Identification of ferroptosis-related genes in type 2 diabetes mellitus based on machine learning.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37904700", "kind": "science-record", "revision": 5, "content_hash": "sha256:1b64f45308dd327706d440383ad21a339a3c3aca59622d9865780e015a7d39bb", "created_at": "2026-11-01T19:02:47Z", "updated_at": "2026-11-01T22:52:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of ferroptosis-related genes in type 2 diabetes mellitus based on machine learning.", "doi": "10.1002/iid3.1036", "pmid": "37904700", "authors": ["Sen Wang", "Yongpan Lu", "Tingting Chi", "Yixin Zhang", "Yuli Zhao", "Huimin Guo", "Li Feng"], "journal": "Immunity, inflammation and disease", "year": 2023, "abstract": "BACKGROUND: Type 2 diabetes mellitus (T2DM), which has a high incidence and several harmful consequences, poses a severe danger to human health. Research on the function of ferroptosis in T2DM is increasing. This study uses bioinformatics techniques identify new diagnostic T2DM biomarkers associated with ferroptosis.\nMETHODS: To identify ferroptosis-related genes (FRGs) that are differentially expressed between T2DM patients and healthy individuals, we first obtained T2DM sequencing data and FRGs from the Gene Expression Omnibus (GEO) database and FerrDb database. Then, drug-gene interaction networks and competitive endogenous RNA (ceRNA) networks linked to the marker genes were built after marker genes were filtered by two machine learning algorithms (LASSO and SVM-RFE algorithms). Finally, to confirm the expression of marker genes, the GSE76895 dataset was utilized. The protein and RNA expression of some marker genes in T2DM and nondiabetic tissues was also examined by Western blotting, immunohistochemistry (IHC), immunofluorescence (IF) and quantitative real-time PCR (qRT-PCR).\nRESULTS: We obtained 58 differentially expressed genes (DEGs) associated with ferroptosis. GO and KEGG enrichment analyses showed that these DEGs were significantly enriched in hypoxia and ferroptosis. Subsequently, eight marker genes (SCD, CD44, HIF1A, BCAT2, MTF1, HILPDA, NR1D2, and MYCN) were screened by LASSO and SVM-RFE machine learning algorithms, and a model was constructed based on these eight genes. This model also has high diagnostic power. In addition, based on these eight genes, we obtained 48 drugs and constructed a complex ceRNA network map. Finally, Western blotting, IHC, IF, and qRT-PCR results of clinical samples further confirmed the results of public databases.\nCONCLUSIONS: The diagnosis and aetiology of T2DM can be greatly aided by eight FRGs, providing novel therapeutic avenues.", "claims": [{"id": "claim-method", "statement": "We examined DEGs between T2DM samples and normal samples using the limma package in R software.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37904700", "locator": "sections[4] \"Screening ferroptosis‐related differentially expressed genes (DEGs)\" paragraph 2", "quote": "We examined DEGs between T2DM samples and normal samples using the limma package in R software."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data that support the findings of this study are available from the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37904700", "locator": "sections[40] \"DATA AVAILABILITY STATEMENT\" paragraph 2", "quote": "The data that support the findings of this study are available from the corresponding author."}], "state": "complete"}, {"id": "claim-target-result", "statement": "According to our ROC curve results, the eight marker gene‐based logistic regression model offered more sensitivity and precision than the independent marker genes for discriminating T2DM samples from normal samples, with an AUC of 0.832 (95% confidence interval [CI]: 0.760–0.896) (Figure 3G).", "kind": "quantitative", "target": {"value": 95.0, "unit": "per cent", "tolerance": null, "source": "According to our ROC curve results, the eight marker gene‐based logistic regression model offered more sensitivity and precision than the independent marker genes for discriminating T2DM samples from normal samples, with an AUC of 0.832 (95% confidence interval [CI]: 0.760–0.896) (Figure 3G)."}, "evidence": [{"asset": "source:pmid:37904700", "locator": "sections[21] \"Eight ferroptosis‐related DEGs were identified as diagnostic genes for T2DM\" paragraph 4", "quote": "According to our ROC curve results, the eight marker gene‐based logistic regression model offered more sensitivity and precision than the independent marker genes for discriminating T2DM samples from normal samples, with an AUC of 0.832 (95% confidence interval [CI]: 0.760–0.896) (Figure 3G)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "According to our ROC curve results, the eight marker gene‐based logistic regression model offered more sensitivity and precision than the independent marker genes for discriminating T2DM samples from normal samples, with an