{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36204232", "kind": "science-record", "revision": 5, "content_hash": "sha256:33cb1ecd1dffae09a4d1b93f675ed11f8254a8a3ceb8644130c2596f325c8f04", "created_at": "2026-11-01T18:15:31Z", "updated_at": "2026-11-01T22:50:15Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatics and network-based screening and discovery of potential molecular targets and small molecular drugs for breast cancer.", "doi": "10.3389/fphar.2022.942126", "pmid": "36204232", "authors": ["Md Shahin Alam", "Adiba Sultana", "Hongyang Sun", "Jin Wu", "Fanfan Guo", "Qing Li", "Haigang Ren", "Zongbing Hao", "Yi Zhang", "Guanghui Wang"], "journal": "Frontiers in pharmacology", "year": 2022, "abstract": "Accurate identification of molecular targets of disease plays an important role in diagnosis, prognosis, and therapies. Breast cancer (BC) is one of the most common malignant cancers in women worldwide. Thus, the objective of this study was to accurately identify a set of molecular targets and small molecular drugs that might be effective for BC diagnosis, prognosis, and therapies, by using existing bioinformatics and network-based approaches. Nine gene expression profiles (GSE54002, GSE29431, GSE124646, GSE42568, GSE45827, GSE10810, GSE65216, GSE36295, and GSE109169) collected from the Gene Expression Omnibus (GEO) database were used for bioinformatics analysis in this study. Two packages, LIMMA and clusterProfiler, in R were used to identify overlapping differential expressed genes (oDEGs) and significant GO and KEGG enrichment terms. We constructed a PPI (protein-protein interaction) network through the STRING database and identified eight key genes (KGs) EGFR, FN1, EZH2, MET, CDK1, AURKA, TOP2A, and BIRC5 by using six topological measures, betweenness, closeness, eccentricity, degree, MCC, and MNC, in the Analyze Network tool in Cytoscape. Three online databases GSCALite, Network Analyst, and GEPIA were used to analyze drug enrichment, regulatory interaction networks, and gene expression levels of KGs. We checked the prognostic power of KGs through the prediction model using the popular machine learning algorithm support vector machine (SVM). We suggested four TFs (TP63, MYC, SOX2, and KDM5B) and four miRNAs (hsa-mir-16-5p, hsa-mir-34a-5p, hsa-mir-1-3p, and hsa-mir-23b-3p) as key transcriptional and posttranscriptional regulators of KGs. Finally, we proposed 16 candidate repurposing drugs YM201636, masitinib, SB590885, GSK1070916, GSK2126458, ZSTK474, dasatinib, fedratinib, dabrafenib, methotrexate, trametinib, tubastatin A, BIX02189, CP466722, afatinib, and belinostat for BC through molecular docking analysis. Using BC cell lines, we validated that masitinib inhibits the mTOR signaling pathway and induces apoptotic cell death. Therefore, the proposed results might play an effective role in the treatment of BC patients.", "claims": [{"id": "claim-method", "statement": "The moderated T-statistics and the Benjamini and Hochberg false discovery rate method were used to calculate the p value and adjusted p value (adj.P.Val) and logFC (fold change), accordingly.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36204232", "locator": "sections[4] \"Data processing and differentially expressed gene identification\" paragraph 2", "quote": "The moderated T-statistics and the Benjamini and Hochberg false discovery rate method were used to calculate the p value and adjusted p value (adj.P.Val) and logFC (fold change), accordingly."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36204232", "locator": "sections[26] \"Data availability statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using BC cell lines, we validated that masitinib inhibits the mTOR signaling pathway and induces apoptotic cell death.