{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34522169", "kind": "science-record", "revision": 5, "content_hash": "sha256:5a9a0b6f2651b3ad149baf4f9091e5e82dbbcc10743a39c83a559dcb689d4fc7", "created_at": "2026-11-01T15:41:51Z", "updated_at": "2026-11-01T22:04:42Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Key Genes and Pathways associated with Endometriosis by Weighted Gene Co-expression Network Analysis.", "doi": "10.7150/ijms.63541", "pmid": "34522169", "authors": ["Jingni Wu", "Xiaoling Fang", "Xiaomeng Xia"], "journal": "International journal of medical sciences", "year": 2021, "abstract": "Background: Endometriosis is a common gynecological disorder with high rates of infertility and pelvic pain. However, its pathogenesis and diagnostic biomarkers remain unclear. This study aimed to elucidate potential hub genes and key pathways associated with endometriosis in ectopic endometrium (EC) and eutopic endometrium (EU). Material and Method: EC and EU-associated microarray datasets were obtained from the gene expression omnibus (GEO) database. Gene set enrichment analysis was performed to obtain further biological insight into the EU and EC-associated genes. Weighted gene co-expression network analysis (WGCNA) was performed to find clinically significant modules of highly-correlated genes. The hub genes that belong to both the weighted gene co-expression network and protein-protein interaction (PPI) network were identified using a Venn diagram. Results: We obtained EC and EU-associated microarray datasets GSE7305 and GSE120103. Genes in the EC were mainly enriched in the immune response and immune cell trafficking, and genes in the EU were mainly enriched in stress response and steroid hormone biosynthesis. PPI networks and weighted gene co-expression networks were constructed. An EC-associated blue module and an EU-associated magenta module were identified, and their function annotations revealed that hormone receptor signaling or inflammatory microenvironments may promote EU passing through the oviducts and migrating to the ovarian surfaces, and adhesion and immune correlated genes may induce the successful ectopic implantation of the endometrium (EC). Twelve hub genes in the EC and sixteen hub genes in the EU were recognized and further validated in independent datasets. Conclusion: Our study identified, for the first time, the hub genes and enrichment pathways in the EC and EU using WGCNA, which may provide a comprehensive understanding of the pathogenesis of endometriosis and have important clinical implications for the treatment and diagnosis of endometriosis.", "claims": [{"id": "claim-data-access", "statement": "The following publicly-available datasets were analyzed in this study: [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE120103]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7305]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE51981].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34522169", "locator": "sections[22] \"Data Availability\" paragraph 2", "quote": "The following publicly-available datasets were analyzed in this study: [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE120103]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7305]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE51981]."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:34522169"], "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:GSE120103"], "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:GSE120103"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34522169", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/ijms.63541", "sha256": "sha256:4702c5b6e7ae771cfb06bac98e5d8c24da808ba384cb896896220516e008da15", "bytes": 33770, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/ijms.63541", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8436105", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE120103", "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=GSE120103", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE120103", "version": null, "note": "The following publicly-available datasets were analyzed in this study: [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE120103]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7305]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE51981].