{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33216732", "kind": "science-record", "revision": 9, "content_hash": "sha256:0699f3a49ff28f9e20473d910dacdf97464011f66ebf09a32a6d3fa496d46c08", "created_at": "2026-11-01T15:41:16Z", "updated_at": "2026-11-01T22:45:38Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Oncostatin M expression and TP53 mutation status regulate tumor-infiltration of immune cells and survival outcomes in cholangiocarcinoma.", "doi": "10.18632/aging.103936", "pmid": "33216732", "authors": ["Qi Liu", "Tian Lan", "Yuxuan Song", "Jianpeng Cai", "Xi Yu", "Wei Chen"], "journal": "Aging", "year": 2020, "abstract": "In this study, we used bioinformatics tools to analyze transcriptome data from cholangiocarcinoma (CCA) patients in multiple datasets (Sun Yat-sen University, TCGA and GSE32225 cohorts) to identify mechanisms that regulate tumor infiltration by immune cells and survival outcomes. We identified 96 differentially expressed genes (DEGs), including 13 upregulated and 83 downregulated genes, in CCA tissues as regulatory T cells were significantly higher and the proportions of activated natural killer cells and monocytes were significantly lower in CCA tissues than the precancerous tissues. The survival outcomes of CCA patients were associated with the TP53 gene mutation status, levels of Oncostatin M (OSM) expression, and the proportions of tumor-infiltrating immune cell types, including dendritic cells, monocytes, and T follicular helper cells. Functional enrichment analysis of the DEGs in the high OSM-expressing CCA tissues showed that pathways related to tumor progression and immune response were significantly upregulated. Our study demonstrates that OSM expression and TP53 mutation status regulate the tumor infiltration by immune cells and survival outcomes in CCA. OSM is thus a potential prognostic biomarker and therapeutic target in cholangiocarcinoma.", "claims": [{"id": "claim-method", "statement": "Kaplan-Meier survival curve analysis and log-rank test showed that overall survival was significantly shorter for CCA patients with low OSM expression (OSMlow group) compared to those in the OSMhighgroup (Figure 5D).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33216732", "locator": "sections[7] \"Prognostic significance of OSM expression in CCA Patients with and without TP53 gene mutations\" paragraph 2", "quote": "Kaplan-Meier survival curve analysis and log-rank test showed that overall survival was significantly shorter for CCA patients with low OSM expression (OSMlow group) compared to those in the OSMhighgroup (Figure 5D)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "We obtained transcriptome data from the TCGA database that included 9 precancerous and 36 CCA tissue samples", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33216732", "locator": "sections[14] \"CCA patient datasets\" paragraph 3", "quote": "We obtained transcriptome data from the TCGA database that included 9 precancerous and 36 CCA tissue samples"}], "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:33216732"], "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:GSE32225"], "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:GSE32225"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33216732", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/aging.103936", "sha256": "sha256:a32005b35f7e95ff5ddaf44dd12b7b79a3626e5ae094bbf2d3b160587fa62ce3", "bytes": 54205, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/aging.103936", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11623973", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE32225", "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=GSE32225", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32225", "version": null, "note": "We