{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34508138", "kind": "science-record", "revision": 5, "content_hash": "sha256:fc2cf0d1a46a97d09a811ad1ef7acf52521c7679a303624a51a61d2e7e14432c", "created_at": "2026-11-01T15:41:51Z", "updated_at": "2026-11-01T21:26:11Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "An integrated analysis of mRNAs, lncRNAs, and miRNAs based on weighted gene co-expression network analysis involved in bovine endometritis.", "doi": "10.1038/s41598-021-97319-y", "pmid": "34508138", "authors": ["Negin Sheybani", "Mohammad Reza Bakhtiarizadeh", "Abdolreza Salehi"], "journal": "Scientific reports", "year": 2021, "abstract": "In dairy cattle, endometritis is a severe infectious disease that occurs following parturition. It is clear that genetic factors are involved in the etiology of endometritis, however, the molecular pathogenesis of endometritis is not entirely understood. In this study, a system biology approach was used to better understand the molecular mechanisms underlying the development of endometritis. Forty transcriptomic datasets comprising of 20 RNA-Seq (GSE66825) and 20 miRNA-Seq (GSE66826) were obtained from the GEO database. Next, the co-expressed modules were constructed based on RNA-Seq (Rb-modules) and miRNA-Seq (mb-modules) data, separately, using a weighted gene co-expression network analysis (WGCNA) approach. Preservation analysis was used to find the non-preserved Rb-modules in endometritis samples. Afterward, the non-preserved Rb-modules were assigned to the mb-modules to construct the integrated regulatory networks. Just highly connected genes (hubs) in the networks were considered and functional enrichment analysis was used to identify the biological pathways associated with the development of the disease. Furthermore, additional bioinformatic analysis including protein-protein interactions network and miRNA target prediction were applied to enhance the reliability of the results. Thirty-five Rb-modules and 10 mb-modules were identified and 19 and 10 modules were non-preserved, respectively, which were enriched in biological pathways related to endometritis like inflammation and ciliogenesis. Two non-preserved Rb-modules were significantly assigned to three mb-modules and three and two important sub-networks in the Rb-modules were identified, respectively, including important mRNAs, lncRNAs and miRNAs genes like IRAK1, CASP3, CCDC40, CCDC39, ZMYND10, FOXJ1, TLR4, IL10, STAT3, FN1, AKT1, CD68, ENSBTAG00000049936, ENSBTAG00000050527, ENSBTAG00000051242, ENSBTAG00000049287, bta-miR-449, bta-miR-484, bta-miR-149, bta-miR-30b and bta-miR-423. The potential roles of these genes have been previously demonstrated in endometritis or related pathways, which reinforced putative functions of the suggested integrated regulatory networks in the endometritis pathogenesis. These findings may help further elucidate the underlying mechanisms of bovine endometritis.", "claims": [{"id": "claim-method", "statement": "To assign the mb-modules to Rb-modules, spearman correlations were calculated between the MEs of Rb-modules and mb-modules.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34508138", "locator": "sections[9] \"Assign the mb-modules to the Rb-modules and target prediction\" paragraph 2", "quote": "To assign the mb-modules to Rb-modules, spearman correlations were calculated between the MEs of Rb-modules and mb-modules."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Raw RNA-Seq and miRNA-Seq data were obtained from the Gene Expression Omnibus (GEO) database at the National Center for Biotechnology Information (NCBI) under the accession number GSE66827. The data contained endometrial samples related to nine healthy and six endometritis cows at 7 and 21 days post-partum6.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34508138", "locator": "sections[3] \"Dataset\" paragraph 2", "quote": "Raw RNA-Seq and miRNA-Seq data were obtained from the Gene Expression Omnibus (GEO) database at the National Center for Biotechnology Information (NCBI) under the accession number GSE66827. The data contained endometrial samples related to nine healthy and six endometritis cows at 7 and 21 days post-partum6."