{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31598425", "kind": "science-record", "revision": 8, "content_hash": "sha256:4e9c9b6c1cf7135aad9f03e87f8456d2294381cb81b586eea87b647574b87147", "created_at": "2026-11-01T15:40:50Z", "updated_at": "2026-11-01T22:44:15Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of potential biomarkers and pivotal biological pathways for prostate cancer using bioinformatics analysis methods.", "doi": "10.7717/peerj.7872", "pmid": "31598425", "authors": ["Zihao He", "Xiaolu Duan", "Guohua Zeng"], "journal": "PeerJ", "year": 2019, "abstract": "BACKGROUND: Prostate cancer (PCa) is a common urinary malignancy, whose molecular mechanism has not been fully elucidated. We aimed to screen for key genes and biological pathways related to PCa using bioinformatics method.\nMETHODS: Differentially expressed genes (DEGs) were filtered out from the GSE103512 dataset and subjected to the gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses. The protein-protein interactions (PPI) network was constructed, following by the identification of hub genes. The results of former studies were compared with ours. The relative expression levels of hub genes were examined in The Cancer Genome Atlas (TCGA) and Oncomine public databases. The University of California Santa Cruz Xena online tools were used to study whether the expression of hub genes was correlated with the survival of PCa patients from TCGA cohorts.\nRESULTS: Totally, 252 (186 upregulated and 66 downregulated) DEGs were identified. GO analysis enriched mainly in \"oxidation-reduction process\" and \"positive regulation of transcription from RNA polymerase II promoter\"; KEGG pathway analysis enriched mostly in \"metabolic pathways\" and \"protein digestion and absorption.\" Kallikrein-related peptidase 3, cadherin 1 (CDH1), Kallikrein-related peptidase 2 (KLK2), forkhead box A1 (FOXA1), and epithelial cell adhesion molecule (EPCAM) were identified as hub genes from the PPI network. CDH1, FOXA1, and EPCAM were validated by other relevant gene expression omnibus datasets. All hub genes were validated by both TCGA and Oncomine except KLK2. Two additional top DEGs (ABCC4 and SLPI) were found to be associated with the prognosis of PCa patients.\nCONCLUSIONS: This study excavated the key genes and pathways in PCa, which might be biomarkers for diagnosis, prognosis, and potential therapeutic targets.", "claims": [{"id": "claim-method", "statement": "The DEGs were filtered using the limma R package (criteria: adjusted P < 0.05 and |log2 fold change| ≥ 1).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31598425", "locator": "sections[10] \"Data processing and screening of DEGs\" paragraph 2", "quote": "The DEGs were filtered using the limma R package (criteria: adjusted P < 0.05 and |log2 fold change| ≥ 1)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE103512.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31598425", "locator": "sections[27] \"Data Availability Statement\" paragraphs 1-3", "quote": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE103512."}], "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:31598425"], "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:GSE103512"], "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:GSE103512"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31598425", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.7872", "sha256": "sha256:278ade96b194d19d375b01c38fc775d2aa7ef28bf02f9f1c167082e7b91573aa", "bytes": 48515, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.7872", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6779116", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE103512", "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=GSE103512", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE103512", "version": null, "note": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE103512.