BRCAGenie: A machine learning-driven 43-gene polygenic risk score model for precision prediction of breast cancer survival.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41162968", "kind": "science-record", "revision": 2, "content_hash": "sha256:06728b9ca02129ab744cd7d0aed4848e97b3e704b05eb1c4aa6c4c835577ef62", "created_at": "2026-11-01T10:25:53Z", "updated_at": "2026-11-01T14:01:50Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "BRCAGenie: A machine learning-driven 43-gene polygenic risk score model for precision prediction of breast cancer survival.", "doi": "10.1186/s12967-025-07100-2", "pmid": "41162968", "authors": null, "journal": "Journal of translational medicine", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:41162968"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:41162968", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:41162968' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41162968", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12967-025-07100-2", "sha256": "sha256:b29e9dd000caf4b41afc4594c8eb87c921d4c16b9510daa5c2cdd78e2088574e", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12967-025-07100-2", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:41162968:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c89f91c9866cfca4bf2c20c4409c90961a05403401705f624c7ffbcfc34e8f2e", "bytes": 655, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#Tab1", "version": null, "note": "Clinical and demographic characteristics of the 1031 subjects in The Cancer Genome Atlas Breast Cancer (TCGA-BRCA) cohort", "structure": {"pmcid": "PMC12574034", "section_index": 4, "section_title": "Data pre-processing", "row_count": 9, "column_count": 3}, "table": {"label": "Table 1", "caption": "Clinical and demographic characteristics of the 1031 subjects in The Cancer Genome Atlas Breast Cancer (TCGA-BRCA) cohort", "rows": [["Variables", "Characteristics", "Overall"], ["(N = 1031)"], ["Age at diagnosis", "Mean (SD)", "58.7 (12.9)"], ["Median [Min, Max]", "58.9 [26.6, 90.0]"], ["Missing", "14 (1.4%)"], ["Three year survival", "Survival Time ≤ 3 years", "603 (58.5%)"], ["Survival Time > 3 years", "428 (41.5%)"], ["Five year survival", "Survival Time ≤ 5 years", "784 (76.0%)"], ["Survival Time > 5 years", "247 (24.0%)"]], "row_count": 9, "column_count": 3, "numeric_cells": 12, "header_rows": 2, "locator": "section[4]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:41162968:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:842481048ba15bfe02bec228e77010bd9f397be01362b2dfe094cc9d1ada3c89", "bytes": 656, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#Tab2", "version": null, "note": "Clinical and demographic characteristics of the 1904 subjects in the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) cohort", "structure": {"pmcid": "PMC12574034", "section_index": 10, "section_title": "External validation", "row_count": 7, "column_count": 3}, "table": {"label": "Table 2", "caption": "Clinical and demographic characteristics of the 1904 subjects in the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) cohort", "rows": [["Variables", "Characteristics", "Overall (N = 1904)"], ["Age at diagnosis", "Mean (SD)", "61.1 (13.0)"], ["Median [Min, Max]", "61.8 [21.9, 96.3]"], ["Three year survival", "Survival time ≤ 3 years", "253 (13.3%)"], ["Survival time > 3 years", "1651 (86.7%)"], ["Five year survival", "Survival time ≤ 5 years", "472 (24.8%)"], ["Survival time > 5 years", "1432 (75.2%)"]], "row_count": 7, "column_count": 3, "numeric_cells": 11, "header_rows": 1, "locator": "section[10]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:41162968:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ce7a179f1bf5e9ccbb0b10bc6bb8310be4421e01f86ac63439bfdf6965453b12", "bytes": 620, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#Tab3", "version": null, "note": "Clinical and demographic characteristics of the 2969 subjects in the Gene Expression Omnibus (GSE96058) cohort", "structure": {"pmcid": "PMC12574034", "section_index": 10, "section_title": "External validation", "row_count": 7, "column_count": 3}, "table": {"label": "Table 3", "caption": "Clinical and demographic characteristics of the 2969 subjects in the Gene Expression Omnibus (GSE96058) cohort", "rows": [["Variables", "Characteristics", "Overall (N = 2969)"], ["Age at diagnosis", "Mean (SD)", "62.8 (13.1)"], ["Median [Min, Max]", "64.0 [24.0, 96.0]"], ["Three year survival", "Survival Time ≤ 3 years", "465 (15.7%)"], ["Survival Time > 3 years", "2504 (84.3%)"], ["Five year survival", "Survival Time ≤ 5 years", "1882 (63.4%)"], ["Survival Time > 5 years", "1087 (36.6%)"]], "row_count": 7, "column_count": 3, "numeric_cells": 11, "header_rows": 1, "locator": "section[10]/table-wrap[2]#Tab3"}}, {"id": "asset:table:pmid:41162968:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1885b79945d1ebe6522b5fca641acffea6aaa46701a108ca5ec9510089107eaf", "bytes": 2564, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#Tab4", "version": null, "note": "Final set of 43 genes selected to be included in the PRS after forward stepwise selection", "structure": {"pmcid": "PMC12574034", "section_index": 14, "section_title": "Development of PRS with machine learning", "row_count": 44, "column_count": 3}, "table": {"label": "Table 4", "caption": "Final set of 43 genes selected to be included in the PRS after forward stepwise selection", "rows": [["Gene name", "Gene symbol", "Multivariate cox coefficient"], ["Endoplasmic reticulum protein 27", "ERP27", "− 2.6490"], ["NUMB like endocytic adaptor protein", "NUMBL", "− 2.6098"], ["Ribosomal protein S6 Kinase B1", "RPS6KB1", "− 2.0842"], ["Brain expressed X-Linked 5", "BEX5", "− 1.7170"], ["Transmembrane Protein 14B", "TMEM14B", "− 1.6914"], ["Solute carrier family 16 member 13", "SLC16A13", "− 1.5049"], ["Cytochrome P450 family 4 subfamily F Member 11", "CYP4F11", "− 1.4646"], ["Growth regulation by estrogen in breast cancer 1 like", "GREB1L", "− 1.2990"], ["Apolipoprotein B MRNA Editing Enzyme Catalytic Subunit 3F", "APOBEC3F", "− 1.2551"], ["Ribosomal protein S29", "RPS29", "− 1.1681"], ["5'-nucleotidase domain containing 3", "NT5DC3", "− 1.1261"], ["Prostaglandin E synthase 3", "PTGES3", "− 0.9675"], ["Zinc finger protein 326", "ZNF326", "− 0.8347"], ["Metastasis associated 1 family member 2", "MTA2", "− 0.8020"], ["Syndecan 3", "SDC3", "− 0.6365"], ["Xg Glycoprotein", "XG", "− 0.4343"], ["Secretogranin II", "SCG2", "0.3120"], ["3-Hydroxybutyrate dehydrogenase 1", "BDH1", "0.6032"], ["ALX Homeobox 4", "ALX4", "0.6334"], ["Cytokine Like 1", "CYTL1", "0.6467"], ["ATPase H + Transporting V1 Subunit E1", "ATP6V1E1", "0.6498"], ["Surfeit 6", "SURF6", "0.6566"], ["Transmembrane Protein 41A", "TMEM41A", "0.6600"], ["HOX Transcript Antisense RNA", "HOTAIR", "0.6655"], ["PPFIA Binding Protein 2", "PPFIBP2", "0.6724"], ["Complement C6", "C6", "0.7013"], ["Malignant T-Cell Amplified Sequence 1", "MCTS1", "0.7264"], ["5'-Nucleotidase Ecto", "NT5E", "0.7425"], ["Argininosuccinate Synthase 1", "ASS1", "0.7785"], ["Transmembrane And Coiled-Coil Domains 1", "TMCO1", "0.7987"], ["P21 (RAC1) Activated Kinase 6", "PAK6", "0.8609"], ["Ring Finger Protein 135", "RNF135", "0.9085"], ["Globoside Alpha-1,3-N-Acetylgalactosaminyltransferase 1", "GBGT1", "0.9389"], ["Transient Receptor Potential Cation Channel Subfamily M Member 2", "TRPM2", "1.0328"], ["Exocyst Complex Component 1", "EXOC1", "1.0401"], ["Phosphoglycerate Kinase 