{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26285647", "kind": "science-record", "revision": 7, "content_hash": "sha256:c16de92a946099af930b633fd71d80dae9734a456a085d53adc6e7522b96da59", "created_at": "2026-11-01T15:40:10Z", "updated_at": "2026-11-01T21:58:34Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "4-protein signature predicting tamoxifen treatment outcome in recurrent breast cancer.", "doi": "10.1016/j.molonc.2015.07.004", "pmid": "26285647", "authors": ["Tommaso De Marchi", "Ning Qing Liu", "Cristoph Stingl", "Mieke A Timmermans", "Marcel Smid", "Maxime P Look", "Mila Tjoa", "Rene B H Braakman", "Mark Opdam", "Sabine C Linn", "Fred C G J Sweep", "Paul N Span", "Mike Kliffen", "Theo M Luider", "John A Foekens", "John W M Martens", "Arzu Umar"], "journal": "Molecular oncology", "year": 2016, "abstract": "Estrogen receptor (ER) positive tumors represent the majority of breast malignancies, and are effectively treated with hormonal therapies, such as tamoxifen. However, in the recurrent disease resistance to tamoxifen therapy is common and a major cause of death. In recent years, in-depth proteome analyses have enabled identification of clinically useful biomarkers, particularly, when heterogeneity in complex tumor tissue was reduced using laser capture microdissection (LCM). In the current study, we performed high resolution proteomic analysis on two cohorts of ER positive breast tumors derived from patients who either manifested good or poor outcome to tamoxifen treatment upon recurrence. A total of 112 fresh frozen tumors were collected from multiple medical centers and divided into two sets: an in-house training and a multi-center test set. Epithelial tumor cells were enriched with LCM and analyzed by nano-LC Orbitrap mass spectrometry (MS), which yielded >3000 and >4000 quantified proteins in the training and test sets, respectively. Raw data are available via ProteomeXchange with identifiers PXD000484 and PXD000485. Statistical analysis showed differential abundance of 99 proteins, of which a subset of 4 proteins was selected through a multivariate step-down to develop a predictor for tamoxifen treatment outcome. The 4-protein signature significantly predicted poor outcome patients in the test set, independent of predictive histopathological characteristics (hazard ratio [HR] = 2.17; 95% confidence interval [CI] = 1.15 to 4.17; multivariate Cox regression p value = 0.017). Immunohistochemical (IHC) staining of PDCD4, one of the signature proteins, on an independent set of formalin-fixed paraffin-embedded tumor tissues provided and independent technical validation (HR = 0.72; 95% CI = 0.57 to 0.92; multivariate Cox regression p value = 0.009). We hereby report the first validated protein predictor for tamoxifen treatment outcome in recurrent ER-positive breast cancer. IHC further showed that PDCD4 is an independent marker.", "claims": [{"id": "claim-method", "statement": "Student t test (p value < 0.05) was then used to assess differences in protein expression levels between good and poor outcome patients.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26285647", "locator": "sections[4] \"Sample sets\" paragraph 3", "quote": "Student t test (p value < 0.05) was then used to assess differences in protein expression levels between good and poor outcome patients."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Raw data are available via ProteomeXchange with identifiers PXD000484 and PXD000485.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26285647", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Raw data are available via ProteomeXchange with identifiers PXD000484 and PXD000485."