Shapley additive explanations based feature selection reveals CXCL14 as a key immune-related gene in predicting idiopathic pulmonary fibrosis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40842541", "kind": "science-record", "revision": 4, "content_hash": "sha256:42a1f9f706eadd2ecd08479b4a834777af2bffacc44ff494c6fd8ff8840cd85e", "created_at": "2026-11-01T20:30:56Z", "updated_at": "2026-11-01T22:57:03Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Shapley additive explanations based feature selection reveals CXCL14 as a key immune-related gene in predicting idiopathic pulmonary fibrosis.", "doi": "10.3389/fmed.2025.1608078", "pmid": "40842541", "authors": ["Bin Chen", "Lu Huan", "Junyu Lu", "Jinhe Yuan"], "journal": "Frontiers in medicine", "year": 2025, "abstract": "Background: Idiopathic pulmonary fibrosis (IPF) is a progressive lung disease marked by excessive fibrous tissue accumulation in the lung interstitium, leading to a gradual deterioration of respiratory function and significantly impairing patients' quality of life. Despite advances in understanding its etiology and pathogenesis, the exact mechanisms remain unclear, underscoring the need for novel biomarkers and therapeutic targets.\nMethods: We analyzed five publicly available datasets from the Gene Expression Omnibus (GEO), specifically \"GSE15197,\" \"GSE53845,\" \"GSE135065,\" \"GSE185691,\" and \"GSE195770,\" to identify gene expression changes associated with IPF. Data were annotated and normalized to minimize batch effects and technical variability. Principal Component Analysis (PCA) verified preprocessing efficacy. Differentially expressed genes (DEGs) were identified using linear modeling. Core DEGs were selected via integrative analysis across datasets.\nResults: Our analysis revealed DEGs that are substantially linked to crucial biological processes such as extracellular matrix organization and immune response regulation. Integrative analysis of five GEO datasets identified CXCL14, MMP7, and MDK as core differentially expressed genes in the final predictive model. Using Least Absolute Shrinkage and Selection Operator (LASSO) regression and Random Forest, we constructed a logistic regression model with robust predictive performance, achieving an AUC of 0.92 in the training cohort and 0.89 in the validation cohort, with sensitivity of 88% and specificity of 85%. The Shapley Additive Explanations (SHAP) method identified CXCL14 (mean SHAP value = 0.38) as the most influential feature, followed by MMP7 and MDK. Functional enrichment analyses highlighted significant enrichment of TGF-β signaling, extracellular matrix organization, and chemokine signaling pathways. Immune infiltration analysis revealed positive correlations between CXCL14 expression and alveolar macrophage/activated fibroblast populations, while SHAP interaction analysis identified synergistic effects between CXCL14 and TGF-β1 in driving fibrosis.\nConclusion: These findings substantiate the hypothesis that IPF pathogenesis is closely linked to extracellular matrix remodeling and immune dysregulation. This suggests that future investigations should delve deeper into the practical applications of identified biomarkers in the early diagnosis and management of IPF. Furthermore, the machine learning-based predictive model demonstrates strong clinical potential and merits further validation in prospective trials to assess its utility and therapeutic implications in real-world settings.", "claims": [{"id": "claim-method", "statement": "Differential gene expression was performed using the limma package (19), which calculates gene expression differences between different groups (IPF group vs. normal control group) through linear modeling.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40842541", "locator": "sections[4] \"Differential gene expression analysis\" paragraph 2", "quote": "Differential gene expression was performed using the limma package (19), which calculates gene expression differences between different groups (IPF group vs. normal control group) through linear modeling."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40842541", "locator": "sections[22] \"Data availability statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Integrative analysis of five GEO datasets identified CXCL14, MMP7, and MDK as core differentially expressed genes, and the LASSO- and random-forest-based logistic regression model achieved an AUC of 0.92 in the training cohort and 0.89 in the validation cohort.", "kind": "quantitative", "target": {"value": 0.92, "unit": "auc", "tolerance": null, "source": "Integrative analysis of five GEO datasets identified CXCL14, MMP7, and MDK as core differentially expressed genes in the final predictive model. Using Least Absolute Shrinkage and Selection Operator (LASSO) regression and Random Forest, we constructed a logistic regression model with robust predictive performance, achieving an AUC of 0.92 in the training cohort and 0.89 in the validation cohort, with sensitivity of 88% and specificity of 85%."