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE103512.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2772660", "GSM2772661", "GSM2772662", "GSM2772663", "GSM2772664", "GSM2772665", "GSM2772666", "GSM2772667", "GSM2772668", "GSM2772669", "GSM2772670", "GSM2772671", "GSM2772672", "GSM2772673", "GSM2772674", "GSM2772675", "GSM2772676", "GSM2772677", "GSM2772678", "GSM2772679", "GSM2772680", "GSM2772681", "GSM2772682", "GSM2772683", "GSM2772684", "GSM2772685", "GSM2772686", "GSM2772687", "GSM2772688", "GSM2772689", "GSM2772690", "GSM2772691", "GSM2772692", "GSM2772693", "GSM2772694", "GSM2772695", "GSM2772696", "GSM2772697", "GSM2772698", "GSM2772699", "GSM2772700", "GSM2772701", "GSM2772702", "GSM2772703", "GSM2772704", "GSM2772705", "GSM2772706", "GSM2772707", "GSM2772708", "GSM2772709", "GSM2772710", "GSM2772711", "GSM2772712", "GSM2772713", "GSM2772714", "GSM2772715", "GSM2772716", "GSM2772717", "GSM2772718", "GSM2772719", "GSM2772720", "GSM2772721", "GSM2772722", "GSM2772723", "GSM2772724", "GSM2772725", "GSM2772726", "GSM2772727", "GSM2772728", "GSM2772729", "GSM2772730", "GSM2772731", "GSM2772732", "GSM2772733", "GSM2772734", "GSM2772735", "GSM2772736", "GSM2772737", "GSM2772738", "GSM2772739", "GSM2772740", "GSM2772741", "GSM2772742", "GSM2772743", "GSM2772744", "GSM2772745", "GSM2772746", "GSM2772747", "GSM2772748", "GSM2772749", "GSM2772750", "GSM2772751", "GSM2772752", "GSM2772753", "GSM2772754", "GSM2772755", "GSM2772756", "GSM2772757", "GSM2772758", "GSM2772759", "GSM2772760", "GSM2772761", "GSM2772762", "GSM2772763", "GSM2772764", "GSM2772765", "GSM2772766", "GSM2772767", "GSM2772768", "GSM2772769", "GSM2772770", "GSM2772771", "GSM2772772", "GSM2772773", "GSM2772774", "GSM2772775", "GSM2772776", "GSM2772777", "GSM2772778", "GSM2772779", "GSM2772780", "GSM2772781", "GSM2772782", "GSM2772783", "GSM2772784", "GSM2772785", "GSM2772786", "GSM2772787", "GSM2772788", "GSM2772789", "GSM2772790", "GSM2772791", "GSM2772792", "GSM2772793", "GSM2772794", "GSM2772795", "GSM2772796", "GSM2772797", "GSM2772798", "GSM2772799", "GSM2772800", "GSM2772801", "GSM2772802", "GSM2772803", "GSM2772804", "GSM2772805", "GSM2772806", "GSM2772807", "GSM2772808", "GSM2772809", "GSM2772810", "GSM2772811", "GSM2772812", "GSM2772813", "GSM2772814", "GSM2772815", "GSM2772816", "GSM2772817", "GSM2772818", "GSM2772819", "GSM2772820", "GSM2772821", "GSM2772822", "GSM2772823", "GSM2772824", "GSM2772825", "GSM2772826", "GSM2772827", "GSM2772828", "GSM2772829", "GSM2772830", "GSM2772831", "GSM2772832", "GSM2772833", "GSM2772834", "GSM2772835", "GSM2772836", "GSM2772837", "GSM2772838", "GSM2772839", "GSM2772840", "GSM2772841", "GSM2772842", "GSM2772843", "GSM2772844", "GSM2772845", "GSM2772846", "GSM2772847", "GSM2772848", "GSM2772849", "GSM2772850", "GSM2772851", "GSM2772852", "GSM2772853", "GSM2772854", "GSM2772855", "GSM2772856", "GSM2772857", "GSM2772858", "GSM2772859", "GSM2772860", "GSM2772861", "GSM2772862", "GSM2772863", "GSM2772864", "GSM2772865", "GSM2772866", "GSM2772867", "GSM2772868", "GSM2772869", "GSM2772870", "GSM2772871", "GSM2772872", "GSM2772873", "GSM2772874", "GSM2772875", "GSM2772876", "GSM2772877", "GSM2772878", "GSM2772879", "GSM2772880", "GSM2772881", "GSM2772882", "GSM2772883", "GSM2772884", "GSM2772885", "GSM2772886", "GSM2772887", "GSM2772888", "GSM2772889", "GSM2772890", "GSM2772891", "GSM2772892", "GSM2772893", "GSM2772894", "GSM2772895", "GSM2772896", "GSM2772897", "GSM2772898", "GSM2772899", "GSM2772900", "GSM2772901", "GSM2772902", "GSM2772903", "GSM2772904", "GSM2772905", "GSM2772906", "GSM2772907", "GSM2772908", "GSM2772909", "GSM2772910", "GSM2772911", "GSM2772912", "GSM2772913", "GSM2772914", "GSM2772915", "GSM2772916", "GSM2772917", "GSM2772918", "GSM2772919", "GSM2772920", "GSM2772921", "GSM2772922", "GSM2772923", "GSM2772924", "GSM2772925", "GSM2772926", "GSM2772927", "GSM2772928", "GSM2772929", "GSM2772930", "GSM2772931", "GSM2772932", "GSM2772933", "GSM2772934", "GSM2772935", "GSM2772936", "GSM2772937", "GSM2772938", "GSM2772939"], "sample_count": 