Combined Use of Three Machine Learning Modeling Methods to Develop a Ten-Gene Signature for the Diagnosis of Ventilator-Associated Pneumonia.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32031163", "kind": "science-record", "revision": 9, "content_hash": "sha256:59f7d538be3d33c9dc31f3043788a0b35b82ba25123f553d66af5b7074afe612", "created_at": "2026-11-01T15:40:56Z", "updated_at": "2026-11-01T22:44:33Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Combined Use of Three Machine Learning Modeling Methods to Develop a Ten-Gene Signature for the Diagnosis of Ventilator-Associated Pneumonia.", "doi": "10.12659/MSM.919035", "pmid": "32031163", "authors": ["Yunfang Cai", "Wen Zhang", "Runze Zhang", "Xiaoying Cui", "Jun Fang"], "journal": "Medical science monitor : international medical journal of experimental and clinical research", "year": 2020, "abstract": "BACKGROUND This study aimed to use three modeling methods, logistic regression analysis, random forest analysis, and fully-connected neural network analysis, to develop a diagnostic gene signature for the diagnosis of ventilator-associated pneumonia (VAP). MATERIAL AND METHODS GSE30385 from the Gene Expression Omnibus (GEO) database identified differentially expressed genes (DEGs) associated with patients with VAP. Gene Ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment identified the molecular functions of the DEGs. The least absolute shrinkage and selection operator (LASSO) regression analysis algorithm was used to select key genes. Three modeling methods, including logistic regression analysis, random forest analysis, and fully-connected neural network analysis, also known as also known as the feed-forward multi-layer perceptron (MLP), were used to identify the diagnostic gene signature for patients with VAP. RESULTS Sixty-six DEGs were identified for patients who had VAP (VAP+) and who did not have VAP (VAP-). Ten essential or feature genes were identified. Upregulated genes included matrix metallopeptidase 8 (MMP8), arginase 1 (ARG1), haptoglobin (HP), interleukin 18 receptor 1 (IL18R1), and NLR family apoptosis inhibitory protein (NAIP). Down-regulated genes included complement factor D (CFD), pleckstrin homology-like domain family A member 2 (PHLDA2), plasminogen activator, urokinase (PLAU), laminin subunit beta 3 (LAMB3), and dual-specificity phosphatase 2 (DUSP2). Logistic regression, random forest, and MLP analysis showed receiver operating characteristic (ROC) curve area under the curve (AUC) values of 0.85, 0.86, and 0.87, respectively. CONCLUSIONS Logistic regression analysis, random forest analysis, and MLP analysis identified a ten-gene signature for the diagnosis of VAP.", "claims": [{"id": "claim-method", "statement": "The Linear Models for Microarray Data (limma) package in R [12] was used to screen the DEGs of the VAP+ and the VAP− groups.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32031163", "locator": "sections[5] \"Screening for differentially expressed genes (DEGs) for the VAP+ and VAP− patient groups\" paragraph 2", "quote": "The Linear Models for Microarray Data (limma) package in R [12] was used to screen the DEGs of the VAP+ and the VAP− groups."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Gene expression profiles were downloaded as raw data (CEL files) from the GSE30385 dataset [8] in the GEO database (http://www.ncbi.nlm.nih.gov/geo) [9]. The GPL201 [HG-Focus] Affymetrix Human HG-Focus Target Array served as the annotation platform. In this dataset, whole blood from 20 patient samples was obtained from patients with serious trauma, including ten patients with ventilator-associated pneumonia (VAP) (VAP+) and ten without VAP (VAP−).