Multi-modal transcriptomics: integrating machine learning and convolutional neural networks to identify immune biomarkers in atherosclerosis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39660117", "kind": "science-record", "revision": 4, "content_hash": "sha256:2e5e88f562da0940ffbdf3b902773d928d47b643e0257d3d745688f19cd57c53", "created_at": "2026-11-01T20:29:57Z", "updated_at": "2026-11-01T22:55:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Multi-modal transcriptomics: integrating machine learning and convolutional neural networks to identify immune biomarkers in atherosclerosis.", "doi": "10.3389/fcvm.2024.1397407", "pmid": "39660117", "authors": ["Haiqing Chen", "Haotian Lai", "Hao Chi", "Wei Fan", "Jinbang Huang", "Shengke Zhang", "Chenglu Jiang", "Lai Jiang", "Qingwen Hu", "Xiuben Yan", "Yemeng Chen", "Jieying Zhang", "Guanhu Yang", "Bin Liao", "Juyi Wan"], "journal": "Frontiers in cardiovascular medicine", "year": 2024, "abstract": "Background: Atherosclerosis, a complex chronic vascular disorder with multifactorial etiology, stands as the primary culprit behind consequential cardiovascular events, imposing a substantial societal and economic burden. Nevertheless, our current understanding of its pathogenesis remains imprecise. In this investigation, our objective is to establish computational models elucidating molecular-level markers associated with atherosclerosis. This endeavor involves the integration of advanced machine learning techniques and comprehensive bioinformatics analyses.\nMaterials and methods: Our analysis incorporated data from three publicly available the Gene Expression Omnibus (GEO) datasets: GSE100927 (104 samples, 30,558 genes), which includes atherosclerotic lesions and control arteries from carotid, femoral, and infra-popliteal arteries of deceased organ donors; GSE43292 (64 samples, 23,307 genes), consisting of paired carotid endarterectomy samples from 32 hypertensive patients, comparing atheroma plaques and intact tissues; and GSE159677 (30,498 single cells, 33,538 genes), examining single-cell transcriptomes of calcified atherosclerotic core plaques and adjacent carotid artery tissues from patients undergoing carotid endarterectomy. Utilizing single-cell sequencing, highly variable atherosclerotic monocyte subpopulations were systematically identified. We analyzed cellular communication patterns with temporal dynamics. The bioinformatics approach Weighted Gene Co-expression Network Analysis (WGCNA) identified key modules, constructing a Protein-Protein Interaction (PPI) network from module-associated genes. Three machine-learning models derived marker genes, formulated through logistic regression and validated via convolutional neural network(CNN) modeling. Subtypes were clustered based on Gene Set Variation Analysis (GSVA) scores, validated through immunoassays.\nResults: Three pivotal atherosclerosis-associated genes-CD36, S100A10, CSNK1A1-were unveiled, offering valuable clinical insights. Profiling based on these genes delineated two distinct isoforms: C2 demonstrated potent microbicidal activity, while C1 engaged in inflammation regulation, tissue repair, and immune homeostasis. Molecular docking analyses explored therapeutic potential for Estradiol, Zidovudine, Indinavir, and Dronabinol for clinical applications.\nConclusion: This study introduces three signature genes for atherosclerosis, shaping a novel paradigm for investigating clinical immunological medications. It distinguishes the high biocidal C2 subtype from the inflammation-modulating C1 subtype, utilizing identified signature gene as crucial targets.", "claims": [{"id": "claim-method", "statement": "One-way analysis of variance (ANOVA) and t-tests were employed to explore potential significant differences in atherosclerosis model genes, functional enrichment results, immune cell infiltration, and immune function scores among the patient groups.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39660117", "locator": "sections[14] \"Statistical analysis\" paragraph 2", "quote": "One-way analysis of variance (ANOVA) and t-tests were employed to explore potential significant differences in atherosclerosis model genes, functional enrichment results, immune cell infiltration, and immune function scores among the patient groups."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39660117", "locator": "sections[31] \"Data availability statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Three pivotal atherosclerosis-associated genes—CD36, S100A10, CSNK1A1—were unveiled, offering valuable clinical insights.