{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33178610", "kind": "science-record", "revision": 7, "content_hash": "sha256:8f94209df0ecb95545ff7b6a2cbbd944a24c08c0be94fdf6a2f6e30fbd98d554", "created_at": "2026-11-01T15:41:15Z", "updated_at": "2026-11-01T22:02:29Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatic Analysis Identifies Potential Key Genes in the Pathogenesis of Melanoma.", "doi": "10.3389/fonc.2020.581985", "pmid": "33178610", "authors": ["Yanjie Han", "Xinxin Li", "Jiliang Yan", "Chunyan Ma", "Xin Wang", "Hong Pan", "Xiaoli Zheng", "Zhen Zhang", "Biao Gao", "Xin-Ying Ji"], "journal": "Frontiers in oncology", "year": 2020, "abstract": "Melanoma is the deadliest skin tumor and is prone to distant metastases. The incidence of melanoma has increased rapidly in the past few decades, and current trends indicate that this growth is continuing. This study was aimed to explore the molecular mechanisms of melanoma pathogenesis and discover underlying pathways and genes associated with melanoma. We used high-throughput expression data to study differential expression profiles of related genes in melanoma. The differentially expressed genes (DEGs) of melanoma in GSE15605, GSE46517, GSE7553, and the Cancer Genome Atlas (TCGA) datasets were analyzed. Differentially expressed genes (DEGs) were identified by paired t-test. Then the DEGs were performed cluster and principal component analyses and protein-protein interaction (PPI) network construction. After that, we analyzed the differential genes through bioinformatics and got hub genes. Finally, the expression of hub genes was confirmed in the TCGA databases and collected patient tissue samples. Total 144 up-regulated DEGs and 16 down-regulated DEGs were identified. A total of 17 gene ontology analysis (GO) terms and 11 pathways were closely related to melanoma. Pathway of pathways in cancer was enriched in 8 DEGs, such as junction plakoglobin (JUP) and epidermal growth factor receptor (EGFR). In the PPI networks, 9 hub genes were obtained, such as loricrin (LOR), filaggrin (FLG), keratin 5 (KRT5), corneodesmosin (CDSN), desmoglein 1 (DSG1), desmoglein 3 (DSG3), keratin 1 (KRT1), involucrin (IVL), and EGFR. The pathway of pathways in cancer and its enriched DEGs may play important roles in the process of melanoma. The hub genes of DEGs may become promising melanoma candidate genes. Five key genes FLG, DSG1, DSG3, IVL, and EGFR were identified in the TCGA database and melanoma tissues. The results suggested that FLG, DSG1, DSG3, IVL, and EGFR might play important roles and potentially be valuable in the prognosis and treatment of melanoma. These hub genes might well have clinical significance as diagnostic markers.", "claims": [{"id": "claim-method", "statement": "Available TCGA patient survival data were used for Kaplan–Meier survival analysis and to generate overall survival plots.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33178610", "locator": "sections[9] \"Hub Genes Expression Level and Survival Analysis\" paragraph 2", "quote": "Available TCGA patient survival data were used for Kaplan–Meier survival analysis and to generate overall survival plots."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/, https://cancergenome.nih.gov/abouttcga/overview.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33178610", "locator": "sections[21] \"Data Availability Statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/, https://cancergenome.nih.gov/abouttcga/overview."