Identification of Clinical Relevant Molecular Subtypes of Pheochromocytoma.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34234737", "kind": "science-record", "revision": 6, "content_hash": "sha256:07c7062d62c9581d771035390fd0e7b0c50746e1a60b1d5a0818a6d77a25aee5", "created_at": "2026-11-01T15:41:42Z", "updated_at": "2026-11-01T21:25:42Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Clinical Relevant Molecular Subtypes of Pheochromocytoma.", "doi": "10.3389/fendo.2021.605797", "pmid": "34234737", "authors": ["Umair Ali Khan Saddozai", "Fengling Wang", "Muhammad Usman Akbar", "Lu Zhang", "Yang An", "Wan Zhu", "Longxiang Xie", "Yongqiang Li", "Xinying Ji", "Xiangqian Guo"], "journal": "Frontiers in endocrinology", "year": 2021, "abstract": "Pheochromocytoma (PCC) is a rare neuroendocrine tumor of the adrenal gland with a high rate of mortality if diagnosed at a late stage. Common symptoms of pheochromocytoma include headache, anxiety, palpitation, and diaphoresis. Different treatments are under observation for PCC but there is still no effective treatment option. Recently, the gene expression profiling of various tumors has provided new subtype-specific options for targeted therapies. In this study, using data sets from TCGA and the GSE19422 cohorts, we identified two distinct PCC subtypes with distinct gene expression patterns. Genes enriched in Subtype I PCCs were involved in the dopaminergic synapse, nicotine addiction, and long-term depression pathways, while genes enriched in subtype II PCCs were involved in protein digestion and absorption, vascular smooth muscle contraction, and ECM receptor interaction pathways. We further identified subtype specific genes such as ALK, IGF1R, RET, and RSPO2 for subtype I and EGFR, ESR1, and SMO for subtype II, the overexpression of which led to cell invasion and tumorigenesis. These genes identified in the present research may serve as potential subtype-specific therapeutic targets to understand the underlying mechanisms of tumorigenesis. Our findings may further guide towards the development of targeted therapies and potential molecular biomarkers against PCC.", "claims": [{"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:34234737", "locator": "sections[15] \"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": 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:34234737"], "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:34234737", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fendo.2021.605797", "sha256": "sha256:ee9a0638911e672f0004c9aa80682f8e1ca1265265f88c68f043f6addd538871", "bytes": 41727, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fendo.2021.605797", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8256389", "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": "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": ["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": "asset:table:pmid:34234737:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1a7b513c6889698dfef331cdc1f57aa8ddb9ebce7b21da2c4917e848042cfb5b", "bytes": 560, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T1", "version": null, "note": "Target genes enriched in each molecular subtype.", "structure": {"pmcid": "PMC8256389", "section_index": 13, "section_title": "Clinical Implication of PCC Subtyping", "row_count": 8, "column_count": 3}, "table": {"label": "Table 1", "caption": "Target genes enriched in each molecular subtype.", "rows": [["Gene overexpressed", "Examples of Potential Therapeutic Agents"], ["", "ALK", "Crizotinib, ALK inhibitors"], ["", "IGF1R", "IGF1R Inhibitor"], ["Subtype I", "RET", "Sorafenib, vandetinib, RET Inhibitors"], ["", "RSPO2", "WNT inhibitors"], ["", "EGFR", "Erlotinib, Gefitinib, EGFR Inhibitors"], ["Subtype II", "ESR1", "Hormonal therapy"], ["", "SMO", "Vismodegib, hedgehog inhibitors"]], "row_count": 8, "column_count": 3, "numeric_cells": 0, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T1"}}], "gaps": ["asset:data:geo:GSE19422 not downloaded", "asset:data:geo:GSE19422 licence not read"]}, "analysis": {"state": "partial", "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": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-2", "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-3", "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"}}, {"id": "method-4", "family": null, "specific": null, "label": "SAMseq analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "“SAMseq analysis was performed in the TCGA dataset to analyze differentially expressed genes between two PCC molecular subtypes.”"}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["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": ["GSE19422"], "resolved_accessions": ["GSE19422"], "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 GSE19422 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:34234737", "data:geo:GSE19422", "asset:table:pmid:34234737:1"], "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": "2026-10-31T18:32:10Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 35965, "completion_tokens": 1968, "cached_tokens": 12032}}, "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:34234737", "type": "paper", "label": "pmid:34234737"}, {"id": "source:pmid:34234737", "type": "manuscript", "label": "PMID 34234737 full text"}, {"id": "data:geo:GSE19422", "type": "dataset", "label": "GEO GSE19422"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34234737", "type": "paper", "label": "pmid:34234737"}, {"id": "source:pmid:34234737", "type": "manuscript", "label": "PMID 34234737 full text"}, {"id": "data:geo:GSE19422", "type": "dataset", "label": "GEO GSE19422"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34234737", "type": "extraction", "used": ["source:pmid:34234737"], "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:34234737", "parent_hash": "sha256:bf3e8f3dc6a7df7ab79854db6d6cab3f0ebe7da40d826f4ff1aa63b7b053e03a", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE19422 licence not read", "asset:data:geo:GSE19422 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": 0.8, "evidence": ["Kaplan-Meier"], "order_basis": "analysis_only", "id": "assay:1"}]}