1", "PGK1", "1.1237"], ["Cation Channel Sperm Associated 3", "CATSPER3", "1.1537"], ["Peroxidasin Like", "PXDNL", "1.2026"], ["Phosphofructokinase, Liver Type", "PFKL", "1.2867"], ["Ectodysplasin A2 Receptor", "EDA2R", "1.2898"], ["Inorganic Pyrophosphatase 2", "PPA2", "1.4623"], ["Tubulin Delta 1", "TUBD1", "2.0995"], ["C–C Motif Chemokine Receptor 7", "CCR7", "3.3420"]], "row_count": 44, "column_count": 3, "numeric_cells": 84, "header_rows": 1, "locator": "section[14]/table-wrap[1]#Tab4"}}, {"id": "asset:table:pmid:41162968:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:978fe78c3ea9c5c6b2d9051344d3d2f00ff1b57b55d990699405a648b6835e92", "bytes": 1748, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#Tab5", "version": null, "note": "Genetic and clinical features included in the PRS model", "structure": {"pmcid": "PMC12574034", "section_index": 20, "section_title": "Incorporation of clinical data", "row_count": 45, "column_count": 3}, "table": {"label": "Table 5", "caption": "Genetic and clinical features included in the PRS model", "rows": [["Variable", "Multivariate coefficient", "P-value"], ["RPS6KB1", "− 1.0039", "3.68E−03"], ["TUBD1", "0.9280", "1.07E−02"], ["PXDNL", "0.5045", "1.17E−07"], ["NUMBL", "− 0.9295", "1.55E−05"], ["CCR7", "0.4976", "2.98E−03"], ["PPA2", "0.1377", "4.25E−01"], ["ALX4", "0.3286", "8.36E−07"], ["PFKL", "0.5750", "3.32E−03"], ["RNF135", "0.4621", "8.77E−05"], ["EXOC1", "0.4085", "1.73E−02"], ["APOBEC3F", "− 0.7288", "1.16E−07"], ["EDA2R", "0.6618", "1.33E−05"], ["PGK1", "0.5598", "1.83E−04"], ["CATSPER3", "0.8440", "2.44E−09"], ["SLC16A13", "− 0.6982", "3.31E−04"], ["TRPM2", "0.2822", "3.62E−02"], ["GBGT1", "0.7154", "5.28E−07"], ["TMEM14B", "− 0.4823", "2.32E−02"], ["PTGES3", "0.0636", "6.82E−01"], ["ERP27", "− 1.1711", "1.83E−04"], ["NT5E", "0.2645", "3.37E−02"], ["BEX5", "− 0.6013", "1.33E−03"], ["C6", "0.3617", "1.37E−04"], ["ASS1", "0.0170", "8.97E−01"], ["PAK6", "0.4733", "3.96E−05"], ["TMCO1", "− 0.0133", "9.29E−01"], ["CYTL1", "0.5822", "1.15E−06"], ["PPFIBP2", "0.3625", "4.37E−04"], ["NT5DC3", "− 0.7307", "3.33E−03"], ["MTA2", "− 0.3961", "6.30E−03"], ["RPS29", "− 0.7609", "5.95E−05"], ["GREB1L", "− 0.7856", "2.12E−04"], ["TMEM41A", "0.5451", "1.18E−04"], ["ATP6V1E1", "0.1664", "2.53E−01"], ["HOTAIR", "0.3975", "2.92E−04"], ["SCG2", "0.2105", "4.62E−05"], ["SURF6", "0.3467", "1.60E−02"], ["ZNF326", "− 0.6445", "3.16E−04"], ["SDC3", "− 0.3120", "5.36E−02"], ["MCTS1", "0.5090", "2.62E−03"], ["XG", "− 0.0445", "6.93E−01"], ["BDH1", "0.2874", "3.09E−02"], ["CYP4F11", "− 0.9185", "1.21E−03"], ["Age at Diagnosis", "0.0107", "2.88E−01"]], "row_count": 45, "column_count": 3, "numeric_cells": 96, "header_rows": 1, "locator": "section[20]/table-wrap[1]#Tab5"}}, {"id": "asset:table:pmid:41162968:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a23e69f697e32081442e5a86f8df5ecbd170e1334d78373cf9e992785db12185", "bytes": 2347, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[25]/table-wrap[1]#Tab6", "version": null, "note": "Model performance of our 43-gene risk score model compared with other published studies", "structure": {"pmcid": "PMC12574034", "section_index": 25, "section_title": "Discussion", "row_count": 14, "column_count": 4}, "table": {"label": "Table 6", "caption": "Model performance of our 43-gene risk score model compared with other published studies", "rows": [["Study", "Gene Number", "Three-year AUC(t)", "Five-year AUC(t)"], ["Construct ceRNA network and risk model of breast cancer using machine learning methods under the mechanism of Cuproptosis [19]", "4", "0.604", "0.550"], ["Establishment of a novel CNV-related prognostic signature predicting prognosis in patients with breast cancer [59]", "9", "0.630", "0.580"], ["Construction