{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36352434", "kind": "science-record", "revision": 5, "content_hash": "sha256:dc9f65a2b1220df9aedc9b59367602d508d4611f0e33e1450da7a1da4fd808e5", "created_at": "2026-11-01T18:15:48Z", "updated_at": "2026-11-01T22:50:34Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Sequential gene expression analysis of cervical malignant transformation identifies RFC4 as a novel diagnostic and prognostic biomarker.", "doi": "10.1186/s12916-022-02630-8", "pmid": "36352434", "authors": ["Jianwei Zhang", "Silu Meng", "Xiaoyan Wang", "Jun Wang", "Xinran Fan", "Haiying Sun", "Ruoqi Ning", "Bing Xiao", "Xiangqin Li", "Yao Jia", "Dongli Kong", "Ruqi Chen", "Changyu Wang", "Ding Ma", "Shuang Li"], "journal": "BMC medicine", "year": 2022, "abstract": "BACKGROUND: Cervical squamous cell carcinoma (SCC) is known to arise through increasingly higher-grade squamous intraepithelial lesions (SILs) or cervical intraepithelial neoplasias (CINs). This study aimed to describe sequential molecular changes and identify biomarkers in cervical malignant transformation.\nMETHODS: Multidimensional data from five publicly available microarray and TCGA-CESC datasets were analyzed. Immunohistochemistry was carried out on 354 cervical tissues (42 normal, 62 CIN1, 26 CIN2, 47 CIN3, and 177 SCC) to determine the potential diagnostic and prognostic value of identified biomarkers.\nRESULTS: We demonstrated that normal epithelium and SILs presented higher molecular homogeneity than SCC. Genes in the region (e.g., 3q, 12q13) with copy number alteration or HPV integration were more likely to lose or gain expression. The IL-17 signaling pathway was enriched throughout disease progression with downregulation of IL17C and decreased Th17 cells at late stage. Furthermore, we identified AURKA, TOP2A, RFC4, and CEP55 as potential causative genes gradually upregulated during the normal-SILs-SCC transition. For detecting high-grade SIL (HSIL), TOP2A and RFC4 showed balanced sensitivity (both 88.2%) and specificity (87.1 and 90.1%), with high AUC (0.88 and 0.89). They had equivalent diagnostic performance alone to the combination of p16INK4a and Ki-67. Meanwhile, increased expression of RFC4 significantly and independently predicted favorable outcomes in multi-institutional cohorts of SCC patients.\nCONCLUSIONS: Our comprehensive study of gene expression profiling has identified dysregulated genes and biological processes during cervical carcinogenesis. RFC4 is proposed as a novel surrogate biomarker for determining HSIL and HSIL+, and an independent prognostic biomarker for SCC.", "claims": [{"id": "claim-method", "statement": "Survival curves were plotted using the Kaplan-Meier method and compared using the log-rank test. Multivariate Cox regression analysis was performed to determine the prognostic value of the selected gene with considering clinical factors.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36352434", "locator": "sections[8] \"Survival analysis\" paragraph 3", "quote": "Survival curves were plotted using the Kaplan-Meier method and compared using the log-rank test. Multivariate Cox regression analysis was performed to determine the prognostic value of the selected gene with considering clinical factors."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. These can be found in The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo/). The tissue microarrays were obtained from Fanpu Biotech. Co., Ltd. (Guilin, China; Product code: CIN1021 and CIN1022) and Outdo Biotech. Co., Ltd. (Shanghai, China; Product Code: HUteS154Su01). The raw experimental data and analysis codes supporting the conclusions of this article will be made available by the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36352434", "locator": "sections[25] \"Availability of data and materials\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. These can be found in The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo/). The tissue microarrays were obtained from Fanpu Biotech. Co., Ltd. (Guilin, China; Product code: CIN1021 and CIN1022) and Outdo Biotech. Co., Ltd. (Shanghai, China; Product Code: HUteS154Su01). The raw experimental data and analysis codes supporting the conclusions of this article will be made available by the corresponding author."