{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32821117", "kind": "science-record", "revision": 9, "content_hash": "sha256:cf532ca21fe4351e06553068c514b5c1f40f19fdf10c77281e1a6db76008ff00", "created_at": "2026-11-01T15:41:08Z", "updated_at": "2026-11-01T22:45:13Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "miR-30d Induced Apoptosis by Targeting Sox4 to Inhibit the Proliferation, Invasion and Migration of Nephroblastoma.", "doi": "10.2147/OTT.S251714", "pmid": "32821117", "authors": ["Shi Zong", "Jia Zhao", "Ling Liu"], "journal": "OncoTargets and therapy", "year": 2020, "abstract": "BACKGROUND: Wilms tumor (WT) is an embryonic malignant tumor, and its related mechanism is still unclear. microRNA (miR), as a short-chain non-coding RNA, has low expression in various tumors. In this study, WT differential miR was screened by multi-chip in GEO database and its mechanism was explored to provide potential therapeutic targets and ideas for clinic.\nMETHODS: We logged into GEO database and downloaded GSE57370 and GSE48137 chip matrix files to analyze potential differences in miR. TargetScan, miRDB, miRTarBase and starBase were applied to predict the target genes of miR with significant differences. qRT-PCR was applied to determine the expression of miR-30d and Sox4 in WT tissue and cell line (G401). The interaction of miR-30d with Sox4 was confirmed by qRT-PCR, Western blot and luciferase assay, respectively. CCK-8, Transwell and flow cytometry were applied to determine the proliferation, invasion, migration and apoptosis of cells.\nRESULTS: We found that miR-30d was low expressed in two chips. qRT-PCR showed that miR-30d was down-regulated and SOX4 was up-regulated in WT tissues and cells. The online target gene prediction software showed there was a targeted binding site between Sox4 and miR-30d. Sox4 was negatively controlled by miR-30d. Subsequent studies found that over-expression of miR-30d inhibited the proliferation, invasion, migration and induced apoptosis of C64 and WiT49 cells. In addition, Sox4 could reverse the proliferation, invasion and migration of C64 and WiT49 induced by miR-30d and induce apoptosis.\nCONCLUSION: miR-30d is poorly expressed in WT and can induce apoptosis and inhibit proliferation, invasion and migration by mediating Sox4.", "claims": [{"id": "claim-method", "statement": "The processed data were analyzed for differences using limma package", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32821117", "locator": "sections[3] \"GEO Database Data Analysis\" paragraph 2", "quote": "The processed data were analyzed for differences using limma package"}], "state": "complete"}, {"id": "claim-data-access", "statement": "We logged into GEO database (https://www.ncbi.nlm.nih.gov/gds) to search Wilms tumor and microRNA related chips. Finally, we selected GSE57370 and GSE48137 chips, downloaded matrix file Series Matrix File (s)", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32821117", "locator": "sections[3] \"GEO Database Data Analysis\" paragraph 2", "quote": "We logged into GEO database (https://www.ncbi.nlm.nih.gov/gds) to search Wilms tumor and microRNA related chips. Finally, we selected GSE57370 and GSE48137 chips, downloaded matrix file Series Matrix File (s)"}], "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:32821117"], "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:GSE48137"], "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:GSE48137"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32821117", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/OTT.S251714", "sha256": "sha256:2ee544abbb15fe8838b0083d0e3d0818cc87f0b388084d6729d2356e7d9f589c", "bytes": 27468, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/OTT.S251714", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7419636", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE48137", "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=GSE48137", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE48137", "version": null, "note": "We logged into GEO database (https://www.ncbi.nlm.nih.gov/gds) to search Wilms tumor and microRNA related chips. Finally, we selected GSE57370 and GSE48137 chips, downloaded matrix file Series Matrix File (s)", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We logged into GEO database (https://www.ncbi.nlm.nih.gov/gds) to search Wilms tumor and microRNA related chips. Finally, we selected GSE57370 and GSE48137 chips, downloaded matrix file Series Matrix File (s)", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1169293", "GSM1169294", "GSM1169295", "GSM1169296", "GSM1169297", "GSM1169298", "GSM1169299", "GSM1169300", "GSM1169301", "GSM1169302", "GSM1169303", "GSM1169304", "GSM1169305", "GSM1169306", "GSM1169307", "GSM1169308", "GSM1169309", "GSM1169310", "GSM1169311", "GSM1169312", "GSM1169313", "GSM1169314", "GSM1169315", "GSM1169316", "GSM1169317", "GSM1169318", "GSM1169319", "GSM1169320", "GSM1169321", "GSM1169322", "GSM1169323", "GSM1169324", "GSM1169325", "GSM1169326", "GSM1169327", "GSM1169328", "GSM1169329", "GSM1169330", "GSM1169331", "GSM1169332", "GSM1169333", "GSM1169334", "GSM1169335", "GSM1169336", "GSM1169337", "GSM1169338", "GSM1169339", "GSM1169340", "GSM1169341", "GSM1169342", "GSM1169343", "GSM1169344", "GSM1169345", "GSM1169346", "GSM1169347", "GSM1169348", "GSM1169349", "GSM1169350", "GSM1169351", "GSM1169352", "GSM1169353", "GSM1169354", "GSM1169355", "GSM1169356", "GSM1169357", "GSM1169358", "GSM1169359", "GSM1169360", "GSM1169361", "GSM1169362", "GSM1169363", "GSM1169364", "GSM1169365", "GSM1169366", "GSM1169367", "GSM1169368", "GSM1169369", "GSM1169370", "GSM1169371", "GSM1169372", "GSM1169373", "GSM1169374", "GSM1169375", "GSM1169376", "GSM1169377", "GSM1169378", "GSM1169379", "GSM1169380", "GSM1169381", "GSM1169382", "GSM1169383", "GSM1169384", "GSM1169385", "GSM1169386", "GSM1169387", "GSM1169388", "GSM1169389", "GSM1169390", "GSM1169391", "GSM1169392", "GSM1169393", "GSM1169394"], "sample_count": 102, "group_sizes": null, "group_sizes_basis": null, "platform": "16770", "taxon": "Homo sapiens", "title": "Circulating miRNA in serum of Wilms tumor 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": "data:geo:GSE57370", "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=GSE57370", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE57370", "version": null, "note": "We logged into GEO database (https://www.ncbi.nlm.nih.gov/gds) to search Wilms tumor and microRNA related chips. Finally, we selected GSE57370 and GSE48137 chips, downloaded matrix file Series Matrix File (s)", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We logged into GEO database (https://www.ncbi.nlm.nih.gov/gds) to search Wilms tumor and microRNA related chips. Finally, we selected GSE57370 and GSE48137 chips, downloaded matrix file Series Matrix File (s)", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1381240", "GSM1381241", "GSM1381242", "GSM1381243", "GSM1381244", "GSM1381245", "GSM1381246", "GSM1381247", "GSM1381248", "GSM1381249", "GSM1381250", "GSM1381251", "GSM1381252", "GSM1381253", "GSM1381254", "GSM1381255", "GSM1381256", "GSM1381257", "GSM1381258", "GSM1381259", "GSM1381260", "GSM1381261", "GSM1381262", "GSM1381263", "GSM1381264", "GSM1381265", "GSM1381266", "GSM1381267", "GSM1381268", "GSM1381269", "GSM1381270", "GSM1381271", "GSM1381272", "GSM1381273", "GSM1381274", "GSM1381275", "GSM1381276", "GSM1381277", "GSM1381278", "GSM1381279", "GSM1381280", "GSM1381281", "GSM1381282", "GSM1381283", "GSM1381284", "GSM1381285", "GSM1381286", "GSM1381287", "GSM1381288", "GSM1381289", "GSM1381290", "GSM1381291", "GSM1381292", "GSM1381293", "GSM1381294", "GSM1381295", "GSM1381296", "GSM1381297", "GSM1381298", "GSM1381299", "GSM1381300", "GSM1381301", "GSM1381302", "GSM1381303", "GSM1381304", "GSM1381305"], "sample_count": 66, "group_sizes": null, "group_sizes_basis": null, "platform": "16770", "taxon": "Homo sapiens", "title": "miRNA expression profiles in Wilms tumor subtypes", "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:GSE66405", "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=GSE66405", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66405", "version": null, "note": "We logged into GEO database (https://www.ncbi.nlm.nih.gov/gds) to search Wilms tumor and microRNA related chips. Finally, we selected GSE57370 and GSE48137 chips, downloaded matrix file Series Matrix File (s)", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We logged into GEO database (https://www.ncbi.nlm.nih.gov/gds) to search Wilms tumor and microRNA related chips. Finally, we selected GSE57370 and GSE48137 chips, downloaded matrix file