obtained transcriptome data from the TCGA database that included 9 precancerous and 36 CCA tissue samples", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We obtained transcriptome data from the TCGA database that included 9 precancerous and 36 CCA tissue samples", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM798481", "GSM798482", "GSM798483", "GSM798484", "GSM798485", "GSM798486", "GSM798487", "GSM798488", "GSM798489", "GSM798490", "GSM798491", "GSM798492", "GSM798493", "GSM798494", "GSM798495", "GSM798496", "GSM798497", "GSM798498", "GSM798499", "GSM798500", "GSM798501", "GSM798502", "GSM798503", "GSM798504", "GSM798505", "GSM798506", "GSM798507", "GSM798508", "GSM798509", "GSM798510", "GSM798511", "GSM798512", "GSM798513", "GSM798514", "GSM798515", "GSM798516", "GSM798517", "GSM798518", "GSM798519", "GSM798520", "GSM798521", "GSM798522", "GSM798523", "GSM798524", "GSM798525", "GSM798526", "GSM798527", "GSM798528", "GSM798529", "GSM798530", "GSM798531", "GSM798532", "GSM798533", "GSM798534", "GSM798535", "GSM798536", "GSM798537", "GSM798538", "GSM798539", "GSM798540", "GSM798541", "GSM798542", "GSM798543", "GSM798544", "GSM798545", "GSM798546", "GSM798547", "GSM798548", "GSM798549", "GSM798550", "GSM798551", "GSM798552", "GSM798553", "GSM798554", "GSM798555", "GSM798556", "GSM798557", "GSM798558", "GSM798559", "GSM798560", "GSM798561", "GSM798562", "GSM798563", "GSM798564", "GSM798565", "GSM798566", "GSM798567", "GSM798568", "GSM798569", "GSM798570", "GSM798571", "GSM798572", "GSM798573", "GSM798574", "GSM798575", "GSM798576", "GSM798577", "GSM798578", "GSM798579", "GSM798580", "GSM798581", "GSM798582", "GSM798583", "GSM798584", "GSM798585", "GSM798586", "GSM798587", "GSM798588", "GSM798589", "GSM798590", "GSM798591", "GSM798592", "GSM798593", "GSM798594", "GSM798595", "GSM798596", "GSM798597", "GSM798598", "GSM798599", "GSM798600", "GSM798601", "GSM798602", "GSM798603", "GSM798604", "GSM798605", "GSM798606", "GSM798607", "GSM798608", "GSM798609", "GSM798610", "GSM798611", "GSM798612", "GSM798613", "GSM798614", "GSM798615", "GSM798616", "GSM798617", "GSM798618", "GSM798619", "GSM798620", "GSM798621", "GSM798622", "GSM798623", "GSM798624", "GSM798625", "GSM798626", "GSM798627", "GSM798628", "GSM798629", "GSM798630", "GSM798631", "GSM798632", "GSM798633", "GSM798634", "GSM798635"], "sample_count": 155, "group_sizes": null, "group_sizes_basis": null, "platform": "8432", "taxon": "Homo sapiens", "title": "Gene-expression profiles of formalin-fixed, paraffin-embedded human intrahepatic cholangiocarcinoma", "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:33216732:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:109d92673f57f058065624848c11124ad91d3ea0b80259ae98282a5d7941ef05", "bytes": 1459, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#t1", "version": null, "note": "Correlation between OSM expression and clinical characteristics in 203 CCA patients by chi-square test.", "structure": {"pmcid": "PMC11623973", "section_index": 8, "section_title": "OSM expression is an independent predictor of prognosis in CCA patients", "row_count": 47, "column_count": 4}, "table": {"label": "Table 1", "caption": "Correlation between OSM expression and clinical characteristics in 203 CCA patients by chi-square test.", "rows": [["Variables", "High (n=101)", "Low (n=102)", "P"], ["Gender", "", "", "0.723"], ["Male", "54", "52", ""], ["Female", "47", "50", ""], ["Age", "", "", "0.529"], [">58", "50", "46", ""], ["≤58", "51", "56", ""], ["Tumor", "", "", "0.726"], [">5cm", "50", "53", ""], ["≤5cm", "51", "49", ""], ["Hepatitis", "", "", "0.834"], ["YES", "21", "20", ""], ["NO", "80", "82", ""], ["Tumor