Integrated multiple machine learning and Mendelian randomization reveal LTF gene as a prognostic biomarker for nonspecific orbital inflammation.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40760708", "kind": "science-record", "revision": 3, "content_hash": "sha256:2f5a131bb7e92f08cb9aafe765ff34cd34643e3fb30c2b40f3bb8943c8cf07a5", "created_at": "2026-11-01T20:30:51Z", "updated_at": "2026-11-01T22:14:29Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Integrated multiple machine learning and Mendelian randomization reveal LTF gene as a prognostic biomarker for nonspecific orbital inflammation.", "doi": "10.1186/s40360-025-00980-6", "pmid": "40760708", "authors": ["Zixuan Wu", "Jinfeng Xu", "Yuan Gao", "Kang Tan", "Xiaolei Yao", "Qinghua Peng"], "journal": "BMC pharmacology & toxicology", "year": 2025, "abstract": "BACKGROUND: Nonspecific orbital inflammation (NSOI), also known as idiopathic orbital inflammation, comprises a heterogeneous group of immune-mediated disorders affecting orbital tissues, unified by the absence of a defined etiology. Lactotransferrin (LTF), an iron-binding glycoprotein, exerts potent antimicrobial activity by sequestering iron essential for microbial growth, and demonstrates broad-spectrum antibacterial, antiviral, and antifungal properties.\nMETHODS: LTF was identified through the intersection analysis of common DEGs from datasets GSE58331 and GSE105149 from the GEO database, alongside immune-related gene lists from the ImmPort database, using Multiple Machine learning and WGCNA analysis. GSEA and GSVA were conducted with gene sets co-expressed with LTF. To further investigate the correlation between LTF and immune-related biological processes, the CIBERSORT algorithm and ESTIMATE method were employed to evaluate immune microenvironment characteristics of each sample. The expression levels of LTF were subsequently validated using GSE105149.\nRESULTS: Lasso and SVM-RFE algorithms pinpointed 28 hub genes. Enrichment analysis revealed that gene sets positively correlated with LTF were enriched in immune-related pathways. For biological function analysis in LTF, retina homeostasis, sensory perception of bitter taste, and tissue homeostasis were emphasized. Immune infiltration analysis indicated that Plasma cells and B cells naive were positively associated (That is, when the expression level of LTF increases, these immune cells also increase accordingly) with LTF, whereas B cells memory, Macrophages M2, Mast cells resting, Monocytes, NK cells activated, T cells regulatory (Tregs) were negatively associated with LTF. LTF demonstrated significant diagnostic potential in differentiating NSOI.\nCONCLUSIONS: This study identifies LTF as a potential biomarker linked to NSOI, providing insights into its pathogenesis and offering new avenues for tracking disease progression.", "claims": [{"id": "claim-method", "statement": "LTF was identified through the intersection analysis of common DEGs from datasets GSE58331 and GSE105149 from the GEO database, alongside immune-related gene lists from the ImmPort database, using Multiple Machine learning and WGCNA analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40760708", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "LTF was identified through the intersection analysis of common DEGs from datasets GSE58331 and GSE105149 from the GEO database, alongside immune-related gene lists from the ImmPort database, using Multiple Machine learning and WGCNA analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated during and/or analyzed during the current study are available in the appendix. Thanks to the KEGG database for the great support [41]. The citation guidelines: www.kegg.jp/kegg/kegg1.html.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40760708", "locator": "sections[22] \"Data availability\" paragraph 2", "quote": "The datasets generated during and/or analyzed during the current study are available in the appendix. Thanks to the KEGG database for the great support [41]. The citation guidelines: www.kegg.jp/kegg/kegg1.html."}], "state": "complete"}, {"id": "claim-target-result", "statement": "LTF demonstrated diagnostic potential for differentiating NSOI, with an AUC of 0.685.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40760708", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "LTF demonstrated significant diagnostic potential in differentiating NSOI."