Oncogenic Network and Hub Genes for Natural Killer/T-Cell Lymphoma Utilizing WGCNA.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32195177", "kind": "science-record", "revision": 6, "content_hash": "sha256:e4c3dc3d7da3b52dc7e3966f7f0329fa78174784e2a1bba6336b947858469978", "created_at": "2026-11-01T15:40:58Z", "updated_at": "2026-11-01T21:23:01Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Oncogenic Network and Hub Genes for Natural Killer/T-Cell Lymphoma Utilizing WGCNA.", "doi": "10.3389/fonc.2020.00223", "pmid": "32195177", "authors": ["Huijiao Liu", "Mei Liu", "Hua You", "Xiru Li", "Xiangdong Li"], "journal": "Frontiers in oncology", "year": 2020, "abstract": "Natural killer (NK)/T-cell lymphoma (NKTCL) is a subtype of non-Hodgkin lymphoma with aggressive progression and poor prognosis. The molecular mechanisms of NKTCL have not been well-studied. Herein, we revealed the lymphoma-associated dysregulated genes and signaling pathways or biological processes in NKTCL. We characterized that the extracellular matrix (ECM) receptor interaction pathway and T-cell receptor signaling pathway were the main dysregulated pathways in NKTCL by Gene Ontology (GO) analysis and pathway enrichment analysis. By using weighted gene co-expression network analysis (WGCNA), the gene co-expression network of NKTCL (SRP049695) was constructed, and hub genes (LMO3, GRB14) were identified. In addition, another Gene Expression Omnibus (GEO) dataset (GSE69406) was used to validate these hub genes. Furthermore, these hub genes were identified and validated by survival analysis (GSE90597). These results provided novel insights into the pathogenesis of NKTCL. Of particular interest, LMO3 and GRB14 might be potential oncoproteins and biomarkers for the diagnosis and treatment of NKTCL.", "claims": [{"id": "claim-method", "statement": "GSE90597 dataset was used to plot the Kaplan–Meier survival curve in ggplot2 of R software.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32195177", "locator": "sections[9] \"Hub Gene Selection and Validation\" paragraph 2", "quote": "GSE90597 dataset was used to plot the Kaplan–Meier survival curve in ggplot2 of R software."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/sra/?term=SRP049695; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE69406; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE90597.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32195177", "locator": "sections[19] \"Data Availability Statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/sra/?term=SRP049695; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE69406; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE90597."}], "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:32195177"], "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:GSE69406"], "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:GSE69406"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32195177", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fonc.2020.00223", "sha256": "sha256:56eb551e69794d7b7aeba7db12a4eaaca8891eaccf9423966f8944535ff3822d", "bytes": 22856, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fonc.2020.00223", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7066115", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE69406", "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=GSE69406", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE69406", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/sra/?term=SRP049695; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE69406; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE90597.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/sra/?term=SRP049695; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE69406; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE90597.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1700790", "GSM1700791", "GSM1700792", "GSM1700793", "GSM1700794", "GSM1700795", "GSM1700796", "GSM1700797", "GSM1700798", "GSM1700799", "GSM1700800", "GSM1700801", "GSM1700802"], "sample_count": 13, "group_sizes": null, "group_sizes_basis": null, "platform": "10332", "taxon": "Homo sapiens", "title": "Exome sequencing identifies somatic mutations of DDX3X in natural killer/T-cell lymphoma", "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:GSE90597", "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=GSE90597", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE90597", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/sra/?term=SRP049695; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE69406; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE90597.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/sra/?term=SRP049695; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE69406; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE90597.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2407413", "GSM2407414", "GSM2407415", "GSM2407416", "GSM2407417", "GSM2407418", "GSM2407419", "GSM2407420", "GSM2407421", "GSM2407422", "GSM2407423", "GSM2407424", "GSM2407425", "GSM2407426", "GSM2407427", "GSM2407428", "GSM2407429", "GSM2407430", "GSM2407431", "GSM2407432", "GSM2407433", "GSM2407434", "GSM2407435", "GSM2407436", "GSM2407437", "GSM2407438", "GSM2407439", "GSM2407440", "GSM2407441", "GSM2407442", "GSM2407443", "GSM2407444", "GSM2407445", "GSM2407446", "GSM2407447", "GSM2407448", "GSM2407449", "GSM2407450", "GSM2407451", "GSM2407452", "GSM2407453", "GSM2407454", "GSM2407455", "GSM2407456", "GSM2407457", "GSM2407458", "GSM2407459", "GSM2407460", "GSM2407461", "GSM2407462", "GSM2407463", "GSM2407464", "GSM2407465", "GSM2407466", "GSM2407467", "GSM2407468", "GSM2407469", "GSM2407470", "GSM2407471", "GSM2407472", "GSM2407473", "GSM2407474", "GSM2407475", "GSM2407476", "GSM2407477", "GSM2407478"], "sample_count": 66, "group_sizes": null, "group_sizes_basis": null, "platform": "10739", "taxon": "Homo sapiens", "title": "Molecular heterogeneity of NK/T-cell lymphoma (expression)", "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:SRP049695", "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=SRP049695", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRP049695", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/sra/?term=SRP049695; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE69406; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE90597.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/sra/?term=SRP049695; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE69406; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE90597.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:35:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE69406 not downloaded", "asset:data:geo:GSE69406 licence not read", "asset:data:geo:GSE90597 not downloaded", "asset:data:geo:GSE90597 licence not read", "asset:data:geo:SRP049695 not downloaded", "asset:data:geo:SRP049695 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "hierarchical clustering"}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "Kaplan–Meier survival analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "GSE90597 dataset was used to plot the Kaplan–Meier survival curve in ggplot2 of R software."}}], "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": ["hierarchical_cluster"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: hierarchical."}, "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": ["SRP049695", "GSE69406", "GSE90597"], "resolved_accessions": ["GSE69406", "GSE90597"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/sra/?term=SRP049695; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE69406; https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE90597."], "basis": "The paper names GSE69406, GSE90597 in National Center for Biotechnology Information (NCBI) Sequence Read Archive (SRA) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["hierarchical_cluster"], "assets": ["source:pmid:32195177", "data:geo:GSE69406"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE69406"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:18:57Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 18604, "completion_tokens": 1424, "cached_tokens": 6400}}, "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:32195177", "type": "paper", "label": "pmid:32195177"}, {"id": "source:pmid:32195177", "type": "manuscript", "label": "PMID 32195177 full text"}, {"id": "data:geo:GSE69406", "type": "dataset", "label": "GEO GSE69406"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32195177", "type": "paper", "label": "pmid:32195177"}, {"id": "source:pmid:32195177", "type": "manuscript", "label": "PMID 32195177 full text"}, {"id": "data:geo:GSE69406", "type": "dataset", "label": "GEO GSE69406"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32195177", "type": "extraction", "used": ["source:pmid:32195177"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE69406", "type": "accession_resolution", "used": ["data:geo:GSE69406"], "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:32195177", "parent_hash": "sha256:9fa6252b02d8a70321cac625b8e447a1e31c5102ced0152f779333ea638fd7fa", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE69406 licence not read", "asset:data:geo:GSE69406 not downloaded", "asset:data:geo:GSE90597 licence not read", "asset:data:geo:GSE90597 not downloaded", "asset:data:geo:SRP049695 licence not read", "asset:data:geo:SRP049695 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "clustering", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["hierarchical_cluster"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["hierarchical clustering"], "order_basis": "analysis_only", "id": "assay:1"}]}