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following publicly-available datasets were analyzed in this study: [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE120103]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7305]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE51981].", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3393491", "GSM3393492", "GSM3393493", "GSM3393494", "GSM3393495", "GSM3393496", "GSM3393497", "GSM3393498", "GSM3393499", "GSM3393500", "GSM3393501", "GSM3393502", "GSM3393503", "GSM3393504", "GSM3393505", "GSM3393506", "GSM3393507", "GSM3393508", "GSM3393509", "GSM3393510", "GSM3393511", "GSM3393512", "GSM3393513", "GSM3393514", "GSM3393515", "GSM3393516", "GSM3393517", "GSM3393518", "GSM3393519", "GSM3393520", "GSM3393521", "GSM3393522", "GSM3393523", "GSM3393524", "GSM3393525", "GSM3393526"], "sample_count": 36, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Homo sapiens whole genome expression microarray of endometrium obtained from fertile and Infertile women with stage IV ovarian endometriosis and without endometriosis", "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:GSE51981", "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=GSE51981", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE51981", "version": null, "note": "The following publicly-available datasets were analyzed in this study: [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE120103]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7305]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE51981].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following publicly-available datasets were analyzed in this study: [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE120103]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7305]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE51981].", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1256653", "GSM1256654", "GSM1256655", "GSM1256656", "GSM1256657", "GSM1256658", "GSM1256659", "GSM1256660", "GSM1256661", "GSM1256662", "GSM1256663", "GSM1256664", "GSM1256665", "GSM1256666", "GSM1256667", "GSM1256668", "GSM1256669", "GSM1256670", "GSM1256671", "GSM1256672", "GSM1256673", "GSM1256674", "GSM1256675", "GSM1256676", "GSM1256677", "GSM1256678", "GSM1256679", "GSM1256680", "GSM1256681", "GSM1256682", "GSM1256683", "GSM1256684", "GSM1256685", "GSM1256686", "GSM1256687", "GSM1256688", "GSM1256689", "GSM1256690", "GSM1256691", "GSM1256692", "GSM1256693", "GSM1256694", "GSM1256695", "GSM1256696", "GSM1256697", "GSM1256698", "GSM1256699", "GSM1256700", "GSM1256701", "GSM1256702", "GSM1256703", "GSM1256704", "GSM1256705", "GSM1256706", "GSM1256707", "GSM1256708", "GSM1256709", "GSM1256710", "GSM1256711", "GSM1256712", "GSM1256713", "GSM1256714", "GSM1256715", "GSM1256716", "GSM1256717", "GSM1256718", "GSM1256719", "GSM1256720", "GSM1256721", "GSM1256722", "GSM1256723", "GSM1256724", "GSM1256725", "GSM1256726", "GSM1256727", "GSM1256728", "GSM1256729", "GSM1256730", "GSM1256731", "GSM1256732", "GSM1256733", "GSM1256734", "GSM1256735", "GSM1256736", "GSM1256737", "GSM1256738", "GSM1256739", "GSM1256740", "GSM1256741", "GSM1256742", "GSM1256743", "GSM1256744", "GSM1256745", "GSM1256746", "GSM1256747", "GSM1256748", "GSM1256749", "GSM1256750", "GSM1256751", "GSM1256752", "GSM1256753", "GSM1256754", "GSM1256755", "GSM1256756", "GSM1256757", "GSM1256758", "GSM1256759", "GSM1256760", "GSM1256761", "GSM1256762", "GSM1256763", "GSM1256764", "GSM1256765", "GSM1256766", "GSM1256767", "GSM1256768", "GSM1256769", "GSM1256770", "GSM1256771", "GSM1256772", "GSM1256773", "GSM1256774", "GSM1256775", "GSM1256776", "GSM1256777", "GSM1256778", "GSM1256779", "GSM1256780", "GSM1256781", "GSM1256782", "GSM1256783", "GSM1256784", "GSM1256785", "GSM1256786", "GSM1256787", "GSM1256788", "GSM1256789", "GSM1256790", "GSM1256791", "GSM1256792", "GSM1256793", "GSM1256794", "GSM1256795", "GSM1256796", "GSM1256797", "GSM1256798", "GSM1256799", "GSM1256800"], "sample_count": 148, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Molecular Classification of Endometriosis and Disease Stage Using High-Dimensional Genomic Data", "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:GSE7305", "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=GSE7305", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE7305", "version": null, "note": "The following publicly-available datasets were analyzed in this study: [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE120103]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7305]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE51981].