Identification of prognostic signatures in pheochromocytomas and paragangliomas based on mitochondrial autophagy and ferroptosis in TCGA and GEO datasets.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41543804", "kind": "science-record", "revision": 3, "content_hash": "sha256:041d89b4ea3ebd29b7458ff1945b7b9eee9471f06b5a95c52fc9ac0f0acc3d23", "created_at": "2026-11-01T20:31:30Z", "updated_at": "2026-11-01T22:15:18Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of prognostic signatures in pheochromocytomas and paragangliomas based on mitochondrial autophagy and ferroptosis in TCGA and GEO datasets.", "doi": "10.1007/s12672-026-04393-7", "pmid": "41543804", "authors": ["Qingke Chen", "Zhiyong Xian", "Qian Zou", "Junming Bi"], "journal": "Discover oncology", "year": 2026, "abstract": "Pheochromocytomas (PCCs) and paragangliomas (PGLs), collectively PPGLs, are rare tumors with significant molecular heterogeneity, which complicates prognosis and treatment. This study analyzed publicly available datasets (TCGA-PPGLs, GSE19422, GSE60459) to identify differentially expressed genes (DEGs) related to mitochondrial autophagy and ferroptosis in PPGLs. We identified 6,286 DEGs, including 31 mitochondrial ferroptosis-related DEGs (MFRDEGs). A prognostic model based on four genes (AMBRA1, EIF2S1, SRC, PHGDH) demonstrated high predictive accuracy (AUC > 0.9). Functional enrichment analysis highlighted key pathways, including mitophagy and Fc epsilon receptor I (FcεRI) signaling. Protein-protein interaction (PPI) and ceRNA network analyses revealed potential regulatory mechanisms. Calibration and decision curve analyses confirmed the model's clinical utility. These findings offer insights into PPGL molecular mechanisms, suggest prognostic biomarkers, and propose candidate therapeutic targets to improve risk stratification and personalized treatment. However, experimental validation is required to confirm their biological relevance before clinical application.", "claims": [{"id": "claim-method", "statement": "Univariate Cox regression analysis was conducted utilizing the R package survival (Version 3.5–7.5) to identify variables significantly associated with the outcome (p-value < 0.05).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41543804", "locator": "sections[5] \"Construction of the prognostic risk model\" paragraph 2", "quote": "Univariate Cox regression analysis was conducted utilizing the R package survival (Version 3.5–7.5) to identify variables significantly associated with the outcome (p-value < 0.05)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "GSE19422 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE19422). GSE60459 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41543804", "locator": "sections[25] \"Data availability\" paragraph 2", "quote": "GSE19422 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE19422). GSE60459 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A four-gene prognostic model based on AMBRA1, EIF2S1, SRC, and PHGDH achieved AUC values exceeding 0.9 for 1-, 2-, and 3-year survival predictions in PPGLs.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41543804", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "A prognostic model based on four genes (AMBRA1, EIF2S1, SRC, PHGDH) demonstrated high predictive accuracy (AUC > 0.9)."}, {"asset": "source:pmid:41543804", "locator": "sections[15] \"Evaluation and validation of the prognostic risk model for PPGLs\" paragraph 2", "quote": "The time-dependent ROC curves (Fig. 4A) showed strong predictive accuracy, with AUC values exceeding 0.9 at 1, 2, and 3 years, respectively."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "A four-gene prognostic model based on AMBRA1, EIF2S1, SRC, and PHGDH achieved AUC values exceeding 0.9 for 1-, 2-, and 3-year survival predictions in PPGLs.", "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:41543804"], "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:GSE19422"], "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:GSE19422"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41543804", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1007/s12672-026-04393-7", "sha256": "sha256:d9032cf911eeff2412f45b7db1250e563fc526f362b61ab83937c2e16d1dab42", "bytes": 45744, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1007/s12672-026-04393-7", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12894528", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE19422", "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=GSE19422", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19422", "version": null, "note": "GSE19422 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE19422). GSE60459 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE19422 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE19422). GSE60459 