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32031163", "locator": "sections[3] \"Gene Expression Omnibus (GEO) database selection\" paragraph 2", "quote": "Gene expression profiles were downloaded as raw data (CEL files) from the GSE30385 dataset [8] in the GEO database (http://www.ncbi.nlm.nih.gov/geo) [9]. The GPL201 [HG-Focus] Affymetrix Human HG-Focus Target Array served as the annotation platform. In this dataset, whole blood from 20 patient samples was obtained from patients with serious trauma, including ten patients with ventilator-associated pneumonia (VAP) (VAP+) and ten without VAP (VAP−)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:32031163"], "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:GSE30385"], "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:GSE30385"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32031163", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.12659/MSM.919035", "sha256": "sha256:14a90d059f8b205f2a92f992e7cdf9dbe8d374c32e2acfd3f178fd5a152c85a4", "bytes": 42141, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.12659/MSM.919035", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7020762", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE30385", "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=GSE30385", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE30385", "version": null, "note": "Gene expression profiles were downloaded as raw data (CEL files) from the GSE30385 dataset [8] in the GEO database (http://www.ncbi.nlm.nih.gov/geo) [9]. The GPL201 [HG-Focus] Affymetrix Human HG-Focus Target Array served as the annotation platform. In this dataset, whole blood from 20 patient samples was obtained from patients with serious trauma, including ten patients with ventilator-associated pneumonia (VAP) (VAP+) and ten without VAP (VAP−).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression profiles were downloaded as raw data (CEL files) from the GSE30385 dataset [8] in the GEO database (http://www.ncbi.nlm.nih.gov/geo) [9]. The GPL201 [HG-Focus] Affymetrix Human HG-Focus Target Array served as the annotation platform. In this dataset, whole blood from 20 patient samples was obtained from patients with serious trauma, including ten patients with ventilator-associated pneumonia (VAP) (VAP+) and ten without VAP (VAP−).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM754022", "GSM754023", "GSM754024", "GSM754025", "GSM754026", "GSM754027", "GSM754028", "GSM754029", "GSM754030", "GSM754031", "GSM754032", "GSM754033", "GSM754034", "GSM754035", "GSM754036", "GSM754037", "GSM754038", "GSM754039", "GSM754040", "GSM754041"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "201", "taxon": "Homo sapiens", "title": "Developing a gene expression model for predicting ventilator-associated pneumonia in trauma patients: a pilot study.", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32031163:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:81e0e9dfb816223e5874b5b7040c896a8693885fcf518eff3cf7a327e1f799b4", "bytes": 1073, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#t2-medscimonit-26-e919035", "version": null, "note": "Details of the ten featured genes in ventilator-associated pneumonia (VAP).", "structure": {"pmcid": "PMC7020762", "section_index": 9, "section_title": "Screening for feature genes", "row_count": 11, "column_count": 5}, "table": {"label": "Table 2", "caption": "Details of the ten featured genes in ventilator-associated pneumonia (VAP).", "rows": [["Gene symbol", "Gene name", "log2-FC", "p-Value", "Regulation"], ["LTF", "Lactotransferrin", "1.051261502", "0.014733312", "Up"], ["MNDA", "Myeloid cell nuclear differentiation antigen", "0.959622573", "0.017834746", "Up"], ["FKBP5", "FK506 binding protein 5", "0.787232999", "0.013536848", "Up"], ["PDGFC", "Platelet derived growth factor C", "0.782415364", "0.00563081", "Up"], ["GADD45A", "Growth arrest and DNA damage inducible alpha", "0.724582865", "0.000672126", "Up"], ["ARHGDIA", "Rho GDP dissociation inhibitor alpha", "0.720167209", "0.033516623", "Up"], ["PPIB", "Peptidylprolyl isomerase B", "−0.608265883", "0.0035643", "Down"], ["RGS2", "Regulator of G protein signaling 2", "−0.745549324", "0.000658377", "Down"], ["KIF3B", "Kinesin family member 3B", "−0.746830664", "0.002775964", "Down"], ["CTSZ", "Cathepsin Z", "−0.862858489", "0.002942944", "Down"]], "row_count": 11, "column_count": 5, "numeric_cells": 24, "header_rows": 1, "locator": "section[17]/table-wrap[1]#t2-medscimonit-26-e919035"}}, {"id": "asset:table:pmid:32031163:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6474514955fdd8c0c17a2235227dbd2aa2590ae2058619c7ce45d525653666e5", "bytes": 1782, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#t1-medscimonit-26-e919035", "version": null, "note": "The top ten differentially expressed genes (DEGs) in ventilator-associated pneumonia (VAP).", "structure": {"pmcid": "PMC7020762", "section_index": 