AUC of 0.832 (95% confidence interval [CI]: 0.760–0.896) (Figure 3G).", "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:37904700"], "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:GSE76895"], "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:GSE76895"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37904700", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1002/iid3.1036", "sha256": "sha256:f75c96873636e84b6f6df8373bd2b2dec1d1c8c65b7e6a11c41b180f47a46b5a", "bytes": 66447, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1002/iid3.1036", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10566453", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE76895", "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=GSE76895", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE76895", "version": null, "note": "The data that support the findings of this study are available from the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data that support the findings of this study are available from the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2040152", "GSM2040153", "GSM2040154", "GSM2040155", "GSM2040156", "GSM2040157", "GSM2040158", "GSM2040159", "GSM2040160", "GSM2040161", "GSM2040162", "GSM2040163", "GSM2040164", "GSM2040165", "GSM2040166", "GSM2040167", "GSM2040168", "GSM2040169", "GSM2040170", "GSM2040171", "GSM2040172", "GSM2040173", "GSM2040174", "GSM2040175", "GSM2040176", "GSM2040177", "GSM2040178", "GSM2040179", "GSM2040180", "GSM2040181", "GSM2040182", "GSM2040183", "GSM2040184", "GSM2040185", "GSM2040186", "GSM2040187", "GSM2040188", "GSM2040189", "GSM2040190", "GSM2040191", "GSM2040192", "GSM2040193", "GSM2040194", "GSM2040195", "GSM2040196", "GSM2040197", "GSM2040198", "GSM2040199", "GSM2040200", "GSM2040201", "GSM2040202", "GSM2040203", "GSM2040204", "GSM2040205", "GSM2040206", "GSM2040207", "GSM2040208", "GSM2040209", "GSM2040210", "GSM2040211", "GSM2040212", "GSM2040213", "GSM2040214", "GSM2040215", "GSM2040216", "GSM2040217", "GSM2040218", "GSM2040219", "GSM2040220", "GSM2040221", "GSM2040222", "GSM2040223", "GSM2040224", "GSM2040225", "GSM2040226", "GSM2040227", "GSM2040228", "GSM2040229", "GSM2040230", "GSM2040231", "GSM2040232", "GSM2040233", "GSM2040234", "GSM2040235", "GSM2040236", "GSM2040237", "GSM2040238", "GSM2040239", "GSM2040240", "GSM2040241", "GSM2040242", "GSM2040243", "GSM2040244", "GSM2040245", "GSM2040246", "GSM2040247", "GSM2040248", "GSM2040249", "GSM2040250", "GSM2040251", "GSM2040252", "GSM2040253", "GSM2040254"], "sample_count": 103, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Affymetrix profiling of IMIDIA biobank samples from organ donors and partially pancreatectomized patients [partially pancreatectomized patient cohort]", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE78721", "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=GSE78721", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE78721", "version": null, "note": "The data that support the findings of this study are available from the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data that support the findings of this study are available from the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2349019", "GSM2349020", "GSM2349021", "GSM2349022", "GSM2349023", "GSM2349024", "GSM2349025", "GSM2349026", "GSM2349027", "GSM2349028", "GSM2349029", "GSM2349030", "GSM2349031", "GSM2349032", "GSM2349033", "GSM2349034", "GSM2349035", "GSM2349036", "GSM2349037", "GSM2349038", "GSM2349039", "GSM2349040", "GSM2349041", "GSM2349042", "GSM2349043", "GSM2349044", "GSM2349045", "GSM2349046", "GSM2349047", "GSM2349048", "GSM2349049", "GSM2349050", "GSM2349051", "GSM2349052", "GSM2349053", "GSM2349054", "GSM2349055", "GSM2349056", "GSM2349057", "GSM2349058", "GSM2349059", "GSM2349060", "GSM2349061", "GSM2349062", "GSM2349063", "GSM2349064", "GSM2349065", "GSM2349066", "GSM2349067", "GSM2349068", "GSM2349069", "GSM2349070", "GSM2349071", "GSM2349072", "GSM2349073", "GSM2349074", "GSM2349075", "GSM2349076", "GSM2349077", "GSM2349078", "GSM2349079", "GSM2349080", "GSM2349081", "GSM2349082", "GSM2349083", "GSM2349084", "GSM2349085", "GSM2349086", "GSM2349087", "GSM2349088", "GSM2349089", "GSM2349090", "GSM2349091", "GSM2349092", "GSM2349093", "GSM2349094", "GSM2349095", "GSM2349096", "GSM2349097", "GSM2349098", "GSM2349099", "GSM2349100", "GSM2349101", "GSM2349102", "GSM2349103", "GSM2349104", "GSM2349105", "GSM2349106", "GSM2349107", "GSM2349108", "GSM2349109", "GSM2349110", "GSM2349111", "GSM2349112", "GSM2349113", "GSM2349114", "GSM2349115", "GSM2349116", "GSM2349117", "GSM2349118", "GSM2349119", "GSM2349120", "GSM2349121", "GSM2349122", "GSM2349123", "GSM2349124", "GSM2349125", "GSM2349126", "GSM2349127", "GSM2349128", "GSM2349129", "GSM2349130", "GSM2349131", "GSM2349132", "GSM2349133", "GSM2349134", "GSM2349135", "GSM2349136", "GSM2349137", "GSM2349138", "GSM3184676", "GSM3184677", "GSM3184678", "GSM3184679", "GSM3184680", "GSM3184681", "GSM3184682", "GSM3184683", "GSM3184684", "GSM3184685"], "sample_count": 