280, "group_sizes": null, "group_sizes_basis": null, "platform": "13158", "taxon": "Homo sapiens", "title": "Gene expression profiles of breast, colorectal, prostate, and non-small cell lung cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31598425:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6c7f584d2a48ab190dc01dce229856be27e0659a4d7d4ad8f770f140aefe856a", "bytes": 1320, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#table-1", "version": null, "note": "Top 10 upregulated and downregulated DEGs between PCa and NP tissues.", "structure": {"pmcid": "PMC6779116", "section_index": 4, "section_title": "Data processing and screening of DEGs", "row_count": 21, "column_count": 4}, "table": {"label": "Table 1", "caption": "Top 10 upregulated and downregulated DEGs between PCa and NP tissues.", "rows": [["Gene symbol", "Log2FC", "adj.P.Val", "State"], ["NPY", "−3.362711603", "0.000789175", "Upregulated"], ["TARP", "−3.206862002", "4.85E-09", "Upregulated"], ["OR51E2", "−2.828448822", "7.28E-05", "Upregulated"], ["NKX3-1", "−2.528690546", "3.58E-12", "Upregulated"], ["MSMB", "−2.517978536", "5.11E-06", "Upregulated"], ["ACPP", "−2.474802744", "2.29E-09", "Upregulated"], ["SLC45A3", "−2.46284327", "2.66E-08", "Upregulated"], ["C15orf21", "−2.327851135", "0.003615423", "Upregulated"], ["ABCC4", "−2.261776258", "1.46E-08", "Upregulated"], ["LOC100287445", "−2.170028348", "0.000544702", "Upregulated"], ["FOLR1", "3.005860886", "8.83E-09", "Downregulated"], ["KRT13", "2.958317838", "2.03E-08", "Downregulated"], ["SEMG1", "2.881097184", "0.001633121", "Downregulated"], ["SEMG2", "2.444264593", "0.00246384", "Downregulated"], ["OLFM4", "2.410939695", "0.000494142", "Downregulated"], ["SLPI", "2.391184301", "3.98E-05", "Downregulated"], ["SCGB1A1", "2.324648206", "2.40E-05", "Downregulated"], ["OSR1", "2.028908547", "3.00E-15", "Downregulated"], ["HSPB6", "1.791949206", "1.19E-06", "Downregulated"], ["CFD", "1.71042558", "1.42E-09", "Downregulated"]], "row_count": 21, "column_count": 4, "numeric_cells": 46, "header_rows": 1, "locator": "section[10]/table-wrap[1]#table-1"}}, {"id": "asset:table:pmid:31598425:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0159f92abafec5d1a133b4930c85db16962c02ef366a31adabcdc3eb8a064808", "bytes": 618, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#table-4", "version": null, "note": "Top five hub genes in the protein–protein interaction (PPI) network.", "structure": {"pmcid": "PMC6779116", "section_index": 6, "section_title": "PPI network construction and modules analyses", "row_count": 6, "column_count": 5}, "table": {"label": "Table 4", "caption": "Top five hub genes in the protein–protein interaction (PPI) network.", "rows": [["Gene symbol", "Gene description", "Degree", "Log2FC", "P-Value"], ["KLK3", "Kallikrein-related peptidase 3", "26", "2.019308668", "2.04E-11"], ["CDH1", "Cadherin 1", "22", "1.21816524", "5.18E-09"], ["KLK2", "Kallikrein-related peptidase 2", "21", "1.954704556", "5.64E-11"], ["FOXA1", "Forkhead Box A1", "20", "1.922009952", "1.66E-11"], ["EPCAM", "Epithelial cell adhesion molecule", "19", "1.076626501", "0.000999371"]], "row_count": 6, "column_count": 5, "numeric_cells": 18, "header_rows": 1, "locator": "section[12]/table-wrap[1]#table-4"}}, {"id": "asset:table:pmid:31598425:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ac4f2acf4c3182d9f0b902ec30e4cc0eeb28996d83e83ba042e9d19063b9bff2", "bytes": 658, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#table-5", "version": null, "note": "Pathway enrichment analysis of the genes in the top two Modules.", "structure": {"pmcid": "PMC6779116", "section_index": 6, "section_title": "PPI network construction and modules analyses", "row_count": 7, "column_count": 5}, "table": {"label": "Table 5", "caption": "Pathway enrichment analysis of the genes in the top two Modules.", "rows": [["Module", "Pathway", "Count", "P-value", "Genes"], ["Module 1", "Adherens junction", "2", "1.0E-2", "CDH1, SNAI2"], ["", "Hippo signaling pathway", "2", "2.0E-2", "CDH1, SNAI2"], ["Module 2", "Fatty acid metabolism", "4", "1.97E-05", "ACSL1, SCD, FASN, ACSL3"], ["", "Fatty acid biosynthesis", "3", "9.79E-05", "ACSL1, FASN, ACSL3"], ["", "PPAR signaling pathway", "3", "0.002925067", "ACSL1, SCD, ACSL3"], ["", "Fatty acid degradation", "2", "0.047850686", "ACSL1, ACSL3"]], "row_count": 7, "column_count": 5, "numeric_cells": 14, "header_rows": 1, "locator": "section[12]/table-wrap[2]#table-5"}}, {"id": "asset:table:pmid:31598425:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6c7f584d2a48ab190dc01dce229856be27e0659a4d7d4ad8f770f140aefe856a", "bytes": 1320, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#table-1", "version": null, "note": "Top 10 upregulated and downregulated DEGs between PCa and NP tissues.", "structure": {"pmcid": "PMC6779116", "section_index": 10, "section_title": "Data processing and screening of DEGs", "row_count": 21, "column_count": 4}, "table": {"label": "Table 1", "caption": "Top 10 upregulated and downregulated DEGs between PCa and NP tissues.", "rows": [["Gene symbol", "Log2FC", "adj.P.Val", "State"], ["NPY", "−3.362711603", "0.000789175", "Upregulated"], ["TARP", "−3.206862002", "4.85E-09", "Upregulated"], ["OR51E2", "−2.828448822", "7.28E-05", "Upregulated"], ["NKX3-1", "−2.528690546", "3.58E-12", "Upregulated"], ["MSMB", "−2.517978536", "5.11E-06", "Upregulated"], ["ACPP", "−2.474802744", "2.29E-09", "Upregulated"], ["SLC45A3", "−2.46284327", "2.66E-08", "Upregulated"], ["C15orf21", "−2.327851135", "0.003615423", "Upregulated"], ["ABCC4", "−2.261776258", "1.46E-08", "Upregulated"], ["LOC100287445", "−2.170028348", "0.000544702", "Upregulated"], ["FOLR1", "3.005860886", "8.83E-09", "Downregulated"], ["KRT13", "2.958317838", "2.03E-08", "Downregulated"], ["SEMG1", "2.881097184", "0.001633121", "Downregulated"], ["SEMG2", "2.444264593", "0.00246384", "Downregulated"], ["OLFM4", "2.410939695", "0.000494142", "Downregulated"], ["SLPI", "2.391184301", "3.98E-05", "Downregulated"], ["SCGB1A1", "2.324648206", "2.40E-05", "Downregulated"], ["OSR1", "2.028908547", "3.00E-15", "Downregulated"], ["HSPB6", "1.791949206", "1.19E-06", "Downregulated"], ["CFD", "1.71042558", "1.42E-09", "Downregulated"]], "row_count": 21, "column_count": 4, "numeric_cells": 46, "header_rows": 1, "locator": "section[10]/table-wrap[1]#table-1"}}, {"id": "asset:table:pmid:31598425:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c2d1c932ae8b52931f6764e66a309793cbd2b8101ca7c95bc0082634aa76ace4", "bytes": 2362, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#table-2", "version": null, "note": "Top 15 enriched gene ontology terms of the upregulated and downregulated DEGs.", "structure": {"pmcid": "PMC6779116", "section_index": 11, "section_title": "Functional and pathway enrichment analyses of DEGs", "row_count": 31, "column_count": 5}, "table": {"label": "Table 2", "caption": "Top 15 enriched gene ontology terms of the upregulated and downregulated DEGs.", "rows": [["Category", "Term", "Count", "P-value", "State"], ["BP", "Oxidation-reduction process", "17", "1.10E-04", "Upregulated"], ["BP", "Proteolysis", "11", "0.01703296", "Upregulated"], ["BP", "Long-chain fatty-acyl-CoA biosynthetic