14, "section_title": "Identification of differentially expressed genes (DEGs) inVAP+ and VAP− patients", "row_count": 21, "column_count": 5}, "table": {"label": "Table 1", "caption": "The top ten differentially expressed genes (DEGs) in ventilator-associated pneumonia (VAP).", "rows": [["Gene symbol", "Gene name", "log2-FC", "p-Value", "Regulation"], ["MMP8", "Matrix metallopeptidase 8", "1.871450982", "0.002938895", "Up"], ["ARG1", "Arginase 1", "1.488811973", "0.003824453", "Up"], ["HP", "Haptoglobin", "1.411448445", "0.007541712", "Up"], ["IL18R1", "Interleukin 18 receptor 1", "1.156128987", "0.008158229", "Up"], ["NAIP", "NLR family apoptosis inhibitory protein", "1.095823284", "0.036770186", "Up"], ["LTF", "Lactotransferrin", "1.051261502", "0.014733312", "Up"], ["CYP1B1", "Cytochrome P450 family 1 subfamily B member 1", "0.982426681", "0.041859932", "Up"], ["DEFA4", "Defensin alpha 4", "0.979954402", "0.034299563", "Up"], ["MNDA", "Myeloid cell nuclear differentiation antigen", "0.959622573", "0.017834746", "Up"], ["ANXA3", "Annexin A3", "0.848970244", "0.019900178", "Up"], ["CTSZ", "Cathepsin Z", "−0.862858489", "0.002942944", "Down"], ["THBD", "Thrombomodulin", "−0.871430229", "0.009507344", "Down"], ["PPIF", "Peptidylprolyl isomerase F", "−0.872320694", "0.006172789", "Down"], ["SLPI", "Secretory leukocyte peptidase inhibitor", "−0.890979857", "0.001666654", "Down"], ["PI3", "Peptidase inhibitor 3", "−0.928381059", "9.68E–05", "Down"], ["DUSP2", "Dual-specificity phosphatase 2", "−0.961242077", "0.005718815", "Down"], ["LAMB3", "Laminin subunit beta 3", "−1.010787763", "0.000192664", "Down"], ["PLAU", "Plasminogen activator, urokinase", "−1.063036567", "0.032298508", "Down"], ["PHLDA2", "Pleckstrin homology like domain family A member 2", "−1.070158334", "0.001626576", "Down"], ["CFD", "Complement factor D", "−1.242598099", "0.013684517", "Down"]], "row_count": 21, "column_count": 5, "numeric_cells": 50, "header_rows": 1, "locator": "section[14]/table-wrap[1]#t1-medscimonit-26-e919035"}}, {"id": "asset:table:pmid:32031163:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:81e0e9dfb816223e5874b5b7040c896a8693885fcf518eff3cf7a327e1f799b4", "bytes": 1073, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#t2-medscimonit-26-e919035", "version": null, "note": "Details of the ten featured genes in ventilator-associated pneumonia (VAP).", "structure": {"pmcid": "PMC7020762", "section_index": 17, "section_title": "Screening for feature genes", "row_count": 11, "column_count": 5}, "table": {"label": "Table 2", "caption": "Details of the ten featured genes in ventilator-associated pneumonia (VAP).", "rows": [["Gene symbol", "Gene name", "log2-FC", "p-Value", "Regulation"], ["LTF", "Lactotransferrin", "1.051261502", "0.014733312", "Up"], ["MNDA", "Myeloid cell nuclear differentiation antigen", "0.959622573", "0.017834746", "Up"], ["FKBP5", "FK506 binding protein 5", "0.787232999", "0.013536848", "Up"], ["PDGFC", "Platelet derived growth factor C", "0.782415364", "0.00563081", "Up"], ["GADD45A", "Growth arrest and DNA damage inducible alpha", "0.724582865", "0.000672126", "Up"], ["ARHGDIA", "Rho GDP dissociation inhibitor alpha", "0.720167209", "0.033516623", "Up"], ["PPIB", "Peptidylprolyl isomerase B", "−0.608265883", "0.0035643", "Down"], ["RGS2", "Regulator of G protein signaling 2", "−0.745549324", "0.000658377", "Down"], ["KIF3B", "Kinesin family member 3B", "−0.746830664", "0.002775964", "Down"], ["CTSZ", "Cathepsin Z", "−0.862858489", "0.002942944", "Down"]], "row_count": 11, "column_count": 5, "numeric_cells": 24, "header_rows": 1, "locator": "section[17]/table-wrap[1]#t2-medscimonit-26-e919035"}}, {"id": "asset:table:pmid:32031163:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f193a28ab80858796f02120ff4f31c273b79247586960de8b8c3bac187fa6510", "bytes": 406, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#t3-medscimonit-26-e919035", "version": null, "note": "The accuracy and area under the curve (AUC) of the three predicted models in ventilator-associated pneumonia (VAP).", "structure": {"pmcid": "PMC7020762", "section_index": 18, "section_title": "Building a gene signature exhibiting diagnostic value using three algorithms", "row_count": 4, "column_count": 3}, "table": {"label": "Table 3", "caption": "The accuracy and area under the curve (AUC) of the three predicted models in ventilator-associated pneumonia (VAP).", "rows": [["Metrics", "Accuracy", "AUC"], ["Logistic regression", "0.75", "0.85"], ["Random forest", "0.80", "0.86"], ["MLP", "0.90", "0.87"]], "row_count": 4, "column_count": 3, "numeric_cells": 6, "header_rows": 1, "locator": "section[18]/table-wrap[1]#t3-medscimonit-26-e919035"}}], "gaps": ["asset:data:geo:GSE30385 not downloaded", "asset:data:geo:GSE30385 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": "The Linear Models for Microarray Data (limma) package in R [12] was used to screen the DEGs of the VAP+ and the VAP− groups."