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36204232", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Using BC cell lines, we validated that masitinib inhibits the mTOR signaling pathway and induces apoptotic cell death."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Using BC cell lines, we validated that masitinib inhibits the mTOR signaling pathway and induces apoptotic cell death.", "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:36204232"], "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:GSE10810"], "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": {"fdr_threshold": "Benjamini and Hochberg false discovery rate adjustment"}, "inputs": ["data:geo:GSE10810"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36204232", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fphar.2022.942126", "sha256": "sha256:6b54d0b25afaab6194e6b0b106d3849eaa36094c94282b19f88d18a84a98d8bc", "bytes": 52758, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fphar.2022.942126", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9531711", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE10810", "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=GSE10810", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10810", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM272923", "GSM272924", "GSM272925", "GSM272926", "GSM272927", "GSM272928", "GSM272929", "GSM272930", "GSM272931", "GSM272932", "GSM272933", "GSM272934", "GSM272935", "GSM272936", "GSM272937", "GSM272938", "GSM272939", "GSM272940", "GSM272941", "GSM272942", "GSM272943", "GSM272944", "GSM272945", "GSM272946", "GSM272947", "GSM272948", "GSM272949", "GSM272950", "GSM272951", "GSM272952", "GSM272953", "GSM272954", "GSM272955", "GSM272956", "GSM272957", "GSM272958", "GSM272959", "GSM272960", "GSM272961", "GSM272962", "GSM272963", "GSM272964", "GSM272965", "GSM272966", "GSM272967", "GSM272968", "GSM272969", "GSM272970", "GSM272971", "GSM272972", "GSM272973", "GSM272974", "GSM272975", "GSM272976", "GSM272977", "GSM272978", "GSM272979", "GSM272980"], "sample_count": 58, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression signatures in breast cancer distinguish phenotype charact., histological subtypes, and tumor invasivness", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE109169", "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=GSE109169", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE109169", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2934481", "GSM2934482", "GSM2934483", "GSM2934484", "GSM2934485", "GSM2934486", "GSM2934487", "GSM2934488", "GSM2934489", "GSM2934490", "GSM2934491", "GSM2934492", "GSM2934493", "GSM2934494", "GSM2934495", "GSM2934496", "GSM2934497", "GSM2934498", "GSM2934499", "GSM2934500", "GSM2934501", "GSM2934502", "GSM2934503", "GSM2934504", "GSM2934505", "GSM2934506", "GSM2934507", "GSM2934508", "GSM2934509", "GSM2934510", "GSM2934511", "GSM2934512", "GSM2934513", "GSM2934514", "GSM2934515", "GSM2934516", "GSM2934517", "GSM2934518", "GSM2934519", "GSM2934520", "GSM2934521", "GSM2934522", "GSM2934523", "GSM2934524", "GSM2934525", "GSM2934526", "GSM2934527", "GSM2934528", "GSM2934529", "GSM2934530"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "5175", "taxon": "Homo sapiens", "title": "Expression data from breast cancer tissues and adjacent 