Screening and validation of differentially expressed genes in adipose tissue of patients with obesity and type 2 diabetes mellitus.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37597213", "kind": "science-record", "revision": 5, "content_hash": "sha256:fd041f1a9865928bff811aff239e81586b7cabb35502e3e4402e8a5d55d5e934", "created_at": "2026-11-01T19:02:24Z", "updated_at": "2026-11-01T22:52:34Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Screening and validation of differentially expressed genes in adipose tissue of patients with obesity and type 2 diabetes mellitus.", "doi": "10.17305/bb.2023.9498", "pmid": "37597213", "authors": ["Xuewei Tong", "Chunyan Liu", "Mengjie Liang", "Xueyan Ye", "Zhaohui Deng", "Xin Zhang"], "journal": "Biomolecules & biomedicine", "year": 2024, "abstract": "White adipose tissue (WAT) plays a pivotal role in the onset of type 2 diabetes mellitus (T2DM) and obesity. Despite its significance the underlying pathogenesis and key genes associated with it remain elusive. In our study, we screened the differentially expressed genes (DEGs) in intra-abdominal WAT of T2DM patients with obesity, as well as those with simple obesity, aiming to lay a foundational theory for an in-depth investigation of T2DM pathogenesis and the identification of novel therapeutic targets. Gene expression datasets (GSE16415 and GSE71416) were retrieved from the Gene Expression Omnibus (GEO) database. We employed R for screening DEGs and conducted a functional enrichment analysis using the Metascape database. Combined Lasso regression and Boruta feature selection algorithms were used to identify key DEGs. Subsequently, these were cross-verified using the GSE29231 dataset. Samples and medical records were collected from clinical study participants. The mRNA and protein expressions of the key DEGs were verified using qRT-PCR and western blotting, respectively. We discerned a total of 130 DEGs, with 40 being upregulated and 90 downregulated. Functional and pathway enrichment analyses illuminated that these genes are instrumental in mediating metabolite and energy production, neutrophil-mediated immunity, and other associated biological processes. This includes their involvement in the tricarboxylic acid cycle, glycolysis/gluconeogenesis, peroxisome proliferator-activated receptors, and other signalling pathways. Two genes, CIDEA and FSCN1 emerged as key DEGs. The low expression of CIDEA and high expression of FSCN1 in the T2DM and obesity group were verified in clinical samples (P < 0.05). We established that CIDEA and FSCN1 manifest significant differential expression in T2DM patients who are obese. This suggests their potential as risk assessment markers and therapeutic targets for T2DM.", "claims": [{"id": "claim-method", "statement": "The analysis and screening of DEGs between sample groups were carried out using the limma package.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37597213", "locator": "sections[4] \"Data pre-processing and identification of DEGs\" paragraph 2", "quote": "The analysis and screening of DEGs between sample groups were carried out using the limma package."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data availability: The datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37597213", "locator": "sections[26] \"Footnotes\" paragraph 2", "quote": "Data availability: The datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We established that CIDEA and FSCN1 manifest significant differential expression in T2DM patients who are obese.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37597213", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We established that CIDEA and FSCN1 manifest significant differential expression in T2DM patients who are obese."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "We established that CIDEA and FSCN1 manifest significant differential expression in T2DM patients who are obese.", "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:37597213"], "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:GSE16415"], "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:GSE16415"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37597213", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.17305/bb.2023.9498", "sha256": "sha256:b4f2b925d844ef2074c9c8632c94d0edcb2616d1f40ea56486c9016396e6caf8", "bytes": 31679, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.17305/bb.2023.9498", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10787618", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE16415", "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=GSE16415", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE16415", "version": null, "note": "Data availability: The datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability: The datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM412607", "GSM412608", "GSM412609", "GSM412610", "GSM412611", "GSM412612", "GSM412613", "GSM412614", "GSM412615", "GSM412616"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "2986", "taxon": "Homo sapiens", "title": "Genome wide gene expression profiling of visceral adipose tissue among Asian Indian diabetics", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE29231", "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=GSE29231", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29231", "version": null, "note": "Data availability: The datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability: The datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM722948", "GSM722949", "GSM722950", "GSM722951", "GSM722952", "GSM722953", "GSM722954", "GSM722955", "GSM722956", "GSM722957", "GSM722958", "GSM722959", "GSM722960", "GSM722961", "GSM722962", "GSM722963", "GSM722964", "GSM722965", "GSM722966", "GSM722967", "GSM722968", "GSM722969", "GSM722970", "GSM722971"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "Global Gene Expression Profiles of  Visceral Adipose in Females with Type 2 Diabetes.", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE71416", "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=GSE71416", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE71416", "version": null, "note": "Data availability: The datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability: The datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1833926", "GSM1833927", "GSM1833928", "GSM1833929", "GSM1833930", "GSM1833931", "GSM1833932", "GSM1833933", "GSM1833934", "GSM1833935", "GSM1833936", "GSM1833937", "GSM1833938", "GSM1833939", "GSM1833940", "GSM1833941", "GSM1833942", "GSM1833943", "GSM1833944", "GSM1833945"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene Expression Profiling in Omental Adipose Tissue of Morbidly Obese Diabetic African Americans", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE16415 not downloaded", "asset:data:geo:GSE16415 licence not read", "asset:data:geo:GSE29231 not downloaded", "asset:data:geo:GSE29231 licence not read", "asset:data:geo:GSE71416 not downloaded", "asset:data:geo:GSE71416 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The analysis and screening of DEGs between sample groups were carried out using the limma package."}}, {"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": "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": "χ2"}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE16415", "GSE71416", "GSE29231"], "resolved_accessions": ["GSE16415", "GSE71416", "GSE29231"], "statements": ["Data availability: The datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request."], "basis": "The paper names GSE16415, GSE71416, GSE29231 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:37597213", "data:geo:GSE16415"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE16415"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:51:07Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9917, "completion_tokens": 1318, "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:37597213", "type": "paper", "label": "pmid:37597213"}, {"id": "source:pmid:37597213", "type": "manuscript", "label": "PMID 37597213 full text"}, {"id": "data:geo:GSE16415", "type": "dataset", "label": "GEO GSE16415"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37597213", "type": "paper", "label": "pmid:37597213"}, {"id": "source:pmid:37597213", "type": "manuscript", "label": "PMID 37597213 full text"}, {"id": "data:geo:GSE16415", "type": "dataset", "label": "GEO GSE16415"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37597213", "type": "extraction", "used": ["source:pmid:37597213"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE16415", "type": "accession_resolution", "used": ["data:geo:GSE16415"], "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:37597213", "parent_hash": "sha256:34feff68f6833d4c3049bef905612b39d455bc743d793af547f00f7c2888cb5d", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE16415 licence not read", "asset:data:geo:GSE16415 not downloaded", "asset:data:geo:GSE29231 licence not read", "asset:data:geo:GSE29231 not downloaded", "asset:data:geo:GSE71416 licence not read", "asset:data:geo:GSE71416 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["the key DEGs were verified using qRT-PCR and western blotting, respectively. We discerned a total of 130 D"], "order_basis": "paper_text_order:1145", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The analysis and screening of DEGs between sample groups were carried out using the limma package."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}