{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35342303", "kind": "science-record", "revision": 3, "content_hash": "sha256:20910683d8bf0d17ed6caa2aaf675a34acfc1fc9f7832f1235dc72f9441cfaaa", "created_at": "2026-11-01T18:14:08Z", "updated_at": "2026-11-01T21:27:31Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Analysis of Ferroptosis-Related LncRNAs Signatures Associated with Tumor Immune Infiltration and Experimental Validation in Clear Cell Renal Cell Carcinoma.", "doi": "10.2147/IJGM.S354682", "pmid": "35342303", "authors": ["Xinyi Chen", "Jingyao Tu", "Li Ma", "Yongbiao Huang", "Chunguang Yang", "Xianglin Yuan"], "journal": "International journal of general medicine", "year": 2022, "abstract": "Background: Clear cell renal cell carcinoma (ccRCC) is the most aggressive subtype of renal cell carcinoma. Ferroptosis is an iron-dependent programmed cell death. Long non-coding RNAs (lncRNAs) emerge as a critical role in regulating cancer progression.\nObjective: This study aimed to identify molecular regulation of ferroptosis-related lncRNAs (FRLs) in ccRCC.\nMethods: The prognostic value of FRLs was investigated in ccRCC samples downloaded from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) dataset. The FRLs were screened out by Pearson correlation test. The 465 FRLs confirmed as potential prognostic factors through univariate Cox regression analysis were entered into Lasso and multivariate Cox regression to build a FRLs prognostic signature. A risk score based on the prognostic model divided ccRCC patients into low- and high-risk groups. A prognostic nomogram, derived from the prognostic signature and integrating clinical characteristics, was constructed. Gene set enrichment analysis (GSEA) revealed the immune- and tumor-associated pathways. Two distinct clusters were identified with different immune signatures through consensus clustering analysis. The prognostic value of some hub FRLs was externally validated via three GEO datasets (GSE46699, GSE53757 and GSE66272) and online databases. Finally, the three FRLs (LINC00460, LINC00941 and LINC02027) were verified through in vitro experiments.\nResults: The FRLs prognostic signature, including 7 independent prognostic lncRNAs, exhibited good accuracy in predicting overall survival (OS) of ccRCC patients. This signature was correlated with immune infiltration and immune checkpoint blockade (ICB). We correlated two distinct clusters with immune infiltration signature of ccRCC. The worse prognosis of cluster 2 was probably mediated by immune evasion. We also found that the expression levels of LINC00460 and LINC00941 in ccRCC cell lines were higher than those in HK-2 cells, but LINC02027 showed the inverse trend.\nConclusion: Collectively, our study demonstrated a FRLs prognostic signature which had great clinical value in prognosis assessment.", "claims": [{"id": "claim-method", "statement": "The FRLs were screened out by Pearson correlation test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35342303", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "The FRLs were screened out by Pearson correlation test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Raw data are available at TCGA (search term: TCGA-KIRC). TCGA belongs to public databases. The patients involved in the database have obtained ethical approval. Users can download relevant data for free for research and publish relevant articles.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35342303", "locator": "sections[27] \"Data Sharing Statement\" paragraph 2", "quote": "Raw data are available at TCGA (search term: TCGA-KIRC). TCGA belongs to public databases. The patients involved in the database have obtained ethical approval. Users can download relevant data for free for research and publish relevant articles."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The FRLs prognostic signature, including 7 independent prognostic lncRNAs, exhibited good accuracy in predicting overall survival (OS) of ccRCC patients.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:35342303", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "The FRLs prognostic signature, including 7 independent prognostic lncRNAs, exhibited good accuracy in predicting overall survival (OS) of ccRCC patients."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The FRLs prognostic signature, including 7 independent prognostic lncRNAs, exhibited good accuracy in predicting overall survival (OS) of ccRCC patients.", "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:35342303"], "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:GSE46699"], "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:GSE46699"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35342303", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/IJGM.S354682", "sha256": "sha256:a264fc6101e88c5f2c3ebef98f72f560cd73374fee193a2a321882ea3b642e2d", "bytes": 61592, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/IJGM.S354682", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8942346", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE46699", "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=GSE46699", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE46699", "version": null, "note": "Raw data are available at TCGA (search term: TCGA-KIRC). TCGA belongs to public databases. The patients involved in the database have obtained ethical approval. Users can download relevant data for free for research and publish relevant articles.