}], "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:34508138"], "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:GSE66825"], "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:GSE66825"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34508138", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-021-97319-y", "sha256": "sha256:0a8e3609767a4a8322da11a1155d1fc5b3206b804a7348a1782215ea55ff71b2", "bytes": 71495, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-021-97319-y", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8433134", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE66825", "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=GSE66825", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66825", "version": null, "note": "Raw RNA-Seq and miRNA-Seq data were obtained from the Gene Expression Omnibus (GEO) database at the National Center for Biotechnology Information (NCBI) under the accession number GSE66827. The data contained endometrial samples related to nine healthy and six endometritis cows at 7 and 21 days post-partum6.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw RNA-Seq and miRNA-Seq data were obtained from the Gene Expression Omnibus (GEO) database at the National Center for Biotechnology Information (NCBI) under the accession number GSE66827. The data contained endometrial samples related to nine healthy and six endometritis cows at 7 and 21 days post-partum6.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1632769", "GSM1632770", "GSM1632771", "GSM1632772", "GSM1632773", "GSM1632774", "GSM1632775", "GSM1632776", "GSM1632777", "GSM1632778", "GSM1632779", "GSM1632780", "GSM1632781", "GSM1632782", "GSM1632783", "GSM1632784", "GSM1632785", "GSM1632786", "GSM1632787", "GSM1632788", "GSM1632789", "GSM1632790", "GSM1632791", "GSM1632792", "GSM1632793", "GSM1632794", "GSM1632795", "GSM1632796", "GSM1632797", "GSM1632798"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "15749", "taxon": "Bos taurus", "title": "Dysregulation of Endometrial Inflammation Precedes the Development of Cytological Endometritis [mRNA]", "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:GSE66826", "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=GSE66826", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66826", "version": null, "note": "Raw RNA-Seq and miRNA-Seq data were obtained from the Gene Expression Omnibus (GEO) database at the National Center for Biotechnology Information (NCBI) under the accession number GSE66827. The data contained endometrial samples related to nine healthy and six endometritis cows at 7 and 21 days post-partum6.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw RNA-Seq and miRNA-Seq data were obtained from the Gene Expression Omnibus (GEO) database at the National Center for Biotechnology Information (NCBI) under the accession number GSE66827. The data contained endometrial samples related to nine healthy and six endometritis cows at 7 and 21 days post-partum6.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1632799", "GSM1632800", "GSM1632801", "GSM1632802", "GSM1632803", "GSM1632804", "GSM1632805", "GSM1632806", "GSM1632807", "GSM1632808", "GSM1632809", "GSM1632810", "GSM1632811", "GSM1632812", "GSM1632813", "GSM1632814", "GSM1632815", "GSM1632816", "GSM1632817", "GSM1632818"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "15749", "taxon": "Bos taurus", "title": "Dysregulation of Endometrial Inflammation Precedes the Development of Cytological Endometritis [miRNA]", "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:GSE66827", "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=GSE66827", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66827", "version": null, "note": "Raw RNA-Seq and miRNA-Seq data were obtained from the Gene Expression Omnibus (GEO) database at the National Center for Biotechnology Information (NCBI) under the accession number GSE66827. The data contained endometrial samples related to nine healthy and six endometritis cows at 7 and 21 days post-partum6.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw RNA-Seq and miRNA-Seq data were obtained from the Gene Expression Omnibus (GEO) database at the National Center for Biotechnology Information (NCBI) under the accession number GSE66827. The data contained endometrial samples related to nine healthy and six endometritis cows at 7 and 21 days post-partum6.