Machine learning and bioinformatics to identify 8 autophagy-related biomarkers and construct gene regulatory networks in dilated cardiomyopathy.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36056063", "kind": "science-record", "revision": 5, "content_hash": "sha256:de6c73d95cdf708908e5956637f468d0b6a220562064325bcf4d915766808d7e", "created_at": "2026-11-01T18:15:14Z", "updated_at": "2026-11-01T22:49:57Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Machine learning and bioinformatics to identify 8 autophagy-related biomarkers and construct gene regulatory networks in dilated cardiomyopathy.", "doi": "10.1038/s41598-022-19027-5", "pmid": "36056063", "authors": ["Fengjun Zhang", "Mingyue Xia", "Jiarong Jiang", "Shuai Wang", "Qiong Zhao", "Cheng Yu", "Jinzhen Yu", "Dexian Xian", "Xiao Li", "Lin Zhang", "Yuan Liu", "Min Peng"], "journal": "Scientific reports", "year": 2022, "abstract": "Dilated cardiomyopathy (DCM) is a condition of impaired ventricular remodeling and systolic diastole that is often complicated by arrhythmias and heart failure with a poor prognosis. This study attempted to identify autophagy-related genes (ARGs) with diagnostic biomarkers of DCM using machine learning and bioinformatics approaches. Differential analysis of whole gene microarray data of DCM from the Gene Expression Omnibus (GEO) database was performed using the NetworkAnalyst 3.0 platform. Differentially expressed genes (DEGs) matching (|log2FoldChange ≥ 0.8, p value &lt; 0.05|) were obtained in the GSE4172 dataset by merging ARGs from the autophagy gene libraries, HADb and HAMdb, to obtain autophagy-related differentially expressed genes (AR-DEGs) in DCM. The correlation analysis of AR-DEGs and their visualization were performed using R language. Gene Ontology (GO) enrichment analysis and combined multi-database pathway analysis were served by the Enrichr online enrichment analysis platform. We used machine learning to screen the diagnostic biomarkers of DCM. The transcription factors gene regulatory network was constructed by the JASPAR database of the NetworkAnalyst 3.0 platform. We also used the drug Signatures database (DSigDB) drug database of the Enrichr platform to screen the gene target drugs for DCM. Finally, we used the DisGeNET database to analyze the comorbidities associated with DCM. In the present study, we identified 23 AR-DEGs of DCM. Eight (PLEKHF1, HSPG2, HSF1, TRIM65, DICER1, VDAC1, BAD, TFEB) molecular markers of DCM were obtained by two machine learning algorithms. Transcription factors gene regulatory network was established. Finally, 10 gene-targeted drugs and complications for DCM were identified.", "claims": [{"id": "claim-method", "statement": "For mRNA in microarrays, the threshold was set to |log2FoldChange|≥ 0.8 with a p value < 0.05, and genes meeting this criterion were considered as DEGs. In this study, the least absolute shrinkage and selection operator (LASSO) logistic regression was used for feature gene selection to reduce the number of genes in the disease prediction model, solve the multicollinearity problem in the regression analysis, and screen the molecular markers of DCM genes87.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36056063", "locator": "sections[13] \"Identification of differentially expressed genes (DEGs) in autophagy-related genes (ARGs)\" paragraph 2", "quote": "For mRNA in microarrays, the threshold was set to |log2FoldChange|≥ 0.8 with a p value < 0.05, and genes meeting this criterion were considered as DEGs."}, {"asset": "source:pmid:36056063", "locator": "sections[15] \"Machine learning identifies molecular markers of AR-DEGs in DCM\" paragraph 2", "quote": "In this study, the least absolute shrinkage and selection operator (LASSO) logistic regression was used for feature gene selection to reduce the number of genes in the disease prediction model, solve the multicollinearity problem in the regression analysis, and screen the molecular markers of DCM genes87."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The dataset GSE4172 for this study can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo). All data generated or analysed during this study are included in this published article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36056063", "locator": "sections[27] \"notes\" paragraph 1", "quote": "The dataset GSE4172 for this study can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo). All data generated or analysed during this study are included in this published article."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study identified 23 autophagy-related differentially expressed genes in dilated cardiomyopathy and selected eight diagnostic biomarkers using two machine-learning algorithms.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36056063", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "In the present study, we identified 23 AR-DEGs of DCM."}, {"asset": "source:pmid:36056063", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Eight (PLEKHF1, HSPG2, HSF1, TRIM65, DICER1, VDAC1, BAD, TFEB) molecular markers of DCM were obtained by two machine learning algorithms."