A pan-cancer transcriptomic study showing tumor specific alterations in central metabolism.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34211032", "kind": "science-record", "revision": 2, "content_hash": "sha256:0483a77c03e84cd1b2762e28bd66d66ec37124eb8c8f5107cb65d53bcfd65ace", "created_at": "2026-11-01T15:41:41Z", "updated_at": "2026-11-01T18:55:58Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A pan-cancer transcriptomic study showing tumor specific alterations in central metabolism.", "doi": "10.1038/s41598-021-93003-3", "pmid": "34211032", "authors": ["Ilir Sheraj", "N Tulin Guray", "Sreeparna Banerjee"], "journal": "Scientific reports", "year": 2021, "abstract": "Recently, there has been a resurgence of interest in metabolic rewiring of tumors to identify clinically relevant genes. However, most of these studies have had either focused on individual tumors, or are too general, providing a broad outlook on overall changes. In this study, we have first curated an extensive list of genes encoding metabolic enzymes and metabolite transporters relevant to carbohydrate, fatty acid and amino acid oxidation and biosynthesis. Next, we have used publicly available transcriptomic data for 20 different tumor types from The Cancer Genome Atlas Network (TCGA) and focused on differential expression of these genes between tumor and adjacent normal tissue. Our study revealed major transcriptional alterations in genes that are involved in central metabolism. Most tumors exhibit upregulation in carbohydrate and amino acid transporters, increased glycolysis and pentose phosphate pathway, and decreased fatty acid and amino acid oxidation. On the other hand, the expression of genes of the tricarboxylic acid cycle, anaplerotic reactions and electron transport chain differed between tumors. Although most transcriptomic alterations were conserved across many tumor types suggesting the initiation of common regulatory programs, expression changes unique to specific tumors were also identified, which can provide gene expression fingerprints as potential biomarkers or drug targets. Our study also emphasizes the value of transcriptomic data in the deeper understanding of metabolic changes in diseases.", "claims": [{"id": "claim-data-access", "statement": "Pre-aligned, raw RNA Sequencing read counts in HTSeq format as well as patient clinical data were downloaded from TCGA database using the TCGABiolinks package according to the package’s instructions for transcriptomic data129,130.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34211032", "locator": "sections[19] \"Data acquisition\" paragraph 2", "quote": "Pre-aligned, raw RNA Sequencing read counts in HTSeq format as well as patient clinical data were downloaded from TCGA database using the TCGABiolinks package according to the package’s instructions for transcriptomic data129,130."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:34211032"], "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:34211032", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-021-93003-3", "sha256": "sha256:2e923b1624a5cb064ef463ed9d63b9c740c153ac9af43bf6e5e71fb5cd49afff", "bytes": 83882, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-021-93003-3", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8249409", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["Pre-aligned, raw RNA Sequencing read counts in HTSeq format as well as patient clinical data were downloaded from TCGA database using the TCGABiolinks package according to the package’s instructions for transcriptomic data129,130."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:34211032"], "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": "2026-10-31T19:39:36Z", "independence": "single_reader"}, "evidence_check": {"method": "absent", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 56484, "completion_tokens": 1197, "cached_tokens": 784}}, "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:34211032", "type": "paper", "label": "pmid:34211032"}, {"id": "source:pmid:34211032", "type": "manuscript", "label": "PMID 34211032 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34211032", "type": "paper", "label": "pmid:34211032"}, {"id": "source:pmid:34211032", "type": "manuscript", "label": "PMID 34211032 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34211032", "type": "extraction", "used": ["source:pmid:34211032"], "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:34211032", "parent_hash": "sha256:1d8f6800998b16a5a81efced982ca645085d8fca5e33645bb9175b7d9c613b87", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}