{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41168787", "kind": "science-record", "revision": 4, "content_hash": "sha256:adf8802adf6e97f163f1092424b00b4fe01a68316267d6bd172e976f7106525f", "created_at": "2026-11-01T20:31:12Z", "updated_at": "2026-11-01T22:57:23Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "The role of TEAD4 gene in the Hippo signaling pathway in triple-negative breast cancer and targeted therapy strategies.", "doi": "10.1186/s12920-025-02245-x", "pmid": "41168787", "authors": ["Xueliang Zhang", "Tao Wang", "Xiaowen Lian", "Changsheng Wei", "Dong Yan", "Yan Liang"], "journal": "BMC medical genomics", "year": 2025, "abstract": "BACKGROUND: Triple-negative breast cancer (TNBC) is an aggressive subtype with poor prognosis and limited targeted therapies. The Hippo signaling pathway, critical in tumor progression, may harbor key genes influencing TNBC behavior. However, the specific genes and their clinical significance remain unclear.\nMETHODS: We analyzed the GSE45827 dataset from the GEO database using differential gene expression analysis (DEG) and weighted gene co-expression network analysis (WGCNA) to identify TNBC-related genes. We enriched Hippo pathway-related genes from the MsigDB database and literature to identify candidate genes (HRGs) that may affect TNBC progression. The Boruta algorithm further screened for core genes, which were validated by immunohistochemistry in TNBC and other breast cancer tissues. Finally, we explored the biological and pharmacological significance of the target through drug prediction, molecular docking, molecular dynamics simulations, and in vitro experiments.\nRESULTS: DEG analysis identified 2,888 differentially expressed genes, and WGCNA yielded 276 TNBC-associated genes. Intersection analysis with 70 hypoxia-related genes (HRGs) revealed four key genes: TEAD4, WWTR1, AREG, and SOX11. TEAD4 was confirmed as the central gene influencing TNBC progression. Immunohistochemical results showed strong TEAD4 expression in TNBC tissues, with negligible expression in adjacent normal tissues or other breast cancer subtypes. Drug prediction and molecular docking identified irinotecan as a potential TEAD4-targeting agent. Molecular dynamics simulations confirmed the stable binding and favorable dynamics of the irinotecan-TEAD4 complex. Both TEAD4 knockdown and irinotecan treatment significantly suppressed TNBC cell migration and invasion. The combination of TEAD4 knockout and irinotecan produced a more pronounced inhibitory effect, underscoring the therapeutic potential of targeting TEAD4 in TNBC.\nCONCLUSIONS: Through comprehensive analysis, we identified TEAD4 as a key gene in TNBC with high expression specificity. Irinotecan may be a potential targeted drug for TEAD4, offering a new therapeutic strategy for TNBC and potentially improving patient outcomes. Further experimental verification is required.", "claims": [{"id": "claim-method", "statement": "To identify genes with significant expression differences in TNBC, we performed differential gene expression analysis using the DESeq2 package (v1.38.3) in R [13].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41168787", "locator": "sections[3] \"Data source and preprocessing\" paragraph 2", "quote": "To identify genes with significant expression differences in TNBC, we performed differential gene expression analysis using the DESeq2 package (v1.38.3) in R [13]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The partial datasets generated and/or analyzed during this research have been included in this published article. The remaining data can be provided by the corresponding author upon reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41168787", "locator": "sections[36] \"notes\" paragraph 1", "quote": "The partial datasets generated and/or analyzed during this research have been included in this published article. The remaining data can be provided by the corresponding author upon reasonable request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "DEG analysis identified 2,888 differentially expressed genes.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41168787", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "DEG analysis identified 2,888 differentially expressed genes, and WGCNA yielded 276 TNBC-associated genes."