Tumor-Infiltrating CD8+ T Cells Driven by the Immune Checkpoint-Associated Gene IDO1 Are Associated With Cervical Cancer Prognosis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34778035", "kind": "science-record", "revision": 3, "content_hash": "sha256:9b2961ad72da8f53433e4fb9f1509a620825c3ed12d94e0e3f8cbb39fa9db9df", "created_at": "2026-11-01T17:36:28Z", "updated_at": "2026-11-01T21:26:37Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Tumor-Infiltrating CD8+ T Cells Driven by the Immune Checkpoint-Associated Gene IDO1 Are Associated With Cervical Cancer Prognosis.", "doi": "10.3389/fonc.2021.720447", "pmid": "34778035", "authors": ["Shun Zhang", "Junhui Wan", "Minjie Chen", "Desheng Cai", "Junlan Xu", "Qi Chen"], "journal": "Frontiers in oncology", "year": 2021, "abstract": "Tumor-infiltrating immune cells, associated with tumor progression, are promising prognostic biomarkers. However, the relationship between levels of gene expression and that of immune cell infiltration in cervical cancer prognosis is unknown. In this study, three cervical cancer gene expression microarrays (GSE6791, GSE63678 and GSE55940) were obtained from the GEO database. The IDO1 gene was identified by differentially expressed gene screening. The gene expression profiles of TCGA and GTEx databases along with comprehensive bioinformatics analysis identified that the IDO1 gene was upregulated in cervical cancer with significant difference in expression at different N stages. In addition, it was also upregulated in HPV16 positive sample. The pan-cancer analysis identified that IDO1 was highly expressed in most cancers. TIMER analysis revealed that the expression of IDO1 in CESC shows positive correlation with CD8+ T cells, CD4+ T cells, neutrophils, dendritic cells. IDO1 expression showed remarkable positive correlation with all immune cell markers except M1 macrophages. CD8+ T cell infiltration GSEA results showed that IDO1 was mainly associated with tumor immune-related signaling pathways.", "claims": [{"id": "claim-method", "statement": "Kaplan-Meier test was performed to analyze the difference between the survival of patients with high and low gene expression or high and low infiltration levels.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34778035", "locator": "sections[6] \"Survival Analysis\" paragraph 2", "quote": "Kaplan-Meier test was performed to analyze the difference between the survival of patients with high and low gene expression or high and low infiltration levels."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34778035", "locator": "sections[20] \"Data Availability Statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material ."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "", "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:34778035"], "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:GSE55940"], "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:GSE55940"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34778035", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fonc.2021.720447", "sha256": "sha256:59c3d01ba0d2a07c0d1f5a25c07201a003f4732704aed43bf9aa007c57a10f34", "bytes": 37784, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fonc.2021.720447", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8578845", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE55940", "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=GSE55940", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE55940", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1348884", "GSM1348885", "GSM1348886", "GSM1348887", "GSM1348888", "GSM1348889", "GSM1348890", "GSM1348891", "GSM1348892", "GSM1348893"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "16238", "taxon": "Homo sapiens", "title": "Human transcriptome expression analysis of cervical cancer", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE63678", "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=GSE63678", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63678", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1555075", "GSM1555076", "GSM1555077", "GSM1555078", "GSM1555079", "GSM1555080", "GSM1555081", "GSM1555082", "GSM1555083", "GSM1555084", "GSM1555085", "GSM1555086", "GSM1555087", "GSM1555088", "GSM1555089", "GSM1555090", "GSM1555091", "GSM1555092", "GSM1555093", "GSM1555094", "GSM1555095", "GSM1555096", "GSM1555097", "GSM1555098", "GSM1555099", "GSM1555100", "GSM1555101", "GSM1555102", "GSM1555103", "GSM1555104", "GSM1555105", "GSM1555106", "GSM1555107", "GSM1555108", "GSM1555109"], "sample_count": 35, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Expression data from Vulvar, Cervical, Endometrial Carcinoma tissue", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE6791", "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=GSE6791", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6791", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM155645", "GSM155646", "GSM155647", "GSM155648", "GSM155649", "GSM155650", "GSM155651", "GSM155652", "GSM155653", "GSM155654", "GSM155655", "GSM155656", "GSM155657", "GSM155658", "GSM155659", "GSM155660", "GSM155661", "GSM155662", "GSM155663", "GSM155664", "GSM155665", "GSM155666", "GSM155667", "GSM155668", "GSM155669", "GSM155670", "GSM155671", "GSM155672", "GSM155673", "GSM155674", "GSM155675", "GSM155676", "GSM155677", "GSM155678", "GSM155679", "GSM155680", "GSM155681", "GSM155682", "GSM155683", "GSM155684", "GSM155685", "GSM155686", "GSM155687", "GSM155688", "GSM155689", "GSM155690", "GSM155691", "GSM155692", "GSM155693", "GSM155694", "GSM155695", "GSM155696", "GSM155697", "GSM155698", "GSM155699", "GSM155700", "GSM155701", "GSM155702", "GSM155703", "GSM155704", "GSM155705", "GSM155706", "GSM155707", "GSM155708", "GSM155709", "GSM155710", "GSM155711", "GSM155712", "GSM155713", "GSM155714", "GSM155715", "GSM155716", "GSM155717", "GSM155718", "GSM155719", "GSM155720", "GSM155721", "GSM155722", "GSM155723", "GSM155724", "GSM155725", "GSM155726", "GSM155727", "GSM155728"], "sample_count": 84, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene Expression Profiles of HPV-Positive and -Negative Head/Neck and Cervical Cancers", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE55940 not downloaded", "asset:data:geo:GSE55940 licence not read", "asset:data:geo:GSE63678 not downloaded", "asset:data:geo:GSE63678 licence not read", "asset:data:geo:GSE6791 not downloaded", "asset:data:geo:GSE6791 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 test was performed to analyze the difference between the survival of patients with high and low gene expression or high and low infiltration levels."}}], "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": ["GSE6791", "GSE55940", "GSE63678"], "resolved_accessions": ["GSE6791", "GSE55940", "GSE63678"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material ."], "basis": "The paper names GSE6791, GSE55940, GSE63678 in Gene Expression Omnibus (GEO) database 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:34778035", "data:geo:GSE55940"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE55940"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:07:30Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 11795, "completion_tokens": 2765, "cached_tokens": 188}}, "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:34778035", "type": "paper", "label": "pmid:34778035"}, {"id": "source:pmid:34778035", "type": "manuscript", "label": "PMID 34778035 full text"}, {"id": "data:geo:GSE55940", "type": "dataset", "label": "GEO GSE55940"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34778035", "type": "paper", "label": "pmid:34778035"}, {"id": "source:pmid:34778035", "type": "manuscript", "label": "PMID 34778035 full text"}, {"id": "data:geo:GSE55940", "type": "dataset", "label": "GEO GSE55940"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34778035", "type": "extraction", "used": ["source:pmid:34778035"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE55940", "type": "accession_resolution", "used": ["data:geo:GSE55940"], "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:34778035", "parent_hash": "sha256:f493834853cab407dd7925f2420f8d1d26d6a97c484304e919e052100667322e", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE55940 licence not read", "asset:data:geo:GSE55940 not downloaded", "asset:data:geo:GSE63678 licence not read", "asset:data:geo:GSE63678 not downloaded", "asset:data:geo:GSE6791 licence not read", "asset:data:geo:GSE6791 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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 test was performed to analyze the difference between the survival of patients with high and low gene expression or high and low infiltration levels."], "order_basis": "analysis_only", "id": "assay:1"}]}