}, {"asset": "source:pmid:40760708", "locator": "sections[12] \"Identification of model gene\" paragraph 2", "quote": "The ROC analysis of the 15 hub genes further confirmed their high predictive accuracy (AUC): (KIT-0.638), (LTF-0.685), (LYZ-0.664), (MMD-0.752), (MPPED2-0.783), (NFKBIZ-0.662), (PHGDH-0.707), (SERPINA3-0.639), (SFRP1-0.668), (SH3BGRL2-0.650), (SIX1-0.809), (SOX9-0.616), (TCEAL2-0.688), (TMEM30B-0.869), (TUBA1A-0.678), (WFDC2-0.732)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "LTF demonstrated diagnostic potential for differentiating NSOI, with an AUC of 0.685.", "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:40760708"], "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:GSE105149"], "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:GSE105149"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40760708", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s40360-025-00980-6", "sha256": "sha256:f4e3c414c4c95a5812ab687d5f7b5a08b27619b271e1db7fe72b4d3b943c06fb", "bytes": 52068, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s40360-025-00980-6", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12323148", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE105149", "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=GSE105149", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE105149", "version": null, "note": "The datasets generated during and/or analyzed during the current study are available in the appendix. Thanks to the KEGG database for the great support [41]. The citation guidelines: www.kegg.jp/kegg/kegg1.html.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated during and/or analyzed during the current study are available in the appendix. Thanks to the KEGG database for the great support [41]. The citation guidelines: www.kegg.jp/kegg/kegg1.html.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2823303", "GSM2823304", "GSM2823305", "GSM2823306", "GSM2823307", "GSM2823308", "GSM2823309", "GSM2823310", "GSM2823311", "GSM2823312", "GSM2823313", "GSM2823314", "GSM2823315", "GSM2823316", "GSM2823317", "GSM2823318", "GSM2823319", "GSM2823320", "GSM2823321", "GSM2823322", "GSM2823323", "GSM2823324", "GSM2823325", "GSM2823326", "GSM2823327", "GSM2823328", "GSM2823329", "GSM2823330", "GSM2823331", "GSM2823332", "GSM2823333", "GSM2823334", "GSM2823335", "GSM2823336", "GSM2823337", "GSM2823338", "GSM2823339", "GSM2823340", "GSM2823341", "GSM2823342", "GSM2823343", "GSM2823344", "GSM2823345", "GSM2823346", "GSM2823347", "GSM2823348", "GSM2823349", "GSM2823350", "GSM2823351"], "sample_count": 49, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene Expression in the Human Lacrimal Gland", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE58331", "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=GSE58331", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE58331", "version": null, "note": "The datasets generated during and/or analyzed during the current study are available in the appendix. Thanks to the KEGG database for the great support [41]. The citation guidelines: www.kegg.jp/kegg/kegg1.html.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated during and/or analyzed during the current study are available in the appendix. Thanks to the KEGG database for the great support [41]. The citation guidelines: www.kegg.jp/kegg/kegg1.html.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1407182", "GSM1407183", "GSM1407184", "GSM1407185", "GSM1407186", "GSM1407187", "GSM1407188", "GSM1407189", "GSM1407190", "GSM1407191", "GSM1407192", "GSM1407193", "GSM1407194", "GSM1407195", "GSM1407196", "GSM1407197", "GSM1407198", "GSM1407199", "GSM1407200", "GSM1407201", "GSM1407202", "GSM1407203", "GSM1407204", "GSM1407205", "GSM1407206", "GSM1407207", "GSM1407208", "GSM1407209", "GSM1407210", "GSM1407211", "GSM1407212", "GSM1407213", "GSM1407214", "GSM1407215", "GSM1407216", "GSM1407217", "GSM1407218", "GSM1407219", "GSM1407220", "GSM1407221", "GSM1407222", "GSM1407223", "GSM1407224", "GSM1407225", "GSM1407226", "GSM1407227", "GSM1407228", "GSM1407229", "GSM1407230", "GSM1407231", "GSM1407232", "GSM1407233", "GSM1407234", "GSM1407235", "GSM1407236", "GSM1407237", "GSM1407238", "GSM1407239", "GSM1407240", "GSM1407241", "GSM1407242", "GSM1407243", "GSM1407244", "GSM1407245", "GSM1407246", "GSM1407247", "GSM1407248", "GSM1407249", "GSM1407250", "GSM1407251", "GSM1407252", "GSM1407253", "GSM1407254", "GSM1407255", "GSM1407256", "GSM1407257", "GSM1407258", "GSM1407259", "GSM1407260", "GSM1407261", "GSM1407262", "GSM1407263", "GSM1407264", "GSM1407265", "GSM1407266", "GSM1407267", "GSM1407268", "GSM1407269", "GSM1407270", "GSM1407271", "GSM1407272", "GSM1407273", "GSM1407274", "GSM1407275", "GSM1407276", "GSM1407277", "GSM1407278", "GSM1407279", "GSM1407280", "GSM1407281", "GSM1407282", "GSM1407283", "GSM1407284", "GSM1407285", "GSM1407286", "GSM1407287", "GSM1407288", "GSM1407289", "GSM1407290", "GSM1407291", "GSM1407292", "GSM1407293", "GSM1407294", "GSM1407295", "GSM1407296", "GSM1407297", "GSM1407298", "GSM1407299", "GSM1407300", "GSM1407301", "GSM1407302", "GSM1407303", "GSM1407304", "GSM1407305", "GSM1407306", "GSM1407307", "GSM1407308", "GSM1407309", "GSM1407310", "GSM1407311", "GSM1407312", "GSM1407313", "GSM1407314", "GSM1407315", "GSM1407316", "GSM1407317", "GSM1407318", "GSM1407319", "GSM1407320", "GSM1407321", "GSM1407322", "GSM1407323", "GSM1407324", "GSM1407325", "GSM1407326", "GSM1407327", "GSM1407328", "GSM1407329", "GSM1407330", "GSM1407331", "GSM1407332", "GSM1407333", "GSM1407334", "GSM1407335", "GSM1407336", "GSM1407337", "GSM1407338", "GSM1407339", "GSM1407340", "GSM1407341", "GSM1407342", "GSM1407343", "GSM1407344", "GSM1407345", "GSM1407346", "GSM1407347", "GSM1407348", "GSM1407349", "GSM1407350", "GSM1407351", "GSM1407352", "GSM1407353", "GSM1407354", "GSM1407355", "GSM1407356"], "sample_count": 175, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression in human orbit", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE105149 not downloaded", "asset:data:geo:GSE105149 licence not read", "asset:data:geo:GSE58331 not downloaded", "asset:data:geo:GSE58331 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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-2", "family": "genetic_association", "specific": "mendelian_randomisation", "label": "Genetic association (GWAS / linkage / MR)", "dsl_operations": ["mr_estimate"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["genotype_phenotype_table"], "evidence": {"score": 0.7, "band": "medium", "quote": "Mendelian randomization"}}, {"id": "method-3", "family": null, "specific": null, "label": "Multiple Machine learning and WGCNA analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "LTF was identified through the intersection analysis of common DEGs from datasets GSE58331 and GSE105149 from the GEO database, alongside immune-related gene lists from the ImmPort database, using Multiple Machine learning and WGCNA analysis."}}], "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": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: support_vector_machine."}, "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": ["GSE58331", "GSE105149"], "resolved_accessions": ["GSE58331", "GSE105149"], "statements": ["The datasets generated during and/or analyzed during the current study are available in the appendix. Thanks to the KEGG database for the great support [41]. The citation guidelines: www.kegg.jp/kegg/kegg1.html."], "basis": "The paper names GSE58331, GSE105149 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "assets": ["source:pmid:40760708", "data:geo:GSE105149"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE105149"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:58:31Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13528, "completion_tokens": 1893, "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:40760708", "type": "paper", "label": "pmid:40760708"}, {"id": "source:pmid:40760708", "type": "manuscript", "label": "PMID 40760708 full text"}, {"id": "data:geo:GSE105149", "type": "dataset", "label": "GEO GSE105149"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40760708", "type": "paper", "label": "pmid:40760708"}, {"id": "source:pmid:40760708", "type": "manuscript", "label": "PMID 40760708 full text"}, {"id": "data:geo:GSE105149", "type": "dataset", "label": "GEO GSE105149"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40760708", "type": "extraction", "used": ["source:pmid:40760708"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE105149", "type": "accession_resolution", "used": ["data:geo:GSE105149"], "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:40760708", "parent_hash": "sha256:d9593a338b5532d5424a81ce492200fda4cc483fbfab1244ecbabb728e7a13d9", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE105149 licence not read", "asset:data:geo:GSE105149 not downloaded", "asset:data:geo:GSE58331 licence not read", "asset:data:geo:GSE58331 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["SVM"], "order_basis": "analysis_only", "id": "assay:1"}]}