Identifying and Validating Extracellular Matrix-Related Gene CTSH in Diabetic Foot Ulcer Using Bioinformatics and Machine Learning.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39228680", "kind": "science-record", "revision": 4, "content_hash": "sha256:092a8625d5d40fdb1fa0e67737453273cd8efc57f3a02417d85e1f101095b131", "created_at": "2026-11-01T20:29:22Z", "updated_at": "2026-11-01T22:55:05Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identifying and Validating Extracellular Matrix-Related Gene CTSH in Diabetic Foot Ulcer Using Bioinformatics and Machine Learning.", "doi": "10.2147/JIR.S467507", "pmid": "39228680", "authors": ["Pei-Yu Wu", "Yan-Lin Yu", "Wen-Rui Zhao", "Bo Zhou"], "journal": "Journal of inflammation research", "year": 2024, "abstract": "Background: Diabetic foot ulcer (DFU) is a serious clinical problem with high amputation and mortality rates, yet there is a lack of desirable therapy. While the extracellular matrix (ECM) contributes significantly to wound healing, ECM-related biomarker for DFU is still unknown. The study was designed to identify ECM-related biomarker in DFU using bioinformatics and machine learning and validate it in STZ-induced mice models.\nMethods: GSE80178 and GSE134431 microarray datasets were fetched from the GEO database, and differentially expressed genes (DEGs) analysis was performed, respectively. By analyzing DEGs and ECM genes, we identified ECM-related DEGs, and functional enrichment analysis was conducted. Subsequently, three machine learning algorithms (LASSO, RF and SVM-RFE) were applied to filter ECM-related DEGs to identify key ECM-related biomarkers. Next, we conducted immune infiltration analysis, GSEA, and correlation analysis to explore the hub gene underlying mechanism. A lncRNA-miRNA-mRNA and drug regulatory network were constructed. Finally, we validated the key ECM-related biomarker in STZ-induced mice models.\nResults: One hundred and forty-five common DEGs in adult DFU between the two datasets were identified. Taking the intersection of 145 common DEGs and 964 ECM genes, we identified 13 ECM-related DEGs. Thirteen ECM-related DEGs were mainly enriched in pathways associated with tissue remodeling, inflammation and defense against infectious agents. Ultimately, CTSH was identified as the key ECM-related biomarker. CTSH was associated with difference immune cells during the occurrence and development of DFU, and it influenced hedgehog, IL-17 and TNF signaling pathway. Additionally, CTSH expression is correlated with many ECM- and immune-related genes. A lncRNA-miRNA-mRNA and drug regulatory network were constructed with 10 lncRNAs, 2 miRNAs, CTSH and 1 drug. Finally, CTSH was validated as a key biomarker for DFU in animal models.\nConclusion: Our study found that CTSH can be used for both diagnostic and prognostic purposes and might be a potential therapeutic target.", "claims": [{"id": "claim-method", "statement": "Hub genes were analyzed using three machine learning methods (LASSO, RF and SVM-RFE).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39228680", "locator": "sections[6] \"Hub Genes Identification via Machine Learning Methods\" paragraph 2", "quote": "Hub genes were analyzed using three machine learning methods (LASSO, RF and SVM-RFE)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets analyzed in this article are accessible to the public. The datasets were acquired from the Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/) database, and the accession numbers were GSE80178, GSE134431, GSE147890 and GSE23006.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39228680", "locator": "sections[28] \"Data Sharing Statement\" paragraph 2", "quote": "The datasets analyzed in this article are accessible to the public. The datasets were acquired from the Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/) database, and the accession numbers were GSE80178, GSE134431, GSE147890 and GSE23006."}], "state": "complete"}, {"id": "claim-target-result", "statement": "CTSH was identified as the key ECM-related biomarker for diabetic foot ulcer through machine-learning analysis and validated in animal models.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39228680", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Ultimately, CTSH was identified as the key ECM-related biomarker."}, {"asset": "source:pmid:39228680", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Finally, CTSH was validated as a key biomarker for DFU in animal models."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "CTSH was identified as the key ECM-related biomarker for diabetic foot ulcer through machine-learning analysis and validated in animal models.", "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:39228680"], "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:GSE134431"], "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:GSE134431"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39228680", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/JIR.S467507", "sha256": "sha256:42a333b7f9507b8d76caebfb7b0936a2f300b07ac4d9095c5bf9f55b8736c21d", "bytes": 41352, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/JIR.S467507", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11370762", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE134431", "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=GSE134431", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE134431", "version": null, "note": "The datasets analyzed in this article are accessible to the public. The datasets were acquired from the Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/) database, and the accession numbers were GSE80178, GSE134431, GSE147890 and GSE23006.