number", "", "", "<0.001"], ["single", "91", "67", ""], ["multiple", "10", "35", ""], ["Tumor capsulation", "", "", "0.136"], ["none", "40", "51", ""], ["complete", "61", "51", ""], ["CA199", "", "", "0.838"], [">37 U/L", "55", "57", ""], ["≤37 U/L", "46", "45", ""], ["CA125", "", "", "0.919"], [">35 U/mL", "32", "33", ""], ["≤35 U/mL", "69", "69", ""], ["CEA", "", "", "0.960"], [">5 μg/L", "34", "34", ""], ["≤5 μg/L", "67", "68", ""], ["Tumor differentiation", "", "", "0.619"], ["High", "4", "2", ""], ["Moderate", "62", "69", ""], ["Moderate-low", "20", "15", ""], ["Low", "15", "16", ""], ["Lymphatic metastasis", "", "", "0.003"], ["YES", "29", "50", ""], ["NO", "72", "52", ""], ["Distant metastasis", "", "", "0.045"], ["YES", "16", "28", ""], ["NO", "85", "74", ""], ["Vascular invasion", "", "", "0.001"], ["YES", "10", "27", ""], ["NO", "91", "75", ""], ["AJCC 8th TNM stage", "", "", "0.033"], ["I", "45", "26", ""], ["II", "12", "17", ""], ["III", "28", "33", ""], ["IV", "16", "26", ""]], "row_count": 47, "column_count": 4, "numeric_cells": 93, "header_rows": 0, "locator": "section[8]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:33216732:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:05ea7fad12b3fdc44ee89208494642570240db46ece57a78187c457c4314fa41", "bytes": 2760, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[2]#t2", "version": null, "note": "Univariate and multivariate Cox analysis of potential prognostic factors in 203 CCA patients.", "structure": {"pmcid": "PMC11623973", "section_index": 8, "section_title": "OSM expression is an independent predictor of prognosis in CCA patients", "row_count": 28, "column_count": 6}, "table": {"label": "Table 2", "caption": "Univariate and multivariate Cox analysis of potential prognostic factors in 203 CCA patients.", "rows": [["", "OS", "", "", "RFS", ""], ["", "HR (95%CI)", "P value", "", "HR (95%CI)", "P value"], ["Univariate COX analysis", "", "", "", "", ""], ["Gender (male versus female)", "1.162(0.823-1.642)", "0.394", "", "1.087(0.784-1.506)", "0.616"], ["Age (year) (>58 versus ≤58)", "0.987(0.698-1.393)", "0.939", "", "0.940(0.678-1.303)", "0.708"], ["Tumor size (cm) (>5 versus ≤5)", "1.321(0.935-1.867)", "0.115", "", "1.435(1.034-1.993)", "0.031"], ["Tumor number (multiple versus single)", "1.986(1.377-2.862)", "0.000", "", "2.171(1.542-3.058)", "0.000"], ["Tumor encapsulation (complete versus none)", "0.510(0.359-0.724)", "0.000", "", "0.652(0.468-0.906)", "0.011"], ["CA199(>37 U/L versus ≤ 37 U/L)", "1.931(1.350-2.764)", "0.000", "", "1.468(1.053-2.046)", "0.023"], ["CA125 (>35 U/mL versus ≤35 U/mL)", "1.995(1.402-2.839)", "0.000", "", "2.121(1.511-2.975)", "0.000"], ["CEA (>5μg/L versus ≤ 5μg/L)", "1.741(1.219-2.487)", "0.002", "", "1.636(1.164-2.298)", "0.005"], ["Stage (IV+III+II versus I)", "3.009(1.992-4.545)", "0.000", "", "2.875(1.955-4.227)", "0.000"], ["Lymphatic metastasis (yes versus no)", "2.507(1.765-3.561)", "0.000", "", "2.119(1.517-2.961)", "0.000"], ["Distant metastasis (yes versus no)", "1.934(1.298-2.880)", "0.001", "", "2.279(1.560-3.331)", "0.000"], ["Vascular invasion (yes versus no)", "2.409(1.605-3.617)", "0.000", "", "1.762(1.180-2.631)", "0.006"], ["OSM (high vs low)", "0.533(0.391-0.783)", "0.001", "", "0.644(0.463-0.896)", "0.009"], ["Liver cirrhosis (yes versus no)", "0.628(0.386-1.021)", "0.061", "", "0.805(0.526-1.231)", "0.316"], ["Multivariate COX analysis", "", "", "", "", ""], ["Tumor number (multiple versus single)", "1.611(1.079-2.407)", "0.020", "", "1.655(1.115-2.457)", "0.012"], ["Tumor encapsulation (complete versus none)", "0.626(0.425-0.922)", "0.018", "", "0.731(0.509-1.049)", "0.089"], ["CA125 (>35 U/mL versus ≤35 U/mL)", "1.322(0.888-1.968)", "0.169", "", "1.595(1.099-2.316)", "0.014"], ["CA199(>37 U/L versus ≤ 