}], "state": "complete"}, {"id": "claim-target-result", "statement": "For detecting high-grade SIL (HSIL), TOP2A and RFC4 showed balanced sensitivity (both 88.2%) and specificity (87.1 and 90.1%), with high AUC (0.88 and 0.89).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36352434", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "For detecting high-grade SIL (HSIL), TOP2A and RFC4 showed balanced sensitivity (both 88.2%) and specificity (87.1 and 90.1%), with high AUC (0.88 and 0.89)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "For detecting high-grade SIL (HSIL), TOP2A and RFC4 showed balanced sensitivity (both 88.2%) and specificity (87.1 and 90.1%), with high AUC (0.88 and 0.89).", "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:36352434"], "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:GSE138080"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE138080"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36352434", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12916-022-02630-8", "sha256": "sha256:ca47d0ed218262c33275f0bac09ffdb064257e8019fde2b2743f355f688dfa18", "bytes": 73284, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12916-022-02630-8", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9648022", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE138080", "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=GSE138080", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE138080", "version": null, "note": "Publicly available datasets were analyzed in this study. These can be found in The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo/). The tissue microarrays were obtained from Fanpu Biotech. Co., Ltd. (Guilin, China; Product code: CIN1021 and CIN1022) and Outdo Biotech. Co., Ltd. (Shanghai, China; Product Code: HUteS154Su01). The raw experimental data and analysis codes supporting the conclusions of this article will be made available by the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. These can be found in The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo/). The tissue microarrays were obtained from Fanpu Biotech. Co., Ltd. (Guilin, China; Product code: CIN1021 and CIN1022) and Outdo Biotech. Co., Ltd. (Shanghai, China; Product Code: HUteS154Su01). The raw experimental data and analysis codes supporting the conclusions of this article will be made available by the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4098861", "GSM4098862", "GSM4098863", "GSM4098864", "GSM4098865", "GSM4098866", "GSM4098867", "GSM4098868", "GSM4098869", "GSM4098870", "GSM4098871", "GSM4098872", "GSM4098873", "GSM4098874", "GSM4098875", "GSM4098876", "GSM4098877", "GSM4098878", "GSM4098879", "GSM4098880", "GSM4098881", "GSM4098882", "GSM4098883", "GSM4098884", "GSM4098885", "GSM4098886", "GSM4098887", "GSM4098888", "GSM4098889", "GSM4098890", "GSM4098891", "GSM4098892", "GSM4098893", "GSM4098894", "GSM4098895"], "sample_count": 35, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "Identification of deregulated pathways, key regulators, and novel miRNA-mRNA interactions in HPV-mediated transformation. [mRNA tissues-Agilent]", "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:GSE27678", "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=GSE27678", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27678", "version": null, "note": "Publicly available datasets were analyzed in this study. These can be found in The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo/). The tissue microarrays were obtained from Fanpu Biotech. Co., Ltd. (Guilin, China; Product code: CIN1021 and CIN1022) and Outdo Biotech. Co., Ltd. (Shanghai, China; Product Code: HUteS154Su01). The raw experimental data and analysis codes supporting the conclusions of this article will be made available by the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. These can be found in The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo/). The tissue microarrays were obtained from Fanpu Biotech. Co., Ltd. (Guilin, China; Product code: CIN1021 and CIN1022) and Outdo Biotech. Co., Ltd. (Shanghai, China; Product Code: HUteS154Su01). The raw experimental data and analysis codes supporting the conclusions of this article will be made available by