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The study used Student’s t-test followed by multivariate Cox regression with a step-down approach to develop and validate a four-protein tamoxifen-outcome signature; proteomic source data were generated from LCM-enriched tumors by nano-LC Orbitrap mass spectrometry and deposited in ProteomeXchange under PXD000484 and PXD000485.", "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:26285647"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:student_t", "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {"p_value": "Student t test (p value < 0"}, "inputs": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:student_t", "step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26285647", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.molonc.2015.07.004", "sha256": "sha256:81ab1071b27d253d596127fd4db0bdd9d4463963e22c5682ad9aed94c85c8581", "bytes": 51632, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.molonc.2015.07.004", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5528925", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:26285647:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:44ea46f1995a64afbc485aa59493f57e5d9ed4fe59afef8ec46cf94a700868f4", "bytes": 1424, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#mol2201610124-tbl-0001", "version": null, "note": "Patient and tumor characteristics.", "structure": {"pmcid": "PMC5528925", "section_index": 4, "section_title": "Sample sets", "row_count": 33, "column_count": 4}, "table": {"label": "Table Table 1", "caption": "Patient and tumor characteristics.", "rows": [["", "Traininga", "Testa"], ["EMC", "NKI‐AVL", "RadboudUMC"], ["All patients", "56 (100)", "41 (100)", "15 (100)"], ["Age"], ["≤ 55 years", "15 (27)", "12 (29)", "1 (7)"], ["> 55 years", "41 (73)", "29 (71)", "14 (93)"], ["Menopausal status"], ["Premenopausal", "10 (18)", "11 (27)", "0 (0)"], ["Postmenopausal", "46 (82)", "30 (63)", "15 (100)"], ["Tumor size"], ["T1 (≤2 cm)", "12 (21)", "20 (49)", "5 (33)"], ["T2 (2–5 cm) + Tx", "40 (72)", "19 (46)", "9 (60)"], ["T3 (>5 cm) + T4", "4 (7)", "2 (5)", "1 (7)"], ["Tumor differentiationb"], ["Good/Moderate", "13 (59)", "29 (71)", "8 (53)"], ["Poor", "33 (23)", "12 (29)", "4 (27)"], ["Unknown", "10 (18)", "0 (0)", "3 (20)"], ["Disease free interval"], ["≤ 12 months", "24 (43)", "4 (10)", "5 (33)"], ["> 12 months", "32 (57)", "37 (90)", "10 (67)"], ["PgRc"], ["Negative", "9 (16)", "17 (41)", "11 (73)"], ["Positive", "44 (79)", "24 (59)", "4 (27)"], ["Involved lymph nodes"], ["0", "31 (55)", "24 (58)", "6 (40)"], ["≥ 1", "20 (36)", "16 (39)", "7 (47)"], ["unknown", "5 (9)", "1 (3)", "2 (13)"], ["Dominant site of relapse"], ["Loco‐regional", "8 (14)", "4 (10)", "0 (0)"], ["Bone", "26 (46)", "12 (29)", "6 (40)"], ["Visceral", "13 (24)", "6 (15)", "9 (60)"], ["Bone and other", "9 (16)", "14 (34)", "0 (0)"], ["Unknown", "0 (0)", "5 (12)", "0 (0)"]], "row_count": 33, "column_count": 4, "numeric_cells": 78, "header_rows": 2, "locator": "section[4]/table-wrap[1]#mol2201610124-tbl-0001"}}, {"id": "asset:table:pmid:26285647:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c544d6dc87fdcec134d720551504ed04bce207b89c7d4dad889adf8c7df16745", "bytes": 821, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#mol2201610124-tbl-0002", "version": null, "note": "LFQ based identification of 4 proteins in discovery and validation sets.", "structure": {"pmcid": "PMC5528925", "section_index": 17, "section_title": "Development of a protein signature predictive of tamoxifen therapy outcome", "row_count": 6, "column_count": 9}, "table": {"label": "Table Table 2", "caption": "LFQ based identification of 4 proteins in discovery and validation sets.", "rows": [["Protein ID", "Gene name", "Molecular weight (kDa)", "Peptides/Unique peptidesa", "Sequence coverage/Unique sequence coverage (%/%)b", "PEP scorec"], ["Training", "Test", "Training", "Test", "Training", "Test"], ["Q9P2M7", "CGN", "136.380", "22/22", "40/40", "22.8/22.8", "39.5/39.5", "3.63E‐133", "7.88E‐268"], ["Q9UN86", "G3BP2", "54.120", "5/5", "8/7", "16.4/16.4", "22.0/19.5", "1.61E‐34", "5.85E‐84"], ["Q9NX40", "OCIAD1", "27.626", "8/8", "9/9", "32.2/32.2", "32.7/32.7", "5.35E‐146", "2.59E‐247"], ["Q53EL6", "PDCD4", "51.735", "19/19", "18/18", "49.3/49.3", "47.8/47.8", "1.24E‐225", "3.23E‐281"]], "row_count": 6, "column_count": 9, "numeric_cells": 31, "header_rows": 2, "locator": "section[17]/table-wrap[1]#mol2201610124-tbl-0002"}}, {"id": "asset:table:pmid:26285647:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:618eac5f5a3f65c5a7dc73bf56a6d2b4c8b7419c3c71278e84b4f141b483c655", "bytes": 682, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[2]#mol2201610124-tbl-0003", "version": null, "note": "Information on the 4 proteins constituting the predictor for tamoxifen therapy outcome.", "structure": {"pmcid": "PMC5528925", "section_index": 