Machine Learning and Experimental Validation Identified Ferroptosis Signature and Innovative Biomarkers (ESR1 and GSTZ1) in Liver Fibrosis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39649424", "kind": "science-record", "revision": 4, "content_hash": "sha256:486883e8433a32d1bbb821459369c56a2b2a97bafc329086f2aa38c57fccc266", "created_at": "2026-11-01T20:29:56Z", "updated_at": "2026-11-01T22:55:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Machine Learning and Experimental Validation Identified Ferroptosis Signature and Innovative Biomarkers (ESR1 and GSTZ1) in Liver Fibrosis.", "doi": "10.2147/JIR.S490258", "pmid": "39649424", "authors": ["Wen Luo", "Hongwen Wu", "Zhijie Yang", "Tian Lan", "Liya Wu", "Yushen Huang"], "journal": "Journal of inflammation research", "year": 2024, "abstract": "Background: Targeting ferroptosis is an effective approach to mitigate hepatic fibrosis, yet no reports exist on the ferroptosis signature in liver fibrosis. This study aimed to explore ferroptosis characteristics in this disease.\nMethods: RNAseq data from GSE6764, GSE188604 and Cancer Genome Atlas Liver Hepatocellular Carcinoma (TCGA-LIHC) were downloaded. Multiple machine learning methods, including Weighted Gene Co-expression Network Analysis (WGCNA), Random Forest (RF) and Support Vector Machine (SVM), were used to identify core genes in liver fibrosis and ferroptosis. WGCNA can pinpoint modules linked to clinical traits, aiding in discovering diagnostic and progression molecules in complex diseases. RF and SVM are often utilized for WGCNA validation to boost result accuracy. Carbon tetrachloride (CCl4) was used to establish a mouse liver fibrosis model to validate core gene expression, which was also assessed in test and validation GEO datasets. Finally, the diagnostic role of the core genes in liver fibrosis and hepatocellular carcinoma (HCC) was also investigated using ROC analysis.\nResults: Multiple machine learning methods screened nine core genes, including IL1B, GSTZ1, LIFR, SLC25A37, PTGS2, MT1G, HSPB1, ESR1, and PHGDH. In vivo experimental validation, RT-PCR showed ESR1 and GSTZ1 were significantly under-expressed in the liver fibrosis group compared to the normal group. Simultaneously, in GSE6764 and GSE188604, ESR1 and GSTZ1 were also identified as protective genes for liver fibrosis. More in-depth research found that ESR1 and GSTZ1 exhibited a good diagnostic performance both in liver fibrosis and HCC, suggesting that a persistent decrease in ESR1 and GSTZ1 in patients might signal the progression from hepatic fibrosis to HCC.\nConclusion: The present study is the first to report the ferroptosis signature in liver fibrosis and identifies two novel biomarkers, ESR1 and GSTZ1, providing new insights for the diagnosis and treatment of liver fibrosis in the future.", "claims": [{"id": "claim-method", "statement": "Multiple machine learning methods, including Weighted Gene Co-expression Network Analysis (WGCNA), Random Forest (RF) and Support Vector Machine (SVM), were used to identify core genes in liver fibrosis and ferroptosis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39649424", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Multiple machine learning methods, including Weighted Gene Co-expression Network Analysis (WGCNA), Random Forest (RF) and Support Vector Machine (SVM), were used to identify core genes in liver fibrosis and ferroptosis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39649424", "locator": "sections[27] \"Data Sharing Statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Multiple machine learning methods screened nine core genes, including IL1B, GSTZ1, LIFR, SLC25A37, PTGS2, MT1G, HSPB1, ESR1, and PHGDH.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39649424", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Multiple machine learning methods screened nine core genes, including IL1B, GSTZ1, LIFR, SLC25A37, PTGS2, MT1G, HSPB1, ESR1, and PHGDH."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Multiple machine learning methods screened nine core genes, including IL1B, GSTZ1, LIFR, SLC25A37, PTGS2, MT1G, HSPB1, ESR1, and PHGDH.", "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:39649424"], "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:GSE188604"], "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:GSE188604"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39649424", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/JIR.S490258", "sha256": "sha256:9761dd4f7c80c3bd1e524e69c3fa5d195efbda8cad64a515f4e5ae584e3d57b4", "bytes": 42523, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/JIR.S490258", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11625426", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE188604", "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=GSE188604", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE188604", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5686696", "GSM5686697", "GSM5686698", "GSM5686699", "GSM5686700", "GSM5686701", "GSM5686702", "GSM5686703", "GSM5686704"], "sample_count": 9, "group_sizes": null, "group_sizes_basis": null, "platform": "14844", "taxon": "Rattus norvegicus", "title": "Tormentic Acid Ameliorates Hepatic Fibrosis in vivo by Inhibiting Glycerophospholipids Metabolism and PI3K/Akt/mTOR and NF-κB Pathways: Based on Transcriptomics and Metabolomics", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE6467", "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=GSE6467", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6467", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM148657", "GSM148658", "GSM148659", "GSM148660", "GSM148661", "GSM148662", "GSM148663", "GSM148664", "GSM148665", "GSM148666", "GSM148667", "GSM148668", "GSM148669", "GSM148670", "GSM148671", "GSM148672", "GSM148673", "GSM148674", "GSM148675", "GSM148676", "GSM148677", "GSM148678", "GSM148679", "GSM148680", "GSM148681", "GSM148682", "GSM148683", "GSM148684", "GSM148685", "GSM148686"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "339", "taxon": "Mus