Identification of endometriosis-associated genes and pathways based on bioinformatic analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34232189", "kind": "science-record", "revision": 5, "content_hash": "sha256:3f860445f772ee59cb3902fe4806c9a45e655b1e7ac3a995d442363376984455", "created_at": "2026-11-01T15:41:42Z", "updated_at": "2026-11-01T22:04:08Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of endometriosis-associated genes and pathways based on bioinformatic analysis.", "doi": "10.1097/MD.0000000000026530", "pmid": "34232189", "authors": ["Ting Wang", "Ruoan Jiang", "Yingsha Yao", "Linhua Qian", "Yu Zhao", "Xiufeng Huang"], "journal": "Medicine", "year": 2021, "abstract": "ABSTRACT: Endometriosis is associated with dysmenorrhea, chronic pelvic pain, and infertility. The specific mechanism of endometriosis remains unclear. The aim of this study was to apply a bioinformatics approach to reveal related pathways or genes involved in the development of endometriosis.The gene expression profiles of GSE25628, GSE5108, and GSE7305 were downloaded from the gene expression omnibus (GEO) database. Differentially expressed gene (DEG) analysis was performed using GEO2R. The database for annotation, visualization, and integrated discovery (DAVID) was utilized to analyze the functional enrichment, gene ontology (GO) and kyoto encyclopedia of genes and genomes (KEGG) pathway of the differentially expressed genes. A protein-protein interaction (PPI) network was constructed and module analysis was performed using search tool for the retrieval of interacting genes and cytoscape.A total of 119 common differentially expressed genes were extracted, consisting of 51 downregulated genes and 68 upregulated genes. The enriched functions and pathways of the DEGs and hub genes include DNA strand separation, cellular proliferation, degradation of the extracellular matrix, encoding of smooth muscle myosin as a major contractile protein, exiting the proliferative cycle and entering quiescence, growth regulation, and implication in a wide variety of biological processes.A bioinformatics approach combined with cell experiments in this study revealed that identifying DEGs and hub genes leads to better understanding of the molecular mechanisms underlying the progression of endometriosis, and efficient biomarkers underlying this pathway need to be further investigated.", "claims": [{"id": "claim-data-access", "statement": "The datasets generated during and/or analyzed during the current study are publicly available.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34232189", "locator": "sections[17] \"Footnotes\" paragraph 2", "quote": "The datasets generated during and/or analyzed during the current study are publicly available."}], "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:34232189"], "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:GSE25628"], "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:GSE25628"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34232189", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/MD.0000000000026530", "sha256": "sha256:473c534a43604e8cd035c3822b65c86c9d212e67d465f3b68778bdf5099ddb67", "bytes": 31127, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/MD.0000000000026530", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8270630", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE25628", "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=GSE25628", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE25628", "version": null, "note": "The datasets generated during and/or analyzed during the current study are publicly available.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated during and/or analyzed during the current study are publicly available.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM629719", "GSM629720", "GSM629721", "GSM629722", "GSM629723", "GSM629724", "GSM629725", "GSM629726", "GSM629727", "GSM629728", "GSM629729", "GSM629730", "GSM629731", "GSM629732", "GSM629733", "GSM629734", "GSM629735", "GSM629736", "GSM629737", "GSM629738", "GSM629739", "GSM629740"], "sample_count": 22, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Endometriosis transcription profiling", "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:GSE5108", "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=GSE5108", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE5108", "version": null, "note": "The datasets generated during and/or analyzed during the current study are publicly available.