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39660117", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Three pivotal atherosclerosis-associated genes—CD36, S100A10, CSNK1A1—were unveiled, offering valuable clinical insights."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Three pivotal atherosclerosis-associated genes—CD36, S100A10, CSNK1A1—were unveiled, offering valuable clinical insights.", "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:39660117"], "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:GSE100927"], "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:GSE100927"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39660117", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fcvm.2024.1397407", "sha256": "sha256:78482dd0af7df78f9c476211e8994f6fb414f94910b3276aa65c4020ef0d0426", "bytes": 70772, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fcvm.2024.1397407", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11628520", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE100927", "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=GSE100927", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE100927", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2696609", "GSM2696610", "GSM2696611", "GSM2696612", "GSM2696613", "GSM2696614", "GSM2696615", "GSM2696616", "GSM2696617", "GSM2696618", "GSM2696619", "GSM2696620", "GSM2696621", "GSM2696622", "GSM2696623", "GSM2696624", "GSM2696625", "GSM2696626", "GSM2696627", "GSM2696628", "GSM2696629", "GSM2696630", "GSM2696631", "GSM2696632", "GSM2696633", "GSM2696634", "GSM2696635", "GSM2696636", "GSM2696637", "GSM2696638", "GSM2696639", "GSM2696640", "GSM2696641", "GSM2696642", "GSM2696643", "GSM2696644", "GSM2696645", "GSM2696646", "GSM2696647", "GSM2696648", "GSM2696649", "GSM2696650", "GSM2696651", "GSM2696652", "GSM2696653", "GSM2696654", "GSM2696655", "GSM2696656", "GSM2696657", "GSM2696658", "GSM2696659", "GSM2696660", "GSM2696661", "GSM2696662", "GSM2696663", "GSM2696664", "GSM2696665", "GSM2696666", "GSM2696667", "GSM2696668", "GSM2696669", "GSM2696670", "GSM2696671", "GSM2696672", "GSM2696673", "GSM2696674", "GSM2696675", "GSM2696676", "GSM2696677", "GSM2696678", "GSM2696679", "GSM2696680", "GSM2696681", "GSM2696682", "GSM2696683", "GSM2696684", "GSM2696685", "GSM2696686", "GSM2696687", "GSM2696688", "GSM2696689", "GSM2696690", "GSM2696691", "GSM2696692", "GSM2696693", "GSM2696694", "GSM2696695", "GSM2696696", "GSM2696697", "GSM2696698", "GSM2696699", "GSM2696700", "GSM2696701", "GSM2696702", "GSM2696703", "GSM2696704", "GSM2696705", "GSM2696706", "GSM2696707", "GSM2696708", "GSM2696709", "GSM2696710", "GSM2696711", "GSM2696712"], "sample_count": 104, "group_sizes": null, "group_sizes_basis": null, "platform": "17077", "taxon": "Homo sapiens", "title": "Atherosclerotic and control peripheral artery gene expression", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE159677", "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=GSE159677", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE159677", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4837523", "GSM4837524", "GSM4837525", "GSM4837526", "GSM4837527", "GSM4837528"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "Decoding the transcriptome of calcified atherosclerotic plaque at single-cell resolution", "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:GSE43292", "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=GSE43292", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE43292", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1060117", "GSM1060118", "GSM1060119", "GSM1060120", "GSM1060121", "GSM1060122", "GSM1060123", "GSM1060124", "GSM1060125", "GSM1060126", "GSM1060127", "GSM1060128", "GSM1060129", "GSM1060130", "GSM1060131", "GSM1060132", "GSM1060133", "GSM1060134", "GSM1060135", "GSM1060136", "GSM1060137", "GSM1060138", "GSM1060139", "GSM1060140", "GSM1060141", "GSM1060142", "GSM1060143", "GSM1060144", "GSM1060145", "GSM1060146", "GSM1060147", "GSM1060148", "GSM1060149", "GSM1060150", "GSM1060151", "GSM1060152", "GSM1060153", "GSM1060154", "GSM1060155", "GSM1060156", "GSM1060157", "GSM1060158", "GSM1060159", "GSM1060160", "GSM1060161", "GSM1060162", "GSM1060163", "GSM1060164", "GSM1060165", "GSM1060166", "GSM1060167", "GSM1060168", "GSM1060169", "GSM1060170", "GSM1060171", "GSM1060172", "GSM1060173", "GSM1060174", "GSM1060175", "GSM1060176", "GSM1060177", "GSM1060178", "GSM1060179", "GSM1060180"], "sample_count": 64, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Genome-wide expression study of human carotid atheroma", "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:GSE100927 not downloaded", "asset:data:geo:GSE100927 licence not read", "asset:data:geo:GSE159677 not downloaded", "asset:data:geo:GSE159677 licence not read", "asset:data:geo:GSE43292 not downloaded", "asset:data:geo:GSE43292 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "One-way analysis of variance (ANOVA) and t-tests were employed to explore potential significant differences in atherosclerosis model genes, functional enrichment results, immune cell infiltration, and immune function scores among the patient 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": "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-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": "clustering", "specific": "kmeans", "label": "Clustering", "dsl_operations": ["kmeans_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "k-means"}}, {"id": "method-6", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "Protein-Protein Interaction"}}], "targets": [], "gaps": []}, "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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE100927", "GSE43292", "GSE159677"], "resolved_accessions": ["GSE100927", "GSE43292", "GSE159677"], "statements": ["The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors."], "basis": "The paper names GSE100927, GSE43292, GSE159677 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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:39660117", "data:geo:GSE100927"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE100927"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:41:34Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15655, "completion_tokens": 2321, "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:39660117", "type": "paper", "label": "pmid:39660117"}, {"id": "source:pmid:39660117", "type": "manuscript", "label": "PMID 39660117 full text"}, {"id": "data:geo:GSE100927", "type": "dataset", "label": "GEO GSE100927"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39660117", "type": "paper", "label": "pmid:39660117"}, {"id": "source:pmid:39660117", "type": "manuscript", "label": "PMID 39660117 full text"}, {"id": "data:geo:GSE100927", "type": "dataset", "label": "GEO GSE100927"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39660117", "type": "extraction", "used": ["source:pmid:39660117"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE100927", "type": "accession_resolution", "used": ["data:geo:GSE100927"], "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:39660117", "parent_hash": "sha256:70984a7dab0cc78249a9988c64b3876abaddec2a11786a30bd6cd8e090a8f6e6", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE100927 licence not read", "asset:data:geo:GSE100927 not downloaded", "asset:data:geo:GSE159677 licence not read", "asset:data:geo:GSE159677 not downloaded", "asset:data:geo:GSE43292 licence not read", "asset:data:geo:GSE43292 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Multi-modal transcriptomics: integrating machine learning and convolutio", "g. Supplementary Figure S2Quality control of transcriptome data. (A) boxplot of intergroup batch effect", "cells, 33,538 genes), examining single-cell transcriptomes of calcified atherosclerotic core plaques an", "dataset. This dataset comprises single-cell RNA-seq data derived from three atherosclerotic core"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "data_generation", "definition_id": "scrna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "unsupported", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["he GSE159677 dataset. This dataset comprises single-cell RNA-seq data derived from three atherosclerotic core", "al Supplementary Figure S1Quality control of scRNA-seq data (A) Expression of scRNA-seq data before", "control of scRNA-seq data (A) Expression of scRNA-seq data before quality control. (A) Each point", "e total UMIs in each cell; (B) Expression of scRNA-seq data after quality control; (C) UMIs vs. sca"], "order_basis": "paper_text_order:3790", "id": "assay:2"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["One-way analysis of variance (ANOVA) and t-tests were employed to explore potential significant differences in atherosclerosis model genes, functional enrichment results, immune cell infiltration, and immune function scores among the patient groups."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]}