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw data are available at TCGA (search term: TCGA-KIRC). TCGA belongs to public databases. The patients involved in the database have obtained ethical approval. Users can download relevant data for free for research and publish relevant articles.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1134764", "GSM1134765", "GSM1134766", "GSM1134767", "GSM1134768", "GSM1134769", "GSM1134770", "GSM1134771", "GSM1134772", "GSM1134773", "GSM1134774", "GSM1134775", "GSM1134776", "GSM1134777", "GSM1134778", "GSM1134779", "GSM1134780", "GSM1134781", "GSM1134782", "GSM1134783", "GSM1134784", "GSM1134785", "GSM1134786", "GSM1134787", "GSM1134788", "GSM1134789", "GSM1134790", "GSM1134791", "GSM1134792", "GSM1134793", "GSM1134794", "GSM1134795", "GSM1134796", "GSM1134797", "GSM1134798", "GSM1134799", "GSM1134800", "GSM1134801", "GSM1134802", "GSM1134803", "GSM1134804", "GSM1134805", "GSM1134806", "GSM1134807", "GSM1134808", "GSM1134809", "GSM1134810", "GSM1134811", "GSM1134812", "GSM1134813", "GSM1134814", "GSM1134815", "GSM1134816", "GSM1134817", "GSM1134818", "GSM1134819", "GSM1134820", "GSM1134821", "GSM1134822", "GSM1134823", "GSM1134824", "GSM1134825", "GSM1134826", "GSM1134827", "GSM1134828", "GSM1134829", "GSM1134830", "GSM1134831", "GSM1134832", "GSM1134833", "GSM1134834", "GSM1134835", "GSM1134836", "GSM1134837", "GSM1134838", "GSM1134839", "GSM1134840", "GSM1134841", "GSM1134842", "GSM1134843", "GSM1134844", "GSM1134845", "GSM1134846", "GSM1134847", "GSM1134848", "GSM1134849", "GSM1134850", "GSM1134851", "GSM1134852", "GSM1134853", "GSM1134854", "GSM1134855", "GSM1134856", "GSM1134857", "GSM1134858", "GSM1134859", "GSM1134860", "GSM1134861", "GSM1134862", "GSM1134863", "GSM1134864", "GSM1134865", "GSM1134866", "GSM1134867", "GSM1134868", "GSM1134869", "GSM1134870", "GSM1134871", "GSM1134872", "GSM1134873", "GSM1134874", "GSM1134875", "GSM1134876", "GSM1134877", "GSM1134878", "GSM1134879", "GSM1134880", "GSM1134881", "GSM1134882", "GSM1134883", "GSM1134884", "GSM1134885", "GSM1134886", "GSM1134887", "GSM1134888", "GSM1134889", "GSM1304420", "GSM1304421", "GSM1304422", "GSM1304423"], "sample_count": 130, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Smoking and Obesity Related Molecular Alterations in Clear Cell Renal Cell Carcinoma", "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:GSE53757", "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=GSE53757", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53757", "version": null, "note": "Raw data are available at TCGA (search term: TCGA-KIRC). TCGA belongs to public databases. The patients involved in the database have obtained ethical approval. Users can download relevant data for free for research and publish relevant articles.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw data are available at TCGA (search term: TCGA-KIRC). TCGA belongs to public databases. The patients involved in the database have obtained ethical approval. Users can download relevant data for free for research and publish relevant articles.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1300062", "GSM1300063", "GSM1300064", "GSM1300065", "GSM1300066", "GSM1300067", "GSM1300068", "GSM1300069", "GSM1300070", "GSM1300071", "GSM1300072", "GSM1300073", "GSM1300074", "GSM1300075", "GSM1300076", "GSM1300077", "GSM1300078", "GSM1300079", "GSM1300080", "GSM1300081", "GSM1300082", "GSM1300083", "GSM1300084", "GSM1300085", "GSM1300086", "GSM1300087", "GSM1300088", "GSM1300089", "GSM1300090", "GSM1300091", "GSM1300092", "GSM1300093", "GSM1300094", "GSM1300095", "GSM1300096", "GSM1300097", "GSM1300098", "GSM1300099", "GSM1300100", "GSM1300101", "GSM1300102", "GSM1300103", "GSM1300104", "GSM1300105", "GSM1300106", "GSM1300107", "GSM1300108", "GSM1300109", "GSM1300110", "GSM1300111", "GSM1300112", "GSM1300113", "GSM1300114", "GSM1300115", "GSM1300116", "GSM1300117", "GSM1300118", "GSM1300119", "GSM1300120", "GSM1300121", "GSM1300122", "GSM1300123", "GSM1300124", "GSM1300125", "GSM1300126", "GSM1300127", "GSM1300128", "GSM1300129", "GSM1300130", "GSM1300131", "GSM1300132", "GSM1300133", "GSM1300134", "GSM1300135", "GSM1300136", "GSM1300137", "GSM1300138", "GSM1300139", "GSM1300140", "GSM1300141", "GSM1300142", "GSM1300143", "GSM1300144", "GSM1300145", "GSM1300146", "GSM1300147", "GSM1300148", "GSM1300149", "GSM1300150", "GSM1300151", "GSM1300152", "GSM1300153", "GSM1300154", "GSM1300155", "GSM1300156", "GSM1300157", "GSM1300158", "GSM1300159", "GSM1300160", "GSM1300161", "GSM1300162", "GSM1300163", "GSM1300164", "GSM1300165", "GSM1300166", "GSM1300167", "GSM1300168", "GSM1300169", "GSM1300170", "GSM1300171", "GSM1300172", "GSM1300173", "GSM1300174", "GSM1300175", "GSM1300176", "GSM1300177", "GSM1300178", "GSM1300179", "GSM1300180", "GSM1300181", "GSM1300182", "GSM1300183", "GSM1300184", "GSM1300185", "GSM1300186", "GSM1300187", "GSM1300188", "GSM1300189", "GSM1300190", "GSM1300191", "GSM1300192", "GSM1300193", "GSM1300194", "GSM1300195", "GSM1300196", "GSM1300197", "GSM1300198", "GSM1300199", "GSM1300200", "GSM1300201", "GSM1300202", "GSM1300203", "GSM1300204", "GSM1300205"], "sample_count": 144, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene array analysis of clear cell renal cell carcinoma tissue versus matched normal kidney tissue", "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:GSE66272", "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=GSE66272", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66272", "version": null, "note": "Raw data are available at TCGA (search term: TCGA-KIRC). TCGA belongs to public databases. The patients involved in the database have obtained ethical approval. Users can download relevant data for free for research and publish relevant articles.