{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40313617", "kind": "science-record", "revision": 4, "content_hash": "sha256:fe221d805df53eb710d13b21749fac07d2992035795ac4cbb512d28b81008231", "created_at": "2026-11-01T20:30:28Z", "updated_at": "2026-11-01T22:56:28Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "LINC01559 drives osimertinib resistance in NSCLC through a ceRNA network regulating miR-320a/IGF2BP3 axis.", "doi": "10.3389/fphar.2025.1592846", "pmid": "40313617", "authors": ["Leidi Xu", "Yibo Zhang", "Liangliang Xing", "Ying Zhou", "Ning Chang", "Hangtian Xi", "Xiangrui Xu", "Jian Zhang"], "journal": "Frontiers in pharmacology", "year": 2025, "abstract": "Background: Osimertinib resistance remains a major challenge in the treatment of lung adenocarcinoma. Long non-coding RNAs (lncRNAs) have emerged as key regulators of drug resistance, but their roles in osimertinib resistance are poorly understood. This study aimed to identify lncRNAs driving osimertinib resistance and elucidate their molecular mechanisms.\nMethods: Multi-cohort analysis (GSE222820, GSE232890, GSE255958) identified osimertinib resistance-associated lncRNAs. Functional validation employed in vitro assays (proliferation, migration, invasion, drug sensitivity) and xenograft models. Mechanistic studies involved luciferase reporter assays, RNA immunoprecipitation (RIP), and Western blotting. Clinical correlations were analyzed using TCGA-LUAD data.\nResults: Our findings demonstrated that LINC01559 was markedly upregulated in LUAD tissues and osimertinib-resistant cell lines, correlating with poor patient survival. Functional analyses revealed that LINC01559 critically regulates processes linked to drug resistance, enhancing tumor cell proliferation, migration, and invasive capabilities. Knockdown of LINC01559 sensitized resistant cells to osimertinib, significantly reducing colony-forming potential and suppressing migratory/invasive behaviors. In contrast, overexpression of LINC01559 exacerbated therapeutic resistance. Mechanistically, LINC01559 functions as a competing endogenous RNA (ceRNA) by sponging miR-320a, promote osimertinib -resistance and upregulate the expression of the miR-320a target IGF2BP3. Rescue experiments and xenograft models confirmed that Linc01559 drives resistance via the miR-320a/IGF2BP3 axis.\nConclusion: This study identifies LINC01559 as a novel ceRNA that drives osimertinib resistance in lung adenocarcinoma by sponging miR-320a to enhance IGF2BP3 expression. Targeting the LINC01559/miR-320a/IGF2BP3 axis may provide a therapeutic strategy to overcome osimertinib resistance.", "claims": [{"id": "claim-method", "statement": "Differentially expressed lncRNAs (DELs) in osimertinib-resistant cells and osimertinib-sensitive cells were identified from three public transcriptomic datasets (GSE222820, GSE232890, GSE255958) using DESeq2 and limma R package (|log2 fold change| >1, adjusted p < 0.05).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40313617", "locator": "sections[15] \"Bioinformatics analysis and target gene prediction\" paragraph 2", "quote": "Differentially expressed lncRNAs (DELs) in osimertinib-resistant cells and osimertinib-sensitive cells were identified from three public transcriptomic datasets (GSE222820, GSE232890, GSE255958) using DESeq2 and limma R package (|log2 fold change| >1, adjusted p < 0.05)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ncbi.nlm.nih.gov/geo/, GSE222820 https://www.ncbi.nlm.nih.gov/geo/, GSE232890 https://www.ncbi.nlm.nih.gov/geo/, GSE255958.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40313617", "locator": "sections[26] \"Data availability statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ncbi.nlm.nih.gov/geo/, GSE222820 https://www.ncbi.nlm.nih.gov/geo/, GSE232890 https://www.ncbi.nlm.nih.gov/geo/, GSE255958."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The LINC01559/miR-320a/IGF2BP3 axis drives osimertinib resistance in lung adenocarcinoma.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40313617", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "This study identifies LINC01559 as a novel ceRNA that drives osimertinib resistance in lung adenocarcinoma by sponging miR-320a to enhance IGF2BP3 expression."