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:GSE124646", "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=GSE124646", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE124646", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3538397", "GSM3538398", "GSM3538399", "GSM3538400", "GSM3538401", "GSM3538402", "GSM3538403", "GSM3538404", "GSM3538405", "GSM3538406", "GSM3538407", "GSM3538408", "GSM3538409", "GSM3538410", "GSM3538411", "GSM3538412", "GSM3538413", "GSM3538414", "GSM3538415", "GSM3538416", "GSM3538417", "GSM3538418", "GSM3538419", "GSM3538420", "GSM3538421", "GSM3538422", "GSM3538423", "GSM3538424", "GSM3538425", "GSM3538426", "GSM3538427", "GSM3538428", "GSM3538429", "GSM3538430", "GSM3538431", "GSM3538432", "GSM3538433", "GSM3538434", "GSM3538435", "GSM3538436", "GSM3538437", "GSM3538438", "GSM3538439", "GSM3538440", "GSM3538441", "GSM3538442", "GSM3538443", "GSM3538444", "GSM3538445", "GSM3538446", "GSM3538447", "GSM3538448", "GSM3538449", "GSM3538450", "GSM3538451", "GSM3538452", "GSM3538453", "GSM3538454", "GSM3538455", "GSM3538456", "GSM3538457", "GSM3538458", "GSM3538459", "GSM3538460", "GSM3538461", "GSM3538462", "GSM3538463", "GSM3538464", "GSM3538465", "GSM3538466", "GSM3538467", "GSM3538468", "GSM3538469", "GSM3538470", "GSM3538471", "GSM3538472", "GSM3538473", "GSM3538474", "GSM3538475", "GSM3538476", "GSM3538477", "GSM3538478", "GSM3538479", "GSM3538480", "GSM3538481", "GSM3538482", "GSM3538483", "GSM3538484", "GSM3538485", "GSM3538486", "GSM3538487", "GSM3538488", "GSM3538489", "GSM3538490", "GSM3538491", "GSM3538492", "GSM3538493", "GSM3538494", "GSM3538495", "GSM3538496"], "sample_count": 100, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Breast cancer and normal breast tissue samples to estimate the effect of contamination of breast cancer samples with normal breast tissue", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE26964", "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=GSE26964", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE26964", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM663722", "GSM663723", "GSM663724", "GSM663725", "GSM663726", "GSM663727", "GSM663728", "GSM663729", "GSM663730", "GSM663731", "GSM663732", "GSM663733", "GSM663734", "GSM663735"], "sample_count": 14, "group_sizes": null, "group_sizes_basis": null, "platform": "8469", "taxon": "Mus musculus; Homo sapiens; Rattus norvegicus", "title": "Altered expression of microRNAs in bone metastasis compared with human prostate cancer", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE29431", "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=GSE29431", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29431", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM728611", "GSM728612", "GSM728613", "GSM728614", "GSM728615", "GSM728616", "GSM728617", "GSM728618", "GSM728619", "GSM728620", "GSM728621", "GSM728622", "GSM728623", "GSM728624", "GSM728625", "GSM728626", "GSM728627", "GSM728628", "GSM728629", "GSM728630", "GSM728631", "GSM728632", "GSM728633", "GSM728634", "GSM728635", "GSM728636", "GSM728637", "GSM728638", "GSM728639", "GSM728640", "GSM728641", "GSM728642", "GSM728643", "GSM728644", "GSM728645", "GSM728646", "GSM728647", "GSM728648", "GSM728649", "GSM728650", "GSM728651", "GSM728652", "GSM728653", "GSM728654", "GSM728655", "GSM728656", "GSM728657", "GSM728658", "GSM728659", "GSM728660", "GSM728661", "GSM728662", "GSM728663", "GSM728664", "GSM728665", "GSM728666", "GSM728667", "GSM728668", "GSM728669", "GSM728670", "GSM728671", "GSM728672", "GSM728673", "GSM728674", "GSM728675", "GSM728676"], "sample_count": 66, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Identifying breast cancer