Identification and Validation of Key Genes Associated With Systemic Sclerosis-Related Pulmonary Hypertension.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32793290", "kind": "science-record", "revision": 7, "content_hash": "sha256:ab06d6458fbee472c8d53da2e418a7da1be25770d4ad90c3c7c571eeeb636d76", "created_at": "2026-11-01T15:41:07Z", "updated_at": "2026-11-01T22:02:01Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification and Validation of Key Genes Associated With Systemic Sclerosis-Related Pulmonary Hypertension.", "doi": "10.3389/fgene.2020.00816", "pmid": "32793290", "authors": ["Ji-Na Zheng", "Yang Li", "Yue-Mei Yan", "Hui Shi", "Tian-Tian Zou", "Wen-Qi Shao", "Qiang Wang"], "journal": "Frontiers in genetics", "year": 2020, "abstract": "Systemic sclerosis-associated with pulmonary arterial hypertension (SSc-PAH) is still a major cause of SSc related deaths. Early diagnosis and prompt treatment are crucial to reduce the mortality of patients with SSc-PAH. To screen the candidate biomarkers and potential therapeutic targets for SSc-PAH, we analyzed the data set (GSE33463 and GSE19617) for confirming key genes in peripheral blood mononuclear cells from SSc-PAH patients. A total of 105 SSc patients from gene expression omnibus (GEO) were included as discovery cohort (n = 69) and duplication cohort (n = 36) for screening hub genes by weighted gene co-expression network analysis (WGCNA). Furthermore, an independent validation cohort (n = 40), including healthy controls, SSc and SSc-PAH patients, was used for further validation by quantitative real-time polymerase chain reaction. The results showed that four key genes, including IFIT2, IFIT3, RSAD2, and PARP14, may serve as potential biomarkers in SSc-PAH. Also, they could be independent risk factors for SSc-PAH. In conclusion, the four key genes can be expected to become the potential therapeutic targets and early biomarkers for accurate therapy and diagnosis of SSc-PAH in the future, which also provides promising insights into the pathogenesis of SSc-PAH at the molecular level.", "claims": [{"id": "claim-method", "statement": "ROC was utilized to determine the area under the curve (AUC) of each hub gene to evaluate the abilities for the diagnosis of SSc-PAH by SPSS 22.0.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32793290", "locator": "sections[11] \"Statistical Analysis\" paragraph 2", "quote": "ROC was utilized to determine the area under the curve (AUC) of each hub gene to evaluate the abilities for the diagnosis of SSc-PAH by SPSS 22.0."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. Discovery cohort and duplication cohort (GSE33463 and GSE19617) were downloaded from GEO (http://www.ncbi.nlm.nih.gov/geo/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32793290", "locator": "sections[20] \"Data Availability Statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. Discovery cohort and duplication cohort (GSE33463 and GSE19617) were downloaded from GEO (http://www.ncbi.nlm.nih.gov/geo/)."}], "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:32793290"], "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:GSE19617"], "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:GSE19617"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32793290", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2020.00816", "sha256": "sha256:bcd56d5036822cd3f7394dac49efbc6e99cf77d8955cfd87c03d2e974f08f13f", "bytes": 34702, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2020.00816", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7393672", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE19617", "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=GSE19617", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19617", "version": null, "note": "Publicly available datasets were analyzed in this study. Discovery cohort and duplication cohort (GSE33463 and GSE19617) were downloaded from GEO (http://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. Discovery cohort and duplication cohort (GSE33463 and GSE19617) were downloaded from GEO (http://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM489194", "GSM489195", "GSM489196", "GSM489197", "GSM489198", "GSM489199", "GSM489200", "GSM489201", "GSM489202", "GSM489203", "GSM489204", "GSM489205", "GSM489206", "GSM489207", "GSM489208", "GSM489209", "GSM489210", "GSM489211", "GSM489212", "GSM489213", "GSM489214", "GSM489215", "GSM489216", "GSM489217", "GSM489218", "GSM489219", "GSM489220", "GSM489221", "GSM489222", "GSM489223", "GSM489224", "GSM489225", "GSM489226", "GSM489227", "GSM489228", "GSM489229", "GSM489230", "GSM489231", "GSM489232", "GSM489233", "GSM489234", "GSM489235", "GSM489236", "GSM489237", "GSM489238", "GSM489239", "GSM489240", "GSM489241", "GSM489242", "GSM489243", "GSM489244", "GSM489245", "GSM489246", "GSM489247"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Limited systemic sclerosis patients with PAH show biomarkers of inflammation and vascular injury", "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:GSE33463", "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=GSE33463", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33463", "version": null, "note": "Publicly available datasets were analyzed in this study. Discovery cohort and duplication cohort (GSE33463 and GSE19617) were downloaded from GEO (http://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. Discovery cohort and duplication cohort (GSE33463 and GSE19617) were downloaded from GEO (http://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM827665", "GSM827666", "GSM827667", "GSM827668", "GSM827669", "GSM827670", "GSM827671", "GSM827672", "GSM827673", "GSM827674", "GSM827675", "GSM827676", "GSM827677", "GSM827678", "GSM827679", "GSM827680", "GSM827681", "GSM827682", "GSM827683", "GSM827684", "GSM827685", "GSM827686", "GSM827687", "GSM827688", "GSM827689", "GSM827690", "GSM827691", "GSM827692", "GSM827693", "GSM827694", "GSM827695", "GSM827696", "GSM827697", "GSM827698", "GSM827699", "GSM827700", "GSM827701", "GSM827702", "GSM827703", "GSM827704", "GSM827705", "GSM827706", "GSM827707", "GSM827708", "GSM827709", "GSM827710", "GSM827711", "GSM827712", "GSM827713", "GSM827714", "GSM827715", "GSM827716", "GSM827717", "GSM827718", "GSM827719", "GSM827720", "GSM827721", "GSM827722", "GSM827723", "GSM827724", "GSM827725", "GSM827726", "GSM827727", "GSM827728", "GSM827729", "GSM827730", "GSM827731", "GSM827732", "GSM827733", "GSM827734", "GSM827735", "GSM827736", "GSM827737", "GSM827738", "GSM827739", "GSM827740", "GSM827741", "GSM827742", "GSM827743", "GSM827744", "GSM827745", "GSM827746", "GSM827747", "GSM827748", "GSM827749", "GSM827750", "GSM827751", "GSM827752", "GSM827753", "GSM827754", "GSM827755", "GSM827756", "GSM827757", "GSM827758", "GSM827759", "GSM827760", "GSM827761", "GSM827762", "GSM827763", "GSM827764", "GSM827765", "GSM827766", "GSM827767", "GSM827768", "GSM827769", "GSM827770", "GSM827771", "GSM827772", "GSM827773", "GSM827774", "GSM827775", "GSM827776", "GSM827777", "GSM827778", "GSM827779", "GSM827780", "GSM827781", "GSM827782", "GSM827783", "GSM827784", "GSM827785", "GSM827786", "GSM827787", "GSM827788", "GSM827789", "GSM827790", "GSM827791", "GSM827792", "GSM827793", "GSM827794", "GSM827795", "GSM827796", "GSM827797", "GSM827798", "GSM827799", "GSM827800", "GSM827801", "GSM827802", "GSM827803", "GSM827804"], "sample_count": 140, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "Erythroid-Specific Transcriptional Changes in PBMCs from Pulmonary Hypertension Patients", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32793290:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2769a428fdffcab3f771acb043595e85df6f610cd06d10d14efc9cb910ff530d", "bytes": 523, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#T1", "version": null, "note": "The primers sequence.", "structure": {"pmcid": "PMC7393672", "section_index": 5, "section_title": "RNA Extraction and qRT-PCR", "row_count": 6, "column_count": 3}, "table": {"label": "TABLE 1", "caption": "The primers sequence.", "rows": [["Primers", "Forward (5′-3′)", "Reverse (5′-3′)"], ["IFIT2", "AAGCACCTCAAAGGGCAAAAC", "TCGGCCCATGTGATAGTAGAC"], ["IFIT3", "TCAGAAGTCTAGTCACTTGGGG", "ACACCTTCGCCCTTTCATTTC"], ["RSAD2", "CAGCGTCAACTATCACTTCACT", "AACTCTACTTTGCAGAACCTCAC"], ["PARP14", "TGTTAGTGGAGAACATAAGTGGC", "TGAATGGTGCTTGGTACAATCAT"], ["β-actin", "CGCGAGAAGATGACCCAGAT", "GGGCATACCCCTCGTAGATG"]], "row_count": 6, "column_count": 3, "numeric_cells": 3, "header_rows": 1, "locator": "section[5]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:32793290:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4e6de890adc1e870a226de87369d84b8adb56110758fda0549e935039ac7c8d1", "bytes": 1681, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#T2", "version": null, "note": "Subject characteristics.", "structure": {"pmcid": "PMC7393672", "section_index": 6, "section_title": "Gene Expression Profiles of SSc Patients and Processing", "row_count": 