}, {"asset": "source:pmid:40313617", "locator": "sections[22] \"The LINC01559/miR-320a/IGF2BP3 axis promotes osimertinib resistance in vitro and in vivo\" paragraph 5", "quote": "These findings collectively establish the LINC01559/miR-320a/IGF2BP3 axis as a critical driver of tumor growth and osimertinib resistance, highlighting its potential as a therapeutic target in NSCLC (Figure 6)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The LINC01559/miR-320a/IGF2BP3 axis drives osimertinib resistance in lung adenocarcinoma.", "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:40313617"], "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:GSE222820"], "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:GSE222820"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40313617", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fphar.2025.1592846", "sha256": "sha256:403eb000cab9a562fb16ba72f2059003358a1750d18ebde211a20b5785ca080c", "bytes": 53696, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fphar.2025.1592846", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12043721", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE222820", "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=GSE222820", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE222820", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ncbi.nlm.nih.gov/geo/, GSE222820 https://www.ncbi.nlm.nih.gov/geo/, GSE232890 https://www.ncbi.nlm.nih.gov/geo/, GSE255958.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ncbi.nlm.nih.gov/geo/, GSE222820 https://www.ncbi.nlm.nih.gov/geo/, GSE232890 https://www.ncbi.nlm.nih.gov/geo/, GSE255958.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM6932737", "GSM6932738", "GSM6932739", "GSM6932740", "GSM6932741", "GSM6932742"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Gene expression of PC9 and PC9-OR cell line [JXQ_RNA]", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE232890", "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=GSE232890", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE232890", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ncbi.nlm.nih.gov/geo/, GSE222820 https://www.ncbi.nlm.nih.gov/geo/, GSE232890 https://www.ncbi.nlm.nih.gov/geo/, GSE255958.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ncbi.nlm.nih.gov/geo/, GSE222820 https://www.ncbi.nlm.nih.gov/geo/, GSE232890 https://www.ncbi.nlm.nih.gov/geo/, GSE255958.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM7385478", "GSM7385479", "GSM7385480", "GSM7385481", "GSM7385482", "GSM7385483", "GSM7385484", "GSM7385485"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "28038", "taxon": "Homo sapiens", "title": "Relation between TP53 GOF mutation and Osimertinib treatment in EGFR mutant lung cancer", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE255958", "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=GSE255958", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE255958", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ncbi.nlm.nih.gov/geo/, GSE222820 https://www.ncbi.nlm.nih.gov/geo/, GSE232890 https://www.ncbi.nlm.nih.gov/geo/, GSE255958.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ncbi.nlm.nih.gov/geo/, GSE222820 https://www.ncbi.nlm.nih.gov/geo/, GSE232890 https://www.ncbi.nlm.nih.gov/geo/, GSE255958.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM8083374", "GSM8083375", "GSM8083376", "GSM8083377", "GSM8083378", "GSM8083379", "GSM8083380", "GSM8083381", "GSM8083382", "GSM8083383", "GSM8083384", "GSM8083385", "GSM8083386", "GSM8083387", "GSM8083388", "GSM8083389", "GSM8083390", "GSM8083391", "GSM8083392", "GSM8083393", "GSM8083394", "GSM8083395", "GSM8083396", "GSM8083397", "GSM8083398", "GSM8083399", "GSM8083400", "GSM8083401", "GSM8083402", "GSM8083403", "GSM8083404", "GSM8083405", "GSM8083406", "GSM8083407", "GSM8083408", "GSM8083409", "GSM8083410", "GSM8083411", "GSM8083412", "GSM8083413", "GSM8083414", "GSM8083415", "GSM8083416", "GSM8083417", "GSM8083418", "GSM8083419", "GSM8083420", "GSM8083421", "GSM8083422", "GSM8083423", "GSM8083424", "GSM8083425", "GSM8083426", "GSM8083427", "GSM8083428", "GSM8083429", "GSM8083430", "GSM8083431", "GSM8083432", "GSM8083433", "GSM8083434", "GSM8083435", "GSM8083436", "GSM8083437", "GSM8083438", "GSM8083439", "GSM8083440", "GSM8083441", "GSM8083442", "GSM8083443", "GSM8083444", "GSM8083445", "GSM8083446", "GSM8083447", "GSM8083448", "GSM8083449", "GSM8083450", "GSM8083451", "GSM8083452", "GSM8083453", "GSM8083454", "GSM8083455"], "sample_count": 82, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Focal adhesion kinase-YAP signaling axis drives drug-tolerant persister cells and residual disease in NSCLC", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE222820 not downloaded", "asset:data:geo:GSE222820 licence not read", "asset:data:geo:GSE232890 not downloaded", "asset:data:geo:GSE232890 licence not read", "asset:data:geo:GSE255958 not downloaded", "asset:data:geo:GSE255958 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Differentially expressed lncRNAs (DELs) in osimertinib-resistant cells and osimertinib-sensitive cells were identified from three public transcriptomic datasets (GSE222820, GSE232890, GSE255958) using DESeq2 and limma R package (|log2 fold change| >1, adjusted p < 0.05)."