process", "6", "3.93E-05", "Upregulated"], ["BP", "Response to organic cyclic compound", "4", "0.01023923", "Upregulated"], ["BP", "Response to endoplasmic reticulum stress", "4", "0.031611372", "Upregulated"], ["CC", "Extracellular exosome", "74", "2.91E-19", "Upregulated"], ["CC", "Integral component of membrane", "65", "0.001627446", "Upregulated"], ["CC", "Plasma membrane", "56", "7.29E-04", "Upregulated"], ["CC", "Membrane", "34", "0.00188457", "Upregulated"], ["CC", "Extracellular space", "27", "1.58E-04", "Upregulated"], ["MF", "Calcium ion binding", "13", "0.032748281", "Upregulated"], ["MF", "Oxidoreductase activity", "9", "5.26E-04", "Upregulated"], ["MF", "Actin binding", "9", "0.004195153", "Upregulated"], ["MF", "Serine-type peptidase activity", "7", "2.40E-05", "Upregulated"], ["MF", "Serine-type endopeptidase activity", "7", "0.030442507", "Upregulated"], ["BP", "Positive regulation of transcription from RNA polymerase II promoter", "8", "0.047270726", "Downregulated"], ["BP", "Negative regulation of transcription from RNA polymerase II promoter", "7", "0.034624047", "Downregulated"], ["BP", "Negative regulation of cell growth", "4", "0.008047189", "Downregulated"], ["BP", "Extracellular matrix organization", "4", "0.028910713", "Downregulated"], ["BP", "Collagen fibril organization", "3", "0.007739592", "Downregulated"], ["CC", "Extracellular exosome", "23", "3.41E-05", "Downregulated"], ["CC", "Extracellular space", "20", "2.27E-08", "Downregulated"], ["CC", "Extracellular region", "15", "4.96E-04", "Downregulated"], ["CC", "Extracellular matrix", "6", "0.002673098", "Downregulated"], ["CC", "Blood microparticle", "4", "0.013152355", "Downregulated"], ["MF", "Protein binding", "34", "0.021626321", "Downregulated"], ["MF", "Drug binding", "4", "0.001392245", "Downregulated"], ["MF", "Protein dimerization activity", "4", "0.009398722", "Downregulated"], ["MF", "ATPase activity", "4", "0.016027571", "Downregulated"], ["MF", "Sodium:potassium-exchanging ATPase activity", "2", "0.028658029", "Downregulated"]], "row_count": 31, "column_count": 5, "numeric_cells": 60, "header_rows": 1, "locator": "section[11]/table-wrap[1]#table-2"}}, {"id": "asset:table:pmid:31598425:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c4d8aaec196568630371b71253bbecdf69525c5b70487b943479a7a10d95ff15", "bytes": 1448, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#table-3", "version": null, "note": "Top 5 enriched pathways of the upregulated and downregulated DEGs.", "structure": {"pmcid": "PMC6779116", "section_index": 11, "section_title": "Functional and pathway enrichment analyses of DEGs", "row_count": 11, "column_count": 6}, "table": {"label": "Table 3", "caption": "Top 5 enriched pathways of the upregulated and downregulated DEGs.", "rows": [["Pathway ID", "Name", "Count", "P-value", "Genes", "State"], ["hsa01100", "Metabolic pathways", "27", "0.001161421", "SAT1, NAMPT, SORD, GCNT2, GALNT7, GLUD1, PPT1, GGT1, ACSL1, ALDH1A3, ARG2, FASN, AMD1, ACSL3, DHCR24, UAP1, ACLY, ADI1, RDH11, FOLH1, ALOX15B, PLA2G7, PLA2G2A, ABAT, MBOAT2, SMS, DCXR", "Upregulated"], ["hsa01212", "Fatty acid metabolism", "5", "0.002342524", "ACSL1, SCD, FASN, PPT1, ACSL3", "Upregulated"], ["hsa00330", "Arginine and proline metabolism", "4", "0.020729538", "SAT1, ARG2, AMD1, SMS", "Upregulated"], ["hsa03320", "PPAR signaling pathway", "4", "0.043990087", "ACSL1, SCD, DBI, ACSL3", "Upregulated"], ["hsa00061", "Fatty acid biosynthesis", "3", "0.009820063", "ACSL1, FASN, ACSL3", "Upregulated"], ["hsa04974", "Protein digestion and absorption", "3", "0.017282616", "ATP1B1, ATP1A2, COL5A3", "Downregulated"], ["hsa04960", "Aldosterone-regulated sodium reabsorption", "2", "0.087044909", "ATP1B1, ATP1A2", "Downregulated"], ["hsa04973", "Carbohydrate digestion