the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM685524", "GSM685525", "GSM685526", "GSM685527", "GSM685528", "GSM685529", "GSM685530", "GSM685531", "GSM685532", "GSM685533", "GSM685534", "GSM685535", "GSM685536", "GSM685537", "GSM685538", "GSM685539", "GSM685540", "GSM685541", "GSM685542", "GSM685543", "GSM685544", "GSM685545", "GSM685546", "GSM685547", "GSM685548", "GSM685549", "GSM685550", "GSM685551", "GSM685552", "GSM685553", "GSM685554", "GSM685555", "GSM685556", "GSM685557", "GSM685558", "GSM685559", "GSM685560", "GSM685561", "GSM685562", "GSM685563", "GSM685564", "GSM685565", "GSM685566", "GSM685567", "GSM685568", "GSM685569", "GSM685570", "GSM685571", "GSM685572", "GSM685573", "GSM685574", "GSM685575", "GSM685576", "GSM685577", "GSM685578", "GSM685579", "GSM685580", "GSM685581", "GSM685582", "GSM685583", "GSM685584", "GSM685585", "GSM685586", "GSM685587", "GSM685588", "GSM685589", "GSM685590", "GSM685591", "GSM685592", "GSM685593", "GSM685594", "GSM685595", "GSM685596", "GSM685597", "GSM685598", "GSM685599", "GSM685600"], "sample_count": 77, "group_sizes": null, "group_sizes_basis": null, "platform": "570;571", "taxon": "Homo sapiens", "title": "Gene expression analysis in a variety of normal, premalignant and squamous cell carcinomas of the cervix", "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:GSE63514", "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=GSE63514", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63514", "version": null, "note": "Publicly available datasets were analyzed in this study. These can be found in The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo/). The tissue microarrays were obtained from Fanpu Biotech. Co., Ltd. (Guilin, China; Product code: CIN1021 and CIN1022) and Outdo Biotech. Co., Ltd. (Shanghai, China; Product Code: HUteS154Su01). The raw experimental data and analysis codes supporting the conclusions of this article will be made available by the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. These can be found in The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo/). The tissue microarrays were obtained from Fanpu Biotech. Co., Ltd. (Guilin, China; Product code: CIN1021 and CIN1022) and Outdo Biotech. Co., Ltd. (Shanghai, China; Product Code: HUteS154Su01). The raw experimental data and analysis codes supporting the conclusions of this article will be made available by the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1551311", "GSM1551312", "GSM1551313", "GSM1551314", "GSM1551315", "GSM1551316", "GSM1551317", "GSM1551318", "GSM1551319", "GSM1551320", "GSM1551321", "GSM1551322", "GSM1551323", "GSM1551324", "GSM1551325", "GSM1551326", "GSM1551327", "GSM1551328", "GSM1551329", "GSM1551330", "GSM1551331", "GSM1551332", "GSM1551333", "GSM1551334", "GSM1551335", "GSM1551336", "GSM1551337", "GSM1551338", "GSM1551339", "GSM1551340", "GSM1551341", "GSM1551342", "GSM1551343", "GSM1551344", "GSM1551345", "GSM1551346", "GSM1551347", "GSM1551348", "GSM1551349", "GSM1551350", "GSM1551351", "GSM1551352", "GSM1551353", "GSM1551354", "GSM1551355", "GSM1551356", "GSM1551357", "GSM1551358", "GSM1551359", "GSM1551360", "GSM1551361", "GSM1551362", "GSM1551363", "GSM1551364", "GSM1551365", "GSM1551366", "GSM1551367", "GSM1551368", "GSM1551369", "GSM1551370", "GSM1551371", "GSM1551372", "GSM1551373", "GSM1551374", "GSM1551375", "GSM1551376", "GSM1551377", "GSM1551378", "GSM1551379", "GSM1551380", "GSM1551381", "GSM1551382", "GSM1551383", "GSM1551384", "GSM1551385", "GSM1551386", "GSM1551387", "GSM1551388", "GSM1551389", "GSM1551390", "GSM1551391", "GSM1551392", "GSM1551393", "GSM1551394", "GSM1551395", "GSM1551396", "GSM1551397", "GSM1551398", "GSM1551399", "GSM1551400", "GSM1551401", "GSM1551402", "GSM1551403", "GSM1551404", "GSM1551405", "GSM1551406", "GSM1551407", "GSM1551408", "GSM1551409", "GSM1551410", "GSM1551411", "GSM1551412", "GSM1551413", "GSM1551414", "GSM1551415", "GSM1551416", "GSM1551417", "GSM1551418", "GSM1551419", "GSM1551420", "GSM1551421", "GSM1551422", "GSM1551423", "GSM1551424", "GSM1551425", "GSM1551426", "GSM1551427", "GSM1551428", "GSM1551429", "GSM1551430", "GSM1551431", "GSM1551432", "GSM1551433", "GSM1551434", "GSM1551435", "GSM1551436", "GSM1551437", "GSM1551438"], "sample_count": 128, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression analysis of cervical cancer progression", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE75132", "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=GSE75132", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE75132", "version": null, "note": "Publicly