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following publicly-available datasets were analyzed in this study: [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE120103]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7305]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE51981].", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM175766", "GSM175767", "GSM175768", "GSM175769", "GSM175770", "GSM175771", "GSM175772", "GSM175773", "GSM175774", "GSM175775", "GSM175776", "GSM175777", "GSM175778", "GSM175779", "GSM175780", "GSM175781", "GSM175782", "GSM175783", "GSM175784", "GSM175785"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Human endometriosis vs normal endometrium study - transcriptional profiling", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE7307", "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=GSE7307", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE7307", "version": null, "note": "The following publicly-available datasets were analyzed in this study: [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE120103]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7305]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE51981].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following publicly-available datasets were analyzed in this study: [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE120103]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7305]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE51981].", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM175786", "GSM175787", "GSM175788", "GSM175789", "GSM175790", "GSM175791", "GSM175792", "GSM175793", "GSM175794", "GSM175795", "GSM175796", "GSM175797", "GSM175798", "GSM175799", "GSM175800", "GSM175801", "GSM175802", "GSM175803", "GSM175804", "GSM175805", "GSM175806", "GSM175807", "GSM175808", "GSM175809", "GSM175810", "GSM175811", "GSM175812", "GSM175813", "GSM175814", "GSM175815", "GSM175816", "GSM175817", "GSM175818", "GSM175819", "GSM175820", "GSM175821", "GSM175822", "GSM175823", "GSM175824", "GSM175825", "GSM175826", "GSM175827", "GSM175828", "GSM175829", "GSM175830", "GSM175831", "GSM175832", "GSM175833", "GSM175834", "GSM175835", "GSM175836", "GSM175837", "GSM175838", "GSM175839", "GSM175840", "GSM175841", "GSM175842", "GSM175843", "GSM175844", "GSM175845", "GSM175846", "GSM175847", "GSM175848", "GSM175849", "GSM175850", "GSM175851", "GSM175852", "GSM175853", "GSM175854", "GSM175855", "GSM175856", "GSM175857", "GSM175858", "GSM175859", "GSM175860", "GSM175861", "GSM175862", "GSM175863", "GSM175864", "GSM175865", "GSM175866", "GSM175867", "GSM175868", "GSM175869", "GSM175870", "GSM175871", "GSM175872", "GSM175873", "GSM175874", "GSM175875", "GSM175876", "GSM175877", "GSM175878", "GSM175879", "GSM175880", "GSM175881", "GSM175882", "GSM175883", "GSM175884", "GSM175885", "GSM175886", "GSM175887", "GSM175888", "GSM175889", "GSM175890", "GSM175891", "GSM175892", "GSM175893", "GSM175894", "GSM175895", "GSM175896", "GSM175897", "GSM175898", "GSM175899", "GSM175900", "GSM175901", "GSM175902", "GSM175903", "GSM175904", "GSM175905", "GSM175906", "GSM175907", "GSM175908", "GSM175909", "GSM175910", "GSM175911", "GSM175912", "GSM175913", "GSM175914", "GSM175915", "GSM175916", "GSM175917", "GSM175918", "GSM175919", "GSM175920", "GSM175921", "GSM175922", "GSM175923", "GSM175924", "GSM175925", "GSM175926", "GSM175927", "GSM175928", "GSM175929", "GSM175930", "GSM175931", "GSM175932", "GSM175933", "GSM175934", "GSM175935", "GSM175936", "GSM175937", "GSM175938", "GSM175939", "GSM175940", "GSM175941", "GSM175942", "GSM175943", "GSM175944", "GSM175945", "GSM175946", "GSM175947", "GSM175948", "GSM175949", "GSM175950", "GSM175951", "GSM175952", "GSM175953", "GSM175954", "GSM175955", "GSM175956", "GSM175957", "GSM175958", "GSM175959", "GSM175960", "GSM175961", "GSM175962", "GSM175963", "GSM175964", "GSM175965", "GSM175966", "GSM175967", "GSM175968", "GSM175969", "GSM175970", "GSM175971", "GSM175972", "GSM175973", "GSM175974", "GSM175975", "GSM175976", "GSM175977", "GSM175978", "GSM175979", "GSM175980", "GSM175981", "GSM175982", "GSM175983", "GSM175984", "GSM175985", "GSM175987", "GSM175988", "GSM175989", "GSM175990", "GSM175991", "GSM175992", "GSM175993", "GSM175994", "GSM175