Ensemble-GNN: federated ensemble learning with graph neural networks for disease module discovery and classification.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37988152", "kind": "science-record", "revision": 3, "content_hash": "sha256:2decd2b611305277795d3c37012be5b7e107abaef3e48b3b6e02007c90329bea", "created_at": "2026-11-01T19:02:54Z", "updated_at": "2026-11-01T22:10:42Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Ensemble-GNN: federated ensemble learning with graph neural networks for disease module discovery and classification.", "doi": "10.1093/bioinformatics/btad703", "pmid": "37988152", "authors": ["Bastian Pfeifer", "Hryhorii Chereda", "Roman Martin", "Anna Saranti", "Sandra Clemens", "Anne-Christin Hauschild", "Tim Beißbarth", "Andreas Holzinger", "Dominik Heider"], "journal": "Bioinformatics (Oxford, England)", "year": 2023, "abstract": "SUMMARY: Federated learning enables collaboration in medicine, where data is scattered across multiple centers without the need to aggregate the data in a central cloud. While, in general, machine learning models can be applied to a wide range of data types, graph neural networks (GNNs) are particularly developed for graphs, which are very common in the biomedical domain. For instance, a patient can be represented by a protein-protein interaction (PPI) network where the nodes contain the patient-specific omics features. Here, we present our Ensemble-GNN software package, which can be used to deploy federated, ensemble-based GNNs in Python. Ensemble-GNN allows to quickly build predictive models utilizing PPI networks consisting of various node features such as gene expression and/or DNA methylation. We exemplary show the results from a public dataset of 981 patients and 8469 genes from the Cancer Genome Atlas (TCGA).\nAVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/pievos101/Ensemble-GNN, and the data at Zenodo (DOI: 10.5281/zenodo.8305122).", "claims": [{"id": "claim-method", "statement": "We assessed the performance of our algorithm using 10-fold cross-validation (see Table 1).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37988152", "locator": "sections[6] \"3.1 Performance of Ensemble-GNN in nonfederated case\" paragraph 2", "quote": "We assessed the performance of our algorithm using 10-fold cross-validation (see Table 1)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The Python package Ensemble-GNN, including comprehensive documentation of its usage is freely available from our GitHub repository (https://github.com/pievos101/Ensemble-GNN) as well as the data at Zenodo (DOI: 10.5281/zenodo.8305122).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37988152", "locator": "sections[11] \"Data availability\" paragraph 2", "quote": "The Python package Ensemble-GNN, including comprehensive documentation of its usage is freely available from our GitHub repository (https://github.com/pievos101/Ensemble-GNN) as well as the data at Zenodo (DOI: 10.5281/zenodo.8305122)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Mean performance values for Ensemble-GNN using the ChebNet architecture were higher, 0.85 and 0.87 respectively.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37988152", "locator": "sections[7] \"3.2 Performance of Ensemble-GNN in federated case\" paragraph 3", "quote": "Mean performance values for Ensemble-GNN using the ChebNet architecture were higher, 0.85 and 0.87 respectively."}, {"asset": "source:pmid:37988152", "locator": "sections[6] \"3.1 Performance of Ensemble-GNN in nonfederated case\" paragraph 2", "quote": "Ensemble-GNN employing ChebNet as a base learner achieved as good classification performance as RF (see Table 1)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Mean performance values for Ensemble-GNN using the ChebNet architecture were higher, 0.85 and 0.87 respectively.", "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:37988152"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37988152", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btad703", "sha256": "sha256:1f05035f02819bc91b9eb2006283fa8658083e04cbfbbc19fae447aeb57662ed", "bytes": 14047, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btad703", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10684359", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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"}}, {"id": "method-2", "family": null, "specific": null, "label": "10-fold cross-validation", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We assessed the performance of our algorithm using 10-fold cross-validation (see Table 1)."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The Python package Ensemble-GNN, including comprehensive documentation of its usage is freely available from our GitHub repository (https://github.com/pievos101/Ensemble-GNN) as well as the data at Zenodo (DOI: 10.5281/zenodo.8305122)."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:37988152"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:59:46Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 5038, "completion_tokens": 1196, "cached_tokens": 256}}, "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:37988152", "type": "paper", "label": "pmid:37988152"}, {"id": "source:pmid:37988152", "type": "manuscript", "label": "PMID 37988152 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37988152", "type": "paper", "label": "pmid:37988152"}, {"id": "source:pmid:37988152", "type": "manuscript", "label": "PMID 37988152 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37988152", "type": "extraction", "used": ["source:pmid:37988152"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:37988152", "parent_hash": "sha256:986757d3e81e9bb80fbeacb01103e986a655908eb920a01e04992815789bfbc0", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "analysis_only", "id": "assay:1"}]}