and absorption", "2", "0.093437569", "ATP1B1, ATP1A2", "Downregulated"], ["hsa04978", "Mineral absorption", "2", "0.097676003", "ATP1B1, ATP1A2", "Downregulated"], ["hsa04961", "Endocrine and other factor-regulated calcium reabsorption", "2", "0.099788246", "ATP1B1, ATP1A2", "Downregulated"]], "row_count": 11, "column_count": 6, "numeric_cells": 31, "header_rows": 1, "locator": "section[11]/table-wrap[2]#table-3"}}, {"id": "asset:table:pmid:31598425:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0159f92abafec5d1a133b4930c85db16962c02ef366a31adabcdc3eb8a064808", "bytes": 618, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#table-4", "version": null, "note": "Top five hub genes in the protein–protein interaction (PPI) network.", "structure": {"pmcid": "PMC6779116", "section_index": 12, "section_title": "PPI network construction and modules analyses", "row_count": 6, "column_count": 5}, "table": {"label": "Table 4", "caption": "Top five hub genes in the protein–protein interaction (PPI) network.", "rows": [["Gene symbol", "Gene description", "Degree", "Log2FC", "P-Value"], ["KLK3", "Kallikrein-related peptidase 3", "26", "2.019308668", "2.04E-11"], ["CDH1", "Cadherin 1", "22", "1.21816524", "5.18E-09"], ["KLK2", "Kallikrein-related peptidase 2", "21", "1.954704556", "5.64E-11"], ["FOXA1", "Forkhead Box A1", "20", "1.922009952", "1.66E-11"], ["EPCAM", "Epithelial cell adhesion molecule", "19", "1.076626501", "0.000999371"]], "row_count": 6, "column_count": 5, "numeric_cells": 18, "header_rows": 1, "locator": "section[12]/table-wrap[1]#table-4"}}, {"id": "asset:table:pmid:31598425:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ac4f2acf4c3182d9f0b902ec30e4cc0eeb28996d83e83ba042e9d19063b9bff2", "bytes": 658, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#table-5", "version": null, "note": "Pathway enrichment analysis of the genes in the top two Modules.", "structure": {"pmcid": "PMC6779116", "section_index": 12, "section_title": "PPI network construction and modules analyses", "row_count": 7, "column_count": 5}, "table": {"label": "Table 5", "caption": "Pathway enrichment analysis of the genes in the top two Modules.", "rows": [["Module", "Pathway", "Count", "P-value", "Genes"], ["Module 1", "Adherens junction", "2", "1.0E-2", "CDH1, SNAI2"], ["", "Hippo signaling pathway", "2", "2.0E-2", "CDH1, SNAI2"], ["Module 2", "Fatty acid metabolism", "4", "1.97E-05", "ACSL1, SCD, FASN, ACSL3"], ["", "Fatty acid biosynthesis", "3", "9.79E-05", "ACSL1, FASN, ACSL3"], ["", "PPAR signaling pathway", "3", "0.002925067", "ACSL1, SCD, ACSL3"], ["", "Fatty acid degradation", "2", "0.047850686", "ACSL1, ACSL3"]], "row_count": 7, "column_count": 5, "numeric_cells": 14, "header_rows": 1, "locator": "section[12]/table-wrap[2]#table-5"}}, {"id": "asset:table:pmid:31598425:9", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:070b26add7cac411af8d1b4d3bfe07ee4e37a60e585714de02dc937f63685cc6", "bytes": 1453, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#table-6", "version": null, "note": "Comparisons between the present study and other studies using the GEO datasets.", "structure": {"pmcid": "PMC6779116", "section_index": 13, "section_title": "Validation of hub genes expression in multiple databases", "row_count": 12, "column_count": 4}, "table": {"label": "Table 6", "caption": "Comparisons between the present study and other studies using the GEO datasets.", "rows": [["Study", "Dataset", "Sample size (PCa, NP)", "Hub genes"], ["Endo et al. (2009).", "–", "3, 1", "TSPAN1, BMPR1B, FOXA1, STEAP1, RCAN3, S100P, LYZ, SCGB3A1, IL8, DPT"], ["Chen et al. (2012)", "–", "4, 4", "PPFIA2, PTPRT, PTPRR, PRR16, CHRM2, KRT23, CYP3A4, CYP3A7, DPYS, DUOXA1"], ["Fang et al. (2017)", "GSE26910", "6, 6", "CDH1, BMP2, NKX3-1, PPARG, PRKAR2B"], ["Zhao