130, "group_sizes": null, "group_sizes_basis": null, "platform": "15207", "taxon": "Homo sapiens", "title": "Genome–wide gene expression profile of adipocytes and infiltration macrophages obtained from abdominal (visceral and subcutaneous) and peripheral (thigh) adipose depots from Normal Glucose Tolerant and Type 2 Diabetics Asian Indians", "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:GSE76895 not downloaded", "asset:data:geo:GSE76895 licence not read", "asset:data:geo:GSE78721 not downloaded", "asset:data:geo:GSE78721 licence not read"]}, "analysis": {"state": "partial", "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": "We examined DEGs between T2DM samples and normal samples using the limma package in R software."}}, {"id": "method-2", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Student's t test"}}, {"id": "method-3", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "SVM"}}, {"id": "method-4", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "logistic regression"}}, {"id": "method-5", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson correlation"}}, {"id": "method-6", "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": 0.8, "band": "high", "quote": "pathway enrichment"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "cross_validate", "expected_value": 95.0, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}, {"id": "target-published-estimate-auc", "claim_id": "claim-target-result", "operation": "cross_validate", "expected_value": 0.832, "unit": "auc", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["GSE78721", "GSE76895"], "resolved_accessions": ["GSE78721", "GSE76895"], "statements": ["The data that support the findings of this study are available from the corresponding author."], "basis": "The paper names GSE78721, GSE76895 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:37904700", "data:geo:GSE76895"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE76895"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:57:59Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 19222, "completion_tokens": 1811, "cached_tokens": 128}}, "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:37904700", "type": "paper", "label": "pmid:37904700"}, {"id": "source:pmid:37904700", "type": "manuscript", "label": "PMID 37904700 full text"}, {"id": "data:geo:GSE76895", "type": "dataset", "label": "GEO GSE76895"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37904700", "type": "paper", "label": "pmid:37904700"}, {"id": "source:pmid:37904700", "type": "manuscript", "label": "PMID 37904700 full text"}, {"id": "data:geo:GSE76895", "type": "dataset", "label": "GEO GSE76895"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37904700", "type": "extraction", "used": ["source:pmid:37904700"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE76895", "type": "accession_resolution", "used": ["data:geo:GSE76895"], "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:37904700", "parent_hash": "sha256:4fe7d8562354c62c41e7b3ae8685eecf3bb119a293fafb68c66c0b877ee3404f", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE76895 licence not read", "asset:data:geo:GSE76895 not downloaded", "asset:data:geo:GSE78721 licence not read", "asset:data:geo:GSE78721 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "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": 0.99, "evidence": ["and nondiabetic tissues was also examined by Western blotting, immunohistochemistry (IHC), immunofluoresce", "ructed a complex ceRNA network map. Finally, Western blotting, IHC, IF, and qRT-PCR results of clinical sa"], "order_basis": "paper_text_order:1040", "id": "assay:1"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ssues was also examined by Western blotting, immunohistochemistry (IHC), immunofluorescence (IF) and quantitat", "estern blotting, immunohistochemistry (IHC), immunofluorescence (IF) and quantitative real-time PCR (qRT-PCR", "d by Western blotting, immunohistochemistry (IHC), immunofluorescence (IF) and quantitative r", "eRNA network map. Finally, Western blotting, IHC, IF, and qRT-PCR results of clinical samples"], "order_basis": "paper_text_order:1058", "id": "assay:2"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["C), immunofluorescence (IF) and quantitative real-time PCR (qRT-PCR). RESULTS: We obtained 58 different"], "order_basis": "paper_text_order:1127", "id": "assay:3"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["were incubated with biotin‐labeled goat anti‐mouse immunoglobulin G polymer for 15 min at room"], "order_basis": "paper_text_order:3558", "id": "assay:4"}, {"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": ["We examined DEGs between T2DM samples and normal samples using the limma package in R software."], "order_basis": "consumes_earlier_output", "id": "assay:5"}]}