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated during and/or analyzed during the current study are publicly available.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM114997", "GSM114998", "GSM114999", "GSM115000", "GSM115001", "GSM115002", "GSM115003", "GSM115004", "GSM115005", "GSM115006", "GSM115007", "GSM115008", "GSM115009", "GSM115010", "GSM115011", "GSM115012", "GSM115013", "GSM115014", "GSM115015", "GSM115016", "GSM115018", "GSM115019"], "sample_count": 22, "group_sizes": null, "group_sizes_basis": null, "platform": "2895", "taxon": "Homo sapiens", "title": "Whole human genome DNA microarray analysis of gene expression in ectopic vs. eutopic endometrium", "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 datasets generated during and/or analyzed during the current study are publicly available.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated during and/or analyzed during the current study are publicly available.", "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": "asset:table:pmid:34232189:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:08a7bfa30dced1144b2614f9210dda95d245e0e60f2928af84cd123e07609803", "bytes": 713, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T3", "version": null, "note": "GO and KEGG analysis of DEGs in the most significant module (P < .01).", "structure": {"pmcid": "PMC8270630", "section_index": 6, "section_title": "Protein-protein interaction network construction and module analysis", "row_count": 9, "column_count": 4}, "table": {"label": "Table 3", "caption": "GO and KEGG analysis of DEGs in the most significant module (P < .01).", "rows": [["Pathway ID", "Pathway description", "Count", "FDR"], ["GO:0005539", "Glycosaminoglycan binding", "8", "0.0675376"], ["GO:1901681", "Sulfur compound binding", "8", "0.1265086"], ["GO:0004181", "Metallocarboxypeptidase activity", "4", "0.9614553"], ["GO:0008201", "Heparin binding", "6", "0.9705039"], ["hsa04512", "ECM-receptor interaction", "6", "0.8194419"], ["hsa04270", "Vascular smooth muscle contraction", "6", "3.4249874"], ["hsa04530", "Tight junction", "5", "6.3134673"], ["hsa04510", "Focal adhesion", "7", "7.225584"]], "row_count": 9, "column_count": 4, "numeric_cells": 24, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:34232189:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1737250506021ad2e224ff3a7b819d85f545dd426cbbac27daedca06425a536d", "bytes": 819, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T4", "version": null, "note": "Functional roles of 5 hub genes.", "structure": {"pmcid": "PMC8270630", "section_index": 7, "section_title": "Hub gene selection and analysis", "row_count": 6, "column_count": 4}, "table": {"label": "Table 4", "caption": "Functional roles of 5 hub genes.", "rows": [["Number", "Gene symbol", "Full name", "Function"], ["1", "HELLS", "Helicase, lymphoid specific", "DNA strand separation, cellular proliferation"], ["2", "TIMP2", "TIMP metallopeptidase inhibitor 2", "Degradation of the extracellular matrix"], ["3", "MYH11", "Myosin heavy chain 11", "Encode smooth muscle myosin as a major contractile protein"], ["4", "QSOX1", "Quiescin sulfhydryl oxidase 1", "Exit the proliferative cycle and enter quiescence, growth regulation"], ["5", "LAMA4", "Laminin subunit alpha 4", "Implicate in a wide variety of biological processes including cell adhesion, differentiation, migration, signaling, neurite outgrowth and metastasis"]], "row_count": 6, "column_count": 4, "numeric_cells": 10, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T4"}}, {"id": "asset:table:pmid:34232189:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e4bf0d72335305e1810e9a6f234dd3fca0dd45f23504d5a0c2dfb0f3766d9b6c", "bytes": 2227, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T1", "version": null, "note": "GO analysis of the common differentially expressed genes (P < .0001).", "structure": {"pmcid": "PMC8270630", "section_index": 10, "section_title": "Gene ontology functional enrichment analysis", "row_count": 33, "column_count": 5}, "table": {"label": "Table 1", "caption": "GO analysis of the common differentially expressed genes (P < .0001).", "rows": [["Category", "Term", "Description", "Count", "Fold enrichment"], ["Downregulated", "", "", "", ""], ["GO MF", "GO:0030674", "Protein binding, bridging", "2", "33.48245614"], ["GO CC", "GO:0005923", "Bicellular tight junction", "4", "17.74306445"], ["", "GO:0070160", "Occluding