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw data are available at TCGA (search term: TCGA-KIRC). TCGA belongs to public databases. The patients involved in the database have obtained ethical approval. Users can download relevant data for free for research and publish relevant articles.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1618387", "GSM1618388", "GSM1618389", "GSM1618390", "GSM1618391", "GSM1618392", "GSM1618393", "GSM1618394", "GSM1618395", "GSM1618396", "GSM1618397", "GSM1618398", "GSM1618399", "GSM1618400", "GSM1618401", "GSM1618402", "GSM1618403", "GSM1618404", "GSM1618405", "GSM1618406", "GSM1618407", "GSM1618408", "GSM1618409", "GSM1618410", "GSM1618411", "GSM1618412", "GSM1618413", "GSM1618414", "GSM1618415", "GSM1618416", "GSM1618417", "GSM1618418", "GSM1618419", "GSM1618420", "GSM1618421", "GSM1618422", "GSM1618423", "GSM1618424", "GSM1618425", "GSM1618426", "GSM1618427", "GSM1618428", "GSM1618429", "GSM1618430", "GSM1618431", "GSM1618432", "GSM1618433", "GSM1618434", "GSM1618435", "GSM1618436", "GSM1618437", "GSM1618438", "GSM1618439", "GSM1618440"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genome-wide analysis of gene expression patterns in human kidney cancer", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE46699 not downloaded", "asset:data:geo:GSE46699 licence not read", "asset:data:geo:GSE53757 not downloaded", "asset:data:geo:GSE53757 licence not read", "asset:data:geo:GSE66272 not downloaded", "asset:data:geo:GSE66272 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The FRLs were screened out by Pearson correlation test."}}, {"id": "method-2", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-3", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Cox regression"}}, {"id": "method-4", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "GO enrichment"}}, {"id": "method-5", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "Chi-square"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["GSE46699", "GSE53757", "GSE66272"], "resolved_accessions": ["GSE46699", "GSE53757", "GSE66272"], "statements": ["Raw data are available at TCGA (search term: TCGA-KIRC). TCGA belongs to public databases. The patients involved in the database have obtained ethical approval. Users can download relevant data for free for research and publish relevant articles."], "basis": "The paper names GSE46699, GSE53757, GSE66272 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": ["pearson_r"], "assets": ["source:pmid:35342303", "data:geo:GSE46699"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE46699"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:39:37Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 16970, "completion_tokens": 2260, "cached_tokens": 264}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:35342303", "type": "paper", "label": "pmid:35342303"}, {"id": "source:pmid:35342303", "type": "manuscript", "label": "PMID 35342303 full text"}, {"id": "data:geo:GSE46699", "type": "dataset", "label": "GEO GSE46699"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35342303", "type": "paper", "label": "pmid:35342303"}, {"id": "source:pmid:35342303", "type": "manuscript", "label": "PMID 35342303 full text"}, {"id": "data:geo:GSE46699", "type": "dataset", "label": "GEO GSE46699"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35342303", "type": "extraction", "used": ["source:pmid:35342303"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE46699", "type": "accession_resolution", "used": ["data:geo:GSE46699"], "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:35342303", "parent_hash": "sha256:c5198bb8d7c244d2f9793c7153c0300c1acb988a35e7c2ac0a46f555771dde45", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE46699 licence not read", "asset:data:geo:GSE46699 not downloaded", "asset:data:geo:GSE53757 licence not read", "asset:data:geo:GSE53757 not downloaded", "asset:data:geo:GSE66272 licence not read", "asset:data:geo:GSE66272 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["a humid 5% CO2 environment and was routinely cultured in RPMI 1640 or DMEM supplemented with 10% feta"], "order_basis": "paper_text_order:2623", "id": "assay:1"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ifferentially expressed FRLs. The results of RT-qPCR showed that the overall trend in the express", "he expression levels of FRLs in vitro. (A–C) RT-qPCR was used to measure the mRNA level of LINC00", "erentially expressed FRLs. The results of RT-qPCR showed that the overall trend in the express", "expression levels of FRLs in vitro. (A–C) RT-qPCR was used to measure the mRNA level of LINC00"], "order_basis": "paper_text_order:7403", "id": "assay:2"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The FRLs were screened out by Pearson correlation test."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T01:43:35+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}}}