and validation of a newly prognostic signature for CRISPR-Cas9-based cancer dependency map genes in breast cancer [27]", "6", "0.649", "0.618"], ["Identification of a 6-gene signature for the survival prediction of breast cancer patients based on integrated multi-omics data analysis [60]", "6", "0.660", "0.630"], ["A novel hypoxia- and lactate metabolism-related signature to predict prognosis and immunotherapy responses for breast cancer by integrating machine learning and bioinformatic analyses [26]", "5", "0.671", "0.638"], ["A novel disulfidptosis-associated expression pattern in breast cancer based on machine learning [22]", "4", "0.687", "0.644"], ["Insights into a Machine Learning-Based Palmitoylation-Related Gene Model for Predicting the Prognosis and Treatment Response of Breast Cancer Patients [28]", "11", "0.743", "0.644"], ["Identification of prognostic genes for breast cancer related to systemic lupus erythematosus by integrated analysis and machine learning [32]", "3", "0.690", "0.690"], ["Development of a Ten-lncRNA Signature Prognostic Model for Breast Cancer Survival: A Study with the TCGA Database [61]", "10", "0.717", "0.717"], ["A six-long non-coding RNAs signature as a potential prognostic marker for survival prediction of ER-positive breast cancer patients [62]", "6", "0.725", "0.717"], ["Integration of Bioinformatics and Machine Learning to Identify CD8 + T Cell-Related Prognostic Signature to Predict Clinical Outcomes and Treatment Response in Breast Cancer Patients [23]", "2", "0.754", "0.727"], ["Development and validation of a prognostic model and gene co-expression networks for breast carcinoma based on scRNA-seq and bulk-seq data [34]", "10", "0.772", "0.736"], ["43-gene risk score model in our study", "43", "0.736", "0.751"]], "row_count": 14, "column_count": 4, "numeric_cells": 52, "header_rows": 1, "locator": "section[25]/table-wrap[1]#Tab6"}}, {"id": "asset:table:pmid:41162968:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a1696a43bd8c9b558a3f90395df74bbaead69378d6e3bdb01ee5e6d2d9d98011", "bytes": 3369, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[25]/table-wrap[2]#Tab7", "version": null, "note": "Summary of literature review of the 43 genes identified in our study", "structure": {"pmcid": "PMC12574034", "section_index": 25, "section_title": "Discussion", "row_count": 44, "column_count": 6}, "table": {"label": "Table 7", "caption": "Summary of literature review of the 43 genes identified in our study", "rows": [["Gene name", "Gene Symbol", "PRSCoefficient", "Good/poor prognostic marker (PRS)", "Good/poor prognostic marker (Lit search)", "References"], ["C–C Motif Chemokine Receptor 7", "CCR7", "3.3420", "", "", "[70–72]"], ["Tubulin Delta 1", "TUBD1", "2.0995", "", "", "[73, 74]"], ["Inorganic Pyrophosphatase 2", "PPA2", "1.4623", "", "", "[75, 76]"], ["Ectodysplasin A2 Receptor", "EDA2R", "1.2898", "", "", "[77, 78]"], ["Phosphofructokinase, Liver Type", "PFKL", "1.2867", "", "", "[79, 80]"], ["Peroxidasin Like", "PXDNL", "1.2026", "", "", "[81, 82]"], ["Cation Channel Sperm Associated 3", "CATSPER3", "1.1537", "", "", "[83]"], ["Phosphoglycerate Kinase 1", "PGK1", "1.1237", "", "", "[84–88]"], ["Exocyst Complex Component 1", "EXOC1", "1.0401", "", "", "[27, 89]"], ["Transient Receptor Potential Cation Channel Subfamily M Member 2", "TRPM2", "1.0328", "", "", "[90–92]"], ["Globoside Alpha-1,3-N-Acetylgalactosaminyltransferase 1", "GBGT1", "0.9389", "", "", "[93]"], ["Ring Finger Protein 135", "RNF135", "0.9085", "", "", "[94, 95]"], ["P21 (RAC1) Activated Kinase 6", "PAK6", "0.8609", "", "", "[96, 97]"], ["Transmembrane And Coiled-Coil Domains 1", "TMCO1", "0.7987", "", "", "[98, 99]"], ["Argininosuccinate