995", "GSM175996", "GSM175997", "GSM175998", "GSM175999", "GSM176000", "GSM176001", "GSM176002", "GSM176003", "GSM176004", "GSM176005", "GSM176006", "GSM176007", "GSM176008", "GSM176009", "GSM176010", "GSM176011", "GSM176012", "GSM176013", "GSM176014", "GSM176015", "GSM176016", "GSM176017", "GSM176018", "GSM176019", "GSM176020", "GSM176021", "GSM176022", "GSM176023", "GSM176024", "GSM176025", "GSM176026", "GSM176027", "GSM176028", "GSM176029", "GSM176030", "GSM176031", "GSM176032", "GSM176033", "GSM176034", "GSM176035", "GSM176036", "GSM176037", "GSM176038", "GSM176039", "GSM176040", "GSM176041", "GSM176042", "GSM176043", "GSM176044", "GSM176045", "GSM176046", "GSM176047", "GSM176048", "GSM176049", "GSM176050", "GSM176051", "GSM176052", "GSM176053", "GSM176054", "GSM176055", "GSM176056", "GSM176057", "GSM176058", "GSM176059", "GSM176060", "GSM176061", "GSM176062", "GSM176063", "GSM176064", "GSM176065", "GSM176066", "GSM176067", "GSM176068", "GSM176069", "GSM176070", "GSM176071", "GSM176072", "GSM176073", "GSM176074", "GSM176075", "GSM176076", "GSM176077", "GSM176078", "GSM176079", "GSM176080", "GSM176081", "GSM176082", "GSM176083", "GSM176084", "GSM176085", "GSM176086", "GSM176087", "GSM176088", "GSM176089", "GSM176090", "GSM176091", "GSM176092", "GSM176093", "GSM176094", "GSM176095", "GSM176096", "GSM176097", "GSM176098", "GSM176099", "GSM176100", "GSM176101", "GSM176102", "GSM176103", "GSM176104", "GSM176105", "GSM176106", "GSM176107", "GSM176108", "GSM176109", "GSM176110", "GSM176111", "GSM176112", "GSM176113", "GSM176114", "GSM176115", "GSM176116", "GSM176117", "GSM176118", "GSM176119", "GSM176120", "GSM176121", "GSM176122", "GSM176123", "GSM176124", "GSM176125", "GSM176126", "GSM176127", "GSM176128", "GSM176129", "GSM176130", "GSM176131", "GSM176132", "GSM176133", "GSM176134", "GSM176135", "GSM176136", "GSM176137", "GSM176138", "GSM176139", "GSM176140", "GSM176141", "GSM176142", "GSM176143", "GSM176144", "GSM176145", "GSM176146", "GSM176147", "GSM176148", "GSM176149", "GSM176150", "GSM176151", "GSM176152", "GSM176153", "GSM176154", "GSM176155", "GSM176156", "GSM176157", "GSM176158", "GSM176159", "GSM176160", "GSM176161", "GSM176162", "GSM176163", "GSM176164", "GSM176165", "GSM176166", "GSM176167", "GSM176168", "GSM176169", "GSM176170", "GSM176171", "GSM176172", "GSM176173", "GSM176174", "GSM176175", "GSM176176", "GSM176177", "GSM176178", "GSM176179", "GSM176180", "GSM176181", "GSM176182", "GSM176183", "GSM176184", "GSM176185", "GSM176186", "GSM176205", "GSM176206", "GSM176207", "GSM176208", "GSM176209", "GSM176210", "GSM176211", "GSM176212", "GSM176213", "GSM176214", "GSM176215", "GSM176216", "GSM176217", "GSM176218", "GSM176219", "GSM176220", "GSM176221", "GSM176222", "GSM176223", "GSM176224", "GSM176225", "GSM176226", "GSM176227", "GSM176228", "GSM176229", "GSM176230", "GSM176231", "GSM176232", "GSM176233", "GSM176234", "GSM176235", "GSM176236", "GSM176237", "GSM176238", "GSM176239", "GSM176240", "GSM176241", "GSM176242", "GSM176243", "GSM176244", "GSM176245", "GSM176246", "GSM176247", "GSM176248", "GSM176249", "GSM176250", "GSM176251", "GSM176252", "GSM176253", "GSM176254", "GSM176255", "GSM176256", "GSM176257", "GSM176258", "GSM176259", "GSM176260", "GSM176261", "GSM176262", "GSM176263", "GSM176264", "GSM176265", "GSM176266", "GSM176267", "GSM176268", "GSM176269", "GSM176270", "GSM176271", "GSM176272", "GSM176273", "GSM176274", "GSM176275", "GSM176276", "GSM176277", "GSM176278", "GSM176279", "GSM176280", "GSM176281", "GSM176282", "GSM176283", "GSM176284", "GSM176285", "GSM176286", "GSM176287", "GSM176288", "GSM176289", "GSM176290", "GSM176291", "GSM176292", "GSM176293", "GSM176294", "GSM176295", "GSM176296", "GSM176297", "GSM176298", "GSM176299", "GSM176300", "GSM176301", "GSM176302", "GSM176303", "GSM176304", "GSM176305", "GSM176306", "GSM176307", "GSM176308", "GSM176309", "GSM176310", "GSM176311", "GSM176312", "GSM176313", "GSM176314", "GSM176315", "GSM176316", "GSM176317", "GSM176318", "GSM176319", "GSM176320", "GSM176321", "GSM176322", "GSM176323", "GSM176324", "GSM176325", "GSM176326", "GSM176327", "GSM176328", "GSM176329", "GSM176330", "GSM176331", "GSM176332", "GSM176333", "GSM176334", "GSM176335", "GSM176336", "GSM176337", "GSM176338", "GSM176339", "GSM176340", "GSM176341", "GSM176342", "GSM176343", "GSM176344", "GSM176345", "GSM176346", "GSM176347", "GSM176348", "GSM176349", "GSM176350", "GSM176351", "GSM176352", "