}}, {"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": 0.8, "band": "high", "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": {}, "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": 0.7, "band": "medium", "quote": "pathway enrichment"}}], "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": ["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": ["GSE30385"], "resolved_accessions": ["GSE30385"], "statements": ["Gene expression profiles were downloaded as raw data (CEL files) from the GSE30385 dataset [8] in the GEO database (http://www.ncbi.nlm.nih.gov/geo) [9]. The GPL201 [HG-Focus] Affymetrix Human HG-Focus Target Array served as the annotation platform. In this dataset, whole blood from 20 patient samples was obtained from patients with serious trauma, including ten patients with ventilator-associated pneumonia (VAP) (VAP+) and ten without VAP (VAP−)."], "basis": "The paper names GSE30385 in Gene Expression Omnibus (GEO) database 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:32031163", "data:geo:GSE30385", "asset:table:pmid:32031163:1", "asset:table:pmid:32031163:2", "asset:table:pmid:32031163:3", "asset:table:pmid:32031163:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE30385"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:18:03Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 32400, "completion_tokens": 980, "cached_tokens": 784}}, "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:32031163", "type": "paper", "label": "pmid:32031163"}, {"id": "source:pmid:32031163", "type": "manuscript", "label": "PMID 32031163 full text"}, {"id": "data:geo:GSE30385", "type": "dataset", "label": "GEO GSE30385"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32031163", "type": "paper", "label": "pmid:32031163"}, {"id": "source:pmid:32031163", "type": "manuscript", "label": "PMID 32031163 full text"}, {"id": "data:geo:GSE30385", "type": "dataset", "label": "GEO GSE30385"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32031163", "type": "extraction", "used": ["source:pmid:32031163"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE30385", "type": "accession_resolution", "used": ["data:geo:GSE30385"], "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:32031163", "parent_hash": "sha256:7a521c9b1bf9f731b3ed90f0ea96db9cd355bd322c09ecf0fc62019726bbb67e", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE30385 licence not read", "asset:data:geo:GSE30385 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": "clinical_cohort", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ially expressed genes (DEGs) associated with patients with VAP. Gene Ontology (GO) and the Kyoto Encycl", "o identify the diagnostic gene signature for patients with VAP. RESULTS Sixty-six DEGs were identified", ". RESULTS Sixty-six DEGs were identified for patients who had VAP (VAP+) and who did not have VAP (VAP"], "order_basis": "paper_text_order:497", "id": "assay:1"}, {"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["eukin 18 receptor 1 (IL18R1), and NLR family apoptosis inhibitory protein (NAIP). Down-regulated ge", "eukin 18 receptor 1 (IL18R1), and NLR family apoptosis inhibitory protein (NAIP). The top down-regu"], "order_basis": "paper_text_order:1361", "id": "assay:2"}, {"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": ["nd VAP− patient groups The Linear Models for Microarray Data (limma) package in R [12] was used to s"], "order_basis": "paper_text_order:2581", "id": "assay:3"}, {"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": ["The Linear Models for Microarray Data (limma) package in R [12] was used to screen the DEGs of the VAP+ and the VAP− groups."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]}