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "DEG analysis identified 2,888 differentially expressed genes.", "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:41168787"], "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:GSE38959"], "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:GSE38959"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41168787", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12920-025-02245-x", "sha256": "sha256:a119f9277714dcc53a249e32ca3325cfdbdc0ce643559a249e38552f58d745c7", "bytes": 45617, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12920-025-02245-x", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12573850", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE38959", "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=GSE38959", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE38959", "version": null, "note": "The partial datasets generated and/or analyzed during this research have been included in this published article. The remaining data can be provided by the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The partial datasets generated and/or analyzed during this research have been included in this published article. The remaining data can be provided by the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM952871", "GSM952872", "GSM952873", "GSM952874", "GSM952875", "GSM952876", "GSM952877", "GSM952878", "GSM952879", "GSM952880", "GSM952881", "GSM952882", "GSM952883", "GSM952884", "GSM952885", "GSM952886", "GSM952887", "GSM952888", "GSM952889", "GSM952890", "GSM952891", "GSM952892", "GSM952893", "GSM952894", "GSM952895", "GSM952896", "GSM952897", "GSM952898", "GSM952899", "GSM952900", "GSM952901", "GSM952902", "GSM952903", "GSM952904", "GSM952905", "GSM952906", "GSM952907", "GSM952908", "GSM952909", "GSM952910", "GSM952911", "GSM952912", "GSM952913", "GSM952914", "GSM952915", "GSM952916", "GSM952917"], "sample_count": 47, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "Gene expression profiling of triple negative breast cancer, normal ductal cells, and normal tissues", "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:GSE45827", "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=GSE45827", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE45827", "version": null, "note": "The partial datasets generated and/or analyzed during this research have been included in this published article. The remaining data can be provided by the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The partial datasets generated and/or analyzed during this research have been included in this published article. The remaining data can be provided by the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1116084", "GSM1116085", "GSM1116086", "GSM1116087", "GSM1116088", "GSM1116089", "GSM1116090", "GSM1116091", "GSM1116092", "GSM1116093", "GSM1116094", "GSM1116095", "GSM1116096", "GSM1116097", "GSM1116098", "GSM1116099", "GSM1116100", "GSM1116101", "GSM1116102", "GSM1116103", "GSM1116104", "GSM1116105", "GSM1116106", "GSM1116107", "GSM1116108", "GSM1116109", "GSM1116110", "GSM1116111", "GSM1116112", "GSM1116113", "GSM1116114", "GSM1116115", "GSM1116116", "GSM1116117", "GSM1116118", "GSM1116119", "GSM1116120", "GSM1116121", "GSM1116122", "GSM1116123", "GSM1116124", "GSM1116125", "GSM1116126", "GSM1116127", "GSM1116128", "GSM1116129", "GSM1116130", "GSM1116131", "GSM1116132", "GSM1116133", "GSM1116134", "GSM1116135", "GSM1116136", "GSM1116137", "GSM1116138", "GSM1116139", "GSM1116140", "GSM1116141", "GSM1116142", "GSM1116143", "GSM1116144", "GSM1116145", "GSM1116146", "GSM1116147", "GSM1116148", "GSM1116149", "GSM1116150", "GSM1116151", "GSM1116152", "GSM1116153", "GSM1116154", "GSM1116155", "GSM1116156", "GSM1116157", "GSM1116158", "GSM1116159", "GSM1116160", "GSM1116161", "GSM1116162", "GSM1116163", "GSM1116164", "GSM1116165", "GSM1116166", "GSM1116167", "GSM1116168", "GSM1116169", "GSM1116170", "GSM1116171", "GSM1116172", "GSM1116173", "GSM1116174", "GSM1116175", "GSM1116176", "GSM1116177", "GSM1116178", "GSM1116179", "GSM1116180", "GSM1116181", "GSM1116182", "GSM1116183", "GSM1116184", "GSM1116185", "GSM1116186", "GSM1116187", "GSM1116188", "GSM1116189", "GSM1116190", "GSM1116191", "GSM1116192", "GSM1116193", "GSM1116194", "GSM1116195", "GSM1116196", "GSM1116197", "GSM1116198", "GSM1116199", "GSM1116200", "GSM1116201", "GSM1116202", "GSM1116203", "GSM1116204", "GSM1116205", "GSM1116206", "GSM1116207", "GSM1116208", "GSM1116209", "GSM1116210", "GSM1116211", "GSM1116212", "GSM1116213", "GSM1116214", "GSM1116215", "GSM1116216", "GSM1116217", "GSM1116218", "GSM1116219", "GSM1116220", "GSM1116221", "GSM1116222", "GSM1116223", "GSM1116224", "GSM1116225", "GSM1116226", "GSM1116227", "GSM1116228", "GSM1116229", "GSM1116230", "GSM1116231", "GSM1116232", "GSM1116233", "GSM1116234", "GSM1116235", "GSM1116236", "GSM1116237", "GSM1116238"], "sample_count": 155, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from Breast cancer 