "GSM1047504", "GSM1047505", "GSM1047506", "GSM1047507", "GSM1047508", "GSM1047509", "GSM1047510", "GSM1047511", "GSM1047512", "GSM1047513", "GSM1047514", "GSM1047515", "GSM1047516", "GSM1047517", "GSM1047518", "GSM1047519", "GSM1047520", "GSM1047521", "GSM1047522", "GSM1047523", "GSM1047524", "GSM1047525", "GSM1047526", "GSM1047527", "GSM1047528", "GSM1047529", "GSM1047530", "GSM1047531"], "sample_count": 64, "group_sizes": null, "group_sizes_basis": null, "platform": "8179", "taxon": "Homo sapiens", "title": "MicroRNA expression profiles for paediatric brain tumours", "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:GSE61710", "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=GSE61710", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE61710", "version": null, "note": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1511526", "GSM1511527", "GSM1511528", "GSM1511529", "GSM1511530", "GSM1511531", "GSM1511532", "GSM1511533", "GSM1511534", "GSM1511535", "GSM1511536", "GSM1511537", "GSM1511538", "GSM1511539", "GSM1511540", "GSM1511541", "GSM1511542"], "sample_count": 17, "group_sizes": null, "group_sizes_basis": null, "platform": "10656", "taxon": "Homo sapiens", "title": "Analysis of microRNA expression profile in malignant glioma tissues", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:30816530:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:505906d4483905e132fe9c5f494dc28ce588876bebf08319249036784559cf0a", "bytes": 554, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tI-or-41-04-2194", "version": null, "note": "Basic information of the three gene chips obtained from Gene Expression Omnibus.", "structure": {"pmcid": "PMC6412522", "section_index": 12, "section_title": "Screening of 10 DEMs in GBM by the RobustRankAggreg method", "row_count": 4, "column_count": 6}, "table": {"label": "Table I.", "caption": "Basic information of the three gene chips obtained from Gene Expression Omnibus.", "rows": [["First author (publication year)", "Country", "Data source", "Platform", "Sample size (T/N)", "(Refs.)"], ["Zhang et al (2012)", "China", "GSE25631", "GPL8179", "82/5", "(31)"], ["Jones et al (2015)", "United Kingdom", "GSE42657", "GPL8179", "5/7", "(32)"], ["Piwecka et al (2015)", "Poland", "GSE61710", "GPL10656", "10/5", "(33)"]], "row_count": 4, "column_count": 6, "numeric_cells": 15, "header_rows": 1, "locator": "section[12]/table-wrap[1]#tI-or-41-04-2194"}}, {"id": "asset:table:pmid:30816530:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:688c82c105747c85a2509e7866c275774f705b312e0fc604463db210736f153a", "bytes": 1540, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#tII-or-41-04-2194", "version": null, "note": "Five top upregulated miRNAs and five top downregulated miRNAs from Gene Expression Omnibus.", "structure": {"pmcid": "PMC6412522", "section_index": 12, "section_title": "Screening of 10 DEMs in GBM by the RobustRankAggreg method", "row_count": 24, "column_count": 6}, "table": {"label": "Table II.", "caption": "Five top upregulated miRNAs and five top downregulated miRNAs from Gene Expression Omnibus.", "rows": [["Literature retrieval"], [""], ["Author", "miRNA", "RobustRankAggreg", "Expression", "Function", "(Refs.)"], ["Dou et al", "hsa-miR-196a", "Up", "", "Polymorphism", "(37)"], ["Yang et al", "", "", "Up", "Tumor growth", "(38)"], ["Guan et al", "", "", "Up", "None", "(39)"], ["Yang et al", "", "", "Up", "None", "(40)"], ["Sasayama et al", "hsa-miR-10b", "Up", "Up", "Cell invasion", "(41)"], ["Guessous et al", "", "", "Up", "Cell invasion, cell migration, tumor growth", "(42)"], ["Gabriely et al", "", "", "Up", "Cell proliferation, cell death", "(43)"], ["Ji et al", "", "", "Up", "None", "(44)"], ["Guan et al", "hsa-miR-196b", "Up", "Up", "None", "(45)"], ["Lakomy et al", "", "", "Up", "None", "(46)"], ["Ma et al", "", "", "Up", "None", "(47)"], ["You et al", "", "", "Up", "None", "(48)"], ["Karsy M et