Series Matrix File (s)", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1621548", "GSM1621549", "GSM1621550", "GSM1621551", "GSM1621552", "GSM1621553", "GSM1621554", "GSM1621555", "GSM1621556", "GSM1621557", "GSM1621558", "GSM1621559", "GSM1621560", "GSM1621561", "GSM1621562", "GSM1621563", "GSM1621564", "GSM1621565", "GSM1621566", "GSM1621567", "GSM1621568", "GSM1621569", "GSM1621570", "GSM1621571", "GSM1621572", "GSM1621573", "GSM1621574", "GSM1621575", "GSM1621576", "GSM1621577", "GSM1621578", "GSM1621579"], "sample_count": 32, "group_sizes": null, "group_sizes_basis": null, "platform": "17077", "taxon": "Homo sapiens", "title": "mRNA expression profiles in Wilms tumor subtypes", "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:32821117:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5b0f5362f20af33c2ad30eb291031f522f54b71a31790f7d7086a2f9f4b9f0f6", "bytes": 882, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#T0001", "version": null, "note": "miR with Top 5 Differences of High and Low Expression in GSE57370 Chip", "structure": {"pmcid": "PMC7419636", "section_index": 16, "section_title": "WT GEO Chip Differential miR Analysis", "row_count": 13, "column_count": 5}, "table": {"label": "Table 1", "caption": "miR with Top 5 Differences of High and Low Expression in GSE57370 Chip", "rows": [["Gene Name", "logFC", "t", "P value", "B"], ["High", "", "", "", ""], ["hsa-miR-452-3P", "1.731", "4.657", "1.592E-05", "2.651"], ["hsa-miR-135b-3P", "1.377", "3.879", "2.439E-04", "0.059"], ["hsa-miR-320d", "1.654", "3.444", "9.998E-04", "−1.262"], ["hsa-miR-320c", "1.843", "3.421", "1.075E-03", "−1.330"], ["hsa-miR-320e", "1.613", "3.282", "1.648E-03", "−1.726"], ["Low", "", "", "", ""], ["hsa-miR-514", "−3.215", "−12.051", "2.373E-18", "31.254"], ["hsa-miR-215", "−4.453", "−10.716", "4.198E-16", "26.257"], ["hsa-miR-192", "−5.230", "−8.857", "7.624E-13", "18.977"], ["hsa-miR-192-3P", "−1.892", "−8.702", "1.435E-12", "18.362"], ["hsa-miR-194", "−5.713", "−8.270", "8.535E-12", "16.629"]], "row_count": 13, "column_count": 5, "numeric_cells": 50, "header_rows": 1, "locator": "section[16]/table-wrap[1]#T0001"}}, {"id": "asset:table:pmid:32821117:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1755e87a7d3201e7aad6f0eda79736bd9583d38df414cba67143b0e612bebd82", "bytes": 868, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[2]#T0002", "version": null, "note": "miR with Top 5 Differences of High and Low Expression in GSE48137 Chip", "structure": {"pmcid": "PMC7419636", "section_index": 16, "section_title": "WT GEO Chip Differential miR Analysis", "row_count": 13, "column_count": 5}, "table": {"label": "Table 2", "caption": "miR with Top 5 Differences of High and Low Expression in GSE48137 Chip", "rows": [["Gene Name", "logFC", "t", "P value", "B"], ["High", "", "", "", ""], ["hsa-miR-1225-5p", "1.192", "5.938", "8.518E-07", "5.737"], ["hsa-miR-769-3p", "1.130", "5.397", "4.499E-06", "4.165"], ["hsa-miR-642b", "1.182", "5.385", "4.661E-06", "4.132"], ["hsa-miR-3692-5P", "1.527", "5.300", "6.045E-06", "3.886"], ["hsa-miR-150", "1.938", "4.810", "2.704E-05", "2.473"], ["Low", "", "", "", ""], ["hsa-miR-514", "−1.164", "−6.555", "1.289E-07", "7.519"], ["hsa-miR-215", "−2.299", "−6.508", "1.490E-07", "7.382"], ["hsa-miR-192", "−1.421", "−5.495", "3.326E-06", "4.450"], ["hsa-miR-192-3P", "−1.023", "−5.088", "1.159E-05", "3.271"], ["hsa-miR-194", "−1.709", "−4.127", "2.086E-04", "0.554"]], "row_count": 13, "column_count": 5, "numeric_cells": 50, "header_rows": 1, "locator": "section[16]/table-wrap[2]#T0002"}}, {"id": "asset:table:pmid:32821117:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2d237c70362489116e9dfcfde42c1d9fb566a4f77cca271f2ee5bba7f0ac0d4d", "bytes": 796, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#T0003", "version": null, "note": "Relationship Between miR-30d and WT Clinical Data", "structure": {"pmcid": "PMC7419636", "section_index": 17, "section_title": "Clinical Value of miR-30d in WT Children", "row_count": 17, "column_count": 5}, "table": {"label": "Table 3", "caption": "Relationship Between miR-30d and WT Clinical Data", "rows": [["Parameter", "", "miR-30d", "P value"], ["Low Expression (n=15)", "High Expression (n=15)"], ["Age", "", "", "", "0.713"], ["", "≥2 years old (n=13)", "6", "7"], ["", "<2 years old (n=17)", "9", "8"], ["Gender", "", "", "", "0.273"], ["", "Male (n=15)", "6", "9"], ["", "Female (n=15)", "9", "6"], ["Histopathological type", "", "", "", "0.028"], ["", "Favorable (FH) (n=16)", "5", "11"], ["", "Unfavorable (UH) (n=14)", "10", "4"], ["NWTS stage", "", "", "", "0.003"], ["", "I+II (n=16)", "4", "12"], ["", "III+IV (n=14)", "11", "3"], ["Lymphatic metastasis", "", "", "", "0.031"], ["", "Transferred (n=7)", "6", "1"], ["", "Non-transferred (n=23)", "9", "14"]], "row_count": 17, "column_count": 5, "numeric_cells": 38, "header_rows": 2, "locator": "section[17]/table-wrap[1]#T0003"}}], "gaps": ["asset:data:geo:GSE48137 not downloaded", "asset:data:geo:GSE48137 licence not read", "asset:data:geo:GSE57370 not downloaded", "asset:data:geo:GSE57370 licence not read", "asset:data:geo:GSE66405 not downloaded", "asset:data:geo:GSE66405 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The processed data were analyzed for differences using limma 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": "ANOVA"}}, {"id": "method-3", "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE57370", "GSE48137", "GSE66405"], "resolved_accessions": ["GSE57370", "GSE48137", "GSE66405"], "statements": ["We logged into GEO database (https://www.ncbi.nlm.nih.gov/gds) to search Wilms tumor and microRNA related chips. Finally, we selected GSE57370 and GSE48137 chips, downloaded matrix file Series Matrix File (s)"], "basis": "The paper names GSE57370, GSE48137, GSE66405 in GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:32821117", "data:geo:GSE48137", "asset:table:pmid:32821117:1", "asset:table:pmid:32821117:2", "asset:table:pmid:32821117:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE48137"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:58Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 23773, "completion_tokens": 1894, "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:32821117", "type": "paper", "label": "pmid:32821117"}, {"id": "source:pmid:32821117", "type": "manuscript", "label": "PMID 32821117 full text"}, {"id": "data:geo:GSE48137", "type": "dataset", "label": "GEO GSE48137"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32821117", "type": "paper", "label": "pmid:32821117"}, {"id": "source:pmid:32821117", "type": "manuscript", "label": "PMID 32821117 full text"}, {"id": "data:geo:GSE48137", "type": "dataset", "label": "GEO GSE48137"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32821117", "type": "extraction", "used": ["source:pmid:32821117"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE48137", "type": "accession_resolution", "used": ["data:geo:GSE48137"], "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:32821117", "parent_hash": "sha256:fc27a7da2be1ba0842cf7a5268e3164104af8d40a048807790b1c7bd2726793c", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE48137 licence not read", "asset:data:geo:GSE48137 not downloaded", "asset:data:geo:GSE57370 licence not read", "asset:data:geo:GSE57370 not downloaded", "asset:data:geo:GSE66405 licence not read", "asset:data:geo:GSE66405 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": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["miR-30d Induced Apoptosis by Targeting Sox4 to Inhibit the Proliferati", "e the proliferation, invasion, migration and apoptosis of cells. RESULTS: We found that miR-30d was", "oliferation, invasion, migration and induced apoptosis of C64 and WiT49 cells. In addition, Sox4 co", "C64 and WiT49 induced by miR-30d and induce apoptosis. CONCLUSION: miR-30d is poorly expressed in"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"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": ["miR-30d with Sox4 was confirmed by qRT-PCR, Western blot and luciferase assay, respectively. CCK-8, T"], "order_basis": "paper_text_order:857", "id": "assay:2"}, {"role": "data_generation", "definition_id": "flow_cytometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["se assay, respectively. CCK-8, Transwell and flow cytometry were applied to determine the proliferation,"], "order_basis": "paper_text_order:926", "id": "assay:3"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The processed data were analyzed for differences using limma package"], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T00:32:48+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}}}