Construction and verification of atopic dermatitis diagnostic model based on pyroptosis related biological markers using machine learning methods.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37330465", "kind": "science-record", "revision": 4, "content_hash": "sha256:0bd44720dfd60c2b9b9eed2e2e90239ed4b9ec59208d9fb40789db1e7183a368", "created_at": "2026-11-01T19:02:04Z", "updated_at": "2026-11-01T22:52:08Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Construction and verification of atopic dermatitis diagnostic model based on pyroptosis related biological markers using machine learning methods.", "doi": "10.1186/s12920-023-01552-5", "pmid": "37330465", "authors": ["Wenfeng Wu", "Gaofei Chen", "Zexin Zhang", "Meixing He", "Hongyi Li", "Fenggen Yan"], "journal": "BMC medical genomics", "year": 2023, "abstract": "OBJECTIVE: The aim of this study was to construct a model used for the accurate diagnosis of Atopic dermatitis (AD) using pyroptosis related biological markers (PRBMs) through the methods of machine learning.\nMETHOD: The pyroptosis related genes (PRGs) were acquired from molecular signatures database (MSigDB). The chip data of GSE120721, GSE6012, GSE32924, and GSE153007 were downloaded from gene expression omnibus (GEO) database. The data of GSE120721 and GSE6012 were combined as the training group, while the others were served as the testing groups. Subsequently, the expression of PRGs was extracted from the training group and differentially expressed analysis was conducted. CIBERSORT algorithm calculated the immune cells infiltration and differentially expressed analysis was conducted. Consistent cluster analysis divided AD patients into different modules according to the expression levels of PRGs. Then, weighted correlation network analysis (WGCNA) screened the key module. For the key module, we used Random forest (RF), support vector machines (SVM), Extreme Gradient Boosting (XGB), and generalized linear model (GLM) to construct diagnostic models. For the five PRBMs with the highest model importance, we built a nomogram. Finally, the results of the model were validated using GSE32924, and GSE153007 datasets.\nRESULTS: Nine PRGs were significant differences in normal humans and AD patients. Immune cells infiltration showed that the activated CD4+ memory T cells and Dendritic cells (DCs) were significantly higher in AD patients than normal humans, while the activated natural killer (NK) cells and the resting mast cells were significantly lower in AD patients than normal humans. Consistent cluster analysis divided the expressing matrix into 2 modules. Subsequently, WGCNA analysis showed that the turquoise module had a significant difference and high correlation coefficient. Then, the machine model was constructed and the results showed that the XGB model was the optimal model. The nomogram was constructed by using HDAC1, GPALPP1, LGALS3, SLC29A1, and RWDD3 five PRBMs. Finally, the datasets GSE32924 and GSE153007 verified the reliability of this result.\nCONCLUSIONS: The XGB model based on five PRBMs can be used for the accurate diagnosis of AD patients.", "claims": [{"id": "claim-method", "statement": "To construct the AD disease diagnosis model, the RF, SVM, XGB, and GLM machine learning models were constructed using repeatedcv, svmRadial, xgbDART, and glm methods and using caret, DALEX, randomForest, kernlab, and glm packages.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37330465", "locator": "sections[8] \"Construction of a disease diagnostic model for AD using machine learning\" paragraph 2", "quote": "To construct the AD disease diagnosis model, the RF, SVM, XGB, and GLM machine learning models were constructed using repeatedcv, svmRadial, xgbDART, and glm methods and using caret, DALEX, randomForest, kernlab, and glm packages."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data of this study were acquired from GEO database (https://www.ncbi.nlm.nih.gov/geo/) and MSigDB database (https://www.gsea-msigdb.org/gsea/index.jsp).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37330465", "locator": "sections[28] \"Availability of data and materials\" paragraph 2", "quote": "The data of this study were acquired from GEO database (https://www.ncbi.nlm.nih.gov/geo/) and MSigDB database (https://www.gsea-msigdb.org/gsea/index.jsp)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The XGB model based on five PRBMs can be used for the accurate diagnosis of AD patients.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37330465", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "The XGB model based on five PRBMs can be used for the accurate diagnosis of AD patients."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The XGB model based on five PRBMs can be used for the accurate diagnosis of AD patients.", "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:37330465"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37330465", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12920-023-01552-5", "sha256": "sha256:3e9a77923508a1aaf8fef93f3234d1f79a87b39ac2218b6bfd1eeb2a6ea725fb", "bytes": 46395, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12920-023-01552-5", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10276470", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "gradient_boosting", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To construct the AD disease diagnosis model, the RF, SVM, XGB, and GLM machine learning models were constructed using repeatedcv, svmRadial, xgbDART, and glm methods and using caret, DALEX, randomForest, kernlab, and glm packages."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "limma"}}, {"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 machines"}}, {"id": "method-5", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "dendrogram"}}, {"id": "method-6", "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.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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "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: gradient_boosting."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The data of this study were acquired from GEO database (https://www.ncbi.nlm.nih.gov/geo/) and MSigDB database (https://www.gsea-msigdb.org/gsea/index.jsp)."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "assets": ["source:pmid:37330465"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:44:00Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14601, "completion_tokens": 1592, "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:37330465", "type": "paper", "label": "pmid:37330465"}, {"id": "source:pmid:37330465", "type": "manuscript", "label": "PMID 37330465 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37330465", "type": "paper", "label": "pmid:37330465"}, {"id": "source:pmid:37330465", "type": "manuscript", "label": "PMID 37330465 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37330465", "type": "extraction", "used": ["source:pmid:37330465"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:37330465", "parent_hash": "sha256:9e366bc3d715ecbba96e21bc5401069a87e2c361d6dbd2e999c4b9d82a2582ef", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "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": 1.0, "evidence": ["To construct the AD disease diagnosis model, the RF, SVM, XGB, and GLM machine learning models were constructed using repeatedcv, svmRadial, xgbDART, and glm methods and using caret, DALEX, randomForest, kernlab, and glm packages."], "order_basis": "analysis_only", "id": "assay:1"}]}