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1632769", "GSM1632770", "GSM1632771", "GSM1632772", "GSM1632773", "GSM1632774", "GSM1632775", "GSM1632776", "GSM1632777", "GSM1632778", "GSM1632779", "GSM1632780", "GSM1632781", "GSM1632782", "GSM1632783", "GSM1632784", "GSM1632785", "GSM1632786", "GSM1632787", "GSM1632788", "GSM1632789", "GSM1632790", "GSM1632791", "GSM1632792", "GSM1632793", "GSM1632794", "GSM1632795", "GSM1632796", "GSM1632797", "GSM1632798", "GSM1632799", "GSM1632800", "GSM1632801", "GSM1632802", "GSM1632803", "GSM1632804", "GSM1632805", "GSM1632806", "GSM1632807", "GSM1632808", "GSM1632809", "GSM1632810", "GSM1632811", "GSM1632812", "GSM1632813", "GSM1632814", "GSM1632815", "GSM1632816", "GSM1632817", "GSM1632818"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "15749", "taxon": "Bos taurus", "title": "Dysregulation of Endometrial Inflammation Precedes the Development of Cytological Endometritis", "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:34508138:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:99d5884de8d9f4cd9c5064ae28beaa4ce2b38a8ba541b8b2d02f330e187f1f25", "bytes": 783, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#Tab1", "version": null, "note": "Results of assignment of the mb-modules to the non-preserved Rb-modules.", "structure": {"pmcid": "PMC8433134", "section_index": 17, "section_title": "Assigning the mb-modules to the Rb-modules and target prediction", "row_count": 11, "column_count": 4}, "table": {"label": "Table 1", "caption": "Results of assignment of the mb-modules to the non-preserved Rb-modules.", "rows": [["mb-module (number of miRNAs)", "Rb-module (number of genes)", "Correlation", "Adjusted p-value"], ["Blue (60)", "Blue (2368)", "− 0.77", "0.2"], ["Blue (60)", "Brown (1006)", "− 0.84", "0.2"], ["Blue (60)", "Turquoise (3188)", "0.84", "0.2"], ["Brown (47)", "Blue (2368)", "− 0.75", "0.2"], ["Brown (47)", "Brown (1006)", "− 0.84", "0.2"], ["Brown (47)", "Turquoise (3188)", "0.78", "0.2"], ["Purple (15)", "Blue (2368)", "0.76", "0.2"], ["Purple (15)", "Brown (1006)", "0.94", "0.2"], ["Purple (15)", "Turquoise (3188)", "− 0.83", "0.2"], ["Yellow (31)", "Brown (1006)", "− 0.77", "0.2"]], "row_count": 11, "column_count": 4, "numeric_cells": 40, "header_rows": 1, "locator": "section[17]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:34508138:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e51e896159756c057e7394658e9474e2ffb71415e46d2ed6c4c966bb88ad0d88", "bytes": 1228, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[2]#Tab2", "version": null, "note": "The summary of the target prediction results for the mb-modules that were negatively correlated with mb-modules.", "structure": {"pmcid": "PMC8433134", "section_index": 17, "section_title": "Assigning the mb-modules to the Rb-modules and target prediction", "row_count": 13, "column_count": 4}, "table": {"label": "Table 2", "caption": "The summary of the target prediction results for the mb-modules that were negatively correlated with mb-modules.", "rows": [["Software", "mb-module (number of miRNAs)", "Rb-module (number of genes)", "Number of the unique predicted targets"], ["miRanda", "Blue (54)", "Brown (1006)", "525 mRNAs, 41 TFs and 8 lncRNAs"], ["Brown (44)", "Brown (1006)", "553 mRNAs, 35 TFs and 7 lncRNAs"], ["Purple (13)", "Turquoise (3188)", "997 mRNAs, 60 TFs and 28 lncRNAs"], ["RNAhybrid", "Blue (54)", "Brown (1006)", "412 mRNAs, 29 TFs and 7 lncRNAs"], ["Brown (44)", "Brown (1006)", "398 mRNAs, 30 TFs and 8 lncRNAs"], ["Purple (13)", "Turquoise (3188)", "326 mRNAs, 20 TFs and 16 lncRNAs"], ["RNA22", "Blue (54)", "Brown (1006)", "654 mRNAs, 45 TFs and 8 lncRNAs"], ["Brown (44)", "Brown (1006)", "645 mRNAs, 45 TFs and 8 lncRNAs"], ["Purple (13)", "Turquoise (3188)", "1122 mRNAs, 60 TFs and 32 lncRNAs"], ["Common results of all softwares", "Blue (54)", "Brown (1006)", "130 mRNAs, 15 TFs and 6 lncRNAs"], ["Brown (44)", "Brown (1006)", "142 mRNAs, 13 TFs and 2 lncRNAs"], ["Purple (13)", "Turquoise (3188)", "59 mRNAs, 4 TFs and 4 lncRNAs"]], "row_count": 13, "column_count": 4, "numeric_cells": 37, "header_rows": 1, "locator": "section[17]/table-wrap[2]#Tab2"}}, {"id": "asset:table:pmid:34508138:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1a0a6be5b6a098b32b0e2fd8ec1b62ec324a38e9d94bd0408e2c15a25b8f4873", "bytes": 1143, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#Tab3", "version": null, "note": "The summary of the interactions in the integrated regulatory networks.", "structure": {"pmcid": "PMC8433134", "section_index": 18, "section_title": "Detection of hub-hub genes and integrated regulatory network construction", "row_count": 10, "column_count": 4}, "table": {"label": "Table 3", "caption": "The summary of the interactions in the integrated regulatory networks.", "rows": [["Rb-module (total number of hub genes)", "Brown (692 genes including 6 lncRNAs, 49 TFs + and 637 mRNAs)", "Turquoise (1910 genes including 22 lncRNAs, 86 TFs and 1570 mRNAs)"], ["Number of hub