biomarkers", "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:GSE36295", "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=GSE36295", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE36295", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM886560", "GSM886561", "GSM886562", "GSM886563", "GSM886564", "GSM886565", "GSM886566", "GSM886567", "GSM886568", "GSM886569", "GSM886570", "GSM886571", "GSM886572", "GSM886573", "GSM886574", "GSM886575", "GSM886576", "GSM886577", "GSM886578", "GSM886579", "GSM886580", "GSM886581", "GSM886582", "GSM886583", "GSM886584", "GSM886585", "GSM886586", "GSM886587", "GSM886588", "GSM886589", "GSM886590", "GSM886591", "GSM886592", "GSM886593", "GSM886594", "GSM886595", "GSM886596", "GSM886597", "GSM886598", "GSM886599", "GSM886600", "GSM886601", "GSM886602", "GSM886603", "GSM886604", "GSM886605", "GSM886606", "GSM886607", "GSM886608", "GSM886609"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Transcriptomic analysis of breast cancer", "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:GSE42568", "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=GSE42568", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE42568", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1045191", "GSM1045192", "GSM1045193", "GSM1045194", "GSM1045195", "GSM1045196", "GSM1045197", "GSM1045198", "GSM1045199", "GSM1045200", "GSM1045201", "GSM1045202", "GSM1045203", "GSM1045204", "GSM1045205", "GSM1045206", "GSM1045207", "GSM1045208", "GSM1045209", "GSM1045210", "GSM1045211", "GSM1045212", "GSM1045213", "GSM1045214", "GSM1045215", "GSM1045216", "GSM1045217", "GSM1045218", "GSM1045219", "GSM1045220", "GSM1045221", "GSM1045222", "GSM1045223", "GSM1045224", "GSM1045225", "GSM1045226", "GSM1045227", "GSM1045228", "GSM1045229", "GSM1045230", "GSM1045231", "GSM1045232", "GSM1045233", "GSM1045234", "GSM1045235", "GSM1045236", "GSM1045237", "GSM1045238", "GSM1045239", "GSM1045240", "GSM1045241", "GSM1045242", "GSM1045243", "GSM1045244", "GSM1045245", "GSM1045246", "GSM1045247", "GSM1045248", "GSM1045249", "GSM1045250", "GSM1045251", "GSM1045252", "GSM1045253", "GSM1045254", "GSM1045255", "GSM1045256", "GSM1045257", "GSM1045258", "GSM1045259", "GSM1045260", "GSM1045261", "GSM1045262", "GSM1045263", "GSM1045264", "GSM1045265", "GSM1045266", "GSM1045267", "GSM1045268", "GSM1045269", "GSM1045270", "GSM1045271", "GSM1045272", "GSM1045273", "GSM1045274", "GSM1045275", "GSM1045276", "GSM1045277", "GSM1045278", "GSM1045279", "GSM1045280", "GSM1045281", "GSM1045282", "GSM1045283", "GSM1045284", "GSM1045285", "GSM1045286", "GSM1045287", "GSM1045288", "GSM1045289", "GSM1045290", "GSM1045291", "GSM1045292", "GSM1045293", "GSM1045294", "GSM1045295", "GSM1045296", "GSM1045297", "GSM1045298", "GSM1045299", "GSM1045300", "GSM1045301", "GSM1045302", "GSM1045303", "GSM1045304", "GSM1045305", "GSM1045306", "GSM1045307", "GSM1045308", "GSM1045309", "GSM1045310", "GSM1045311"], "sample_count": 121, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Breast Cancer Gene Expression Analysis", "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": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "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:GSE54002", "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=GSE54002", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE54002", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1305324", "GSM1305325", "GSM1305326", "GSM1305327", "GSM1305328", "GSM1305329", "GSM1305330", "GSM1305331", "GSM1305332", "GSM1305333", "GSM1305334", "GSM1305335", "GSM1305336", "GSM1305337", "GSM1305338", "GSM1305339", "GSM1305340", "GSM1305341", "GSM1305342", "GSM1305343", "GSM1305344", "GSM1305345", "GSM1305346", "GSM1305347", "GSM1305348", "GSM1305349", "GSM1305350", "GSM1305351", "GSM1305352", "GSM1305353", "GSM1305354", "GSM1305355", "GSM1305356", "GSM1305357", "GSM1305358