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed in this article are accessible to the public. The datasets were acquired from the Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/) database, and the accession numbers were GSE80178, GSE134431, GSE147890 and GSE23006.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3946485", "GSM3946486", "GSM3946487", "GSM3946488", "GSM3946489", "GSM3946490", "GSM3946491", "GSM3946492", "GSM3946493", "GSM3946494", "GSM3946495", "GSM3946496", "GSM3946497", "GSM3946498", "GSM3946499", "GSM3946500", "GSM3946501", "GSM3946502", "GSM3946503", "GSM3946504", "GSM3946505"], "sample_count": 21, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "Deregulated immune signature orchestrated by FOXM1 impairs human diabetic wound healing", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE147890", "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=GSE147890", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE147890", "version": null, "note": "The datasets analyzed in this article are accessible to the public. The datasets were acquired from the Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/) database, and the accession numbers were GSE80178, GSE134431, GSE147890 and GSE23006.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed in this article are accessible to the public. The datasets were acquired from the Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/) database, and the accession numbers were GSE80178, GSE134431, GSE147890 and GSE23006.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4448280", "GSM4448281", "GSM4448282", "GSM4448283", "GSM4448284", "GSM4448285", "GSM4448286", "GSM4448287", "GSM4448288", "GSM4448289", "GSM4448290", "GSM4448291", "GSM4448292", "GSM4448293", "GSM4448294", "GSM4448295", "GSM4448296", "GSM4448297", "GSM4448298", "GSM4448299", "GSM4448300", "GSM4448301", "GSM4448302", "GSM4448303", "GSM4448304", "GSM4448305"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Transcriptomic characterization of the delayed wound healing response in a diabetic skin humanized mice model", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE23006", "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=GSE23006", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE23006", "version": null, "note": "The datasets analyzed in this article are accessible to the public. The datasets were acquired from the Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/) database, and the accession numbers were GSE80178, GSE134431, GSE147890 and GSE23006.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed in this article are accessible to the public. The datasets were acquired from the Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/) database, and the accession numbers were GSE80178, GSE134431, GSE147890 and GSE23006.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM567618", "GSM567619", "GSM567620", "GSM567621", "GSM567622", "GSM567623", "GSM567624", "GSM567625", "GSM567626", "GSM567627", "GSM567628", "GSM567629", "GSM567630", "GSM567631", "GSM567632", "GSM567633", "GSM567634", "GSM567635", "GSM567636", "GSM567637", "GSM567638", "GSM567639", "GSM567640", "GSM567641", "GSM567642", "GSM567643", "GSM567644", "GSM567645", "GSM567646", "GSM567647", "GSM567648", "GSM567649", "GSM567650", "GSM567651", "GSM567652", "GSM567653", "GSM567654", "GSM567655", "GSM567656", "GSM567657", "GSM567658", "GSM567659", "GSM567660", "GSM567661", "GSM567662", "GSM567663", "GSM567664", "GSM567665"], "sample_count": 48, "group_sizes": null, "group_sizes_basis": null, "platform": "1261", "taxon": "Mus musculus", "title": "Transcriptional profiling of a  wound healing process in skin and oral mucosa", "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:GSE80178", "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=GSE80178", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE80178", "version": null, "note": "The datasets analyzed in this article are accessible to the public. The datasets were acquired from the Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/) database, and the accession numbers were GSE80178, GSE134431, GSE147890 and GSE23006.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed in this article are accessible to the public. The datasets were acquired from the Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/) database, and the accession numbers were GSE80178, GSE134431, GSE147890 and GSE23006.