37 U/L)", "1.519(1.037-2.226)", "0.032", "", "1.100(0.774-1.563)", "0.594"], ["CEA (>5μg/L versus ≤ 5μg/L)", "1.300(0.868-1.948)", "0.203", "", "1.146(0.783-1.676)", "0.483"], ["Stage (IV+III+II versus I)", "1.534(0.891-2.672)", "0.121", "", "1.770(1.063-2.947)", "0.028"], ["Lymphatic metastasis (yes versus no)", "1.432(0.904-2.270)", "0.126", "", "1.194(0.771-1.850)", "0.427"], ["Distant metastasis (yes versus no)", "0.921(0.582-1.457)", "0.724", "", "1.375(0.878-2.154)", "0.164"], ["Vascular invasion (yes versus no)", "1.160(0.733-1.835)", "0.527", "", "0.978(0.618-1.549)", "0.926"], ["OSM (high versus low)", "0.541(0.372-0.787)", "0.001", "", "0.745(0.518-1.073)", "0.114"]], "row_count": 28, "column_count": 6, "numeric_cells": 106, "header_rows": 0, "locator": "section[8]/table-wrap[2]#t2"}}, {"id": "asset:table:pmid:33216732:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9d2e63dfeafb4cca787384acc4d4235cbe412507b36420da6303e300aefbc9a7", "bytes": 1792, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#t3", "version": null, "note": "Correlations between OSM and related genes and markers of immune cells in TIMER by spearman analysis.", "structure": {"pmcid": "PMC11623973", "section_index": 9, "section_title": "OSM expression correlates with tumor infiltration of immune cells in CCA tissues", "row_count": 39, "column_count": 6}, "table": {"label": "Table 3", "caption": "Correlations between OSM and related genes and markers of immune cells in TIMER by spearman analysis.", "rows": [["Cell type", "Gene marker", "None", "Purity"], ["", "", "Cor", "P", "Cor", "P"], ["B cell", "CD19", "-0.084", "0.631", "-0.414", "0.012"], ["", "CD22", "0.233", "0.177", "-", "-"], ["", "CD70", "0.248", "0.151", "-", "-"], ["CD8+T Cell", "CD8A", "0.144", "0.409", "-", "-"], ["", "CD8B", "0.042", "0.811", "-", "-"], ["Tfh", "IL21", "0.008", "0.964", "-", "-"], ["", "ICOS", "0.355", "0.037", "-", "-"], ["", "BCL-6", "0.340", "0.046", "-", "-"], ["Thl", "IL12RB2", "0.228", "0.188", "-", "-"], ["", "T-bet (TBX21)", "0.085", "0.628", "", ""], ["", "IFN-γ (IFNG)", "0.117", "0.505", "", ""], ["", "TNF-α (TNF)", "0.219", "0.207", "", ""], ["Th2", "GATA3", "0.159", "0.363", "", ""], ["", "STAT5A", "0.120", "0.493", "", ""], ["", "IL13", "-0.259", "0.133", "", ""], ["Th17", "IL17A", "0.294", "0.087", "-", "-"], ["", "STAT3", "0.153", "0.380", "-", "-"], ["Treg", "FOXP3", "0.298", "0.082", "", ""], ["", "CCR8", "0.204", "0.240", "", ""], ["", "STAT5B", "0.148", "0.396", "", ""], ["", "TGFβ (TGFB1)", "0.173", "0.321", "-", "-"], ["TAM", "CCL2", "0.289", "0.092", "-", "-"], ["", "CD68", "0.298", "0.082", "-", "-"], ["", "IL10", "0.291", "0.089", "-", "-"], ["M1 macrophages", "NOS2", "0.102", "0.559", "-", "-"], ["", "ROS", "0.121", "0.488", "-", "-"], ["M2 macrophages", "ARG1", "0.124", "0.477", "-", "-"], ["", "MRC1", "0.092", "0.599", "-", "-"], ["Monocyte", "CD14", "0.245", "0.155", "-", "-"], ["", "CD33", "0.384", "0.023", "-", "-"], ["NK", "XCL1", "0.066", "0.708", "-", "-"], ["", "KIR3DL1", "0.002", "0.991", "-", "-"], ["", "CD7", "0.135", "0.440", "-", "-"], ["Neutrophil", "MPO", "0.074", "0.671", "-", "-"], ["Dendritic cell", "CD80", "0.602", "<0.001", "-", "-"], ["", "CD83", "0.456", "0.006", "-", "-"], ["", "CD86", "0.500", "0.002", "-", "-"]], "row_count": 39, "column_count": 6, "numeric_cells": 93, "header_rows": 0, "locator": "section[9]/table-wrap[1]#t3"}}, {"id": "asset:table:pmid:33216732:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:174194cd8e4151fc2593d8f2db2f910426489ef6b274d3254369eb6003010605", "bytes": 1446, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[2]#t4", "version": null, "note": "Correlations between OSM and genes markers of B cells, T helper cells, TAMs, monocytes, DCs and