", "GSM1305359", "GSM1305360", "GSM1305361", "GSM1305362", "GSM1305363", "GSM1305364", "GSM1305365", "GSM1305366", "GSM1305367", "GSM1305368", "GSM1305369", "GSM1305370", "GSM1305371", "GSM1305372", "GSM1305373", "GSM1305374", "GSM1305375", "GSM1305376", "GSM1305377", "GSM1305378", "GSM1305379", "GSM1305380", "GSM1305381", "GSM1305382", "GSM1305383", "GSM1305384", "GSM1305385", "GSM1305386", "GSM1305387", "GSM1305388", "GSM1305389", "GSM1305390", "GSM1305391", "GSM1305392", "GSM1305393", "GSM1305394", "GSM1305395", "GSM1305396", "GSM1305397", "GSM1305398", "GSM1305399", "GSM1305400", "GSM1305401", "GSM1305402", "GSM1305403", "GSM1305404", "GSM1305405", "GSM1305406", "GSM1305407", "GSM1305408", "GSM1305409", "GSM1305410", "GSM1305411", "GSM1305412", "GSM1305413", "GSM1305414", "GSM1305415", "GSM1305416", "GSM1305417", "GSM1305418", "GSM1305419", "GSM1305420", "GSM1305421", "GSM1305422", "GSM1305423", "GSM1305424", "GSM1305425", "GSM1305426", "GSM1305427", "GSM1305428", "GSM1305429", "GSM1305430", "GSM1305431", "GSM1305432", "GSM1305433", "GSM1305434", "GSM1305435", "GSM1305436", "GSM1305437", "GSM1305438", "GSM1305439", "GSM1305440", "GSM1305441", "GSM1305442", "GSM1305443", "GSM1305444", "GSM1305445", "GSM1305446", "GSM1305447", "GSM1305448", "GSM1305449", "GSM1305450", "GSM1305451", "GSM1305452", "GSM1305453", "GSM1305454", "GSM1305455", "GSM1305456", "GSM1305457", "GSM1305458", "GSM1305459", "GSM1305460", "GSM1305461", "GSM1305462", "GSM1305463", "GSM1305464", "GSM1305465", "GSM1305466", "GSM1305467", "GSM1305468", "GSM1305469", "GSM1305470", "GSM1305471", "GSM1305472", "GSM1305473", "GSM1305474", "GSM1305475", "GSM1305476", "GSM1305477", "GSM1305478", "GSM1305479", "GSM1305480", "GSM1305481", "GSM1305482", "GSM1305483", "GSM1305484", "GSM1305485", "GSM1305486", "GSM1305487", "GSM1305488", "GSM1305489", "GSM1305490", "GSM1305491", "GSM1305492", "GSM1305493", "GSM1305494", "GSM1305495", "GSM1305496", "GSM1305497", "GSM1305498", "GSM1305499", "GSM1305500", "GSM1305501", "GSM1305502", "GSM1305503", "GSM1305504", "GSM1305505", "GSM1305506", "GSM1305507", "GSM1305508", "GSM1305509", "GSM1305510", "GSM1305511", "GSM1305512", "GSM1305513", "GSM1305514", "GSM1305515", "GSM1305516", "GSM1305517", "GSM1305518", "GSM1305519", "GSM1305520", "GSM1305521", "GSM1305522", "GSM1305523", "GSM1305524", "GSM1305525", "GSM1305526", "GSM1305527", "GSM1305528", "GSM1305529", "GSM1305530", "GSM1305531", "GSM1305532", "GSM1305533", "GSM1305534", "GSM1305535", "GSM1305536", "GSM1305537", "GSM1305538", "GSM1305539", "GSM1305540", "GSM1305541", "GSM1305542", "GSM1305543", "GSM1305544", "GSM1305545", "GSM1305546", "GSM1305547", "GSM1305548", "GSM1305549", "GSM1305550", "GSM1305551", "GSM1305552", "GSM1305553", "GSM1305554", "GSM1305555", "GSM1305556", "GSM1305557", "GSM1305558", "GSM1305559", "GSM1305560", "GSM1305561", "GSM1305562", "GSM1305563", "GSM1305564", "GSM1305565", "GSM1305566", "GSM1305567", "GSM1305568", "GSM1305569", "GSM1305570", "GSM1305571", "GSM1305572", "GSM1305573", "GSM1305574", "GSM1305575", "GSM1305576", "GSM1305577", "GSM1305578", "GSM1305579", "GSM1305580", "GSM1305581", "GSM1305582", "GSM1305583", "GSM1305584", "GSM1305585", "GSM1305586", "GSM1305587", "GSM1305588", "GSM1305589", "GSM1305590", "GSM1305591", "GSM1305592", "GSM1305593", "GSM1305594", "GSM1305595", "GSM1305596", "GSM1305597", "GSM1305598", "GSM1305599", "GSM1305600", "GSM1305601", "GSM1305602", "GSM1305603", "GSM1305604", "GSM1305605", "GSM1305606", "GSM1305607", "GSM1305608", "GSM1305609", "GSM1305610", "GSM1305611", "GSM1305612", "GSM1305613", "GSM1305614", "GSM1305615", "GSM1305616", "GSM1305617", "GSM1305618", "GSM1305619", "GSM1305620", "GSM1305621