27, "column_count": 7}, "table": {"label": "TABLE 2", "caption": "Subject characteristics.", "rows": [["Variable", "Discovery cohort", "Duplication cohort", "Validation cohort"], ["", "SSc-PAH", "SSc", "SSc-PAH", "SSc", "SSc-PAH", "SSc"], ["Number", "50", "19", "15", "21", "10", "10"], ["Age (mean ± SD years)", "58 ± 10", "45 ± 12", "65 ± 6", "50 ± 11", "58 ± 9", "50 ± 8"], ["Gender n (%)"], ["Male", "11 (22)", "7 (24)", "3 (20)", "3 (14)", "2 (20)", "2 (20)"], ["Female", "39 (78)", "12 (76)", "12 (80)", "18 (86)", "8 (80)", "8 (80)"], ["Race n (%)"], ["African American", "8 (16)", "0", "NA", "NA", "0 (0)", "0 (0)"], ["Asian", "2 (4)", "0", "NA", "NA", "10 (100)", "10 (100)"], ["Caucasian", "40 (80)", "19 (100)", "NA", "NA", "0 (0)", "0 (0)"], ["Hispanic", "0", "0", "NA", "NA", "0 (0)", "0 (0)"], ["NYHA functional class n"], ["(% of the PAH subjects)"], ["I", "2 (4)", "NA", "NA", "NA", "0 (0)", "NA"], ["II", "23 (46)", "NA", "NA", "NA", "2 (20)", "NA"], ["III", "24 (48)", "NA", "NA", "NA", "8 (80)", "NA"], ["IV", "1 (2)", "NA", "NA", "NA", "0 (0)", "NA"], ["6-MWD (mean ± SD)", "1058 ± 346", "NA", "NA", "NA", "878 ± 317", "NA"], ["mPAP (mean ± SD)", "NA", "NA", "43.6 ± 9.0", "NA", "45.4 ± 7.4", "NA"], ["PCWP (mean ± SD)", "NA", "NA", "11.9 ± 3.6", "NA", "12.4 ± 3.0", "NA"], ["PVR (mean ± SD)", "NA", "NA", "513.8 ± 216.6", "NA", "NA", "NA"], ["FVC (% predicted) (mean ± SD)", "NA", "NA", "80.2 ± 17.3", "NA", "79.8 ± 19.4", "NA"], ["DLCO (% predicted) (mean ± SD)", "NA", "NA", "46.1 ± 9.8", "NA", "47.7 ± 11.6", "NA"], ["RAP (mean ± SD)", "7.8 ± 4.3", "NA", "NA", "NA", "8.4 ± 3.7", "NA"], ["CI (mean ± SD)", "2.7 ± 0.7", "NA", "NA", "NA", "3.0 ± 0.7", "NA"], ["PVRI", "969 ± 553", "NA", "NA", "NA", "998 ± 534", "NA"]], "row_count": 27, "column_count": 7, "numeric_cells": 66, "header_rows": 2, "locator": "section[6]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:32793290:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a5b54d2e0d59d6ad57db8a5f84080a9f88297e937d14180094a5fb5af7ed619e", "bytes": 1630, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#T3", "version": null, "note": "GO enrichment analysis of genes in co-expression modules.", "structure": {"pmcid": "PMC7393672", "section_index": 15, "section_title": "Functional Enrichment Analysis", "row_count": 23, "column_count": 5}, "table": {"label": "TABLE 3", "caption": "GO enrichment analysis of genes in co-expression modules.", "rows": [["Term ID", "Term ontology", "Count", "P-value", "Term name"], ["Saddlebrown module"], ["GO:0051607", "BP", "29", "8.55E-43", "Defense response to virus"], ["GO:0009615", "BP", "31", "1.89E-42", "Response to virus"], ["GO:0060337", "BP", "20", "3.09E-34", "Type I interferon signaling pathway"], ["GO:0071357", "BP", "20", "3.09E-34", "Cellular response to type I interferon"], ["GO:0034340", "BP", "20", "1.05E-33", "Response to type I interferon"], ["GO:0045071", "BP", "11", "1.55E-18", "Negative regulation of viral genome replication"], ["GO:0043900", "BP", "18", "2.81E-18", "Regulation of multi-organism process"], ["GO:0034341", "BP", "15", "3.71E-18", "Response to interferon-gamma"], ["GO:0048525", "BP", "12", "1.29E-17", "Negative regulation of viral process"], ["GO:1903901", "BP", "11", "1.29E-16", "Negative regulation of viral life cycle"], ["Purple module"], ["GO:0005622", "CC", "217", "2.60E-59", "Intracellular"], ["GO:0043170", "BP", "181", "2.91E-59", "Macromolecule metabolic process"], ["GO:0005488", "MF", "215", "6.00E-57", "Binding"], ["GO:0044424", "CC", "212", "6.00E-57", "Intracellular part"], ["GO:0071704", "BP", "190", "1.11E-56", "Organic substance metabolic process"], ["GO:0019222", "BP", "152", "1.11E-56", "Regulation of metabolic process"], ["GO:0044260", "BP", "172", "1.52E-56", "Cellular macromolecule metabolic process"], ["GO:0044464", "CC", "224", "8.41E-56", "Cell part"], ["GO:0005623", "CC", "224", "1.04E-55", "Cell"], ["GO:0008152", "BP", "191", "2.62E-55", "Metabolic process"]], "row_count": 23, "column_count": 5, "numeric_cells": 60, "header_rows": 1, "locator": "section[15]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:32793290:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:76c950dd7d9eec51f3dc134e851fec959a9f68bf13d7ebfe8227f8aa4e4a81f8", "bytes": 972, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#T4", "version": null, "note": "Univariate and multivariate logistic regression of hub genes and clinical traits.", "structure": {"pmcid": "PMC7393672", "section_index": 