MDSCs in GEPIA by spearman analysis.", "structure": {"pmcid": "PMC11623973", "section_index": 9, "section_title": "OSM expression correlates with tumor infiltration of immune cells in CCA tissues", "row_count": 27, "column_count": 6}, "table": {"label": "Table 4", "caption": "Correlations between OSM and genes markers of B cells, T helper cells, TAMs, monocytes, DCs and MDSCs in GEPIA by spearman analysis.", "rows": [["Cell type", "Gene marker", "Tumor", "Normal"], ["", "", "Cor", "P", "Cor", "P"], ["B cell", "CD19", "0.22", "0.2", "-0.46", "0.21"], ["", "CD22", "0.33", "0.051", "0.3", "0.43"], ["", "CD70", "0.4", "0.016", "-0.17", "0.66"], ["Tfh", "CXCR5", "0.046", "0.79", "-0.17", "0.68"], ["", "ICOS", "0.52", "0.001", "0.53", "0.14"], ["", "BCL-6", "0.31", "0.064", "0.67", "0.059"], ["Thl", "IL12RB2", "0.3", "0.072", "0.35", "0.35"], ["", "T-bet (TBX21)", "0.31", "0.066", "", ""], ["", "STAT4", "0.2", "0.24", "0.05", "0.91"], ["Th2", "CCR3", "0.26", "0.13", "0.35", "0.36"], ["", "CCR4", "0.46", "0.005", "0.37", "0.34"], ["Th17", "IL-23R", "0.42", "0.012", "-0.028", "0.94"], ["", "STAT3", "0.19", "0.25", "0.57", "0.12"], ["Treg", "FOXP3", "0.41", "0.012", "-0.2", "0.61"], ["", "IL-2Ra", "0.45", "0.006", "0.084", "0.83"], ["TAM", "CCL2", "0.14", "0.42", "0.65", "0.06"], ["", "CD68", "0.21", "0.22", "0.23", "0.54"], ["", "IL10", "0.28", "0.095", "0.71", "0.034"], ["Monocyte", "CD14", "0.43", "0.009", "0.43", "0.25"], ["", "CD33", "0.46", "0.005", "-0.05", "0.91"], ["Dendritic cell", "CD80", "0.68", "<0.001", "0.47", "0.2"], ["", "CD83", "0.55", "<0.001", "0.37", "0.34"], ["", "CD86", "0.64", "<0.001", "0.63", "0.076"], ["MDSCs", "CD33", "0.46", "0.005", "-0.05", "0.91"], ["", "CD11b", "0.22", "0.2", "0.53", "0.15"]], "row_count": 27, "column_count": 6, "numeric_cells": 116, "header_rows": 0, "locator": "section[9]/table-wrap[2]#t4"}}, {"id": "asset:table:pmid:33216732:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4739fb37b2d84be4fe7ae59e547dd582371e583e55fec6846004c84c055aa6e8", "bytes": 372, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#t5", "version": null, "note": "OSM expression correlates with four immune regulatory checkpoints in CCA tissue.", "structure": {"pmcid": "PMC11623973", "section_index": 10, "section_title": "OSM expression correlates with three immune regulatory checkpoints in CCA tissues", "row_count": 3, "column_count": 9}, "table": {"label": "Table 5", "caption": "OSM expression correlates with four immune regulatory checkpoints in CCA tissue.", "rows": [["", "CTLA4", "HAVCR2", "LAG3", "PDL1"], ["Cor", "P", "Cor", "P", "Cor", "P", "Cor", "P"], ["OSM", "0.33", "0.049", "0.45", "0.006", "0.13", "0.45", "0.43", "0.009"]], "row_count": 3, "column_count": 9, "numeric_cells": 8, "header_rows": 0, "locator": "section[10]/table-wrap[1]#t5"}}, {"id": "asset:table:pmid:33216732:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:69011409380a657b33cee4faf04272f88e723988ae9b6fc501a6094633feda44", "bytes": 2770, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#t6", "version": null, "note": "Gene Set Enrichment Analysis (GSEA) reveals biological function of OSM in CCA.", "structure": {"pmcid": "PMC11623973", "section_index": 11, "section_title": "Functional enrichment analysis of OSM-related genes in CCA tissues", "row_count": 43, "column_count": 4}, "table": {"label": "Table 6", "caption": "Gene Set Enrichment Analysis (GSEA) reveals biological function of OSM in CCA.", "rows": [["GO/KEGG pathway Description", "Gene Count", "Enrichment Score", "P Value"], ["GO terms for biological process (BP)", "", "", ""], ["Positive Regulation of Acute Inflammatory Response", "28", "0.69", "<0.001"], ["Innate Immune Response Activating Cell Surface Receptor Signaling