{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38875364", "kind": "science-record", "revision": 3, "content_hash": "sha256:7c1ce418221481e748bc51e122a6c873e6cfb3cb2776a9936460d2f803088ae4", "created_at": "2026-11-01T20:28:56Z", "updated_at": "2026-11-01T22:12:02Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "The crosstalk between metabolic reprogramming and epithelial-mesenchymal transition and their synergistic roles in distant metastasis in breast cancer.", "doi": "10.1097/MD.0000000000038462", "pmid": "38875364", "authors": ["Liyan Yu", "Yongni Chen", "Yingyu Chen", "Kangwei Luo"], "journal": "Medicine", "year": 2024, "abstract": "BACKGROUND: Metabolic reprogramming (MR) and epithelial-mesenchymal transition (EMT) are crucial phenomena involved in the distant metastasis of breast cancer (BRCA). This study aims to assess the risk of distant metastasis in BRCA patients based on MR and EMT processes and investigate their underlying mechanisms.\nMETHODS: Gene sets related to EMT and MR were downloaded. MR-related genes (MRG) and EMT-related genes (ERG) were obtained. Principal Component Analysis method was used to define the EMT Potential Index (EPI) and MR Potential Index (MPI) to quantify the EMT and MR levels in each tumor tissue. A linear scoring model, the Metastasis Score, was derived using the union of MRGs and ERGs to evaluate the risk of distant metastasis/recurrence in BRCA. The Metastasis Score was then validated in multiple datasets. Additionally, our study explored the underlying mechanism of the Metastasis Score and its association with tumor immunity, focusing on HPRT1 gene expression in breast cancer tissues of transfer and untransferred groups using experimental methods.\nRESULTS: A total of 59 MRGs and 30 ERGs were identified in the present study. Stratifying the dataset based on EPI and MPI revealed significantly lower survival rates (P < .05) in the MPI_high and EPI_high groups. Kaplan-Meier analysis indicated the lowest survival rate in the EPI-high + MPI-high group. The Metastasis Score demonstrated its ability to distinguish prognoses in GSE2034, GSE17705, and TCGA-BRCA datasets. Additionally, differences in mutated genes were found between the high- and the low-Metastasis Score groups, displaying significant associations with immune cell infiltration and anti-tumor immune status. Notably, the 13 genes included in the Metastasis Score showed a strong association with prognosis and tumor immunity. Immunohistochemistry and western blot results revealed high expression of the HPRT1 gene in the transfer group.\nCONCLUSION: This study established the Metastasis Score as a reliable tool for evaluating the risk of distant metastasis/recurrence in BRCA patients. Additionally, we identified key genes involved in MR and EMT crosstalk, offering valuable insights into their roles in tumor immunity and other relevant aspects.", "claims": [{"id": "claim-method", "statement": "The GSE2034 dataset was used to identify MR and EMT genes associated with distant metastasis or recurrence through univariate Cox analysis, with distant metastasis/recurrence time as the target variable.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38875364", "locator": "sections[14] \"3.1. Identification of MRG and ERG related to distant metastasis or recurrence\" paragraph 2", "quote": "The GSE2034 dataset was used to identify MR and EMT genes associated with distant metastasis or recurrence through univariate Cox analysis, with distant metastasis/recurrence time as the target variable."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data generated or analyzed during this study are included in this published article [and its supplementary information files].Supplemental Digital Content is available for this article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38875364", "locator": "sections[27] \"(untitled)\" paragraph 1", "quote": "All data generated or analyzed during this study are included in this published article [and its supplementary information files].Supplemental Digital Content is available for this article."}], "state": "complete"}, {"id": "claim-target-result", "statement": "This study established the Metastasis Score as a reliable tool for evaluating the risk of distant metastasis/recurrence in BRCA patients.