et al. (2017)", "GSE38241, GSE3933", "47, 37", "CDCA8, CDCA5, UBE2C, TK1"], ["Fan et al. (2018)", "GSE55945", "18, 8", "RPS21, FOXO1, BIRC5, POLR2H, RPL22L1, NPM1"], ["He et al. (2018)", "GSE46602", "36, 14", "PIK3R1, BIRC5, ITGB4, RRM2, TOP2A, ANXA1, LPAR1, ITGB8"], ["Lu & Ding (2019)", "GSE32448, GSE45016, GSE46602, GSE104749", "90, 59", "EPCAM, TWIST1, CD38, VEGFA"], ["Song et al. (2019b)", "GSE6919, GSE6956, GSE32448, GSE32571, GSE35988, GSE46602, GSE68555, GSE69223, GSE70768, GSE88808", "569, 402", "LMNB1, TK1, RACGAP1, ZWINT"], ["Tan, Jin & Wang (2019)", "GSE38240, GSE26910", "14, 10", "IGF2, GATA5, F10, CFI, AGTR1, FOXA1, BZRAP1-AS1, KRT8"], ["Tong, Song & Deng (2019)", "GSE26910, GSE30174, GSE46602, GSE55945, GSE69223", "140, 53", "IKZF1, PPM1A, FBP1, SMCHD1, ALPL, CASP5, PYHIN1, DAPK1, CASP8"], ["The present study", "GSE103512", "60, 7", "KLK3, CDH1, KLK2, FOXA1, EPCAM"]], "row_count": 12, "column_count": 4, "numeric_cells": 36, "header_rows": 1, "locator": "section[13]/table-wrap[1]#table-6"}}], "gaps": ["asset:data:geo:GSE103512 not downloaded", "asset:data:geo:GSE103512 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The DEGs were filtered using the limma R package (criteria: adjusted P < 0.05 and |log2 fold change| ≥ 1)."}}, {"id": "method-2", "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": "PPI"}}], "targets": [], "gaps": []}, "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE103512"], "resolved_accessions": ["GSE103512"], "statements": ["The following information was supplied regarding data availability:\nData is available at NCBI GEO: GSE103512."], "basis": "The paper names GSE103512 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:31598425", "data:geo:GSE103512", "asset:table:pmid:31598425:1", "asset:table:pmid:31598425:2", "asset:table:pmid:31598425:3", "asset:table:pmid:31598425:4", "asset:table:pmid:31598425:5", "asset:table:pmid:31598425:6", "asset:table:pmid:31598425:7", "asset:table:pmid:31598425:8", "asset:table:pmid:31598425:9"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE103512"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:23Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 40917, "completion_tokens": 1072, "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:31598425", "type": "paper", "label": "pmid:31598425"}, {"id": "source:pmid:31598425", "type": "manuscript", "label": "PMID 31598425 full text"}, {"id": "data:geo:GSE103512", "type": "dataset", "label": "GEO GSE103512"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31598425", "type": "paper", "label": "pmid:31598425"}, {"id": "source:pmid:31598425", "type": "manuscript", "label": "PMID 31598425 full text"}, {"id": "data:geo:GSE103512", "type": "dataset", "label": "GEO GSE103512"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31598425", "type": "extraction", "used": ["source:pmid:31598425"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE103512", "type": "accession_resolution", "used": ["data:geo:GSE103512"], "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:31598425", "parent_hash": "sha256:20e8bdfffc0a077299225fa4e5b068c86fd8b1ad450176e124e57affb0ba0028", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE103512 licence not read", "asset:data:geo:GSE103512 not downloaded", "execution.not_run", "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": 0.93, "evidence": ["ata processing and screening of DEGs The PCa microarray expression dataset GSE103512 contained infor"], "order_basis": "paper_text_order:3275", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The DEGs were filtered using the limma R package (criteria: adjusted P < 0.05 and |log2 fold change| ≥ 1)."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T02:54:05+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}}}