available datasets were analyzed in this study. These can be found in The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo/). The tissue microarrays were obtained from Fanpu Biotech. Co., Ltd. (Guilin, China; Product code: CIN1021 and CIN1022) and Outdo Biotech. Co., Ltd. (Shanghai, China; Product Code: HUteS154Su01). The raw experimental data and analysis codes supporting the conclusions of this article will be made available by the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. These can be found in The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo/). The tissue microarrays were obtained from Fanpu Biotech. Co., Ltd. (Guilin, China; Product code: CIN1021 and CIN1022) and Outdo Biotech. Co., Ltd. (Shanghai, China; Product Code: HUteS154Su01). The raw experimental data and analysis codes supporting the conclusions of this article will be made available by the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1943705", "GSM1943706", "GSM1943707", "GSM1943708", "GSM1943709", "GSM1943710", "GSM1943711", "GSM1943712", "GSM1943713", "GSM1943714", "GSM1943715", "GSM1943716", "GSM1943717", "GSM1943718", "GSM1943719", "GSM1943720", "GSM1943721", "GSM1943722", "GSM1943723", "GSM1943724", "GSM1943725", "GSM1943726", "GSM1943727", "GSM1943728", "GSM1943729", "GSM1943730", "GSM1943731", "GSM1943732", "GSM1943733", "GSM1943734", "GSM1943735", "GSM1943736", "GSM1943737", "GSM1943738", "GSM1943739", "GSM1943740", "GSM1943741", "GSM1943742", "GSM1943743", "GSM1943744", "GSM1943745"], "sample_count": 41, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "TMEM45A, SERPINB5 and p16INK4A transcript levels are predictive for development of high-grade cervical lesions", "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:GSE7803", "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=GSE7803", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE7803", "version": null, "note": "Publicly available datasets were analyzed in this study. These can be found in The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo/). The tissue microarrays were obtained from Fanpu Biotech. Co., Ltd. (Guilin, China; Product code: CIN1021 and CIN1022) and Outdo Biotech. Co., Ltd. (Shanghai, China; Product Code: HUteS154Su01). The raw experimental data and analysis codes supporting the conclusions of this article will be made available by the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. These can be found in The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo/). The tissue microarrays were obtained from Fanpu Biotech. Co., Ltd. (Guilin, China; Product code: CIN1021 and CIN1022) and Outdo Biotech. Co., Ltd. (Shanghai, China; Product Code: HUteS154Su01). The raw experimental data and analysis codes supporting the conclusions of this article will be made available by the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM189381", "GSM189382", "GSM189383", "GSM189384", "GSM189385", "GSM189386", "GSM189387", "GSM189388", "GSM189389", "GSM189390", "GSM189391", "GSM189392", "GSM189393", "GSM189394", "GSM189395", "GSM189396", "GSM189397", "GSM189398", "GSM189399", "GSM189400", "GSM189401", "GSM189402", "GSM189403", "GSM189404", "GSM189405", "GSM189406", "GSM189407", "GSM189408", "GSM189409", "GSM189410", "GSM189411", "GSM189412", "GSM189413", "GSM189414", "GSM189415", "GSM189416", "GSM189417", "GSM189418", "GSM189419", "GSM189420", "GSM189421"], "sample_count": 41, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Human pre-invasive and invasive cervical squamous cell carcinomas and normal cervical epithelia", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE138080 not downloaded", "asset:data:geo:GSE138080 licence not read", "asset:data:geo:GSE27678 not downloaded", "asset:data:geo:GSE27678 licence not read", "asset:data:geo:GSE63514 not downloaded", "asset:data:geo:GSE63514 licence not read", "asset:data:geo:GSE75132 not downloaded", "asset:data:geo:GSE75132 licence not read", "asset:data:geo:GSE7803 not downloaded", "asset:data:geo:GSE7803 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "Survival curves were plotted using the Kaplan-Meier method and compared using the log-rank test. Multivariate Cox regression analysis was performed to determine the prognostic value of the selected gene with considering clinical factors."