}, "evidence": [{"asset": "source:pmid:40842541", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Integrative analysis of five GEO datasets identified CXCL14, MMP7, and MDK as core differentially expressed genes in the final predictive model. Using Least Absolute Shrinkage and Selection Operator (LASSO) regression and Random Forest, we constructed a logistic regression model with robust predictive performance, achieving an AUC of 0.92 in the training cohort and 0.89 in the validation cohort, with sensitivity of 88% and specificity of 85%."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Integrative analysis of five GEO datasets identified CXCL14, MMP7, and MDK as core differentially expressed genes, and the LASSO- and random-forest-based logistic regression model achieved an AUC of 0.92 in the training cohort and 0.89 in the validation cohort.", "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:40842541"], "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:GSE135065"], "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:GSE135065"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40842541", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fmed.2025.1608078", "sha256": "sha256:a15102396decfa98b10dcf559fff9d7b4ee5053d01d06997e2d5eb19320c855b", "bytes": 53220, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fmed.2025.1608078", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12364669", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE135065", "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=GSE135065", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE135065", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3984766", "GSM3984767", "GSM3984768", "GSM3984769", "GSM3984770", "GSM3984771", "GSM3984772", "GSM3984773", "GSM3984774", "GSM3984775", "GSM3984776", "GSM3984777", "GSM3984778", "GSM3984779", "GSM3984780", "GSM3984781", "GSM3984782", "GSM3984783"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "15207", "taxon": "Homo sapiens", "title": "Transforming growth factor beta 1 induces methylation changes in lung fibroblasts [Affymetrix]", "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:GSE15197", "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=GSE15197", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15197", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM379316", "GSM379317", "GSM379318", "GSM379319", "GSM379320", "GSM379321", "GSM379322", "GSM379323", "GSM379324", "GSM379325", "GSM379326", "GSM379327", "GSM379328", "GSM379329", "GSM379330", "GSM379331", "GSM379332", "GSM379333", "GSM379334", "GSM379335", "GSM379336", "GSM379337", "GSM379338", "GSM379339", "GSM379340", "GSM379341", "GSM379342", "GSM379343", "GSM379344", "GSM379345", "GSM379346", "GSM379347", "GSM379348", "GSM379349", "GSM379350", "GSM379351", "GSM379352", "GSM379353", "GSM379354"], "sample_count": 39, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "RNA Expression Profiling of Lung Tissue Identifies Mutually Distinct Molecular Signatures in PAH and PH Secondary to IPF", "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:GSE185691", "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=GSE185691", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE185691", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5621625", "GSM5621626", "GSM5621627", "GSM5621628", "GSM5621629", "GSM5621630", "GSM5621631", "GSM5621632", "GSM5621633", "GSM5621634", "GSM5621635", "GSM5621636", "GSM5621637", "GSM5621638"], "sample_count": 14, "group_sizes": null, "group_sizes_basis": null, "platform": "20844", "taxon": "Homo sapiens", "title": "Differential Lysotracker Uptake Defines Two Populations of Distal Epithelial Cells in Idiopathic Pulmonary Fibrosis", "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:GSE195770", "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=GSE195770", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE195770", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5849919", "GSM5849920", "GSM5849921", "GSM5849922", "GSM5849923", "GSM5849924", "GSM5849925", "GSM5849926"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "20844", "taxon": "Homo sapiens", "title": "Idiopathic pulmonary fibrosis (IPF)", "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:GSE53845", "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=GSE53845", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53845", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1302033", "GSM1302034", "GSM1302035", "GSM1302036", "GSM1302037", "GSM1302038", "GSM1302039", "GSM1302040", "GSM1302041", "GSM1302042", "GSM1302043", "GSM1302044", "GSM1302045", "GSM1302046", "GSM1302047", "GSM1302048", "GSM1302049", "GSM1302050", "GSM1302051", "GSM1302052", "GSM1302053", "GSM1302054", "GSM1302055", "GSM1302056", "GSM1302057", "GSM1302058", "GSM1302059", "GSM1302060", "GSM1302061", "GSM1302062", "GSM1302063", "GSM1302064", "GSM1302065", "GSM1302066", "GSM1302067", "GSM1302068", "GSM1302069", "GSM1302070", "GSM1302071", "GSM1302072", "GSM1302073", "GSM1302074", "GSM1302075", "GSM1302076", "GSM1302077", "GSM1302078", "GSM1302079", "GSM1302080"], "sample_count": 48, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "40 IPF patients and 8 healthy controls", "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:GSE135065 not downloaded", "asset:data:geo:GSE135065 licence not read", "asset:data:geo:GSE15197 not downloaded", "asset:data:geo:GSE15197 licence not read", "asset:data:geo:GSE185691 not downloaded", "asset:data:geo:GSE185691 licence not read", "asset:data:geo:GSE195770 not downloaded", "asset:data:geo:GSE195770 licence not read", "asset:data:geo:GSE53845 not downloaded", "asset:data:geo:GSE53845 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": "Differential gene expression was performed using the limma package (19), which calculates gene expression differences between different groups (IPF group vs. normal control group) through linear modeling."}}, {"id": "method-2", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Principal Component Analysis"}}, {"id": "method-3", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {"auc": "rformance, achieving an AUC of 0"}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Random Forest"}}, {"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": 0.7, "band": "medium", "quote": "logistic regression"}}, {"id": "method-5", "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": "GO enrichment"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "differential_expression_fit", "expected_value": 0.92, "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": ["GSE15197", "GSE53845", "GSE135065", "GSE185691", "GSE195770"], "resolved_accessions": ["GSE15197", "GSE53845", "GSE135065", "GSE185691", "GSE195770"], "statements": ["The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author."], "basis": "The paper names GSE15197, GSE53845, GSE135065, GSE185691, GSE195770 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:40842541", "data:geo:GSE135065"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE135065"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:00:07Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13575, "completion_tokens": 1772, "cached_tokens": 256}}, "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:40842541", "type": "paper", "label": "pmid:40842541"}, {"id": "source:pmid:40842541", "type": "manuscript", "label": "PMID 40842541 full text"}, {"id": "data:geo:GSE135065", "type": "dataset", "label": "GEO GSE135065"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40842541", "type": "paper", "label": "pmid:40842541"}, {"id": "source:pmid:40842541", "type": "manuscript", "label": "PMID 40842541 full text"}, {"id": "data:geo:GSE135065", "type": "dataset", "label": "GEO GSE135065"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40842541", "type": "extraction", "used": ["source:pmid:40842541"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE135065", "type": "accession_resolution", "used": ["data:geo:GSE135065"], "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:40842541", "parent_hash": "sha256:8058efcbe34a43de299d61730e700177f055df09e3ccc2a8c9c3809b9d6d5338", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE135065 licence not read", "asset:data:geo:GSE135065 not downloaded", "asset:data:geo:GSE15197 licence not read", "asset:data:geo:GSE15197 not downloaded", "asset:data:geo:GSE185691 licence not read", "asset:data:geo:GSE185691 not downloaded", "asset:data:geo:GSE195770 licence not read", "asset:data:geo:GSE195770 not downloaded", "asset:data:geo:GSE53845 licence not read", "asset:data:geo:GSE53845 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": ["Differential gene expression was performed using the limma package (19), which calculates gene expression differences between different groups (IPF group vs. normal control group) through linear modeling."], "order_basis": "analysis_only", "id": "assay:1"}]}