}}, {"id": "method-2", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "ANOVA"}}, {"id": "method-3", "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-4", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-5", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {"fold_change": "limma R package (|log2 fold change| >1, adjusted p < 0"}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.8, "band": "high", "quote": "limma"}}], "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: deseq2."}, "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": ["GSE222820", "GSE232890", "GSE255958"], "resolved_accessions": ["GSE222820", "GSE232890", "GSE255958"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ncbi.nlm.nih.gov/geo/, GSE222820 https://www.ncbi.nlm.nih.gov/geo/, GSE232890 https://www.ncbi.nlm.nih.gov/geo/, GSE255958."], "basis": "The paper names GSE222820, GSE232890, GSE255958 in https://www.ncbi.nlm.nih.gov/geo/ and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:40313617", "data:geo:GSE222820"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE222820"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:51:41Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15887, "completion_tokens": 2588, "cached_tokens": 256}}, "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:40313617", "type": "paper", "label": "pmid:40313617"}, {"id": "source:pmid:40313617", "type": "manuscript", "label": "PMID 40313617 full text"}, {"id": "data:geo:GSE222820", "type": "dataset", "label": "GEO GSE222820"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40313617", "type": "paper", "label": "pmid:40313617"}, {"id": "source:pmid:40313617", "type": "manuscript", "label": "PMID 40313617 full text"}, {"id": "data:geo:GSE222820", "type": "dataset", "label": "GEO GSE222820"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40313617", "type": "extraction", "used": ["source:pmid:40313617"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE222820", "type": "accession_resolution", "used": ["data:geo:GSE222820"], "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:40313617", "parent_hash": "sha256:7d1dbd97d2f126633b3dd507f431dbea8c6c7608a824a03cb25275857b41dca1", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE222820 licence not read", "asset:data:geo:GSE222820 not downloaded", "asset:data:geo:GSE232890 licence not read", "asset:data:geo:GSE232890 not downloaded", "asset:data:geo:GSE255958 licence not read", "asset:data:geo:GSE255958 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": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["r assays, RNA immunoprecipitation (RIP), and Western blotting. Clinical correlations were analyzed using T"], "order_basis": "paper_text_order:756", "id": "assay:1"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": ["ation, migration, and invasive capabilities. Knockdown of LINC01559 sensitized resistant cells to o"], "order_basis": "paper_text_order:1177", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ciences (CAS, Shanghai, China), and all were cultured in RPMI-1640 (H1975, PC9, HCC827) or DMEM (A549", "resistant cell line establishment Cell lines A549, H1299, H1975, PC9, HCC827, HEK-293t, and BE", "d in RPMI-1640 (H1975, PC9, HCC827) or DMEM (A549, H1299, BEAS-2B, HEK293T) supplemented with"], "order_basis": "paper_text_order:2096", "id": "assay:3"}, {"role": "data_generation", "definition_id": "clinical_trial", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["NU/NU nude mice (6 weeks old, Charles River) were randomized into four groups (n = 6/group) and housed under s"], "order_basis": "paper_text_order:2807", "id": "assay:4"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": [", with volume calculated as length×width22 . Mice were sacrificed at Day 30, and tumors were excised and weigh", ", with volume calculated as length×width22 . Mice were sacrificed at Day 30, and tumors were excise"], "order_basis": "paper_text_order:3237", "id": "assay:5"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Differentially expressed lncRNAs (DELs) in osimertinib-resistant cells and osimertinib-sensitive cells were identified from three public transcriptomic datasets (GSE222820, GSE232890, GSE255958) using DESeq2 and limma R package (|log2 fold change| >1, adjusted p < 0.05)."], "order_basis": "consumes_earlier_output", "id": "assay:6"}]},"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":"2026-11-04T02:11:48+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}}}