", "GSM1305622", "GSM1305623", "GSM1305624", "GSM1305625", "GSM1305626", "GSM1305627", "GSM1305628", "GSM1305629", "GSM1305630", "GSM1305631", "GSM1305632", "GSM1305633", "GSM1305634", "GSM1305635", "GSM1305636", "GSM1305637", "GSM1305638", "GSM1305639", "GSM1305640", "GSM1305641", "GSM1305642", "GSM1305643", "GSM1305644", "GSM1305645", "GSM1305646", "GSM1305647", "GSM1305648", "GSM1305649", "GSM1305650", "GSM1305651", "GSM1305652", "GSM1305653", "GSM1305654", "GSM1305655", "GSM1305656", "GSM1305657", "GSM1305658", "GSM1305659", "GSM1305660", "GSM1305661", "GSM1305662", "GSM1305663", "GSM1305664", "GSM1305665", "GSM1305666", "GSM1305667", "GSM1305668", "GSM1305669", "GSM1305670", "GSM1305671", "GSM1305672", "GSM1305673", "GSM1305674", "GSM1305675", "GSM1305676", "GSM1305677", "GSM1305678", "GSM1305679", "GSM1305680", "GSM1305681", "GSM1305682", "GSM1305683", "GSM1305684", "GSM1305685", "GSM1305686", "GSM1305687", "GSM1305688", "GSM1305689", "GSM1305690", "GSM1305691", "GSM1305692", "GSM1305693", "GSM1305694", "GSM1305695", "GSM1305696", "GSM1305697", "GSM1305698", "GSM1305699", "GSM1305700", "GSM1305701", "GSM1305702", "GSM1305703", "GSM1305704", "GSM1305705", "GSM1305706", "GSM1305707", "GSM1305708", "GSM1305709", "GSM1305710", "GSM1305711", "GSM1305712", "GSM1305713", "GSM1305714", "GSM1305715", "GSM1305716", "GSM1305717", "GSM1305718", "GSM1305719", "GSM1305720", "GSM1305721", "GSM1305722", "GSM1305723", "GSM1305724", "GSM1305725", "GSM1305726", "GSM1305727", "GSM1305728", "GSM1305729", "GSM1305730", "GSM1305731", "GSM1305732", "GSM1305733", "GSM1305734", "GSM1305735", "GSM1305736", "GSM1305737", "GSM1305738", "GSM1305739", "GSM1305740", "GSM1305741", "GSM1305742", "GSM1305743", "GSM1305744", "GSM1305745", "GSM1305746", "GSM1305747", "GSM1305748", "GSM1305749", "GSM1305750", "GSM1305751", "GSM1305752", "GSM1305753", "GSM1305754", "GSM1305755", "GSM1305756"], "sample_count": 433, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiling of LCM captured breast cancer cells", "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:GSE65216", "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=GSE65216", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE65216", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169.", "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", "GSM1589620", "GSM1589621", "GSM1589622", "GSM1589623", "GSM1589624", "GSM1589625", "GSM1589626", "GSM1589627", "GSM1589628", "GSM1589629", "GSM1589630", "GSM1589631", "GSM1589632", "GSM1589633", "GSM1589634", "GSM1589635", "GSM1589636", "GSM1589637", "GSM1589638", "GSM1589639", "GSM1589640", "GSM1589641", "GSM1589642", "GSM1589643", "GSM1589644", "GSM1589645", "GSM1589646", "GSM1589647", "GSM1589648", "GSM1589649", "GSM1589650", "GSM1589651", "GSM1589652", "GSM1589653", "GSM1589654", "GSM1589655", "GSM1589656", "GSM1589657", "GSM1589658", "GSM1589659", "GSM1589660", "GSM1589661", "GSM1589662", "GSM1589663", "GSM1589664", "GSM1589665", "GSM1589666", "GSM1589667", "GSM1589668", "GSM1589669", "GSM1589670", "GSM1589671", "GSM1589672", "GSM1589673", "GSM1589674", "GSM1589675", "GSM1589676", "GSM1589677", "GSM1589678", "GSM1589679", "GSM1589680", "GSM1589681", "GSM1589682", "GSM1589683", "GSM1589684", "GSM1589685", "GSM1589686", "GSM1589687", "GSM1589688", "GSM1589689", "GSM1589690", "GSM1589691", "GSM1589692", "GSM1589693", "GSM1589694", "GSM1589695", "GSM1589696", "GSM1589697", "GSM1589698", "GSM1589699", "GSM1589700", "GSM1589701", "GSM1589702", "GSM1589703", "GSM1589704", "GSM1589705", "GSM1589706", "GSM1589707", "GSM1589708", "GSM1589709", "GSM1589710", "GSM1589711", "GSM1589712", "GSM1589713", "GSM1589714", "GSM1589715", "GSM1589716", "GSM