Identification of MORN3 and LLGL2 as novel diagnostic biomarkers for latent tuberculosis infection using machine learning strategies and experimental verification.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39054612", "kind": "science-record", "revision": 4, "content_hash": "sha256:b7f715cfbbbdfbe5b21fa235fba9ecc94cafc3aa5443b41894df9c5f4757535e", "created_at": "2026-11-01T20:29:07Z", "updated_at": "2026-11-01T22:54:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of MORN3 and LLGL2 as novel diagnostic biomarkers for latent tuberculosis infection using machine learning strategies and experimental verification.", "doi": "10.1080/07853890.2024.2380797", "pmid": "39054612", "authors": ["Longxiang Xie", "Gaoya Zhu", "Sibo Long", "Mengna Wang", "Xinxin Cheng", "Yuzhe Dong", "Chaoyang Wang", "Guirong Wang"], "journal": "Annals of medicine", "year": 2024, "abstract": "BACKGROUND: Current diagnostic methods cannot effectively distinguish between latent tuberculosis infection (LTBI) and active tuberculosis (ATB). This study aims to explore novel non-invasive diagnostic biomarkers for LTBI and to elucidate possible molecular mechanisms of LTBI pathogenesis.\nMETHODS: Three GEO datasets (GSE19439, GSE19444, and GSE62525) were utilized to analyze the differentially expressed genes (DEGs). Functional enrichment studies were then performed on these DEGs. To ascertain potential diagnostic biomarkers, we utilized two different machine learning techniques: LASSO and RF. ROC curves were constructed in both the training and validation datasets to assess the diagnostic efficacy. The expression of identified biomarkers was verified by RT-qPCR in our own Chinese cohort. Using CIBERSORT, we estimated the abundances of 22 immune cell types in LTBI group, and subsequently analyzed the relationship between biomarker expression and immune cell infiltration.\nRESULTS: 166 DEGs were identified between ATB and LTBI groups, which are primarily associated with immune responses, inflammatory signaling pathways, and infection factors. Following that, 22 candidate diagnostic biomarkers for LTBI were selected in the machine learning process. Three up-regulated genes, MORN3, LLGL2, and IFT140, whose expression levels were not previously reported in TB, were validated using the training and validation cohort datasets. In our own Chinese cohort, we also found that MORN3 and LLGL2 showed good diagnostic effect using RT-qPCR method. Finally, we revealed the specific infiltration features of immune cells in LTBI and observed a notable correlation between potential marker expression and immune cells.\nCONCLUSIONS: MORN3 and LLGL2 emerged as candidate diagnostic biomarkers for LTBI, following the elucidation of the key immune cell types involved. Our findings will contribute to providing a potential target for early noninvasive diagnosis of LTBI patients.", "claims": [{"id": "claim-method", "statement": "To select the candidate biomarkers in the DEGs of training set, LASSO regression model and random forest were performed.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39054612", "locator": "sections[6] \"Identification of candidate biomarkers in LTBI using machine learning methods\" paragraph 2", "quote": "To select the candidate biomarkers in the DEGs of training set, LASSO regression model and random forest were performed."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The GEO database provides access to the datasets examined in this study (http://www.ncbi.nlm.nih.gov/geo/). Please contact the corresponding author if you have any more questions.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39054612", "locator": "sections[26] \"Data availability statement\" paragraph 2", "quote": "The GEO database provides access to the datasets examined in this study (http://www.ncbi.nlm.nih.gov/geo/). Please contact the corresponding author if you have any more questions."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The combined two-gene approach further enhanced diagnostic capabilities, achieving AUCs of 0.994 (LTBI vs ATB), 0.782 (LTBI vs HC), and 0.914 (ATB vs HC).