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2114231", "GSM2114232", "GSM2114233", "GSM2114234", "GSM2114235", "GSM2114236", "GSM2114237", "GSM2114238", "GSM2114239", "GSM2114240", "GSM2114241", "GSM2114242"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "16686", "taxon": "Homo sapiens", "title": "Genomic Profiling of Diabetic Foot Ulcers Identifies miR-15b-5p as a Major Regulator that Leads to Suboptimal Inflammatory Response and Diminished DNA Repair Mechanisms", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE134431 not downloaded", "asset:data:geo:GSE134431 licence not read", "asset:data:geo:GSE147890 not downloaded", "asset:data:geo:GSE147890 licence not read", "asset:data:geo:GSE23006 not downloaded", "asset:data:geo:GSE23006 licence not read", "asset:data:geo:GSE80178 not downloaded", "asset:data:geo:GSE80178 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": "verbatim", "quote": "Hub genes were analyzed using three machine learning methods (LASSO, RF and SVM-RFE)."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"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": 0.8, "band": "high", "quote": "random Forest"}}, {"id": "method-4", "family": "machine_learning", "specific": "decision_tree", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "decision tree"}}], "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": ["GSE80178", "GSE134431", "GSE147890", "GSE23006"], "resolved_accessions": ["GSE80178", "GSE134431", "GSE147890", "GSE23006"], "statements": ["The datasets analyzed in this article are accessible to the public. The datasets were acquired from the Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/) database, and the accession numbers were GSE80178, GSE134431, GSE147890 and GSE23006."], "basis": "The paper names GSE80178, GSE134431, GSE147890, GSE23006 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:39228680", "data:geo:GSE134431"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE134431"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:30:16Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 11620, "completion_tokens": 2554, "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:39228680", "type": "paper", "label": "pmid:39228680"}, {"id": "source:pmid:39228680", "type": "manuscript", "label": "PMID 39228680 full text"}, {"id": "data:geo:GSE134431", "type": "dataset", "label": "GEO GSE134431"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39228680", "type": "paper", "label": "pmid:39228680"}, {"id": "source:pmid:39228680", "type": "manuscript", "label": "PMID 39228680 full text"}, {"id": "data:geo:GSE134431", "type": "dataset", "label": "GEO GSE134431"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39228680", "type": "extraction", "used": ["source:pmid:39228680"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE134431", "type": "accession_resolution", "used": ["data:geo:GSE134431"], "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:39228680", "parent_hash": "sha256:6c106de83cfd842aab969d73bef597c76e7c980d7800e57904461908af824064", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE134431 licence not read", "asset:data:geo:GSE134431 not downloaded", "asset:data:geo:GSE147890 licence not read", "asset:data:geo:GSE147890 not downloaded", "asset:data:geo:GSE23006 licence not read", "asset:data:geo:GSE23006 not downloaded", "asset:data:geo:GSE80178 licence not read", "asset:data:geo:GSE80178 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": 0.99, "evidence": ["mice models. Methods: GSE80178 and GSE134431 microarray datasets were fetched from the GEO database,", "nd (Figure 9A). Then, to verify this result, microarray data (GSE23006) was discovered which analyze", "(1d, 3d, 5d, 7d and 10d) were extracted from microarray dataset (GSE23006). n=3 at every different t"], "order_basis": "paper_text_order:550", "id": "assay:1"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["e, 6–8 weeks old) were procured. All C57BL/6 mice were raised under controlled environmental condit", ") with free access to food and water. C57/B6 mice were anaesthetized through intraperitoneal inject", "for external validation. For diabetic model, mice were induced through intraperitoneal injection wi", "to day 10 during skin wound healing process in mice skin wounds (Figure 9B). Our results and ext"], "order_basis": "paper_text_order:3859", "id": "assay:2"}, {"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": ["1; (I) TLR3; (J) TLR4. Validation of CTSH by RT-qPCR and Western Blot in Animal Models The expres", "healing process of wounds in wild-type mice. RT-qPCR results showed dynamic changes in CTSH expre", "pe or diabetic mice on day 5 was analyzed by RT-qPCR and Western blot. Our results showed that CT", "(Figure 9C-D).Figure 9Validation of CTSH by RT-qPCR and Western blot in animal models. (A) The e"], "order_basis": "paper_text_order:9566", "id": "assay:3"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["(J) TLR4. Validation of CTSH by RT-qPCR and Western Blot in Animal Models The expression of CTSH was", "ic mice on day 5 was analyzed by RT-qPCR and Western blot. Our results showed that CTSH expression was", "D).Figure 9Validation of CTSH by RT-qPCR and Western blot in animal models. (A) The expression of CTSH", "e on day 5 was analyzed by RT-qPCR (n=5) and Western blot (n=4). All results are expressed as means ±"], "order_basis": "paper_text_order:9579", "id": "assay:4"}, {"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": ["Hub genes were analyzed using three machine learning methods (LASSO, RF and SVM-RFE)."], "order_basis": "consumes_earlier_output", "id": "assay:5"}]}