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM482992", "GSM482993", "GSM482994", "GSM482995", "GSM482996", "GSM482997", "GSM482998", "GSM482999", "GSM483000", "GSM483001", "GSM483002", "GSM483003", "GSM483004", "GSM483005", "GSM483006", "GSM483007", "GSM483008", "GSM483009", "GSM483010", "GSM483011", "GSM483012", "GSM483013", "GSM483014", "GSM483015", "GSM483016", "GSM483017", "GSM483018", "GSM483019", "GSM483020", "GSM483021", "GSM483022", "GSM483023", "GSM483024", "GSM483025", "GSM483026", "GSM483027", "GSM483028", "GSM483029", "GSM483030", "GSM483031", "GSM483032", "GSM483033", "GSM483034", "GSM483035", "GSM483036", "GSM483037", "GSM483038", "GSM483039", "GSM483040", "GSM483041", "GSM483042", "GSM483043", "GSM483044", "GSM483045", "GSM483046", "GSM483047", "GSM483048", "GSM483049", "GSM483050", "GSM483051", "GSM483052", "GSM483053", "GSM483054", "GSM483055", "GSM483056", "GSM483057", "GSM483058", "GSM483059", "GSM483060", "GSM483061", "GSM483062", "GSM483063", "GSM483064", "GSM483065", "GSM483066", "GSM483067", "GSM483068", "GSM483069", "GSM483070", "GSM483071", "GSM483072", "GSM483073", "GSM483074", "GSM483075", "GSM483076", "GSM483077", "GSM483078", "GSM483079", "GSM483080", "GSM483081"], "sample_count": 90, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Gene expression profiling of pheochromocytoma (PCC)/paraganglioma (PGL) tumors", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE60459", "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=GSE60459", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE60459", "version": null, "note": "GSE19422 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE19422). GSE60459 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE19422 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE19422). GSE60459 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1480328", "GSM1480329", "GSM1480330", "GSM1480331", "GSM1480332", "GSM1480333", "GSM1480334", "GSM1480335", "GSM1480336", "GSM1480337", "GSM1480338", "GSM1480339", "GSM1480340", "GSM1480341", "GSM1480342", "GSM1480343", "GSM1480344", "GSM1480345", "GSM1480346", "GSM1480347", "GSM1480348", "GSM1480349", "GSM1480350", "GSM1480351", "GSM1480352", "GSM1480353", "GSM1480354"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "10152;13607", "taxon": "Homo sapiens", "title": "Expression and copy number profiles of pheochromocytoma and paraganglioma", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE19422 not downloaded", "asset:data:geo:GSE19422 licence not read", "asset:data:geo:GSE60459 not downloaded", "asset:data:geo:GSE60459 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Univariate Cox regression analysis was conducted utilizing the R package survival (Version 3.5–7.5) to identify variables significantly associated with the outcome (p-value < 0.05)."}}, {"id": "method-2", "family": "group_comparison", "specific": "mann_whitney", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_mann_whitney"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Mann-Whitney"}}, {"id": "method-3", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "Protein-protein interaction"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE19422", "GSE60459"], "resolved_accessions": ["GSE19422", "GSE60459"], "statements": ["GSE19422 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE19422). GSE60459 dataset: Available from the GEO database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi)."], "basis": "The paper names GSE19422, GSE60459 in GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:41543804", "data:geo:GSE19422"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE19422"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:10:14Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13275, "completion_tokens": 2452, "cached_tokens": 128}}, "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:41543804", "type": "paper", "label": "pmid:41543804"}, {"id": "source:pmid:41543804", "type": "manuscript", "label": "PMID 41543804 full text"}, {"id": "data:geo:GSE19422", "type": "dataset", "label": "GEO GSE19422"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41543804", "type": "paper", "label": "pmid:41543804"}, {"id": "source:pmid:41543804", "type": "manuscript", "label": "PMID 41543804 full text"}, {"id": "data:geo:GSE19422", "type": "dataset", "label": "GEO GSE19422"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41543804", "type": "extraction", "used": ["source:pmid:41543804"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE19422", "type": "accession_resolution", "used": ["data:geo:GSE19422"], "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:41543804", "parent_hash": "sha256:0a66759c160c1b9db6e1563b04e1f9f76d73b3b93055dc935498daf6a6be694e", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE19422 licence not read", "asset:data:geo:GSE19422 not downloaded", "asset:data:geo:GSE60459 licence not read", "asset:data:geo:GSE60459 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Univariate Cox regression analysis was conducted utilizing the R package survival (Version 3.5–7.5) to identify variables significantly associated with the outcome (p-value < 0.05)."], "order_basis": "analysis_only", "id": "assay:1"}]}