mRNAs that were analyzed in STRING", "459", "1639"], ["Number of obtained interactions in STRING", "1015", "14,909"], ["p-value of the network in STRING", "1.0e−16", "1.0e−16"], ["Number of hub-mRNAs and hub-lncRNAs were imported into WGCNA", "692", "250"], ["Number of interactions among genes and lncRNAs predicted by WGCNA", "4131", "4995"], ["Number of hub-hub genes", "23 (6 lncRNAs and 17 mRNAs)", "24 (21 lncRNAs and 3 mRNAs)"], ["Assigned mb-module to Rb-module (total number of miRNAs)", "Brown (47)", "Blue (60)", "Purple (15)"], ["Number of interactions among miRNAs predicted by WGCNA", "Brown = 373", "Blue = 641", "PURPLE = 41"], ["Number of assigned miRNAs to genes of Rb-modules in each mb-module", "Brown = 22", "Blue = 19", "Purple = 7"]], "row_count": 10, "column_count": 4, "numeric_cells": 23, "header_rows": 1, "locator": "section[18]/table-wrap[1]#Tab3"}}], "gaps": ["asset:data:geo:GSE66825 not downloaded", "asset:data:geo:GSE66825 licence not read", "asset:data:geo:GSE66826 not downloaded", "asset:data:geo:GSE66826 licence not read", "asset:data:geo:GSE66827 not downloaded", "asset:data:geo:GSE66827 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To assign the mb-modules to Rb-modules, spearman correlations were calculated between the MEs of Rb-modules and mb-modules."}}], "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": ["spearman_rho"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: spearman."}, "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": ["GSE66827", "GSE66825", "GSE66826"], "resolved_accessions": ["GSE66827", "GSE66825", "GSE66826"], "statements": ["Raw RNA-Seq and miRNA-Seq data were obtained from the Gene Expression Omnibus (GEO) database at the National Center for Biotechnology Information (NCBI) under the accession number GSE66827. The data contained endometrial samples related to nine healthy and six endometritis cows at 7 and 21 days post-partum6."], "basis": "The paper names GSE66827, GSE66825, GSE66826 in Gene Expression Omnibus (GEO) database at the National Center for Biotechnology Information (NCBI) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["spearman_rho"], "assets": ["source:pmid:34508138", "data:geo:GSE66825", "asset:table:pmid:34508138:1", "asset:table:pmid:34508138:2", "asset:table:pmid:34508138:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE66825"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:34:32Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 55053, "completion_tokens": 1597, "cached_tokens": 528}}, "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:34508138", "type": "paper", "label": "pmid:34508138"}, {"id": "source:pmid:34508138", "type": "manuscript", "label": "PMID 34508138 full text"}, {"id": "data:geo:GSE66825", "type": "dataset", "label": "GEO GSE66825"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34508138", "type": "paper", "label": "pmid:34508138"}, {"id": "source:pmid:34508138", "type": "manuscript", "label": "PMID 34508138 full text"}, {"id": "data:geo:GSE66825", "type": "dataset", "label": "GEO GSE66825"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34508138", "type": "extraction", "used": ["source:pmid:34508138"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE66825", "type": "accession_resolution", "used": ["data:geo:GSE66825"], "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:34508138", "parent_hash": "sha256:398d238f97f3cd1a201dd4f0d2f898bd1f23e948f094472424776afa07194ac5", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE66825 licence not read", "asset:data:geo:GSE66825 not downloaded", "asset:data:geo:GSE66826 licence not read", "asset:data:geo:GSE66826 not downloaded", "asset:data:geo:GSE66827 licence not read", "asset:data:geo:GSE66827 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["rty transcriptomic datasets comprising of 20 RNA-Seq (GSE66825) and 20 miRNA-Seq (GSE66826) were", "-expressed modules were constructed based on RNA-Seq (Rb-modules) and miRNA-Seq (mb-modules) data", "lying the development of endometritis. Forty transcriptomic datasets comprising of 20 RNA-Seq (GSE66825)"], "order_basis": "paper_text_order:496", "id": "assay:1"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["spearman_rho"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["To assign the mb-modules to Rb-modules, spearman correlations were calculated between the MEs of Rb-modules and mb-modules."], "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":"2026-11-04T03:12:31+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}}}