al", "", "", "Up", "None", "(49)"], ["", "hsa-miR-18b", "Up", "", "None", "No ref."], ["Cai et al", "hsa-miR-543-3p", "Up", "Down", "Cell invasion", "(50)a"], ["", "hsa-miR-219-2-3p", "Down", "", "None", "No ref."], ["Qian et al", "hsa-miR-1224-5p", "Down", "Down", "Cell proliferation, cell invasion, cell apoptosis", "(51)"], ["Ouyang et al", "hsa-miR-129-3p", "Down", "Down", "Cell proliferation, tumor growth", "(52)"], ["Fang et al", "", "", "Down", "Cell viability, cell growth", "(53)"], ["", "hsa-miR-876-3p", "Down", "", "None", "No ref."], ["", "hsa-miR-770-5p", "Down", "", "None", "No ref."]], "row_count": 24, "column_count": 6, "numeric_cells": 27, "header_rows": 3, "locator": "section[12]/table-wrap[2]#tII-or-41-04-2194"}}, {"id": "asset:table:pmid:30816530:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b0323d6f607400fe30bf66aa2a11fe0bed1db37c94e655bf02981523e68d2182", "bytes": 509, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#tIII-or-41-04-2194", "version": null, "note": "Three chemicals identified as therapeutic agents for glioblastoma multiforme from CMap analysis.", "structure": {"pmcid": "PMC6412522", "section_index": 15, "section_title": "Identification of three potential chemicals for GBM treatment using CMap analysis", "row_count": 4, "column_count": 6}, "table": {"label": "Table III.", "caption": "Three chemicals identified as therapeutic agents for glioblastoma multiforme from CMap analysis.", "rows": [["CMap name", "Enrichment", "Dose", "Cell lines", "Up score", "Down score"], ["W-13", "−0.989", "10 µM", "MCF7", "−0.356", "0.532"], ["Gefitinib", "−0.989", "10 µM", "HL60", "−0.289", "0.479"], ["Exemestane", "−0.981", "10 nM", "MCF7", "−0.382", "0.351"]], "row_count": 4, "column_count": 6, "numeric_cells": 14, "header_rows": 1, "locator": "section[15]/table-wrap[1]#tIII-or-41-04-2194"}}, {"id": "asset:table:pmid:30816530:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5672a71f169f6fb9f9ae9f4c3fa115ab55773acdae19e1ab768ec4db5bf6bf17", "bytes": 1697, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#tIV-or-41-04-2194", "version": null, "note": "Results of protein-ligand docking.", "structure": {"pmcid": "PMC6412522", "section_index": 16, "section_title": "Exploration of the interactions between the three chemicals and the eight genes", "row_count": 22, "column_count": 7}, "table": {"label": "Table IV.", "caption": "Results of protein-ligand docking.", "rows": [["Gene symbol", "Protein name", "PDB ID", "Chemical", "Total score", "Crash", "Polar"], ["CDK6", "Cyclin-dependent kinase 6", "1BI7", "W-13", "6.9158", "−0.6018", "1.0852"], ["", "", "", "Gefitinib", "4.5461", "−1.5497", "1.0374"], ["", "", "", "Exemestane", "4.2617", "−0.6835", "1.2109"], ["RB1", "Retinoblastoma-associated protein", "2QDJ", "W-13", "6.1141", "−0.7408", "2.1589"], ["", "", "", "Gefitinib", "5.1361", "−3.0039", "1.0429"], ["", "", "", "Exemestane", "4.5673", "−1.2303", "2.2315"], ["CAMK2G", "Calcium/calmodulin-dependent protein kinase type II subunit gamma", "2V7O", "W-13", "6.5899", "−0.9631", "2.1155"], ["", "", "", "Gefitinib", "5.5314", "−0.8239", "4.6009"], ["", "", "", "Exemestane", "5.5085", "−2.4882", "2.8500"], ["CAMK2B", "Calcium/calmodulin-dependent protein kinase type II subunit beta", "3BHH", "W-13", "6.9781", "−0.8004", "2.9012"], ["", "", "", "Gefitinib", "5.4665", "−1.7396", "3.6928"], ["", "", "", "Exemestane", "4.7782", "−1.8678", "4.6573"], ["NRAS", "GTPase NRas", "3CON", "W-13", "6.9580", "−0.7966", "3.5558"], ["", "", "", "Gefitinib", "5.1191", "−1.6695", "2.1113"], ["", "", "", "Exemestane", "3.7527", "−1.3243", "1.6902"], ["PRKCB", "Protein kinase C beta type", "3PFQ", "W-13", "5.9087", "−0.7642", "4.3292"], ["", "", "", "Gefitinib", "5.9886", "−0.9356", "2.5291"], ["", "", "", "Exemestane", "3.5943", "−0.6226", "2.3138"], ["PDGFRA", "Platelet-derived growth factor receptor alpha", "5K5X", "W-13", "6.7711", "−1.3263", "4.9966"], ["", "", "", "Gefitinib", "4.0157", "−1.0638", "1.1911"], ["", "", "", "Exemestane", "4.8780", "−0.9005", "2.6185"]], "row_count": 