GSM176353", "GSM176354", "GSM176355", "GSM176356", "GSM176357", "GSM176358", "GSM176359", "GSM176360", "GSM176361", "GSM176362", "GSM176363", "GSM176364", "GSM176365", "GSM176366", "GSM176367", "GSM176368", "GSM176369", "GSM176370", "GSM176371", "GSM176372", "GSM176373", "GSM176374", "GSM176375", "GSM176376", "GSM176377", "GSM176378", "GSM176379", "GSM176380", "GSM176381", "GSM176382", "GSM176383", "GSM176384", "GSM176385", "GSM176386", "GSM176387", "GSM176388", "GSM176389", "GSM176390", "GSM176391", "GSM176392", "GSM176393", "GSM176394", "GSM176395", "GSM176396", "GSM176397", "GSM176398", "GSM176399", "GSM176400", "GSM176401", "GSM176402", "GSM176403", "GSM176404", "GSM176405", "GSM176406", "GSM176407", "GSM176408", "GSM176409", "GSM176410", "GSM176411", "GSM176412", "GSM176413", "GSM176414", "GSM176415", "GSM176416", "GSM176417", "GSM176418", "GSM176419", "GSM176420", "GSM176421", "GSM176422", "GSM176423", "GSM176424", "GSM176425", "GSM176426", "GSM176427", "GSM176428", "GSM176429", "GSM176430", "GSM176431", "GSM176432", "GSM176433", "GSM176434", "GSM176435", "GSM176436", "GSM176437", "GSM176438", "GSM176439", "GSM176440", "GSM176441", "GSM176442", "GSM176443", "GSM176444", "GSM176445", "GSM176446", "GSM176447", "GSM176448", "GSM176449", "GSM176450", "GSM176451", "GSM176452", "GSM176453", "GSM176454", "GSM176455", "GSM176456", "GSM176457", "GSM176458", "GSM176459", "GSM176460", "GSM176461", "GSM176462", "GSM176463", "GSM176464", "GSM176465", "GSM176466", "GSM176467", "GSM176468", "GSM176469", "GSM176470", "GSM176471", "GSM176472", "GSM176473", "GSM176474", "GSM176475", "GSM176476", "GSM176477", "GSM176478", "GSM176479", "GSM176480", "GSM176481"], "sample_count": 677, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Human body index - transcriptional profiling", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:34522169:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:18e24a0db6585a6e31661f0ef50e6821dba3a63ead661ef011a3ee40d9bfc1b9", "bytes": 3299, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#T1", "version": null, "note": "The GO and KEGG Pathway analysis of genes in the blue module", "structure": {"pmcid": "PMC8436105", "section_index": 16, "section_title": "Function analysis of the most significant module", "row_count": 41, "column_count": 4}, "table": {"label": "Table 1", "caption": "The GO and KEGG Pathway analysis of genes in the blue module", "rows": [["Category", "Term", "Description", "Log(p-value)"], ["GO Biological Processes", "GO:0030029", "actin filament-based process", "-20.593297"], ["GO Biological Processes", "GO:0071417", "cellular response to organonitrogen compound", "-20.2406423"], ["GO Biological Processes", "GO:0030155", "regulation of cell adhesion", "-20.0365408"], ["GO Biological Processes", "GO:0006914", "autophagy", "-15.9477686"], ["GO Biological Processes", "GO:0010942", "positive regulation of cell death", "-14.3658968"], ["GO Biological Processes", "GO:0007264", "small GTPase mediated signal transduction", "-14.0979829"], ["GO Biological Processes", "GO:0070848", "response to growth factor", "-13.3811234"], ["GO Biological Processes", "GO:0045055", "regulated exocytosis", "-13.372418"], ["GO Biological Processes", "GO:0051345", "positive regulation of hydrolase activity", "-13.0915765"], ["GO Biological Processes", "GO:0001568", "blood vessel development", "-12.7380519"], ["GO Biological Processes", "GO:0000904", "cell morphogenesis involved in differentiation", "-12.5393524"], ["GO Biological Processes", "GO:0043062", "extracellular structure organization", "-12.4268848"], ["GO Biological Processes", "GO:0009611", "response to wounding", "-12.0333641"], ["GO Biological Processes", "GO:0043408", "regulation of MAPK cascade", "-11.5789888"], ["GO Biological Processes", "GO:0022604", "regulation of cell morphogenesis", "-11.4691072"], ["GO Biological Processes", "GO:0002576", "platelet degranulation", "-11.2263844"], ["GO Biological Processes", "GO:0019221", "cytokine-mediated signaling pathway", "-10.9869128"], ["GO Biological Processes", "GO:0045936", "negative regulation of phosphate metabolic process", "-10.9676618"], ["GO Biological Processes", "GO:0003012", "muscle system process", "-10.2900458"], ["GO Biological Processes", "GO:0051129", "negative regulation of cellular component organization", "-10.2118548"], ["KEGG Pathway", "hsa04068", "FoxO signaling pathway", "-9.5"], ["KEGG