1589717", "GSM1589718", "GSM1589719", "GSM1589720", "GSM1589721", "GSM1589722", "GSM1589723", "GSM1589724", "GSM1589725", "GSM1589726", "GSM1589727", "GSM1589728", "GSM1589729", "GSM1589730", "GSM1589731", "GSM1589732", "GSM1589733", "GSM1589734", "GSM1589735", "GSM1589736", "GSM1589737", "GSM1589738", "GSM1589739", "GSM1589740", "GSM1589741", "GSM1589742", "GSM1589743", "GSM1589744", "GSM1589745", "GSM1589746", "GSM1589747", "GSM1589748", "GSM1589749", "GSM1589750", "GSM1589751", "GSM1589752", "GSM1589753", "GSM1589754", "GSM1589755", "GSM1589756", "GSM1589757", "GSM1589758", "GSM1589759", "GSM1589760", "GSM1589761", "GSM1589762", "GSM1589763", "GSM1589764", "GSM1589765", "GSM1589766", "GSM1589767", "GSM1589768", "GSM1589769", "GSM1589770", "GSM1589771", "GSM1589772", "GSM1589773", "GSM1589774", "GSM1589775", "GSM1589776", "GSM1589777", "GSM1589778", "GSM1589779", "GSM1589780", "GSM1589781", "GSM1589782", "GSM1589783", "GSM1589784", "GSM1589785", "GSM1589786", "GSM1589787", "GSM1589788", "GSM1589789", "GSM1589790", "GSM1589791", "GSM1589792", "GSM1589793", "GSM1589794", "GSM1589795", "GSM1589796", "GSM1589797"], "sample_count": 356, "group_sizes": null, "group_sizes_basis": null, "platform": "570;14877", "taxon": "Homo sapiens", "title": "Expression profiling of breast cancer samples from Institut Curie (Maire cohort)", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE10810 not downloaded", "asset:data:geo:GSE10810 licence not read", "asset:data:geo:GSE109169 not downloaded", "asset:data:geo:GSE109169 licence not read", "asset:data:geo:GSE124646 not downloaded", "asset:data:geo:GSE124646 licence not read", "asset:data:geo:GSE26964 not downloaded", "asset:data:geo:GSE26964 licence not read", "asset:data:geo:GSE29431 not downloaded", "asset:data:geo:GSE29431 licence not read", "asset:data:geo:GSE36295 not downloaded", "asset:data:geo:GSE36295 licence not read", "asset:data:geo:GSE42568 not downloaded", "asset:data:geo:GSE42568 licence not read", "asset:data:geo:GSE45827 not downloaded", "asset:data:geo:GSE45827 licence not read", "asset:data:geo:GSE54002 not downloaded", "asset:data:geo:GSE54002 licence not read", "asset:data:geo:GSE65216 not downloaded", "asset:data:geo:GSE65216 licence not read"]}, "analysis": {"state": "complete", "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": {"fdr_threshold": "Benjamini and Hochberg false discovery rate adjustment"}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The moderated T-statistics and the Benjamini and Hochberg false discovery rate method were used to calculate the p value and adjusted p value (adj.P.Val) and logFC (fold change), accordingly."}}, {"id": "method-2", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "support vector machine"}}, {"id": "method-3", "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": 0.7, "band": "medium", "quote": "PPI"}}, {"id": "method-4", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-5", "family": "network_analysis", "specific": "centrality", "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": "centrality"}}], "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: 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": ["GSE54002", "GSE29431", "GSE124646", "GSE42568", "GSE45827", "GSE10810", "GSE65216", "GSE36295", "GSE109169", "GSE26964"], "resolved_accessions": ["GSE54002", "GSE29431", "GSE124646", "GSE42568", "GSE45827", "GSE10810", "GSE65216", "GSE36295", "GSE109169", "GSE26964"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54002 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29431 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124646 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42568 