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38875364", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "This study established the Metastasis Score as a reliable tool for evaluating the risk of distant metastasis/recurrence in BRCA patients."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "This study established the Metastasis Score as a reliable tool for evaluating the risk of distant metastasis/recurrence in BRCA patients.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:38875364"], "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:GSE176078"], "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:group_comparison_wilcoxon", "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:GSE176078"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:group_comparison_wilcoxon"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38875364", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/MD.0000000000038462", "sha256": "sha256:fccf9f4e22ea90225089ca7a0e2ebf296a9b59583b06d3793e5c4b1665b50dd5", "bytes": 66728, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/MD.0000000000038462", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11175907", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE176078", "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=GSE176078", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE176078", "version": null, "note": "All data generated or analyzed during this study are included in this published article [and its supplementary information files].Supplemental Digital Content is available for this article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article [and its supplementary information files].Supplemental Digital Content is available for this article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5354513", "GSM5354514", "GSM5354515", "GSM5354516", "GSM5354517", "GSM5354518", "GSM5354519", "GSM5354520", "GSM5354521", "GSM5354522", "GSM5354523", "GSM5354524", "GSM5354525", "GSM5354526", "GSM5354527", "GSM5354528", "GSM5354529", "GSM5354530", "GSM5354531", "GSM5354532", "GSM5354533", "GSM5354534", "GSM5354535", "GSM5354536", "GSM5354537", "GSM5354538"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "A single-cell and spatially resolved atlas of human breast cancers", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE17705", "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=GSE17705", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE17705", "version": null, "note": "All data generated or analyzed during this study are included in this published article [and its supplementary information files].Supplemental Digital Content is available for this article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article [and its supplementary information files].Supplemental Digital Content is available for this article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM441624", "GSM441625", "GSM441626", "GSM441627", "GSM441628", "GSM441629", "GSM441630", "GSM441631", "GSM441632", "GSM441633", "GSM441634", "GSM441635", "GSM441636", "GSM441637", "GSM441638", "GSM441639", "GSM441640", "GSM441641", "GSM441642", "GSM441643", "GSM441644", "GSM441645", "GSM441646", "GSM441647", "GSM441648", "GSM441649", "GSM441650", "GSM441651", "GSM441652", "GSM441653", "GSM441654", "GSM441655", "GSM441656", "GSM441657", "GSM441658", "GSM441659", "GSM441660", "GSM441661", "GSM441662", "GSM441663", "GSM441664", "GSM441665", "GSM441666", "GSM441667", "GSM441668", "GSM441669", "GSM441670", "GSM441671", "GSM441672", "GSM441673", "GSM441674", "GSM441675", "GSM441676", "GSM441677", "GSM441678", "GSM441679", "GSM441680", "GSM441681", "GSM441682", "GSM441683", "GSM441684", "GSM441685", "GSM441686", "GSM441687", "GSM441688", "GSM441689", "GSM441690", "GSM441691", "GSM441692", "GSM441693", "GSM441694", "GSM441695", "GSM441696", "GSM441697", "GSM441698", "GSM441699", "GSM441700", "GSM441701", "GSM441702", "GSM441703", "GSM441704", "GSM441705", "GSM441706", "GSM441707", "GSM441708", "GSM441709", "GSM441710", "GSM441711", "GSM441712", "GSM441713", "GSM441714", "GSM441715", "GSM441716", "GSM441717", "GSM441718", "GSM441719", "GSM441720", "GSM441721", "GSM441722", "GSM441723", "GSM441724", "GSM441725", "GSM441726", "GSM441727", "GSM441728", "GSM441729", "GSM441730", "GSM441731", "GSM441732", "GSM441733", "GSM441734", "GSM441735", "GSM441736", "GSM441737", "GSM441738", "GSM441739", "GSM441740", "GSM441741", "GSM441742", "GSM441743", "GSM441744", "GSM441745", "GSM441746", "GSM441747", "GSM441748", "GSM441749", "GSM441750", "GSM441751", "GSM441752", "GSM441753", "GSM441754", "GSM441755", "GSM441756", "GSM441757", "GSM441758", "GSM441759", "GSM441760", "GSM441761", "GSM441762", "GSM441763", "GSM441764", "GSM441765", "GSM441766", "GSM441767", "GSM441768", "GSM441769", "GSM441770", "GSM441771", "GSM441772", "GSM441773", "GSM441774", "GSM441775", "GSM441776", "GSM441777", "GSM441778", "GSM441779", "GSM441780", "GSM441781", "GSM441782", "GSM441783", "GSM441784", "GSM441785", "GSM441786", "GSM441787", "GSM441788", "GSM441789", "GSM441790", "GSM441791", "GSM441792", "GSM441793", "GSM441794", "GSM441795", "GSM441796", "GSM441797", "GSM441798", "GSM441799", "GSM441800", "GSM441801", "GSM441802", "GSM441803", "GSM441804", "GSM441805", "GSM441806", "GSM441807", "GSM441808", "GSM441809", "GSM441810", "GSM441811", "GSM441812", "GSM441813", "GSM441814", "GSM441815", "GSM441816", "GSM441817", "GSM441818", "GSM441819", "GSM441820", "GSM441821", "GSM441822", "GSM441823", "GSM441824", "GSM441825", "GSM441826", "GSM441827", "GSM441828", "GSM441829", "GSM441830", "GSM441831", "GSM441832", "GSM441833", "GSM441834", "GSM441835", "GSM441836", "GSM441837", "GSM441838", "GSM441839", "GSM441840", "GSM441841", "GSM441842", "GSM441843", "GSM441844", "GSM441845", "GSM441846", "GSM441847", "GSM441848", "GSM441849", "GSM441850", "GSM441851", "GSM441852", "GSM441853", "GSM441854", "GSM441855", "GSM441856", "GSM441857", "GSM441858", "GSM441859", "GSM441860", "GSM441861", "GSM441862", "GSM441863", "GSM441864", "GSM441865", "GSM441866", "GSM441867", "GSM441868", "GSM441869", "GSM441870", "GSM441871", "GSM441872", "GSM441873", "GSM441874", "GSM441875", "GSM441876", "GSM441877", "GSM441878", "GSM441879", "GSM441880", "GSM441881", "GSM441882", "GSM441883", "GSM441884", "GSM441885", "GSM441886", "GSM441887", "GSM441888", "GSM441889", "GSM441890", "GSM441891", "GSM441892", "GSM441893", "GSM441894", "GSM441895", "GSM441896", "GSM441897", "GSM441898", "GSM441899", "GSM441900", "GSM441901", "GSM441902", "GSM441903", "GSM441904", "GSM441905", "GSM441906", "GSM441907", "GSM441908", "GSM441909", "GSM441910", "GSM441911", "GSM441912", "GSM441913", "GSM441914", "GSM441915", "GSM441916", "GSM441917", "GSM441918", "GSM441919", "GSM441920", "GSM441921"], "sample_count": 298, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Endocrine Sensitivity Index Validation Dataset", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE2034", "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=GSE2034", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE2034", "version": null, "note": "All data generated or analyzed during this study are included in this published article [and its supplementary information files].Supplemental Digital Content is available for this article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article [and its supplementary information files].Supplemental Digital Content is available for this article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM36777", "GSM36778", "GSM36779", "GSM36780", "GSM36781", "GSM36782", "GSM36783", "GSM36784", "GSM36785", "GSM36786", "GSM36787", "GSM36788", "GSM36789", "GSM36790", "GSM36791", "GSM36792", "GSM36793", "GSM36794", "GSM36795", "GSM36796", "GSM36797", "GSM36798", "GSM36799", "GSM36800", "GSM36801", "GSM36802", "GSM36803", "GSM36804", "GSM36805", "GSM36806", "GSM36807", "GSM36808", "GSM36809", "GSM36810", "GSM36811", "GSM36812", "GSM36813", "GSM36814", "GSM36815", "GSM36816", "GSM36817", "GSM36818", "GSM36819", "GSM36820", "GSM36821", "GSM36822", "GSM36823", "GSM36824", "GSM36825", "GSM36826", "GSM36827", "GSM36828", "GSM36829", "GSM36830", "GSM36831", "GSM36832", "GSM36833", "GSM36834", "GSM36835", "GSM36836", "GSM36837", "GSM36838", "GSM36839", "GSM36840", "GSM36841", "GSM36842", "GSM36843", "GSM36844", "GSM36845", "GSM36846", "GSM36847", "GSM36848", "GSM36849", "GSM36850", "GSM36851", "GSM36852", "GSM36853", "GSM36854", "GSM36855", "GSM36856", "GSM36857", "GSM36858", "GSM36859", "GSM36860", "GSM36861", "GSM36862", "GSM36863", "GSM36864", "GSM36865", "GSM36866", "GSM36867", "GSM36868", "GSM36869", "GSM36870", "GSM36871", "GSM36872", "GSM36873", "GSM36874", "GSM36875", "GSM36876", "GSM36877", "GSM36878", "GSM36879", "GSM36880", "GSM36881", "GSM36882", "GSM36883", "GSM36884", "GSM36885", "GSM36886", "GSM36887", "GSM36888", "GSM36889", "GSM36890", "GSM36891", "GSM36892", "GSM36893", "GSM36894", "GSM36895", "GSM36896", "GSM36897", "GSM36898", "GSM36899", "GSM36900", "GSM36901", "GSM36902", "GSM36903", "GSM36904", "GSM36905", "GSM36906", "GSM36907", "GSM36908", "GSM36909", "GSM36910", "GSM36911", "GSM36912", "GSM36913", "GSM36914", "GSM36915", "GSM36916", "GSM36917", "GSM36918", "GSM36919", "GSM36920", "GSM36921", "GSM36922", "GSM36923", "GSM36924", "GSM36925", "GSM36926", "GSM36927", "GSM36928", "GSM36929", "GSM36930", "GSM36931", "GSM36932", "GSM36933", "GSM36934", "GSM36935", "GSM36936", "GSM36937", "GSM36938", "GSM36939", "GSM36940", "GSM36941", "GSM36942", "GSM36943", "GSM36944", "GSM36945", "GSM36946", "GSM36947", "GSM36948", "GSM36949", "GSM36950", "GSM36951", "GSM36952", "GSM36953", "GSM36954", "GSM36955", "GSM36956", "GSM36957", "GSM36958", "GSM36959", "GSM36960", "GSM36961", "GSM36962", "GSM36963", "GSM36964", "GSM36965", "GSM36966", "GSM36967", "GSM36968", "GSM36969", "GSM36970", "GSM36971", "GSM36972", "GSM36973", "GSM36974", "GSM36975", "GSM36976", "GSM36977", "GSM36978", "GSM36979", "GSM36980", "GSM36981", "GSM36982", "GSM36983", "GSM36984", "GSM36985", "GSM36986", "GSM36987", "GSM36988", "GSM36989", "GSM36990", "GSM36991", "GSM36992", "GSM36993", "GSM36994", "GSM36995", "GSM36996", "GSM36997", "GSM36998", "GSM36999", "GSM37000", "GSM37001", "GSM37002", "GSM37003", "GSM37004", "GSM37005", "GSM37006", "GSM37007", "GSM37008", "GSM37009", "GSM37010", "GSM37011", "GSM37012", "GSM37013", "GSM37014", "GSM37015", "GSM37016", "GSM37017", "GSM37018", "GSM37019", "GSM37020", "GSM37021", "GSM37022", "GSM37023", "GSM37024", "GSM37025", "GSM37026", "GSM37027", "GSM37028", "GSM37029", "GSM37030", "GSM37031", "GSM37032", "GSM37033", "GSM37034", "GSM37035", "GSM37036", "GSM37037", "GSM37038", "GSM37039", "GSM37040", "GSM37041", "GSM37042", "GSM37043", "GSM37044", "GSM37045", "GSM37046", "GSM37047", "GSM37048", "GSM37049", "GSM37050", "GSM37051", "GSM37052", "GSM37053", "GSM37054", "GSM37055", "GSM37056", "GSM37057", "GSM37058", "GSM37059", "GSM37060", "GSM37061", "GSM37062"], "sample_count": 286, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Breast cancer relapse free survival", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE43837", "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=GSE43837", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE43837", "version": null, "note": "All data generated or analyzed during this study are included in this published article [and its supplementary information files].Supplemental Digital Content is available for this article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article [and its supplementary information files].Supplemental Digital Content is available for this article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1071862", "GSM1071863", "GSM1071864", "GSM1071865", "GSM1071866", "GSM1071867", "GSM1071868", "GSM1071869", "GSM1071870", "GSM1071871", "GSM1071872", "GSM1071873", "GSM1071874", "GSM1071875", "GSM1071876", "GSM1071877", "GSM1071878", "GSM1071879", "GSM1071880", "GSM1071881", "GSM1071882", "GSM1071883", "GSM1071884", "GSM1071885", "GSM1071886", "GSM1071887", "GSM1071888", "GSM1071889", "GSM1071890", "GSM1071891", "GSM1071892", "GSM1071893", "GSM1071894", "GSM1071895", "GSM1071896", "GSM1071897", "GSM1071898", "GSM1071899"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "1352", "taxon": "Homo sapiens", "title": "A BRCA1 Deficient-Like Signature is Enriched in Breast Cancer Brain Metastases", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE176078 not downloaded", "asset:data:geo:GSE176078 licence not read", "asset:data:geo:GSE17705 not downloaded", "asset:data:geo:GSE17705 licence not read", "asset:data:geo:GSE2034 not downloaded", "asset:data:geo:GSE2034 licence not read", "asset:data:geo:GSE43837 not downloaded", "asset:data:geo:GSE43837 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"id": "method-2", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-3", "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-4", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Principal Component Analysis"}}, {"id": "method-5", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman correlation"}}, {"id": "method-6", "family": "image_quantification", "specific": "densitometry", "label": "Image analysis / quantification", "dsl_operations": ["segment_objects", "quantify_intensity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["image_stack"], "evidence": {"score": 0.8, "band": "high", "quote": "optical density"}}, {"id": "method-7", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "chi-square"}}, {"id": "method-8", "family": null, "specific": null, "label": "univariate Cox analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The GSE2034 dataset was used to identify MR and EMT genes associated with distant metastasis or recurrence through univariate Cox analysis, with distant metastasis/recurrence time as the target variable."