Pathway", "hsa04510", "Focal adhesion", "-9"], ["KEGG Pathway", "hsa04014", "Ras signaling pathway", "-8.6"], ["KEGG Pathway", "hsa04010", "MAPK signaling pathway", "-8.2"], ["KEGG Pathway", "hsa05200", "Pathways in cancer", "-7.3"], ["KEGG Pathway", "hsa05205", "Proteoglycans in cancer", "-7.2"], ["KEGG Pathway", "hsa04380", "Osteoclast differentiation", "-6.8"], ["KEGG Pathway", "hsa04610", "Complement and coagulation cascades", "-6.6"], ["KEGG Pathway", "hsa04630", "Jak-STAT signaling pathway", "-6"], ["KEGG Pathway", "hsa05418", "Fluid shear stress and atherosclerosis", "-5.9"], ["KEGG Pathway", "hsa04270", "Vascular smooth muscle contraction", "-5.9"], ["KEGG Pathway", "hsa04144", "Endocytosis", "-5.9"], ["KEGG Pathway", "hsa04727", "GABAergic synapse", "-5.8"], ["KEGG Pathway", "hsa04137", "Mitophagy - animal", "-5.5"], ["KEGG Pathway", "hsa04915", "Estrogen signaling pathway", "-5.5"], ["KEGG Pathway", "hsa04621", "NOD-like receptor signaling pathway", "-5.1"], ["KEGG Pathway", "hsa05202", "Transcriptional misregulation in cancer", "-4.2"], ["KEGG Pathway", "hsa04720", "Long-term potentiation", "-4.1"], ["KEGG Pathway", "hsa04668", "TNF signaling pathway", "-3.8"], ["KEGG Pathway", "hsa04020", "Calcium signaling pathway", "-3.7"]], "row_count": 41, "column_count": 4, "numeric_cells": 80, "header_rows": 1, "locator": "section[16]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:34522169:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1532eb88b6a6823cebd08480441ad93687bd3ce921996c4b29f29ff60b16c93e", "bytes": 2644, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[2]#T2", "version": null, "note": "The GO and KEGG Pathway analysis of genes in the magenta module", "structure": {"pmcid": "PMC8436105", "section_index": 16, "section_title": "Function analysis of the most significant module", "row_count": 30, "column_count": 4}, "table": {"label": "Table 2", "caption": "The GO and KEGG Pathway analysis of genes in the magenta module", "rows": [["Category", "Term", "Description", "Log(p-value)"], ["GO Biological Processes", "GO:0043408", "regulation of MAPK cascade", "-6.05131099"], ["GO Biological Processes", "GO:0043409", "negative regulation of MAPK cascade", "-4.84419894"], ["GO Biological Processes", "GO:1903351", "cellular response to dopamine", "-4.25433626"], ["GO Biological Processes", "GO:0035666", "TRIF-dependent toll-like receptor signaling pathway", "-3.72907579"], ["GO Biological Processes", "GO:0060398", "regulation of growth hormone receptor signaling pathway", "-3.59181535"], ["GO Biological Processes", "GO:1904407", "positive regulation of nitric oxide metabolic process", "-3.51272839"], ["GO Biological Processes", "GO:0009190", "cyclic nucleotide biosynthetic process", "-3.38699864"], ["GO Biological Processes", "GO:0000226", "microtubule cytoskeleton organization", "-3.37279545"], ["GO Biological Processes", "GO:0030258", "lipid modification", "-3.34130208"], ["GO Biological Processes", "GO:0016569", "covalent chromatin modification", "-3.19790154"], ["GO Biological Processes", "GO:0046856", "phosphatidylinositol dephosphorylation", "-3.11446184"], ["GO Biological Processes", "GO:0046777", "protein autophosphorylation", "-3.11274876"], ["GO Biological Processes", "GO:0090336", "positive regulation of brown fat cell differentiation", "-3.07693529"], ["GO Biological Processes", "GO:0060391", "positive regulation of SMAD protein signal transduction", "-3.07693529"], ["GO Biological Processes", "GO:0007099", "centriole replication", "-3.06412444"], ["GO Biological Processes", "GO:0031570", "DNA integrity checkpoint", "-2.93592311"], ["GO Biological Processes", "GO:0019835", "cytolysis", "-2.87954652"], ["GO Biological Processes", "GO:0007030", "Golgi organization", "-2.79292724"], ["GO Biological Processes", "GO:0048539", "bone marrow development", "-2.684576"], ["KEGG Pathway", "hsa00310", "Lysine degradation", "-5"], ["KEGG Pathway", "hsa04668", "TNF signaling pathway", "-3.4"], ["KEGG Pathway", "hsa04621", "NOD-like receptor signaling pathway", "-3.2"], ["KEGG Pathway", "hsa05020", "Prion diseases", "-2.4"], ["KEGG Pathway", "hsa00514", "Other types of O-glycan biosynthesis", "-2.4"], ["KEGG Pathway", "hsa04140", "Autophagy - animal", "-2.3"], ["KEGG Pathway", "hsa04912", "GnRH signaling pathway", "-2.2"], ["KEGG Pathway", "hsa04070", "Phosphatidylinositol signaling system", "-2.1"], ["KEGG