17, "section_title": "Four Hub Genes Could Be Good Diagnostic Biomarkers for SSc-PAH", "row_count": 11, "column_count": 7}, "table": {"label": "TABLE 4", "caption": "Univariate and multivariate logistic regression of hub genes and clinical traits.", "rows": [["Hub genes/clinical traits", "Univariate logistic regression", "Multivariate logistic regression"], ["", "OR", "95% CI", "P-value", "OR", "95% CI", "P-value"], ["Gender", "1.538", "0.268, 8.818", "0.629", "", "", ""], ["Age", "1.196", "1.069, 1.337", "0.002***", "0.620", "0.103, 3.717", "0.601"], ["ILD", "1.636", "0.384, 6.968", "0.505", "", "", ""], ["FVC (%predict)", "0.970", "0.932, 1.009", "0.134", "", "", ""], ["DLCO (%predict)", "0.890", "0.820, 0.966", "0.005**", "0.979", "0.173, 5.864", "0.980"], ["PAPR14", "2.222", "1.124, 4.394", "0.022*", "0.978", "0.172, 5.543", "0.997"], ["RSAD2", "3.705", "1.492, 9.200", "0.005**", "", "", ""], ["IFIT2", "4.157", "1.161, 10.734", "0.003***", "1.108", "0.890, 1.378", "0.363"], ["IFIT3", "3.705", "1.492, 9.200", "0.005**", "1.048", "0.959, 1.146", "0.298"]], "row_count": 11, "column_count": 7, "numeric_cells": 45, "header_rows": 2, "locator": "section[17]/table-wrap[1]#T4"}}], "gaps": ["asset:data:geo:GSE19617 not downloaded", "asset:data:geo:GSE19617 licence not read", "asset:data:geo:GSE33463 not downloaded", "asset:data:geo:GSE33463 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "logistic regression"}}, {"id": "method-2", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "dendrogram"}}, {"id": "method-3", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "PPI"}}, {"id": "method-4", "family": null, "specific": null, "label": "Receiver operating characteristic (ROC) analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "ROC was utilized to determine the area under the curve (AUC) of each hub gene to evaluate the abilities for the diagnosis of SSc-PAH by SPSS 22.0."}}], "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": ["glm_logit_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: logistic."}, "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": ["GSE33463", "GSE19617"], "resolved_accessions": ["GSE33463", "GSE19617"], "statements": ["Publicly available datasets were analyzed in this study. Discovery cohort and duplication cohort (GSE33463 and GSE19617) were downloaded from GEO (http://www.ncbi.nlm.nih.gov/geo/)."], "basis": "The paper names GSE33463, GSE19617 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": ["glm_logit_fit"], "assets": ["source:pmid:32793290", "data:geo:GSE19617", "asset:table:pmid:32793290:1", "asset:table:pmid:32793290:2", "asset:table:pmid:32793290:3", "asset:table:pmid:32793290:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE19617"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:50Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 26186, "completion_tokens": 1230, "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:32793290", "type": "paper", "label": "pmid:32793290"}, {"id": "source:pmid:32793290", "type": "manuscript", "label": "PMID 32793290 full text"}, {"id": "data:geo:GSE19617", "type": "dataset", "label": "GEO GSE19617"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32793290", "type": "paper", "label": "pmid:32793290"}, {"id": "source:pmid:32793290", "type": "manuscript", "label": "PMID 32793290 full text"}, {"id": "data:geo:GSE19617", "type": "dataset", "label": "GEO GSE19617"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32793290", "type": "extraction", "used": ["source:pmid:32793290"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE19617", "type": "accession_resolution", "used": ["data:geo:GSE19617"], "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:32793290", "parent_hash": "sha256:5227da5e3f8ae1a784e56291d2c40d0597432dc344c356e3372ea0805836d406", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE19617 licence not read", "asset:data:geo:GSE19617 not downloaded", "asset:data:geo:GSE33463 licence not read", "asset:data:geo:GSE33463 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": 0.93, "evidence": ["latform is Agilent-014850 Whole Human Genome Microarray. The raw data were preprocessed by the R pac"], "order_basis": "paper_text_order:4604", "id": "assay:1"}, {"role": "analysis", "definition_id": "regression_modelling", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["glm_logit_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["logistic regression"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}