TCGA Expression Analyses of 10 Carcinoma Types Reveal Clinically Significant Racial Differences.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37345032", "kind": "science-record", "revision": 2, "content_hash": "sha256:7946a8cb65afbb155e473b3fefac455f3cc616b1ddc20e93eb56c303f5aabfe2", "created_at": "2026-11-01T19:02:05Z", "updated_at": "2026-11-01T21:31:01Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "TCGA Expression Analyses of 10 Carcinoma Types Reveal Clinically Significant Racial Differences.", "doi": "10.3390/cancers15102695", "pmid": "37345032", "authors": ["Brian Lei", "Xinyin Jiang", "Anjana Saxena"], "journal": "Cancers", "year": 2023, "abstract": "Epidemiological studies reveal disparities in cancer incidence and outcome rates between racial groups in the United States. In our study, we investigated molecular differences between racial groups in 10 carcinoma types. We used publicly available data from The Cancer Genome Atlas to identify patterns of differential gene expression in tumor samples obtained from 4112 White, Black/African American, and Asian patients. We identified race-dependent expression of numerous genes whose mRNA transcript levels were significantly correlated with patients' survival. Only a small subset of these genes was differentially expressed in multiple carcinomas, including genes involved in cell cycle progression such as CCNB1, CCNE1, CCNE2, and FOXM1. In contrast, most other genes, such as transcriptional factor ETS1 and apoptotic gene BAK1, were differentially expressed and clinically significant only in specific cancer types. Our analyses also revealed race-dependent, cancer-specific regulation of biological pathways. Importantly, homology-directed repair and ERBB4-mediated nuclear signaling were both upregulated in Black samples compared to White samples in four carcinoma types. This large-scale pan-cancer study refines our understanding of the cancer health disparity and can help inform the use of novel biomarkers in clinical settings and the future development of precision therapies.", "claims": [{"id": "claim-method", "statement": "We used log rank tests performed by cBioPortal to assess statistical significance; a p-value ≤ 0.05 was considered statistically significant.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37345032", "locator": "sections[4] \"2.2. Race-Based Kaplan–Meier Survival Analysis\" paragraph 2", "quote": "We used log rank tests performed by cBioPortal to assess statistical significance; a p-value ≤ 0.05 was considered statistically significant."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The results shown in this study are in whole or part based upon data generated by the TCGA Research Network: https://www.cancer.gov/tcga (accessed on 18 July 2021). Data used in this article is publicly available and has been referenced. The computer code can be found at https://github.com/brian-lei/cancer-racial-disparity (accessed on 18 January 2021).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37345032", "locator": "sections[59] \"notes\" paragraph 1", "quote": "The results shown in this study are in whole or part based upon data generated by the TCGA Research Network: https://www.cancer.gov/tcga (accessed on 18 July 2021). Data used in this article is publicly available and has been referenced. The computer code can be found at https://github.com/brian-lei/cancer-racial-disparity (accessed on 18 January 2021)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Race-dependent expression of numerous genes whose mRNA transcript levels were significantly correlated with patients’ survival.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37345032", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We identified race-dependent expression of numerous genes whose mRNA transcript levels were significantly correlated with patients’ survival."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Race-dependent expression of numerous genes whose mRNA transcript levels were significantly correlated with patients’ survival.", "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:37345032"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37345032", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/cancers15102695", "sha256": "sha256:a9a3f1f0fe57b4656e8c6befa7e6f219ccda4c6aa8eb09245ff41d8bac28e589", "bytes": 49085, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/cancers15102695", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10216530", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "We used log rank tests performed by cBioPortal to assess statistical significance; a p-value ≤ 0.05 was considered statistically significant."}}, {"id": "method-2", "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": "KM"}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["logrank_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: log_rank_test."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The results shown in this study are in whole or part based upon data generated by the TCGA Research Network: https://www.cancer.gov/tcga (accessed on 18 July 2021). Data used in this article is publicly available and has been referenced. The computer code can be found at https://github.com/brian-lei/cancer-racial-disparity (accessed on 18 January 2021)."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["logrank_test"], "assets": ["source:pmid:37345032"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:44:25Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14035, "completion_tokens": 1588, "cached_tokens": 264}}, "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:37345032", "type": "paper", "label": "pmid:37345032"}, {"id": "source:pmid:37345032", "type": "manuscript", "label": "PMID 37345032 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37345032", "type": "paper", "label": "pmid:37345032"}, {"id": "source:pmid:37345032", "type": "manuscript", "label": "PMID 37345032 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37345032", "type": "extraction", "used": ["source:pmid:37345032"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:37345032", "parent_hash": "sha256:957ca0dd8f752760c6152e1c3b000219ca0fc85c65d59d2a67b7f2b979b32e3c", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["logrank_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["We used log rank tests performed by cBioPortal to assess statistical significance; a p-value ≤ 0.05 was considered statistically significant."], "order_basis": "analysis_only", "id": "assay:1"}]}