Pathway", "hsa04210", "Apoptosis", "-2.1"], ["KEGG Pathway", "hsa04550", "Signaling pathways regulating pluripotency of stem cells", "-2"]], "row_count": 30, "column_count": 4, "numeric_cells": 58, "header_rows": 1, "locator": "section[16]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:34522169:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:82cd5f460615a905a8644007fc40ef4d09165331fdff1e939cb89ad15a0cdc6d", "bytes": 4128, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#T3", "version": null, "note": "The common hub genes of WGCNA and PPI analysis in the blue and magenta modules", "structure": {"pmcid": "PMC8436105", "section_index": 17, "section_title": "Identification of hub genes", "row_count": 30, "column_count": 11}, "table": {"label": "Table 3", "caption": "The common hub genes of WGCNA and PPI analysis in the blue and magenta modules", "rows": [["Gene Symbol", "Gene Description", "Module", "WGCNA", "PPI Analysis", "Limma Analysis"], ["GS", "GS P value", "MM", "MM, P value", "K Score", "Log2FC", "FDR", "Up or Down"], ["ACTG2", "actin, gamma 2, smooth muscle, enteric", "blue", "0.922139646", "7.51E-09", "0.923366176", "6.54E-09", "5.667", "3.548158459", "1.02E-08", "up"], ["C1R", "complement C1r subcomponent", "blue", "0.897984733", "7.81E-08", "0.96174151", "1.45E-11", "4", "2.208552292", "1.14E-07", "up"], ["CDH3", "cadherin 3", "blue", "0.931420936", "2.48E-09", "0.971836642", "9.56E-13", "6.2", "2.775338929", "3.97E-09", "up"], ["CLU", "clusterin", "blue", "0.863575842", "9.38E-07", "0.878310934", "3.54E-07", "4", "2.044619742", "1.29E-06", "up"], ["COL8A1", "collagen type VIII alpha 1 chain", "blue", "0.92193141", "7.69E-09", "0.941172973", "6.47E-10", "3", "4.329881143", "1.01E-08", "Up"], ["GATA6", "GATA binding protein 6", "blue", "0.98763453", "6.14E-16", "0.972736196", "7.16E-13", "5.667", "4.878194698", "1.42E-15", "up"], ["HOXC6", "homeobox C6", "blue", "0.944317318", "3.99E-10", "0.90875176", "2.98E-08", "4.8", "3.487499137", "6.36E-10", "up"], ["LMOD1", "leiomodin 1", "blue", "0.880126801", "3.12E-07", "0.947799849", "2.26E-10", "5.667", "2.476035697", "4.14E-07", "up"], ["MYH11", "myosin heavy chain 11", "blue", "0.933072838", "2.00E-09", "0.975751992", "2.52E-13", "5.667", "3.708376486", "2.96E-09", "Up"], ["MYLK", "myosin light chain kinase", "blue", "0.914954646", "1.62E-08", "0.94723591", "2.48E-10", "5.667", "2.125367821", "2.54E-08", "up"], ["MYOCD", "myocardin", "blue", "0.859995861", "1.17E-06", "0.929712545", "3.08E-09", "5.667", "3.441041169", "1.43E-06", "up"], ["PROS1", "protein S (alpha)", "blue", "0.934607399", "1.64E-09", "0.984275338", "5.27E-15", "4", "2.899254277", "2.67E-09", "up"], ["SERPING1", "serpin family G member 1", "blue", "0.859067114", "1.23E-06", "0.937390849", "1.12E-09", "4", "2.424791429", "1.61E-06", "up"], ["TAGLN", "transgelin", "blue", "0.909061849", "2.89E-08", "0.959903156", "2.20E-11", "5.667", "2.815676431", "3.97E-08", "up"], ["THBS1", "thrombospondin 1", "blue", "0.764480323", "8.68E-05", "0.84490284", "2.77E-06", "4", "2.047575043", "0.000118406", "up"], ["THBS2", "thrombospondin 2", "blue", "0.870101501", "6.18E-07", "0.92128971", "8.25E-09", "3", "2.397111323", "8.17E-07", "up"], ["ABCC8", "ATP binding cassette subfamily C member 8", "magenta", "0.726050115", "0.000966995", "0.922624053", "1.35214E-07", "3", "2.368106299", "0.000000474", "Up"], ["COL4A6", "collagen type IV alpha 6 chain", "magenta", "0.831303264", "3.54879E-05", "0.873736048", "4.59798E-06", "4.71", "3.592049292", "5.82E-08", "up"], ["COL5A3", "collagen type V alpha 3 chain", "magenta", "0.864722139", "7.50448E-06", "0.96496314", "4.02139E-10", "4.71", "2.690812909", "6.65E-08", "up"], ["CXCL13", "C-X-C motif chemokine ligand 13", "magenta", "0.676038594", "2.89E-03", "0.808787134", "8.47082E-05", "20.9", "2.692421845", "0.00000669", "up"], ["CYP2E1", "cytochrome P450 family 2 subfamily E member 1", "magenta", "0.813393515", "7.1566E-05", "0.937472578", "2.85784E-08", "4.5", "2.3219305", "4.78E-08", "up"], ["CYP4B1", "cytochrome P450 family 4 subfamily B member 1", "magenta", "0.736111943", "0.000754364", "0.858320627", "1.04106E-05", "4.5", "3.0752333", "0.000000839", "up"], ["DKK1", "dickkopf WNT signaling pathway inhibitor 1", "magenta", "0.697058489", "0.001871854", "0.815860925", "6.53E-05", "4.71", "3.533265993", "0.000000546", "up"], ["FSTL3", "follistatin like 