Synthase 1", "ASS1", "0.7785", "", "", "[100–103]"], ["5'-Nucleotidase Ecto", "NT5E", "0.7425", "", "", "[104–107]"], ["Malignant T-Cell Amplified Sequence 1", "MCTS1", "0.7264", "", "", "[108–110]"], ["Complement C6", "C6", "0.7013", "", "", "[111]"], ["PPFIA Binding Protein 2", "PPFIBP2", "0.6724", "", "", "[112–114]"], ["HOX Transcript Antisense RNA", "HOTAIR", "0.6655", "", "", "[115–119]"], ["Transmembrane Protein 41A", "TMEM41A", "0.6600", "", "", "[120]"], ["Surfeit 6", "SURF6", "0.6566", "", "", "[121]"], ["ATPase H + Transporting V1 Subunit E1", "ATP6V1E1", "0.6498", "", "", "[122]"], ["Cytokine Like 1", "CYTL1", "0.6467", "", "", "[123–125]"], ["ALX Homeobox 4", "ALX4", "0.6334", "", "", "[126–130]"], ["3-Hydroxybutyrate Dehydrogenase 1", "BDH1", "0.6032", "", "", "[131, 132]"], ["Secretogranin II", "SCG2", "0.3120", "", "", "[133–136]"], ["Xg Glycoprotein", "XG", "− 0.4343", "", "", ""], ["Syndecan 3", "SDC3", "− 0.6365", "", "", "[137]"], ["Metastasis Associated 1 Family Member 2", "MTA2", "− 0.8020", "", "", "[138–141]"], ["Zinc Finger Protein 326", "ZNF326", "− 0.8347", "", "", "[142–146]"], ["Prostaglandin E Synthase 3", "PTGES3", "− 0.9675", "", "", "[147–150]"], ["5'-Nucleotidase Domain Containing 3", "NT5DC3", "− 1.1261", "", "", "[151, 152]"], ["Ribosomal Protein S29", "RPS29", "− 1.1681", "", "", "[153, 154]"], ["Apolipoprotein B MRNA Editing Enzyme Catalytic Subunit 3F", "APOBEC3F", "− 1.2551", "", "", "[155, 156]"], ["Growth Regulation By Estrogen In Breast Cancer 1 Like", "GREB1L", "− 1.2990", "", "", "[157]"], ["Cytochrome P450 Family 4 Subfamily F Member 11", "CYP4F11", "− 1.4646", "", "", "[158–160]"], ["Solute Carrier Family 16 Member 13", "SLC16A13", "− 1.5049", "", "", "[161, 162]"], ["Transmembrane Protein 14B", "TMEM14B", "− 1.6914", "", "", "[34, 163]"], ["Brain Expressed X-Linked 5", "BEX5", "− 1.7170", "", "", "[164]"], ["Ribosomal Protein S6 Kinase B1", "RPS6KB1", "− 2.0842", "", "", "[165–167]"], ["NUMB Like Endocytic Adaptor Protein", "NUMBL", "− 2.6098", "", "", "[168]"], ["Endoplasmic Reticulum Protein 27", "ERP27", "− 2.6490", "", "", "[169–172]"]], "row_count": 44, "column_count": 6, "numeric_cells": 126, "header_rows": 1, "locator": "section[25]/table-wrap[2]#Tab7"}}], "gaps": ["asset:source:pmid:41162968 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:41162968", "asset:table:pmid:41162968:1", "asset:table:pmid:41162968:2", "asset:table:pmid:41162968:3", "asset:table:pmid:41162968:4", "asset:table:pmid:41162968:5", "asset:table:pmid:41162968:6", "asset:table:pmid:41162968:7"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41162968"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [], "target_providers": [], "agreement": false, "disagreements": [], "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": [{"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}]}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked", "review.machine_critique.providers"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:9c51aef71106c06759f1e65e8ae2eba45994a011695979f083f2a0ce689b1457", "type": "sep_package", "label": "SEP v1 package for pmid:41162968"}], "activities": [{"id": "activity:conversion:pmid:41162968", "type": "conversion", "used": ["package:9c51aef71106c06759f1e65e8ae2eba45994a011695979f083f2a0ce689b1457"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:41162968", "parent_hash": "sha256:15f35e134b4d8b4a3198922effc99acc0f80786ae7c76f12ab42d44ae32ad6f6", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:41162968 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "review.machine_critique.providers", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:41162968' does not resolve to a declared asset", "targets"]}