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study identified 23 autophagy-related differentially expressed genes in dilated cardiomyopathy and selected eight diagnostic biomarkers using two machine-learning algorithms.", "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:36056063"], "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:GSE4172"], "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:GSE4172"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36056063", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-022-19027-5", "sha256": "sha256:5347369ad1a7dc59339e07738685831968605e15964780322cff369a593865fc", "bytes": 43050, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-022-19027-5", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9440113", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE4172", "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=GSE4172", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE4172", "version": null, "note": "The dataset GSE4172 for this study can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo). All data generated or analysed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The dataset GSE4172 for this study can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo). All data generated or analysed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM94831", "GSM94836", "GSM94837", "GSM94838", "GSM94839", "GSM94840", "GSM94841", "GSM94842", "GSM94843", "GSM94854", "GSM94855", "GSM94870"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiling of human inflammatory Cardiomyopathy", "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:GSE4172 not downloaded", "asset:data:geo:GSE4172 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": 1.0, "band": "reordered", "quote": "For mRNA in microarrays, the threshold was set to |log2FoldChange|≥ 0.8 with a p value < 0.05, and genes meeting this criterion were considered as DEGs. In this study, the least absolute shrinkage and selection operator (LASSO) logistic regression was used for feature gene selection to reduce the number of genes in the disease prediction model, solve the multicollinearity problem in the regression analysis, and screen the molecular markers of DCM genes87."}}, {"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"}}], "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": ["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": ["GSE4172"], "resolved_accessions": ["GSE4172"], "statements": ["The dataset GSE4172 for this study can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo). All data generated or analysed during this study are included in this published article."], "basis": "The paper names GSE4172 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": ["train_classifier", "cross_validate", "roc_auc"], "assets": ["source:pmid:36056063", "data:geo:GSE4172"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE4172"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:03:02Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 12229, "completion_tokens": 1751, "cached_tokens": 128}}, "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:36056063", "type": "paper", "label": "pmid:36056063"}, {"id": "source:pmid:36056063", "type": "manuscript", "label": "PMID 36056063 full text"}, {"id": "data:geo:GSE4172", "type": "dataset", "label": "GEO GSE4172"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36056063", "type": "paper", "label": "pmid:36056063"}, {"id": "source:pmid:36056063", "type": "manuscript", "label": "PMID 36056063 full text"}, {"id": "data:geo:GSE4172", "type": "dataset", "label": "GEO GSE4172"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36056063", "type": "extraction", "used": ["source:pmid:36056063"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE4172", "type": "accession_resolution", "used": ["data:geo:GSE4172"], "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:36056063", "parent_hash": "sha256:40b94925614ae25aa111a505403f0f67fa7cd4ae1fb5defb738ace16d974e6cf", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE4172 licence not read", "asset:data:geo:GSE4172 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": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["roaches. Differential analysis of whole gene microarray data of DCM from the Gene Expression Omnibus"], "order_basis": "paper_text_order:471", "id": "assay:1"}, {"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": ["For mRNA in microarrays, the threshold was set to |log2FoldChange|≥ 0.8 with a p value < 0.05, and genes meeting this criterion were considered as DEGs. In this study, the least absolute shrinkage and selection operator (LASSO) logistic regression was used for feature gene selection to reduce the number of genes in the disease prediction model, solve the multicollinearity problem in the regression analysis, and screen the molecular markers of DCM genes87."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}