junction", "4", "17.02375102"], ["", "GO:0043296", "Apical junction complex", "4", "14.82067736"], ["", "GO:0072686", "Mitotic spindle", "3", "20.9959596"], ["GO BP", "GO:0007049", "Cell cycle", "11", "3.825756266"], ["", "GO:0000278", "Mitotic cell cycle", "8", "5.095283318"], ["", "GO:1903047", "Mitotic cell cycle process", "7", "5.183658447"], ["", "GO:0051726", "Regulation of cell cycle", "8", "4.168868169"], ["", "GO:0000280", "Nuclear division", "6", "5.914747673"], ["", "GO:0007067", "Mitotic nuclear division", "5", "7.85630613"], ["", "GO:0048285", "Organelle fission", "6", "5.398926655"], ["", "GO:0051445", "regulation of meiotic cell cycle", "3", "28.13986014"], ["Upregulated", "", "", "", ""], ["GO MF", "GO:1901681", "Sulfur compound binding", "8", "12.56706192"], ["", "GO:0005539", "Glycosaminoglycan binding", "7", "12.13978182"], ["", "GO:0008201", "Heparin binding", "6", "14.13794466"], ["", "GO:0004181", "Metallocarboxypeptidase activity", "4", "37.70118577"], ["", "GO:0004180", "Carboxypeptidase activity", "4", "25.50374332"], ["", "GO:0008238", "Exopeptidase activity", "5", "13.21840355"], ["GO CC", "GO:0031012", "Extracellular matrix", "17", "10.92711213"], ["", "GO:0044421", "Extracellular region part", "32", "2.171676543"], ["", "GO:0005576", "Extracellular region", "32", "2.008260584"], ["", "GO:0005578", "Proteinaceous extracellular matrix", "8", "7.509960509"], ["", "GO:0070062", "Extracellular exosome", "23", "2.071438795"], ["", "GO:1903561", "Extracellular vesicle", "23", "2.06223649"], ["", "GO:0043230", "Extracellular organelle", "23", "2.061320755"], ["", "GO:0005615", "Extracellular space", "14", "2.961868597"], ["GO BP", "GO:0072359", "Circulatory system development", "12", "3.726522906"], ["", "GO:0072358", "Cardiovascular system development", "12", "3.726522906"], ["", "GO:0001568", "Blood vessel development", "9", "4.553181156"]], "row_count": 33, "column_count": 5, "numeric_cells": 90, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:34232189:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ec103df5318bff7702ac0d7332014b58227b4dfbca8cf73fa7a3000000381d3b", "bytes": 875, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T2", "version": null, "note": "KEGG pathway enrichment analysis of the common differentially expressed genes (P < .05).", "structure": {"pmcid": "PMC8270630", "section_index": 11, "section_title": "Kyoto encyclopedia of genes and genomes pathway enrichment analysis", "row_count": 12, "column_count": 5}, "table": {"label": "Table 2", "caption": "KEGG pathway enrichment analysis of the common differentially expressed genes (P < .05).", "rows": [["KEGG pathway", "Term", "Description", "Count", "Fold enrichment"], ["Downregulated", "", "", "", ""], ["", "hsa05200", "Pathways in cancer", "5", "4.326923077"], ["", "hsa04270", "Vascular smooth muscle contraction", "3", "8.728448276"], ["Upregulated", "", "", "", ""], ["", "hsa04510", "Focal adhesion", "6", "5.590062112"], ["", "hsa04512", "ECM-receptor interaction", "4", "8.866995074"], ["", "hsa04530", "Tight junction", "4", "8.766233766"], ["", "hsa04670", "Leukocyte transendothelial migration", "4", "6.650246305"], ["", "hsa05144", "Malaria", "3", "11.80758017"], ["", "hsa04145", "Phagosome", "4", "5.672268908"], ["", "hsa00590", "Arachidonic acid metabolism", "3", "9.484777518"]], "row_count": 12, "column_count": 5, "numeric_cells": 27, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:34232189:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:08a7bfa30dced1144b2614f9210dda95d245e0e60f2928af84cd123e07609803", "bytes": 713, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T3", "version": null, "note": "GO and KEGG analysis of DEGs in the most significant module (P < .01).", "structure": {"pmcid": "PMC8270630", "section_index": 12, "section_title": "Protein-protein interaction network construction and module analysis", "row_count": 9, "column_count": 4}, "table": {"label": "Table 3", "caption": "GO and KEGG analysis of DEGs in the most significant module (P < .01).", "rows": [["Pathway ID", "Pathway description", "Count", "FDR"], ["GO:0005539", "Glycosaminoglycan binding", "8", "0.0675376"], ["GO:1901681", "Sulfur compound binding", "8", "0.1265086"], ["GO:0004181", "Metallocarboxypeptidase activity", "4", "0.9614553"], ["GO:0008201", "Heparin binding", "6", "0.9705039"], ["hsa04512", "ECM-receptor interaction", "6", "0.8194419"], ["hsa04270", "Vascular smooth muscle