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:GSE53752", "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=GSE53752", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53752", "version": null, "note": "The partial datasets generated and/or analyzed during this research have been included in this published article. The remaining data can be provided by the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The partial datasets generated and/or analyzed during this research have been included in this published article. The remaining data can be provided by the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1299990", "GSM1299991", "GSM1299992", "GSM1299993", "GSM1299994", "GSM1299995", "GSM1299996", "GSM1299997", "GSM1299998", "GSM1299999", "GSM1300000", "GSM1300001", "GSM1300002", "GSM1300003", "GSM1300004", "GSM1300005", "GSM1300006", "GSM1300007", "GSM1300008", "GSM1300009", "GSM1300010", "GSM1300011", "GSM1300012", "GSM1300013", "GSM1300014", "GSM838826", "GSM838827", "GSM838828", "GSM838829", "GSM838830", "GSM838831", "GSM838832", "GSM838833", "GSM838834", "GSM838835", "GSM838836", "GSM838837", "GSM838838", "GSM838839", "GSM838840", "GSM838841", "GSM838842", "GSM838843", "GSM838844", "GSM838845", "GSM838846", "GSM838847", "GSM838848", "GSM838849", "GSM838850", "GSM838851", "GSM838852", "GSM838853", "GSM838854", "GSM838855", "GSM838856", "GSM838857", "GSM838858", "GSM838859", "GSM838860", "GSM838861", "GSM838862", "GSM838863", "GSM838864", "GSM838865", "GSM838866", "GSM838867", "GSM838868", "GSM838869", "GSM838870", "GSM838871", "GSM838872", "GSM838873", "GSM838874", "GSM838875", "GSM838876"], "sample_count": 76, "group_sizes": null, "group_sizes_basis": null, "platform": "7264", "taxon": "Homo sapiens", "title": "Molecular characteristics and metastasis predictor genes of triple-negative breast cancer (II)", "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:GSE65194", "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=GSE65194", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE65194", "version": null, "note": "The partial datasets generated and/or analyzed during this research have been included in this published article. The remaining data can be provided by the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The partial datasets generated and/or analyzed during this research have been included in this published article. The remaining data can be provided by the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1588970", "GSM1588971", "GSM1588972", "GSM1588973", "GSM1588974", "GSM1588975", "GSM1588976", "GSM1588977", "GSM1588978", "GSM1588979", "GSM1588980", "GSM1588981", "GSM1588982", "GSM1588983", "GSM1588984", "GSM1588985", "GSM1588986", "GSM1588987", "GSM1588988", "GSM1588989", "GSM1588990", "GSM1588991", "GSM1588992", "GSM1588993", "GSM1588994", "GSM1588995", "GSM1588996", "GSM1588997", "GSM1588998", "GSM1588999", "GSM1589000", "GSM1589001", "GSM1589002", "GSM1589003", "GSM1589004", "GSM1589005", "GSM1589006", "GSM1589007", "GSM1589008", "GSM1589009", "GSM1589010", "GSM1589011", "GSM1589012", "GSM1589013", "GSM1589014", "GSM1589015", "GSM1589016", "GSM1589017", "GSM1589018", "GSM1589019", "GSM1589020", "GSM1589021", "GSM1589022", "GSM1589023", "GSM1589024", "GSM1589025", "GSM1589026", "GSM1589027", "GSM1589028", "GSM1589029", "GSM1589030", "GSM1589031", "GSM1589032", "GSM1589033", "GSM1589034", "GSM1589035", "GSM1589036", "GSM1589037", "GSM1589038", "GSM1589039", "GSM1589040", "GSM1589041", "GSM1589042", "GSM1589043", "GSM1589044", "GSM1589045", "GSM1589046", "GSM1589047", "GSM1589048", "GSM1589049", "GSM1589050", "GSM1589051", "GSM1589052", "GSM1589053", "GSM1589054", "GSM1589055", "GSM1589056", "GSM1589057", "GSM1589058", "GSM1589059", "GSM1589060", "GSM1589061", "GSM1589062", "GSM1589063", "GSM1589064", "GSM1589065", "GSM1589066", "GSM1589067", "GSM1589068", "GSM1589069", "GSM1589070", "GSM1589071", "GSM1589072", "GSM1589073", "GSM1589074", "GSM1589075", "GSM1589076", "GSM1589077", "GSM1589078", "GSM1589079", "GSM1589080", "GSM1589081", "GSM1589082", "GSM1589083", "GSM1589084", "GSM1589085", "GSM1589086", "GSM1589087", "GSM1589088", "GSM1589089", "GSM1589090", "GSM1589091", "GSM1589092", "GSM1589093", "GSM1589094", "GSM1589095", "GSM1589097", "GSM1589098", "GSM1589099", "GSM1589101", "GSM1589103", "GSM1589105", "GSM1589107", "GSM1589109", "GSM1589110", "GSM1589111", "GSM1589112", "GSM1589113", "GSM1589114", "GSM1589115", "GSM1589116", "GSM1589117", "GSM1589118", "GSM1589119", "GSM1589120", "GSM1589121", "GSM1589122", "GSM1589123", "GSM1589124", "GSM1589125", "GSM1589126", "GSM1589127", "GSM1589128", "GSM1589129", "GSM1589130", "GSM1589131", "GSM1589132", "GSM1589133", "GSM1589134", "GSM1589135", "GSM1589136", "GSM1589137", "GSM1589138", "GSM1589139", "GSM1589140", "GSM1589141", "GSM1589142", "GSM1589143", "GSM1589144", "GSM1589145", "GSM1589146", "GSM1589147", "GSM1589148", "GSM1589149", "GSM1589150", "GSM1589151", "GSM1589152", "GSM1589153"], "sample_count": 178, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression profiling of breast cancer samples from Institut Curie (Maire cohort) --Affy CDF", "resolution_checked_at": "2026-11-01T11:38:18Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE38959 not downloaded", "asset:data:geo:GSE38959 licence not read", "asset:data:geo:GSE45827 not downloaded", "asset:data:geo:GSE45827 licence not read", "asset:data:geo:GSE53752 not downloaded", "asset:data:geo:GSE53752 licence not read", "asset:data:geo:GSE65194 not downloaded", "asset:data:geo:GSE65194 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "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": "To identify genes with significant expression differences in TNBC, we performed differential gene expression analysis using the DESeq2 package (v1.38.3) in R [13]."}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["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: deseq2."}, "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": ["GSE45827", "GSE53752", "GSE65194", "GSE38959"], "resolved_accessions": ["GSE45827", "GSE53752", "GSE65194", "GSE38959"], "statements": ["The partial datasets generated and/or analyzed during this research have been included in this published article. The remaining data can be provided by the corresponding author upon reasonable request."], "basis": "The paper names GSE45827, GSE53752, GSE65194, GSE38959 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:41168787", "data:geo:GSE38959"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE38959"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:04:31Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 12361, "completion_tokens": 1737, "cached_tokens": 128}}, "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:41168787", "type": "paper", "label": "pmid:41168787"}, {"id": "source:pmid:41168787", "type": "manuscript", "label": "PMID 41168787 full text"}, {"id": "data:geo:GSE38959", "type": "dataset", "label": "GEO GSE38959"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41168787", "type": "paper", "label": "pmid:41168787"}, {"id": "source:pmid:41168787", "type": "manuscript", "label": "PMID 41168787 full text"}, {"id": "data:geo:GSE38959", "type": "dataset", "label": "GEO GSE38959"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41168787", "type": "extraction", "used": ["source:pmid:41168787"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE38959", "type": "accession_resolution", "used": ["data:geo:GSE38959"], "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:41168787", "parent_hash": "sha256:f32809fd23010d0e0f9d3a6bc5333ae87c003707f118d72cb7123abe62010982", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE38959 licence not read", "asset:data:geo:GSE38959 not downloaded", "asset:data:geo:GSE45827 licence not read", "asset:data:geo:GSE45827 not downloaded", "asset:data:geo:GSE53752 licence not read", "asset:data:geo:GSE53752 not downloaded", "asset:data:geo:GSE65194 licence not read", "asset:data:geo:GSE65194 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ened for core genes, which were validated by immunohistochemistry in TNBC and other breast cancer tissues. Fin", "e central gene influencing TNBC progression. Immunohistochemical results showed strong TEAD4 expression in TN"], "order_basis": "paper_text_order:815", "id": "assay:1"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["of the irinotecan-TEAD4 complex. Both TEAD4 knockdown and irinotecan treatment significantly suppr", "Methods Cell culture and transfection The human TNBC cell line MDA-MB-231 was obta", "with 5% CO₂. For TEAD4 knockdown, cells were transfected with a specific small interfering RNA (siRNA", "UCAUUTT-3’si-NC: 5’-UUCUCCGAACGUGUCACGUTT-3’ Transfection was performed using Lipofectamine 3000 reage"], "order_basis": "paper_text_order:1752", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["n Type Culture Collection (ATCC). Cells were cultured in Dulbecco’s Modified Eagle Medium (DMEM, HyCl"], "order_basis": "paper_text_order:2467", "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": ["To identify genes with significant expression differences in TNBC, we performed differential gene expression analysis using the DESeq2 package (v1.38.3) in R [13]."], "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":"2026-11-04T02:37:22+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}}}