Machine learning combining multi-omics data and network algorithms identifies adrenocortical carcinoma prognostic biomarkers.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38028548", "kind": "science-record", "revision": 5, "content_hash": "sha256:1caf5fe458705262fef3df1dd538618dae24e1fb39a1c5c90c2fbe35e65616bb", "created_at": "2026-11-01T19:02:57Z", "updated_at": "2026-11-01T22:53:12Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Machine learning combining multi-omics data and network algorithms identifies adrenocortical carcinoma prognostic biomarkers.", "doi": "10.3389/fmolb.2023.1258902", "pmid": "38028548", "authors": ["Roberto Martin-Hernandez", "Sergio Espeso-Gil", "Clara Domingo", "Pablo Latorre", "Sergi Hervas", "Jose Ramon Hernandez Mora", "Ekaterina Kotelnikova"], "journal": "Frontiers in molecular biosciences", "year": 2023, "abstract": "Background: Rare endocrine cancers such as Adrenocortical Carcinoma (ACC) present a serious diagnostic and prognostication challenge. The knowledge about ACC pathogenesis is incomplete, and patients have limited therapeutic options. Identification of molecular drivers and effective biomarkers is required for timely diagnosis of the disease and stratify patients to offer the most beneficial treatments. In this study we demonstrate how machine learning methods integrating multi-omics data, in combination with system biology tools, can contribute to the identification of new prognostic biomarkers for ACC. Methods: ACC gene expression and DNA methylation datasets were downloaded from the Xena Browser (GDC TCGA Adrenocortical Carcinoma cohort). A highly correlated multi-omics signature discriminating groups of samples was identified with the data integration analysis for biomarker discovery using latent components (DIABLO) method. Additional regulators of the identified signature were discovered using Clarivate CBDD (Computational Biology for Drug Discovery) network propagation and hidden nodes algorithms on a curated network of molecular interactions (MetaBase™). The discriminative power of the multi-omics signature and their regulators was delineated by training a random forest classifier using 55 samples, by employing a 10-fold cross validation with five iterations. The prognostic value of the identified biomarkers was further assessed on an external ACC dataset obtained from GEO (GSE49280) using the Kaplan-Meier estimator method. An optimal prognostic signature was finally derived using the stepwise Akaike Information Criterion (AIC) that allowed categorization of samples into high and low-risk groups. Results: A multi-omics signature including genes, micro RNA's and methylation sites was generated. Systems biology tools identified additional genes regulating the features included in the multi-omics signature. RNA-seq, miRNA-seq and DNA methylation sets of features revealed a high power to classify patients from stages I-II and stages III-IV, outperforming previously identified prognostic biomarkers. Using an independent dataset, associations of the genes included in the signature with Overall Survival (OS) data demonstrated that patients with differential expression levels of 8 genes and 4 micro RNA's showed a statistically significant decrease in OS. We also found an independent prognostic signature for ACC with potential use in clinical practice, combining 9-gene/micro RNA features, that successfully predicted high-risk ACC cancer patients. Conclusion: Machine learning and integrative analysis of multi-omics data, in combination with Clarivate CBDD systems biology tools, identified a set of biomarkers with high prognostic value for ACC disease. Multi-omics data is a promising resource for the identification of drivers and new prognostic biomarkers in rare diseases that could be used in clinical practice.", "claims": [{"id": "claim-method", "statement": "Univariate association of the features with overall survival (OS) was estimated by log-rank test and the Kaplan-Meier method.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38028548", "locator": "sections[7] \"Survival analysis and construction of a prognostic model\" paragraph 2", "quote": "Univariate association of the features with overall survival (OS) was estimated by log-rank test and the Kaplan-Meier method."}], "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 author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38028548", "locator": "sections[17] \"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 author."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A nine-feature multi-omics signature comprising five genes and four microRNAs stratified ACC patients into equally sized high- and low-risk groups, with high-risk patients showing significantly decreased overall survival in the external dataset.", "kind": "quantitative", "target": {"value": 95.0, "unit": "per cent", "tolerance": null, "source": "As shown in Figure 5, high-risk patients showed significant decreased OS as compared to low-risk ACC patients (p-value = 2.1 × 10−4; HR = 1.13; 95% CI 0,04–0.46), highlighting the utility of the 9 features as an independent prognostic factor of poor prognosis for ACC."