Pathway", "106", "0.55", "<0.001"], ["Regulation of Neutrophil Migration", "30", "0.68", "<0.001"], ["Positive Regulation of Neutrophil Migration", "26", "0.68", "<0.001"], ["Inflammatory Response", "440", "0.54", "<0.001"], ["Cilium Movement", "31", "-0.62", "0.021"], ["Photoreceptor Cell Maintenance", "34", "-0.55", "0.021"], ["Regulation of Activin Receptor Signaling Pathway", "25", "-0.55", "0.022"], ["Protein Transport Along Microtubule", "26", "-0.57", "0.039"], ["Negative Regulation of Protein Kinase B Signaling", "33", "-0.47", "0.04"], ["GO terms for cellular component (CC)", "", "", ""], ["Recycling Endosome Membrane", "40", "0.5", "0.023"], ["Extrinsic Component of Cytoplasmic Side of Plasma Membrane", "97", "0.55", "<0.001"], ["Cytoplasmic Side of Membrane", "167", "0.48", "0.021"], ["Immunological Synapse", "31", "0.65", "0.038"], ["Extrinsic Component of Membrane", "245", "0.46", "0.047"], ["Ciliary Tip", "42", "-0.61", "0.017"], ["Mitochondrial Membrane Part", "140", "-0.58", "0.023"], ["Mitochondrial Protein Complex", "108", "-0.62", "0.023"], ["Organelle Inner Membrane", "472", "-0.48", "<0.001"], ["Intrinsic Component of Mitochondrial Inner Membrane", "16", "-0.63", "0.043"], ["GO terms for molecular function (MF)", "", "", ""], ["Immunoglobulin Binding", "21", "0.76", "<0.001"], ["Tumor Necrosis Factor Receptor Binding", "29", "0.65", "<0.001"], ["Chemokine Activity", "46", "0.6", "0.023"], ["Cytokine Receptor Binding", "264", "0.44", "<0.001"], ["Cytokine Receptor Activity", "85", "0.56", "0.059"], ["Oxidoreductase Activity Acting on NAD P H Quinone Or Similar Compound as Acceptor", "52", "-0.67", "0.021"], ["Oxidoreductase Activity Acting on A Heme Group of Donors", "25", "-0.64", "0.021"], ["Oxidoreductase Activity Acting on NAD P H", "92", "-0.51", "0.042"], ["Gaba Receptor Activity", "22", "-0.58", "0.039"], ["Metal Cluster Binding", "61", "-0.46", "0.04"], ["KEGG signaling pathways", "", "", ""], ["JAK Stat Signaling Pathway", "151", "0.52", "<0.001"], ["Toll Like Receptor Signaling Pathway", "101", "0.51", "<0.001"], ["Cytokine Receptor Interaction", "257", "0.52", "0.019"], ["Natural Killer Cell Mediated Cytotoxicity", "131", "0.52", "0.018"], ["T Cell Receptor Signaling Pathway", "106", "0.53", "<0.001"], ["B Cell Receptor Signaling Pathway", "74", "0.59", "<0.001"], ["Huntingtons Disease", "161", "-0.49", "0.042"], ["Parkinsons Disease", "100", "-0.61", "0.08"]], "row_count": 43, "column_count": 4, "numeric_cells": 114, "header_rows": 0, "locator": "section[11]/table-wrap[1]#t6"}}], "gaps": ["asset:data:geo:GSE32225 not downloaded", "asset:data:geo:GSE32225 licence not read"]}, "analysis": {"state": "complete", "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": "Kaplan-Meier survival curve analysis and log-rank test showed that overall survival was significantly shorter for CCA patients with low OSM expression (OSMlow group) compared to those in the OSMhighgroup (Figure 5D)."}}, {"id": "method-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "wed that tumor numbers (HR=1"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Cox regression"}}, {"id": "method-3", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-4", "family": "differential_expression", "specific": "edger", "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": 0.8, "band": "high", "quote": "edgeR"}}, {"id": "method-5", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "logistic regression"}}, {"id": "method-6", "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": 0.8, "band": "high", "quote": "PPI"}}, {"id": "method-7", "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-8", "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": []}, "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": ["GSE32225"], "resolved_accessions": ["GSE32225"], "statements": ["We