musculus", "title": "Twelve weeks expression data of the antipsychotics Clozapine and Haloperidol in the mouse brain (Affymetrix, GCRMA).", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE6764", "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=GSE6764", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6764", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM155919", "GSM155920", "GSM155921", "GSM155922", "GSM155923", "GSM155924", "GSM155925", "GSM155926", "GSM155927", "GSM155928", "GSM155929", "GSM155930", "GSM155931", "GSM155932", "GSM155933", "GSM155934", "GSM155935", "GSM155936", "GSM155937", "GSM155938", "GSM155939", "GSM155940", "GSM155941", "GSM155942", "GSM155943", "GSM155944", "GSM155945", "GSM155946", "GSM155947", "GSM155948", "GSM155949", "GSM155950", "GSM155951", "GSM155952", "GSM155953", "GSM155954", "GSM155955", "GSM155956", "GSM155957", "GSM155958", "GSM155959", "GSM155960", "GSM155961", "GSM155962", "GSM155963", "GSM155964", "GSM155965", "GSM155966", "GSM155967", "GSM155968", "GSM155969", "GSM155970", "GSM155971", "GSM155972", "GSM155973", "GSM155974", "GSM155975", "GSM155976", "GSM155977", "GSM155978", "GSM155979", "GSM155980", "GSM155981", "GSM155982", "GSM155983", "GSM155984", "GSM155985", "GSM155986", "GSM155987", "GSM155988", "GSM155989", "GSM155990", "GSM155991", "GSM155992", "GSM155993"], "sample_count": 75, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genome-wide molecular profiles of HCV-induced dysplasia and hepatocellular carcinoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE188604 not downloaded", "asset:data:geo:GSE188604 licence not read", "asset:data:geo:GSE6467 not downloaded", "asset:data:geo:GSE6467 licence not read", "asset:data:geo:GSE6764 not downloaded", "asset:data:geo:GSE6764 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": "Multiple machine learning methods, including Weighted Gene Co-expression Network Analysis (WGCNA), Random Forest (RF) and Support Vector Machine (SVM), were used to identify core genes in liver fibrosis and ferroptosis."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"id": "method-3", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Random Forest"}}, {"id": "method-4", "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": "Support Vector Machine"}}, {"id": "method-5", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.7, "band": "medium", "quote": "ROC analysis"}}], "targets": [], "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": ["GSE6764", "GSE188604", "GSE6467"], "resolved_accessions": ["GSE6764", "GSE188604", "GSE6467"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article."], "basis": "The paper names GSE6764, GSE188604, GSE6467 in 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:39649424", "data:geo:GSE188604"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE188604"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:41:16Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 11060, "completion_tokens": 2532, "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:39649424", "type": "paper", "label": "pmid:39649424"}, {"id": "source:pmid:39649424", "type": "manuscript", "label": "PMID 39649424 full text"}, {"id": "data:geo:GSE188604", "type": "dataset", "label": "GEO GSE188604"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39649424", "type": "paper", "label": "pmid:39649424"}, {"id": "source:pmid:39649424", "type": "manuscript", "label": "PMID 39649424 full text"}, {"id": "data:geo:GSE188604", "type": "dataset", "label": "GEO GSE188604"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39649424", "type": "extraction", "used": ["source:pmid:39649424"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE188604", "type": "accession_resolution", "used": ["data:geo:GSE188604"], "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:39649424", "parent_hash": "sha256:a5096971c6f69cd20807cba32d8dcdac0b8c538385dbd4372c6d748045bfa9b9", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE188604 licence not read", "asset:data:geo:GSE188604 not downloaded", "asset:data:geo:GSE6467 licence not read", "asset:data:geo:GSE6467 not downloaded", "asset:data:geo:GSE6764 licence not read", "asset:data:geo:GSE6764 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": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["is characteristics in this disease. Methods: RNAseq data from GSE6764, GSE188604 and Cancer Geno"], "order_basis": "paper_text_order:335", "id": "assay:1"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["C25A37, PTGS2, MT1G, HSPB1, ESR1, and PHGDH. In vivo experimental validation, RT-PCR showed ESR1", "tetrachloride (CCl4) was used to establish a mouse liver fibrosis model to validate core gene e"], "order_basis": "paper_text_order:938", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ethods Cell Culture HepG2 and L02 cells were cultured in DMEM medium containing 10% heat-inactivated", "Materials and Methods Cell Culture HepG2 and L02 cells were cultured in DMEM medium c"], "order_basis": "paper_text_order:2151", "id": "assay:3"}, {"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": ["Multiple machine learning methods, including Weighted Gene Co-expression Network Analysis (WGCNA), Random Forest (RF) and Support Vector Machine (SVM), were used to identify core genes in liver fibrosis and ferroptosis."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]}