contraction", "6", "3.4249874"], ["hsa04530", "Tight junction", "5", "6.3134673"], ["hsa04510", "Focal adhesion", "7", "7.225584"]], "row_count": 9, "column_count": 4, "numeric_cells": 24, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:34232189:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1737250506021ad2e224ff3a7b819d85f545dd426cbbac27daedca06425a536d", "bytes": 819, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T4", "version": null, "note": "Functional roles of 5 hub genes.", "structure": {"pmcid": "PMC8270630", "section_index": 13, "section_title": "Hub gene selection and analysis", "row_count": 6, "column_count": 4}, "table": {"label": "Table 4", "caption": "Functional roles of 5 hub genes.", "rows": [["Number", "Gene symbol", "Full name", "Function"], ["1", "HELLS", "Helicase, lymphoid specific", "DNA strand separation, cellular proliferation"], ["2", "TIMP2", "TIMP metallopeptidase inhibitor 2", "Degradation of the extracellular matrix"], ["3", "MYH11", "Myosin heavy chain 11", "Encode smooth muscle myosin as a major contractile protein"], ["4", "QSOX1", "Quiescin sulfhydryl oxidase 1", "Exit the proliferative cycle and enter quiescence, growth regulation"], ["5", "LAMA4", "Laminin subunit alpha 4", "Implicate in a wide variety of biological processes including cell adhesion, differentiation, migration, signaling, neurite outgrowth and metastasis"]], "row_count": 6, "column_count": 4, "numeric_cells": 10, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T4"}}], "gaps": ["asset:data:geo:GSE25628 not downloaded", "asset:data:geo:GSE25628 licence not read", "asset:data:geo:GSE5108 not downloaded", "asset:data:geo:GSE5108 licence not read", "asset:data:geo:GSE7305 not downloaded", "asset:data:geo:GSE7305 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": "GEO2R", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "“Differentially expressed gene (DEG) analysis for the 3 datasets were carried out using GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r/).” “Three gene expression datasets [GSE25628 (Platforms: GPL571, Affymetrix Human Genome U133A 2.0 Array),[11] GSE5108 (Platforms: GPL2895, GE Healthcare/Amersham Biosciences CodeLink Human Whole Genome Bioarray),[12] and GSE7305 (Platforms: GPL570, Affymetrix Human Genome U133 Plus 2.0 Array)][13] were downloaded from GEO.”"}}], "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": ["GSE25628", "GSE5108", "GSE7305"], "resolved_accessions": ["GSE25628", "GSE5108", "GSE7305"], "statements": ["The datasets generated during and/or analyzed during the current study are publicly available."], "basis": "The paper names GSE25628, GSE5108, GSE7305 in gene expression omnibus (GEO) database 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:34232189", "data:geo:GSE25628", "asset:table:pmid:34232189:1", "asset:table:pmid:34232189:2", "asset:table:pmid:34232189:3", "asset:table:pmid:34232189:4", "asset:table:pmid:34232189:5", "asset:table:pmid:34232189:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE25628"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:31:52Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 23169, "completion_tokens": 1767, "cached_tokens": 792}}, "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:34232189", "type": "paper", "label": "pmid:34232189"}, {"id": "source:pmid:34232189", "type": "manuscript", "label": "PMID 34232189 full text"}, {"id": "data:geo:GSE25628", "type": "dataset", "label": "GEO GSE25628"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34232189", "type": "paper", "label": "pmid:34232189"}, {"id": "source:pmid:34232189", "type": "manuscript", "label": "PMID 34232189 full text"}, {"id": "data:geo:GSE25628", "type": "dataset", "label": "GEO GSE25628"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34232189", "type": "extraction", "used": ["source:pmid:34232189"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE25628", "type": "accession_resolution", "used": ["data:geo:GSE25628"], "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:34232189", "parent_hash": "sha256:76bce5973e95e45662df324a5b8c7381b44ea00065b2a0a31ed7907010e88d68", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE25628 licence not read", "asset:data:geo:GSE25628 not downloaded", "asset:data:geo:GSE5108 licence not read", "asset:data:geo:GSE5108 not downloaded", "asset:data:geo:GSE7305 licence not read", "asset:data:geo:GSE7305 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": "analysis_only", "id": "assay:1"}]}