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:33178610"], "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:GSE15605"], "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:GSE15605"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33178610", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fonc.2020.581985", "sha256": "sha256:f91c0fa5a844ee42de587feb22227563ab78a51c12dd366361e7f21dc4faf944", "bytes": 25385, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fonc.2020.581985", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7596746", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE15605", "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=GSE15605", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15605", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/, https://cancergenome.nih.gov/abouttcga/overview.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/, https://cancergenome.nih.gov/abouttcga/overview.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM390208", "GSM390209", "GSM390210", "GSM390211", "GSM390212", "GSM390213", "GSM390214", "GSM390215", "GSM390216", "GSM390217", "GSM390218", "GSM390219", "GSM390220", "GSM390221", "GSM390222", "GSM390223", "GSM390224", "GSM390225", "GSM390226", "GSM390227", "GSM390228", "GSM390229", "GSM390230", "GSM390231", "GSM390232", "GSM390233", "GSM390234", "GSM390235", "GSM390236", "GSM390237", "GSM390238", "GSM390239", "GSM390240", "GSM390241", "GSM390242", "GSM390243", "GSM390244", "GSM390245", "GSM390246", "GSM390247", "GSM390248", "GSM390249", "GSM390250", "GSM390251", "GSM390252", "GSM390253", "GSM390254", "GSM390255", "GSM390256", "GSM390257", "GSM390258", "GSM390259", "GSM390260", "GSM390261", "GSM390262", "GSM390263", "GSM390264", "GSM390265", "GSM390266", "GSM390267", "GSM390268", "GSM390269", "GSM390270", "GSM390271", "GSM390272", "GSM390273", "GSM390274", "GSM390275", "GSM390276", "GSM390277", "GSM390278", "GSM390279", "GSM390280", "GSM390281"], "sample_count": 74, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Transcriptome profiling identifies HMGA2 as a novel gene in melanoma progression", "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:GSE46517", "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=GSE46517", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE46517", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/, https://cancergenome.nih.gov/abouttcga/overview.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/, https://cancergenome.nih.gov/abouttcga/overview.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1131566", "GSM1131567", "GSM1131568", "GSM1131569", "GSM1131570", "GSM1131571", "GSM1131572", "GSM1131573", "GSM1131574", "GSM1131575", "GSM1131576", "GSM1131577", "GSM1131578", "GSM1131579", "GSM1131580", "GSM1131581", "GSM1131582", "GSM1131583", "GSM1131584", "GSM1131585", "GSM1131586", "GSM1131587", "GSM1131588", "GSM1131589", "GSM1131590", "GSM1131591", "GSM1131592", "GSM1131593", "GSM1131594", "GSM1131595", "GSM1131596", "GSM1131597", "GSM1131598", "GSM1131599", "GSM1131600", "GSM1131601", "GSM1131602", "GSM1131603", "GSM1131604", "GSM1131605", "GSM1131606", "GSM1131607", "GSM1131608", "GSM1131609", "GSM1131610", "GSM1131611", "GSM1131612", "GSM1131613", "GSM1131614", "GSM1131615", "GSM1131616", "GSM1131617", "GSM1131618", "GSM1131619", "GSM1131620", "GSM1131621", "GSM1131622", "GSM1131623", "GSM1131624", "GSM1131625", "GSM1131626", "GSM1131627", "GSM1131628", "GSM1131629", "GSM1131630", "GSM1131631", "GSM1131632", "GSM1131633", "GSM1131634", "GSM1131635", "GSM1131636", "GSM1131637", "GSM1131638", "GSM1131639", "GSM1131640", "GSM1131641", "GSM1131642", "GSM1131643", "GSM1131644", "GSM1131645", "GSM1131646", "GSM1131647", "GSM1131648", "GSM1131649", "GSM1131650", "GSM1131651", "GSM1131652", "GSM1131653", "GSM1131654", "GSM1131655", "GSM1131656", "GSM1131657", "GSM1131658", "GSM1131659", "GSM1131660", "GSM1131661", "GSM1131662", "GSM1131663", "GSM1131664", "GSM1131665", "GSM1131666", "GSM1131667", "GSM1131668", "GSM1131669", "GSM1131670", "GSM1131671", "GSM1131672", "GSM1131673", "GSM1131674", "GSM1131675", "GSM1131676", "GSM1131677", "GSM1131678", "GSM1131679", "GSM1131680", "GSM1131681", "GSM1131682", "GSM1131683", "GSM1131684", "GSM1131685", "GSM1131686"], "sample_count": 121, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Human melanoma samples comparing nevi and primary and metastatic melanoma", "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:GSE7553", "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=GSE7553", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE7553", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/, https://cancergenome.nih.gov/abouttcga/overview.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/, https://cancergenome.nih.gov/abouttcga/overview.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM183218", "GSM183219", "GSM183220", "GSM183221", "GSM183222", "GSM183223", "GSM183224", "GSM183225", "GSM183226", "GSM183227", "GSM183228", "GSM183229", "GSM183230", "GSM183231", "GSM183232", "GSM183233", "GSM183234", "GSM183235", "GSM183236", "GSM183237", "GSM183238", "GSM183239", "GSM183240", "GSM183241", "GSM183242", "GSM183243", "GSM183244", "GSM183245", "GSM183246", "GSM183247", "GSM183248", "GSM183249", "GSM183250", "GSM183251", "GSM183252", "GSM183253", "GSM183254", "GSM183255", "GSM183256", "GSM183257", "GSM183258", "GSM183259", "GSM183260", "GSM183261", "GSM183262", "GSM183263", "GSM183264", "GSM183265", "GSM183266", "GSM183267", "GSM183268", "GSM183269", "GSM183270", "GSM183271", "GSM183272", "GSM183273", "GSM183274", "GSM183275", "GSM183276", "GSM183277", "GSM183278", "GSM183279", "GSM183280", "GSM183281", "GSM183282", "GSM183283", "GSM183284", "GSM183285", "GSM183286", "GSM183287", "GSM183288", "GSM183289", "GSM183290", "GSM183291", "GSM183292", "GSM183293", "GSM183294", "GSM183295", "GSM183296", "GSM183297", "GSM183298", "GSM183299", "GSM183300", "GSM183301", "GSM183302", "GSM183303", "GSM183304"], "sample_count": 87, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene Expression Patterns Involved in the Malignant Transformation and Progression of Metastatic Melanoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33178610:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f28d307226196be2f456280f551ec63831f6138d5f97ea68a43e242b20a2ac39", "bytes": 1257, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T1", "version": null, "note": "160 differentially expressed genes (DEGs) were identified from datasets.", "structure": {"pmcid": "PMC7596746", "section_index": 12, "section_title": "Search Results and Study Characteristics", "row_count": 3, "column_count": 2}, "table": {"label": "Table 1", "caption": "160 differentially expressed genes (DEGs) were identified from datasets.", "rows": [["DEGs"], ["Up-regulated genes", "LOR KRT15 GATA3 FLG PKP1 LGALS7B LGALS7 FGFR3 POF1B EFNA3 CST6 KRT2 CDSN COL17A1 DSG1 TRIM29 LY6D SCEL SERPINB5 TACSTD2 LCE2B PPL DSC1 SFN RAPGEFL1 CRCT1 KLK11 KRT23 CCL27 IL37 CA12 C1orf116 KRT1 KLF5 CALML5 PTK6 KRT5 DSC3 HOPX CLCA2 EVPL CHP2 FGFR2 JUP CWH43 ZNF750 POU2F3 ELOVL4 LYPD3 S100A14 KLK5 ANK3 EPHB6 SERPINB7 AIM1L RORA EGFR CXCL14 ANXA8 ANXA8L1 BBOX1 SCNN1A GJB5 ALDH3B2 CXADR PSORS1C2 ADIRF CYP4B1 PERP KLK10 AQP3 KLK7 HAL ASS1 SDC1 EPHX3 TP63 AZGP1 CYP3A5 RAB25 CALML3 KCNK7 EXPH5 TACC2 SPINK5 NEBL DSG3 ADH1B FERMT1 PKP3 DUOX1 CEBPA SLC24A3 ALOX15B CDS1 PTPRF HLA-DQB2 ARHGEF4 GJB3 PDZD2 CLEC3B NMU SPINT2 BCL11A LY6G6C MMP28 C1orf68 SCGB1D2 GPR87 F2RL1 DEFB1 LAD1 LAMB4 MAOA ALOXE3 PAMR1 NTRK2 SLC15A1 ARG1 KRT19 HLF C1orf106 PDZK1IP1 PALMD RNF39 PPP1R13L AIM1 ACSBG1 AKR1C2 PLLP NPY1R AP1M2 