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39054612", "locator": "sections[17] \"Validation of potential biomarkers in our Chinese samples\" paragraph 4", "quote": "The combined two-gene approach further enhanced diagnostic capabilities, achieving AUCs of 0.994 (LTBI vs ATB), 0.782 (LTBI vs HC), and 0.914 (ATB vs HC)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The combined two-gene approach further enhanced diagnostic capabilities, achieving AUCs of 0.994 (LTBI vs ATB), 0.782 (LTBI vs HC), and 0.914 (ATB vs HC).", "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:39054612"], "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:GSE19439"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:machine_learning_random_forest", "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:GSE19439"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:machine_learning_random_forest"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39054612", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1080/07853890.2024.2380797", "sha256": "sha256:87f6af666e812a307ffa9357164d6735cf495a97536af9bfc12cc4481c5beab5", "bytes": 32044, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1080/07853890.2024.2380797", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11285216", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE19439", "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=GSE19439", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19439", "version": null, "note": "The GEO database provides access to the datasets examined in this study (http://www.ncbi.nlm.nih.gov/geo/). Please contact the corresponding author if you have any more questions.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GEO database provides access to the datasets examined in this study (http://www.ncbi.nlm.nih.gov/geo/). Please contact the corresponding author if you have any more questions.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM484448", "GSM484449", "GSM484450", "GSM484451", "GSM484452", "GSM484453", "GSM484454", "GSM484455", "GSM484456", "GSM484457", "GSM484458", "GSM484459", "GSM484460", "GSM484461", "GSM484462", "GSM484463", "GSM484464", "GSM484465", "GSM484466", "GSM484467", "GSM484468", "GSM484469", "GSM484470", "GSM484471", "GSM484472", "GSM484473", "GSM484474", "GSM484475", "GSM484476", "GSM484477", "GSM484478", "GSM484479", "GSM484480", "GSM484481", "GSM484482", "GSM484483", "GSM484484", "GSM484485", "GSM484486", "GSM484487", "GSM484488", "GSM484489"], "sample_count": 42, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "Blood Transcriptional Profiles in Active and Latent Tuberculosis UK (Training Set)", "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:GSE19444", "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=GSE19444", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19444", "version": null, "note": "The GEO database provides access to the datasets examined in this study (http://www.ncbi.nlm.nih.gov/geo/). Please contact the corresponding author if you have any more questions.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GEO database provides access to the datasets examined in this study (http://www.ncbi.nlm.nih.gov/geo/). Please contact the corresponding author if you have any more questions.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM484595", "GSM484596", "GSM484597", "GSM484598", "GSM484599", "GSM484600", "GSM484601", "GSM484602", "GSM484603", "GSM484604", "GSM484605", "GSM484606", "GSM484607", "GSM484608", "GSM484609", "GSM484610", "GSM484611", "GSM484612", "GSM484613", "GSM484614", "GSM484615", "GSM484616", "GSM484617", "GSM484618", "GSM484619", "GSM484620", "GSM484621", "GSM484622", "GSM484623", "GSM484624", "GSM484625", "GSM484626", "GSM484627", "GSM484628", "GSM484629", "GSM484630", "GSM484631", "GSM484632", "GSM484633", "GSM484634", "GSM484635", "GSM484636", "GSM484637", "GSM484638", "GSM484639", "GSM484640", "GSM484641", "GSM484642", "GSM484643", "GSM484644", "GSM484645", "GSM484646", "GSM484647", "GSM484648"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "Blood Transcriptional Profiles of Active and Latent TB (UK Test Set)", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE62525", "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=GSE62525", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62525", "version": null, "note": "The GEO database provides access to the datasets examined in this study (http://www.ncbi.nlm.nih.gov/geo/). Please contact the corresponding author if you have any more questions.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GEO database provides access to the datasets examined in this study (http://www.ncbi.nlm.nih.gov/geo/). Please contact the corresponding author if you have any more questions.