22, "column_count": 7, "numeric_cells": 78, "header_rows": 1, "locator": "section[16]/table-wrap[1]#tIV-or-41-04-2194"}}], "gaps": ["asset:data:geo:GSE25631 not downloaded", "asset:data:geo:GSE25631 licence not read", "asset:data:geo:GSE42657 not downloaded", "asset:data:geo:GSE42657 licence not read", "asset:data:geo:GSE61710 not downloaded", "asset:data:geo:GSE61710 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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's t-test"}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "PPI"}}, {"id": "method-3", "family": null, "specific": null, "label": "RobustRankAggreg", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "“The DEMs in the individual gene chips were then integrated and ranked with RobustRankAggreg (20), which is an R package for the comprehensive integration of the gene list.”"}}], "targets": [], "gaps": ["method.reader_named_unmapped", "method.student_t"]}, "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": false, "required_operations": [], "missing_operations": ["student_t"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: student_t_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": ["GSE25631", "GSE42657", "GSE61710"], "resolved_accessions": ["GSE25631", "GSE42657", "GSE61710"], "statements": ["The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE25631, GSE42657, GSE61710 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": [], "assets": ["source:pmid:30816530", "data:geo:GSE25631", "asset:table:pmid:30816530:1", "asset:table:pmid:30816530:2", "asset:table:pmid:30816530:3", "asset:table:pmid:30816530:4"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "student_t", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE25631"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:13:58Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 43019, "completion_tokens": 1542, "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:30816530", "type": "paper", "label": "pmid:30816530"}, {"id": "source:pmid:30816530", "type": "manuscript", "label": "PMID 30816530 full text"}, {"id": "data:geo:GSE25631", "type": "dataset", "label": "GEO GSE25631"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30816530", "type": "paper", "label": "pmid:30816530"}, {"id": "source:pmid:30816530", "type": "manuscript", "label": "PMID 30816530 full text"}, {"id": "data:geo:GSE25631", "type": "dataset", "label": "GEO GSE25631"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30816530", "type": "extraction", "used": ["source:pmid:30816530"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE25631", "type": "accession_resolution", "used": ["data:geo:GSE25631"], "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:30816530", "parent_hash": "sha256:0f9e3ba5d2474fd57f30129c1c1b9f0dbbbcadbf81dadc7fa144b8afcca8309f", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE25631 licence not read", "asset:data:geo:GSE25631 not downloaded", "asset:data:geo:GSE42657 licence not read", "asset:data:geo:GSE42657 not downloaded", "asset:data:geo:GSE61710 licence not read", "asset:data:geo:GSE61710 not downloaded", "execution.not_run", "method.reader_named_unmapped", "method.student_t", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:student_t"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["from GEO. The basic information of the three microarray datasets are presented in Table I and the ma"], "order_basis": "paper_text_order:2518", "id": "assay:1"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ein kinase C beta type; CALM3, calmodulin 3. Immunohistochemistry staining of the proteins encoded by the 8 mi"], "order_basis": "paper_text_order:9444", "id": "assay:2"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Student's t-test"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T03:16:24+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}}}