17, "section_title": "Development of a protein signature predictive of tamoxifen therapy outcome", "row_count": 5, "column_count": 5}, "table": {"label": "Table Table 3", "caption": "Information on the 4 proteins constituting the predictor for tamoxifen therapy outcome.", "rows": [["Gene name", "GO cellular component", "Protein name", "Student t", "p value"], ["CGN", "Cell junction", "Cingulin", "3.13", "0.006"], ["G3BP2", "Cytoplasm", "Ras GTPase‐activating protein‐binding protein 2", "3.50", "<0.001"], ["OCIAD1", "Endosome, Mitochondrion", "Ovarian carcinoma immunogenic antigen domain‐containing protein 1", "4.15", "<0.001"], ["PDCD4", "Cytoplasm, Nucleus", "Programmed cell death protein 4", "3.99", "<0.001"]], "row_count": 5, "column_count": 5, "numeric_cells": 11, "header_rows": 1, "locator": "section[17]/table-wrap[2]#mol2201610124-tbl-0003"}}, {"id": "asset:table:pmid:26285647:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dbbee7ba44858ba90057e9da4a0a18b04d2748b81ae2901cd6a770af97bb68cb", "bytes": 1063, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[3]#mol2201610124-tbl-0004", "version": null, "note": "Univariate and multivariate Cox regression analysis for time to progression.", "structure": {"pmcid": "PMC5528925", "section_index": 17, "section_title": "Development of a protein signature predictive of tamoxifen therapy outcome", "row_count": 18, "column_count": 7}, "table": {"label": "Table Table 4", "caption": "Univariate and multivariate Cox regression analysis for time to progression.", "rows": [["Factors", "Hazard ratio", "Univariate 95% CI", "p value", "Hazard ratio", "Multivariate 95% CI", "p value"], ["4 protein predictor score"], ["High", "1.00", "", "", "1.00", "", ""], ["Low", "2.44", "1.30–4.54", "0.006", "2.17", "1.15–4.17", "0.017"], ["Age"], ["≤55 years", "1.00", "", "", "1.00", "", ""], [">55 years", "0.44", "0.23–0.86", "0.017", "0.55", "0.28–1.08", "0.083"], ["Disease free interval"], ["≤12 months", "1.00", "", "", "", "", ""], [">12 months", "0.63", "0.30–1.31", "0.213", "", "", ""], ["Dominant site of relapse", "", "", "Overall p", "", "", ""], ["Loco‐regional", "1.00", "", "0.270", "", "", ""], ["Bone", "0.89", "0.30–2.68", "", "", "", ""], ["Visceral", "0.68", "0.22–2.09", "", "", "", ""], ["Bone and other", "0.45", "0.14–1.40", "", "", "", ""], ["PgR"], ["Negative", "1.00", "", "", "", "", ""], ["Positive", "0.57", "0.32–1.00", "0.052", "", "", ""]], "row_count": 18, "column_count": 7, "numeric_cells": 39, "header_rows": 1, "locator": "section[17]/table-wrap[3]#mol2201610124-tbl-0004"}}, {"id": "asset:table:pmid:26285647:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c7d3e8ec4751e2c1431f1b40303e6263f15d9cad527e76208ae095e53b56748a", "bytes": 1057, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#mol2201610124-tbl-0005", "version": null, "note": "Univariate and multivariate Cox regression analysis for time to progression.", "structure": {"pmcid": "PMC5528925", "section_index": 18, "section_title": "Immunohistochemical assessment of PDCD4 expression and correlation with TTP", "row_count": 18, "column_count": 7}, "table": {"label": "Table Table 5", "caption": "Univariate and multivariate Cox regression analysis for time to progression.", "rows": [["Factors", "Hazard ratio", "Univariate 95% CI", "p value", "Hazard ratio", "Multivariate 95% CI", "p value"], ["PDCD4"], ["Low", "1.00", "", "", "1.00", "", ""], ["High", "0.75", "0.59–0.96", "0.020", "0.72", "0.57–0.92", "0.009"], ["Age"], ["≤55", "1.00", "", "", "1.00", "", ""], [">55", "0.58", "0.45–0.70", "<0.001", "0.52", "0.40–0.67", "<0.001"], ["Disease free interval"], ["≤12 months", "1.00", "", "", "1.00", "", ""], [">12 months", "0.73", "0.54–0.99", "0.042", "0.63", "0.46–0.87", "0.004"], ["Dominant site of relapse", "", "", "Overall p", "", "", ""], ["Loco‐regional", "1.00", "", "0.310", "", "", ""], ["Bone", "1.39", "0.91–2.10", "", "", "", ""], ["Visceral", "1.15", "0.73–1.81", "", "", "", ""], ["Bone and other", "1.38", "0.89–2.13", "", "", "", ""], ["PgR"], ["Negative", "1.00", "", "", "", "", ""], ["Positive", "0.77", "0.59–1.01", "0.062", "", "", ""]], "row_count": 18, "column_count": 7, "numeric_cells": 42, "header_rows": 