obtained transcriptome data from the TCGA database that included 9 precancerous and 36 CCA tissue samples"], "basis": "The paper names GSE32225 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": ["survival_km"], "assets": ["source:pmid:33216732", "data:geo:GSE32225", "asset:table:pmid:33216732:1", "asset:table:pmid:33216732:2", "asset:table:pmid:33216732:3", "asset:table:pmid:33216732:4", "asset:table:pmid:33216732:5", "asset:table:pmid:33216732:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE32225"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:24:29Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 43331, "completion_tokens": 2480, "cached_tokens": 512}}, "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:33216732", "type": "paper", "label": "pmid:33216732"}, {"id": "source:pmid:33216732", "type": "manuscript", "label": "PMID 33216732 full text"}, {"id": "data:geo:GSE32225", "type": "dataset", "label": "GEO GSE32225"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33216732", "type": "paper", "label": "pmid:33216732"}, {"id": "source:pmid:33216732", "type": "manuscript", "label": "PMID 33216732 full text"}, {"id": "data:geo:GSE32225", "type": "dataset", "label": "GEO GSE32225"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33216732", "type": "extraction", "used": ["source:pmid:33216732"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE32225", "type": "accession_resolution", "used": ["data:geo:GSE32225"], "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:33216732", "parent_hash": "sha256:5bcf3c8140e313cdeac9ce53bff14a47cb55adfcedff8f66a0978a4d9416f973", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE32225 licence not read", "asset:data:geo:GSE32225 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["udy, we used bioinformatics tools to analyze transcriptome data from cholangiocarcinoma (CCA) patients", "CGA and ICGC databases for further analysis. RNA-seq data processing We used the R software packa", "wn in the Supplementary Table 2. We obtained transcriptome data from the TCGA database that included 9", "ttps://www.r-project.org) to analyze the RNA transcriptome and somatic nucleotide variation data. We id"], "order_basis": "paper_text_order:148", "id": "assay:1"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ndent predictor of prognosis in CCA patients Western blot assays in 12 paired CCA tumor and adjacent n", "or (T) and adjacent non-tumor tissues (P) by western blotting. (B) Representative immunostaining images of", "or RNA high-throughput sequencing and 12 for western blotting. This study was approved by the Ethics Commi"], "order_basis": "paper_text_order:4655", "id": "assay:2"}, {"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": ["clinicopathological characteristics and OSM immunohistochemistry. We also recruited 5 out of 208 patients bet", "(P) by western blotting. (B) Representative immunostaining images of OSM in CCA. (C) Boxplots depicted", "Sen university cohort of 203 CCA patients by IHC and divided the patients into high- and low-", "=101 and n=102, respectively) using a median IHC expression score of 4 (Figure 6B). Kaplan-Me"], "order_basis": "paper_text_order:5061", "id": "assay:3"}, {"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": ["Kaplan-Meier survival curve analysis and log-rank test showed that overall survival was significantly shorter for CCA patients with low OSM expression (OSMlow group) compared to those in the OSMhighgroup (Figure 5D)."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"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":"2026-11-04T02:38:57+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}}}