3", "magenta", "0.76382863", "0.000358509", "0.894831724", "1.24E-06", "5.067", "2.997977144", "0.000000244", "up"], ["KLF4", "Kruppel like factor 4", "magenta", "0.725261009", "0.000985574", "0.884368596", "2.45E-06", "4.71", "3.223838581", "9.88E-08", "up"], ["NR4A2", "nuclear receptor subfamily 4 group A member 2", "magenta", "0.800101777", "0.000115047", "0.864686086", "7.52E-06", "4.71", "3.44866934", "4.88E-08", "up"], ["PROK1", "prokineticin 1", "magenta", "0.830706844", "3.6373E-05", "0.807977649", "8.72E-05", "11", "4.082022638", "1.93E-08", "up"], ["WDR27", "WD repeat domain 27", "magenta", "0.790440633", "0.000159037", "0.950669894", "5.02E-09", "3", "2.232448342", "9.99E-08", "up"]], "row_count": 30, "column_count": 11, "numeric_cells": 220, "header_rows": 2, "locator": "section[17]/table-wrap[1]#T3"}}], "gaps": ["asset:data:geo:GSE120103 not downloaded", "asset:data:geo:GSE120103 licence not read", "asset:data:geo:GSE51981 not downloaded", "asset:data:geo:GSE51981 licence not read", "asset:data:geo:GSE7305 not downloaded", "asset:data:geo:GSE7305 licence not read", "asset:data:geo:GSE7307 not downloaded", "asset:data:geo:GSE7307 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": "protein-protein interaction"}}, {"id": "method-2", "family": null, "specific": null, "label": "Weighted gene co-expression network analysis (WGCNA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "\"We used the WGCNA R package to establish co-expression networks 14 for the genes in GSE7305 and GSE120103.\" \"Expression profiles of endometriosis-associated mRNAs in GSE7305, GSE120103, GSE7307 and GSE51981 were downloaded from Gene Expression Omnibus (GEO) database.\""}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE7305", "GSE120103", "GSE7307", "GSE51981"], "resolved_accessions": ["GSE7305", "GSE120103", "GSE7307", "GSE51981"], "statements": ["The following publicly-available datasets were analyzed in this study: [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE120103]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7305]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi]; [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE51981]."], "basis": "The paper names GSE7305, GSE120103, GSE7307, GSE51981 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": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:34522169", "data:geo:GSE120103", "asset:table:pmid:34522169:1", "asset:table:pmid:34522169:2", "asset:table:pmid:34522169:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE120103"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:34:41Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 26347, "completion_tokens": 1966, "cached_tokens": 784}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:34522169", "type": "paper", "label": "pmid:34522169"}, {"id": "source:pmid:34522169", "type": "manuscript", "label": "PMID 34522169 full text"}, {"id": "data:geo:GSE120103", "type": "dataset", "label": "GEO GSE120103"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34522169", "type": "paper", "label": "pmid:34522169"}, {"id": "source:pmid:34522169", "type": "manuscript", "label": "PMID 34522169 full text"}, {"id": "data:geo:GSE120103", "type": "dataset", "label": "GEO GSE120103"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34522169", "type": "extraction", "used": ["source:pmid:34522169"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE120103", "type": "accession_resolution", "used": ["data:geo:GSE120103"], "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:34522169", "parent_hash": "sha256:f91e74a7c79fa07942858374b267f0e963dabba331c10c427c9686fed36b884c", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE120103 licence not read", "asset:data:geo:GSE120103 not downloaded", "asset:data:geo:GSE51981 licence not read", "asset:data:geo:GSE51981 not downloaded", "asset:data:geo:GSE7305 licence not read", "asset:data:geo:GSE7305 not downloaded", "asset:data:geo:GSE7307 licence not read", "asset:data:geo:GSE7307 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["). Material and Method: EC and EU-associated microarray datasets were obtained from the gene express", "m. Results: We obtained EC and EU-associated microarray datasets GSE7305 and GSE120103. Genes in the"], "order_basis": "paper_text_order:449", "id": "assay:1"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T03:10:31+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}}}