}}], "targets": [], "gaps": ["method.reader_named_unmapped", "method.group_comparison_wilcoxon"]}, "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": false, "required_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: wilcoxon."}, "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": ["GSE2034", "GSE17705", "GSE43837", "GSE176078"], "resolved_accessions": ["GSE2034", "GSE17705", "GSE43837", "GSE176078"], "statements": ["All data generated or analyzed during this study are included in this published article [and its supplementary information files].Supplemental Digital Content is available for this article."], "basis": "The paper names GSE2034, GSE17705, GSE43837, GSE176078 in Gene Expression Omnibus and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:38875364", "data:geo:GSE176078"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_wilcoxon", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE176078"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:21:12Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 17486, "completion_tokens": 2155, "cached_tokens": 264}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:38875364", "type": "paper", "label": "pmid:38875364"}, {"id": "source:pmid:38875364", "type": "manuscript", "label": "PMID 38875364 full text"}, {"id": "data:geo:GSE176078", "type": "dataset", "label": "GEO GSE176078"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38875364", "type": "paper", "label": "pmid:38875364"}, {"id": "source:pmid:38875364", "type": "manuscript", "label": "PMID 38875364 full text"}, {"id": "data:geo:GSE176078", "type": "dataset", "label": "GEO GSE176078"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38875364", "type": "extraction", "used": ["source:pmid:38875364"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE176078", "type": "accession_resolution", "used": ["data:geo:GSE176078"], "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:38875364", "parent_hash": "sha256:cd5878724b07c4fdb5e82dcc12149678f5716a9d107ccc7b27f8e8596a0a372f", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE176078 licence not read", "asset:data:geo:GSE176078 not downloaded", "asset:data:geo:GSE17705 licence not read", "asset:data:geo:GSE17705 not downloaded", "asset:data:geo:GSE2034 licence not read", "asset:data:geo:GSE2034 not downloaded", "asset:data:geo:GSE43837 licence not read", "asset:data:geo:GSE43837 not downloaded", "execution.not_run", "method.group_comparison_wilcoxon", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:group_comparison_wilcoxon"], "assays": [{"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": ["sociation with prognosis and tumor immunity. Immunohistochemistry and western blot results revealed high expre", "tal results of HPRT1 Based on the results of immunohistochemistry, we found that the HPRT1 staining of breast", "ognosis of BRCA patients to some extent. (A) Immunohistochemical results of breast cancer specimens in the tr", "cancer specimens in the transfer group. (B) Immunohistochemical results of breast cancer specimens in the un"], "order_basis": "paper_text_order:1925", "id": "assay:1"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["and tumor immunity. Immunohistochemistry and western blot results revealed high expression of the HPRT", "he transfer group (P < 0.001) (Fig. 8C). The Western blot results showed that the protein level of HPR", "transfer group and untransferred group. (D) Western Blot results show the expression of HPRT1 in brea", "p and untransferred group. (E) Comparison of western blot results of HPRT1 expression between the tran"], "order_basis": "paper_text_order:1950", "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": ["Wilcoxon"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:44:21+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}}}