}, "evidence": [{"asset": "source:pmid:38028548", "locator": "sections[14] \"Survival analysis and construction of a prognostic signature\" paragraph 5", "quote": "A total of 9 features involving 5 genes and 4 micro RNAs showed the optimal AIC value and were subsequently used to establish a risk score using the formula: OptMultiSig risk score = [1.958 x EXP GATA4]+[-22.285 x EXP N4BP2L1]+[1.087 x EXP KCNJ14]+[3.157 x EXP SNORD1143]+[2.271 x EXP UBE2S]+[20.908 x EXP microRNA 615]+[-1.173 x EXP microRNA 1179]+[-19.938 x EXP microRNA 217]+[-20.976 x EXP microRNA 5690]."}, {"asset": "source:pmid:38028548", "locator": "sections[14] \"Survival analysis and construction of a prognostic signature\" paragraph 5", "quote": "According to the median OptMultiSig risk score of 165.575, we classified patients into low and high-risk groups comprising 22 samples each."}, {"asset": "source:pmid:38028548", "locator": "sections[14] \"Survival analysis and construction of a prognostic signature\" paragraph 5", "quote": "As shown in Figure 5, high-risk patients showed significant decreased OS as compared to low-risk ACC patients (p-value = 2.1 × 10−4; HR = 1.13; 95% CI 0,04–0.46), highlighting the utility of the 9 features as an independent prognostic factor of poor prognosis for ACC."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "A nine-feature multi-omics signature comprising five genes and four microRNAs stratified ACC patients into equally sized high- and low-risk groups, with high-risk patients showing significantly decreased overall survival in the external dataset.", "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:38028548"], "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:GSE49280"], "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:GSE49280"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38028548", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fmolb.2023.1258902", "sha256": "sha256:241d641e708a714de38af1ef2f601966413a93a55cb437c937e65f8f784602b9", "bytes": 42999, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fmolb.2023.1258902", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10658191", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE49280", "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=GSE49280", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE49280", "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 author.", "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 author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1196383", "GSM1196384", "GSM1196385", "GSM1196386", "GSM1196387", "GSM1196388", "GSM1196389", "GSM1196390", "GSM1196391", "GSM1196392", "GSM1196393", "GSM1196394", "GSM1196395", "GSM1196396", "GSM1196397", "GSM1196398", "GSM1196399", "GSM1196400", "GSM1196401", "GSM1196402", "GSM1196403", "GSM1196404", "GSM1196405", "GSM1196406", "GSM1196407", "GSM1196408", "GSM1196409", "GSM1196410", "GSM1196411", "GSM1196412", "GSM1196413", "GSM1196414", "GSM1196415", "GSM1196416", "GSM1196417", "GSM1196418", "GSM1196419", "GSM1196420", "GSM1196421", "GSM1196422", "GSM1196423", "GSM1196424", "GSM1196425", "GSM1196426", "GSM1196427", "GSM1196428", "GSM1196429", "GSM1196430", "GSM1196431", "GSM1196432", "GSM1196433", "GSM1196434", "GSM1196435", "GSM1196436", "GSM1196437", "GSM1196438", "GSM1196439", "GSM1196440", "GSM1196441", "GSM1196442", "GSM1196443", "GSM1196444", "GSM1196445", "GSM1196446", "GSM1196447", "GSM1196448", "GSM1196449", "GSM1196450", "GSM1196451", "GSM1196452", "GSM1196453", "GSM1196454", "GSM1196455", "GSM1196456", "GSM1196457", "GSM1196458", "GSM1196459", "GSM1196460", "GSM1196461", "GSM1196462", "GSM1196463", "GSM1196464", "GSM1196465", "GSM1196466", "GSM1196467", "GSM1196468", "GSM1196469", "GSM1196470", "GSM1196471", "GSM1196472", "GSM1196473", "GSM1196474", "GSM1196475", "GSM1196476", "GSM1196477", "GSM1196480", "GSM1196481", "GSM1196482", "GSM1196483", "GSM1196484", "GSM1196485", "GSM1196486", "GSM1196487", "GSM1196488", "GSM1196489", "GSM1196490", "GSM1196491", "GSM1196492", "GSM1196493", "GSM1196494", "GSM1196495", "GSM1196496", "GSM1196497", "GSM1196498", "GSM1196499", "GSM1196500", "GSM1196501", "GSM1196502", "GSM1196503", "GSM1196504", "GSM1196505", "GSM1196506", "GSM1196507", "GSM1196508", "GSM1196509", "GSM1196510", "GSM1196511", "GSM1196512", "GSM1196513", "GSM1196514", "GSM1196515", "GSM1196516", "GSM1196517", "GSM1196518", "GSM1196519", "GSM1196520", "GSM1196521", "GSM1196522", "GSM1196523", "GSM1196524", "GSM1196525", "GSM1196526", "GSM1196527", "GSM1196528", "GSM1196529", "GSM1196530", "GSM1196531", "GSM1196532", "GSM1196533", "GSM1196534", "GSM1196535", "GSM1196536", "GSM1196537", "GSM1196538", "GSM1196539", "GSM1196540", "GSM1196541", "GSM1196542", "GSM1196543", "GSM1196544", "GSM1196545", "GSM1196546", "GSM1196547", "GSM1196548", "GSM1196549", "GSM1196550", "GSM1196551", "GSM1196552", "GSM1196553", "GSM1196554", "GSM1196555", "GSM1196556", "GSM1196557", "GSM1196558", "GSM1196559", "GSM1196560", "GSM1196561", "GSM1196562", "GSM1196563", "GSM1196564", "GSM1196565", "GSM1196566", "GSM1196567", "GSM1196568", "GSM1196569", "GSM1196570", "GSM1196571", "GSM1196572", "GSM1196573", "GSM1196574", "GSM1196575", "GSM1196576", "GSM1196577", "GSM1196578", "GSM1196579", "GSM1196580", "GSM1196581", "GSM1196582", "GSM1196583", "GSM1196584", "GSM1196585", "GSM1196586", "GSM1196587", "GSM1196588", "GSM1196589", "GSM1196590", "GSM1196591", "GSM1196592", "GSM1196593", "GSM1196594", "GSM1196595", "GSM1196596", "GSM1196597", "GSM1196598", "GSM1196599", "GSM1196600", "GSM1196601", "GSM1196602", "GSM1196603", "GSM1196604", "GSM1196605", "GSM1196606", "GSM1196607", "GSM1196608", "GSM1196609", "GSM1196610", "GSM1196611", "GSM1196612", "GSM1196613", "GSM1196614", "GSM1196615", "GSM1196616", "GSM1196617", "GSM1196618", "GSM1196619", "GSM1196620", "GSM1196621", "GSM1196622", "GSM1196623", "GSM1196624", "GSM1196625", "GSM1196626", "GSM1196627", "GSM1196628", "GSM1196629", "GSM1196630", "GSM1196631", "GSM1196632", "GSM1262431", "GSM1262432", "GSM1262433", "GSM1262434", "GSM1262435", "GSM1262436", "GSM1262437", "GSM1262438", "GSM1262439", "GSM1262440", "GSM1262441", "GSM1262442", "GSM1262443", "GSM1262444", "GSM1262445", "GSM1262446", "GSM1262447", "GSM1262448", "GSM1262449", "GSM1262450", "GSM1262451", "GSM1262452", "GSM1262453", "GSM1262454", "GSM1262455", "GSM1262456", "GSM1262457", "GSM1262458", "GSM1262459", "GSM1262460", "GSM1262461", "GSM1262462", "GSM1262463", "GSM1262464", "GSM1262465", "GSM1262466", "GSM1262467", "GSM1262468", "GSM1262469", "GSM1262470", "GSM1262471", "GSM1262472", "GSM1262473", "GSM1262474", "GSM1262475", "GSM1262476", "GSM1262477", "GSM1262478", "GSM1262479", "GSM1262480", "GSM1262481", "GSM1262482", "GSM1262483", "GSM1262484", "GSM1262485", "GSM1262486", "GSM1262487", "GSM1262488", "GSM1262489", "GSM1262490", "GSM1262491", "GSM1262492", "GSM1262493", "GSM1262494", "GSM1262495", "GSM1262496", "GSM1262497", "GSM1262498", "GSM1262499", "GSM1262500", "GSM1262501", "GSM1262502", "GSM1262503", "GSM1262504", "GSM1262505", "GSM1262506"], "sample_count": 324, "group_sizes": null, "group_sizes_basis": null, "platform": "8490;17913;16686;13135;8887;11154", "taxon": "Homo sapiens", "title": "Integrated genomic analyses of adrenocortical tumors (SNP array, DNA methylation, mRNA and miRNA expression).", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE49280 not downloaded", "asset:data:geo:GSE49280 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Univariate association of the features with overall survival (OS) was estimated by log-rank test and the Kaplan-Meier method."}}, {"id": "method-2", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-3", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {"cross_validation_folds": "samples, by employing a 10-fold cross validation with five iterations"}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "random forest"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "logrank_test", "expected_value": 95.0, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}, {"id": "target-published-estimate-hazard-ratio", "claim_id": "claim-target-result", "operation": "logrank_test", "expected_value": 1.13, "unit": "hazard ratio", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}, {"id": "target-published-estimate-p-value", "claim_id": "claim-target-result", "operation": "logrank_test", "expected_value": 2.1, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE49280"], "resolved_accessions": ["GSE49280"], "statements": ["The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author."], "basis": "The paper names GSE49280 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:38028548", "data:geo:GSE49280"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE49280"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:00:49Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 10647, "completion_tokens": 2225, "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:38028548", "type": "paper", "label": "pmid:38028548"}, {"id": "source:pmid:38028548", "type": "manuscript", "label": "PMID 38028548 full text"}, {"id": "data:geo:GSE49280", "type": "dataset", "label": "GEO GSE49280"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38028548", "type": "paper", "label": "pmid:38028548"}, {"id": "source:pmid:38028548", "type": "manuscript", "label": "PMID 38028548 full text"}, {"id": "data:geo:GSE49280", "type": "dataset", "label": "GEO GSE49280"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38028548", "type": "extraction", "used": ["source:pmid:38028548"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE49280", "type": "accession_resolution", "used": ["data:geo:GSE49280"], "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:38028548", "parent_hash": "sha256:04ad59f679206a0dd1a86b30d72ae4add52f6862cbd24e5d51d60e1b7cee073a", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE49280 licence not read", "asset:data:geo:GSE49280 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": 0.93, "evidence": ["tures included in the multi-omics signature. RNA-seq, miRNA-seq and DNA methylation sets of featu"], "order_basis": "paper_text_order:2024", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Univariate association of the features with overall survival (OS) was estimated by log-rank test and the Kaplan-Meier method."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}