1, "locator": "section[18]/table-wrap[1]#mol2201610124-tbl-0005"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {"p_value": "Student t test (p value < 0"}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Student t test"}}, {"id": "method-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {"p_value": "ivariate Cox regression p value = 0"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Cox regression"}}, {"id": "method-3", "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-4", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson correlation"}}, {"id": "method-5", "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": "Hierarchical clustering"}}, {"id": "method-6", "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": "χ2"}}, {"id": "method-7", "family": null, "specific": null, "label": "Student’s t test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Student t test (p value < 0.05) was then used to assess differences in protein expression levels between good and poor outcome patients."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "chi_square_test", "expected_value": 0.01, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "gaps": ["method.reader_named_unmapped", "method.student_t"]}, "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": false, "required_operations": [], "missing_operations": ["student_t"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: student_t_test."}, "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": "R4", "reachable": false, "accessions": ["PXD000484 and PXD000485"], "resolved_accessions": [], "statements": ["Raw data are available via ProteomeXchange with identifiers PXD000484 and PXD000485."], "basis": "The paper names PXD000484 and PXD000485, but the accession does not resolve in the repository (no reason recorded), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:26285647", "asset:table:pmid:26285647:1", "asset:table:pmid:26285647:2", "asset:table:pmid:26285647:3", "asset:table:pmid:26285647:4", "asset:table:pmid:26285647:5"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "student_t", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:24:30Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 96989, "completion_tokens": 3490, "cached_tokens": 1568}}, "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:26285647", "type": "paper", "label": "pmid:26285647"}, {"id": "source:pmid:26285647", "type": "manuscript", "label": "PMID 26285647 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26285647", "type": "paper", "label": "pmid:26285647"}, {"id": "source:pmid:26285647", "type": "manuscript", "label": "PMID 26285647 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26285647", "type": "extraction", "used": ["source:pmid:26285647"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:26285647", "parent_hash": "sha256:48dae0723cf64983f21383910157a6517da2884460b83eb76dc32c1524916bc1", "fork_of": null, "generation": 6}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "method.student_t", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on method:student_t"], "assays": [{"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ed with LCM and analyzed by nano-LC Orbitrap mass spectrometry (MS), which yielded >3000 and >4000 quantifi", "current study, we performed high resolution proteomic analysis on two cohorts of ER positive breas", "nt cohorts and separately measured by LC‐MS. Proteomic data from training and test sets were analyz", "ing data (10 minimum observations for global proteomic analysis and allowing 30% and 0% missing dat"], "order_basis": "paper_text_order:573", "id": "assay:1"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ultivariate Cox regression p value = 0.017). Immunohistochemical (IHC) staining of PDCD4, one of the signatur", "ssion p value = 0.017). Immunohistochemical (IHC) staining of PDCD4, one of the signature pro", "come in recurrent ER-positive breast cancer. IHC further showed that PDCD4 is an independent", "e polymerase chain reaction (RadboudUMC), or IHC (NKI‐AVL). All patients underwent surgery of"], "order_basis": "paper_text_order:1646", "id": "assay:2"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Student t 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":"2026-11-04T03:34:17+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}}}