KRT31 KRT7 FAT2 PTGS1 IVL CDHR1 ZBTB16 SCNN1B IRF6 ATP2C2 IRX4 ACSL1"], ["Down-regulated genes", "TRIB2 SLC16A4 SNX10 BCL2A1 AP1S2 ALX1 UPP1 PHLDA1 SOX10 ETV5 PLAT LEF1 CITED1 IGF2BP3 SERPINE2 SPP1"]], "row_count": 3, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33178610:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:86b851fcef0c2fd5f3a2a05f36bbee93cb72b3f80afc2920494e376b16a9db36", "bytes": 356, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#T2", "version": null, "note": "The statistical results of connectivity degrees of the PPI network.", "structure": {"pmcid": "PMC7596746", "section_index": 15, "section_title": "PPI Network Analysis", "row_count": 10, "column_count": 2}, "table": {"label": "Table 2", "caption": "The statistical results of connectivity degrees of the PPI network.", "rows": [["Gene", "Degree"], ["LOR", "26"], ["FLG", "25"], ["KRT5", "24"], ["CDSN", "24"], ["DSG1", "22"], ["DSG3", "22"], ["KRT1", "21"], ["IVL", "21"], ["EGFR", "21"]], "row_count": 10, "column_count": 2, "numeric_cells": 9, "header_rows": 1, "locator": "section[15]/table-wrap[1]#T2"}}], "gaps": ["asset:data:geo:GSE15605 not downloaded", "asset:data:geo:GSE15605 licence not read", "asset:data:geo:GSE46517 not downloaded", "asset:data:geo:GSE46517 licence not read", "asset:data:geo:GSE7553 not downloaded", "asset:data:geo:GSE7553 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "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-3", "family": null, "specific": null, "label": "Kaplan–Meier survival analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Available TCGA patient survival data were used for Kaplan–Meier survival analysis and to generate overall survival plots."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE15605", "GSE46517", "GSE7553"], "resolved_accessions": ["GSE15605", "GSE46517", "GSE7553"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/, https://cancergenome.nih.gov/abouttcga/overview."], "basis": "The paper names GSE15605, GSE46517, GSE7553 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:33178610", "data:geo:GSE15605", "asset:table:pmid:33178610:1", "asset:table:pmid:33178610:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE15605"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:24:07Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 18827, "completion_tokens": 1773, "cached_tokens": 784}}, "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:33178610", "type": "paper", "label": "pmid:33178610"}, {"id": "source:pmid:33178610", "type": "manuscript", "label": "PMID 33178610 full text"}, {"id": "data:geo:GSE15605", "type": "dataset", "label": "GEO GSE15605"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33178610", "type": "paper", "label": "pmid:33178610"}, {"id": "source:pmid:33178610", "type": "manuscript", "label": "PMID 33178610 full text"}, {"id": "data:geo:GSE15605", "type": "dataset", "label": "GEO GSE15605"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33178610", "type": "extraction", "used": ["source:pmid:33178610"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE15605", "type": "accession_resolution", "used": ["data:geo:GSE15605"], "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:33178610", "parent_hash": "sha256:28b3d204aab0d43da94f7a87c54e288bb31f9c364fec0331e9a3fda20e2bf6d6", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE15605 licence not read", "asset:data:geo:GSE15605 not downloaded", "asset:data:geo:GSE46517 licence not read", "asset:data:geo:GSE46517 not downloaded", "asset:data:geo:GSE7553 licence not read", "asset:data:geo:GSE7553 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T03:36:31+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}}}