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1528336", "GSM1528337", "GSM1528338", "GSM1528339", "GSM1528340", "GSM1528341", "GSM1528342", "GSM1528343", "GSM1528344", "GSM1528345", "GSM1528346", "GSM1528347", "GSM1528348", "GSM1528349", "GSM1528350", "GSM1528351", "GSM1528352", "GSM1528353", "GSM1528354", "GSM1528355", "GSM1528356", "GSM1528357", "GSM1528358", "GSM1528359", "GSM1528360", "GSM1528361", "GSM1528362", "GSM1528363", "GSM1528364", "GSM1528365", "GSM1528366", "GSM1528367", "GSM1528368", "GSM1528369", "GSM1528370", "GSM1528371", "GSM1528372", "GSM1528373", "GSM1528374", "GSM1528375", "GSM1528376", "GSM1528377"], "sample_count": 42, "group_sizes": null, "group_sizes_basis": null, "platform": "16951", "taxon": "Homo sapiens", "title": "Gene expression profiling identifies candidate biomarkers for active and latent tuberculosis", "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:GSE19439 not downloaded", "asset:data:geo:GSE19439 licence not read", "asset:data:geo:GSE19444 not downloaded", "asset:data:geo:GSE19444 licence not read", "asset:data:geo:GSE62525 not downloaded", "asset:data:geo:GSE62525 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "To select the candidate biomarkers in the DEGs of training set, LASSO regression model and random forest were performed."}}, {"id": "method-2", "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-3", "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": 0.8, "band": "high", "quote": "ROC curve"}}], "targets": [], "gaps": ["method.machine_learning_random_forest"]}, "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": false, "required_operations": [], "missing_operations": ["machine_learning_random_forest"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: random_forest."}, "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": ["GSE19439", "GSE19444", "GSE62525"], "resolved_accessions": ["GSE19439", "GSE19444", "GSE62525"], "statements": ["The GEO database provides access to the datasets examined in this study (http://www.ncbi.nlm.nih.gov/geo/). Please contact the corresponding author if you have any more questions."], "basis": "The paper names GSE19439, GSE19444, GSE62525 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": [], "assets": ["source:pmid:39054612", "data:geo:GSE19439"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "machine_learning_random_forest", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE19439"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:25:07Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9225, "completion_tokens": 2043, "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:39054612", "type": "paper", "label": "pmid:39054612"}, {"id": "source:pmid:39054612", "type": "manuscript", "label": "PMID 39054612 full text"}, {"id": "data:geo:GSE19439", "type": "dataset", "label": "GEO GSE19439"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39054612", "type": "paper", "label": "pmid:39054612"}, {"id": "source:pmid:39054612", "type": "manuscript", "label": "PMID 39054612 full text"}, {"id": "data:geo:GSE19439", "type": "dataset", "label": "GEO GSE19439"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39054612", "type": "extraction", "used": ["source:pmid:39054612"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE19439", "type": "accession_resolution", "used": ["data:geo:GSE19439"], "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:39054612", "parent_hash": "sha256:6c5275e9c110c37b4b02ee5636299a9f64c0782f4a1ca55a7976d7fb27adecd6", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE19439 licence not read", "asset:data:geo:GSE19439 not downloaded", "asset:data:geo:GSE19444 licence not read", "asset:data:geo:GSE19444 not downloaded", "asset:data:geo:GSE62525 licence not read", "asset:data:geo:GSE62525 not downloaded", "execution.not_run", "method.machine_learning_random_forest", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:machine_learning_random_forest"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ion of identified biomarkers was verified by RT-qPCR in our own Chinese cohort. Using CIBERSORT,", "nd LLGL2 showed good diagnostic effect using RT-qPCR method. Finally, we revealed the specific in", "of identified biomarkers was verified by RT-qPCR in our own Chinese cohort. Using CIBERSORT,", "LLGL2 showed good diagnostic effect using RT-qPCR method. Finally, we revealed the specific in"], "order_basis": "paper_text_order:886", "id": "assay:1"}, {"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["To select the candidate biomarkers in the DEGs of training set, LASSO regression model and random forest were performed."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}