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45827 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10810 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE65216 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE36295 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109169."], "basis": "The paper names GSE54002, GSE29431, GSE124646, GSE42568, GSE45827, GSE10810, GSE65216, GSE36295, GSE109169, GSE26964 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:36204232", "data:geo:GSE10810"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE10810"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:08:35Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 16430, "completion_tokens": 3659, "cached_tokens": 264}}, "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:36204232", "type": "paper", "label": "pmid:36204232"}, {"id": "source:pmid:36204232", "type": "manuscript", "label": "PMID 36204232 full text"}, {"id": "data:geo:GSE10810", "type": "dataset", "label": "GEO GSE10810"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36204232", "type": "paper", "label": "pmid:36204232"}, {"id": "source:pmid:36204232", "type": "manuscript", "label": "PMID 36204232 full text"}, {"id": "data:geo:GSE10810", "type": "dataset", "label": "GEO GSE10810"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36204232", "type": "extraction", "used": ["source:pmid:36204232"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE10810", "type": "accession_resolution", "used": ["data:geo:GSE10810"], "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:36204232", "parent_hash": "sha256:fa96ca3fb1c4c4a435486f4cfb49477122fadc483e5af8f8a66f534d7d689088", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE10810 licence not read", "asset:data:geo:GSE10810 not downloaded", "asset:data:geo:GSE109169 licence not read", "asset:data:geo:GSE109169 not downloaded", "asset:data:geo:GSE124646 licence not read", "asset:data:geo:GSE124646 not downloaded", "asset:data:geo:GSE26964 licence not read", "asset:data:geo:GSE26964 not downloaded", "asset:data:geo:GSE29431 licence not read", "asset:data:geo:GSE29431 not downloaded", "asset:data:geo:GSE36295 licence not read", "asset:data:geo:GSE36295 not downloaded", "asset:data:geo:GSE42568 licence not read", "asset:data:geo:GSE42568 not downloaded", "asset:data:geo:GSE45827 licence not read", "asset:data:geo:GSE45827 not downloaded", "asset:data:geo:GSE54002 licence not read", "asset:data:geo:GSE54002 not downloaded", "asset:data:geo:GSE65216 licence not read", "asset:data:geo:GSE65216 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["C cell lines MCF-7 and MDA-MB-231 cells were cultured in Dulbecco’s modified Eagle’s medium (Gibco, L", "culture and drug treatment The BC cell lines MCF-7 and MDA-MB-231 cells were cultured in Dulbec"], "order_basis": "paper_text_order:4562", "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": ["e cells were harvested with lysis buffer for immunoblot analyses or fixed with 4% paraformaldehyde f"], "order_basis": "paper_text_order:5054", "id": "assay:2"}, {"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": ["alyses or fixed with 4% paraformaldehyde for immunofluorescent staining. Functional and pathway enrichment"], "order_basis": "paper_text_order:5112", "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 moderated T-statistics and the Benjamini and Hochberg false discovery rate method were used to calculate the p value and adjusted p value (adj.P.Val) and logFC (fold change), accordingly."], "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":"2026-11-04T03:10:59+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}}}