}}, {"id": "method-2", "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-3", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "ANOVA"}}, {"id": "method-4", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Cox regression"}}, {"id": "method-5", "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-6", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "Pathway enrichment"}}, {"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"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE63514", "GSE27678", "GSE7803", "GSE138080", "GSE75132"], "resolved_accessions": ["GSE63514", "GSE27678", "GSE7803", "GSE138080", "GSE75132"], "statements": ["Publicly available datasets were analyzed in this study. These can be found in The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo/). The tissue microarrays were obtained from Fanpu Biotech. Co., Ltd. (Guilin, China; Product code: CIN1021 and CIN1022) and Outdo Biotech. Co., Ltd. (Shanghai, China; Product Code: HUteS154Su01). The raw experimental data and analysis codes supporting the conclusions of this article will be made available by the corresponding author."], "basis": "The paper names GSE63514, GSE27678, GSE7803, GSE138080, GSE75132 in NCBI Gene Expression Omnibus and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:36352434", "data:geo:GSE138080"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE138080"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:15:09Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 20487, "completion_tokens": 2351, "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:36352434", "type": "paper", "label": "pmid:36352434"}, {"id": "source:pmid:36352434", "type": "manuscript", "label": "PMID 36352434 full text"}, {"id": "data:geo:GSE138080", "type": "dataset", "label": "GEO GSE138080"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36352434", "type": "paper", "label": "pmid:36352434"}, {"id": "source:pmid:36352434", "type": "manuscript", "label": "PMID 36352434 full text"}, {"id": "data:geo:GSE138080", "type": "dataset", "label": "GEO GSE138080"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36352434", "type": "extraction", "used": ["source:pmid:36352434"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE138080", "type": "accession_resolution", "used": ["data:geo:GSE138080"], "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:36352434", "parent_hash": "sha256:4acc620fe20162729ae5e4f7e4b8c9998e302a8761d081c35017ba1d0f83ca36", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE138080 licence not read", "asset:data:geo:GSE138080 not downloaded", "asset:data:geo:GSE27678 licence not read", "asset:data:geo:GSE27678 not downloaded", "asset:data:geo:GSE63514 licence not read", "asset:data:geo:GSE63514 not downloaded", "asset:data:geo:GSE75132 licence not read", "asset:data:geo:GSE75132 not downloaded", "asset:data:geo:GSE7803 licence not read", "asset:data:geo:GSE7803 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["imensional data from five publicly available microarray and TCGA-CESC datasets were analyzed. Immuno", "ve bioinformatic analysis of gene expression microarray datasets was conducted to identify molecular", ". Figure S10. The illustration of the tissue microarray (HUteS154Su01; TMA) from Outdo Biotech. Co.,", "TMA) from Outdo Biotech. Co., Ltd. Table S1. Microarray datasets analyzed in this study. Table S2. H"], "order_basis": "paper_text_order:462", "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": ["oarray and TCGA-CESC datasets were analyzed. Immunohistochemistry was carried out on 354 cervical tissues (42", "nce alone to the combination of p16INK4a and Ki-67. Meanwhile, increased expression of RFC4 sig", "Figure S2. The flow of sample selection and immunohistochemistry (IHC), related to Table S2. Figure S3. Pathw", "Gene Sets1&2. Table S4. Antibodies used for immunohistochemical staining. Table S5. Immunohistochemical scor"], "order_basis": "paper_text_order:511", "id": "assay:2"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Survival curves were plotted using the Kaplan-Meier method and compared using the log-rank test. Multivariate Cox regression analysis was performed to determine the prognostic value of the selected gene with considering clinical factors."], "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":"2026-11-04T03:37:04+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}}}