The role of graph topology in the performance of biomedical Knowledge Graph Completion models.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41056421", "kind": "science-record", "revision": 2, "content_hash": "sha256:b59e3bbaf949201dc76aed112f341ab13fa991dc9b393fb9b8ef4f7325e0ea13", "created_at": "2026-11-01T20:31:07Z", "updated_at": "2026-11-01T21:35:51Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "The role of graph topology in the performance of biomedical Knowledge Graph Completion models.", "doi": "10.1093/bioinformatics/btaf547", "pmid": "41056421", "authors": ["Alberto Cattaneo", "Stephen Bonner", "Thomas Martynec", "Edward Morrissey", "Carlo Luschi", "Ian P Barrett", "Daniel Justus"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "MOTIVATION: Knowledge Graph Completion has been increasingly adopted as a useful method for helping address several tasks in biomedical research, such as drug repurposing or drug-target identification. To that end, a variety of datasets and Knowledge Graph Embedding models have been proposed over the years. However, little is known about the properties that render a dataset, and associated modelling choices, useful for a given task. Moreover, even though theoretical properties of Knowledge Graph Embedding models are well understood, their practical utility in this field remains controversial.\nRESULTS: In this work, we conduct a comprehensive investigation into the topological properties of publicly available biomedical Knowledge Graphs and establish links to the accuracy observed in real-world tasks. By releasing all model predictions and a new suite of analysis tools we invite the community to build upon our work and continue improving the understanding of these crucial applications.\nAVAILABILITY AND IMPLEMENTATION: The code used to perform experiments and analyze results in this article as well as all experimental data is available at https://github.com/graphcore-research/kg-topology-toolbox/tree/main/the_role_of_graph_topology_paper and archived on Zenodo, at https://doi.org/10.5281/zenodo.12097376.", "claims": [{"id": "claim-method", "statement": "Indeed, for a given triple, we observe a strong positive correlation between model accuracy and the in-degree of the tail entity as well as a strong negative correlation between model accuracy and the out-degree of the head entity", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41056421", "locator": "sections[13] \"5.2 Effect of topological properties on model accuracy\" paragraph 6", "quote": "Indeed, for a given triple, we observe a strong positive correlation between model accuracy and the in-degree of the tail entity as well as a strong negative correlation between model accuracy and the out-degree of the head entity"}], "state": "complete"}, {"id": "claim-data-access", "statement": "All models have been trained on six publicly available datasets, as detailed in the text. The code used to perform experiments and analyse results in this article, together with all experimental data generated, is available at https://github.com/graphcore-research/kg-topology-toolbox/tree/main/the_role_of_graph_topology_paper and archived on Zenodo, at https://doi.org/10.5281/zenodo.12097376.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41056421", "locator": "sections[24] \"Data availability\" paragraph 2", "quote": "All models have been trained on six publicly available datasets, as detailed in the text. The code used to perform experiments and analyse results in this article, together with all experimental data generated, is available at https://github.com/graphcore-research/kg-topology-toolbox/tree/main/the_role_of_graph_topology_paper and archived on Zenodo, at https://doi.org/10.5281/zenodo.12097376."}], "state": "complete"}, {"id": "claim-target-result", "statement": "On the contrary, models trained on Hetionet consistently perform better, even when using the same embedding size.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41056421", "locator": "sections[18] \"5.4 Case study: effect of additional training data\" paragraph 4", "quote": "On the contrary, models trained on Hetionet consistently perform better, even when using the same embedding size."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "On the contrary, models trained on Hetionet consistently perform better, even when using the same embedding size.", "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:41056421"], "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:41056421", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf547", "sha256": "sha256:3fa070935b9ce0d1f55ac8b49e01f85ca5de1255b991cd23a8d3f61f30a6bfe9", "bytes": 41791, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf547", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12560816", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "correlation", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Indeed, for a given triple, we observe a strong positive correlation between model accuracy and the in-degree of the tail entity as well as a strong negative correlation between model accuracy and the out-degree of the head entity"}}], "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": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (correlation), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["All models have been trained on six publicly available datasets, as detailed in the text. The code used to perform experiments and analyse results in this article, together with all experimental data generated, is available at https://github.com/graphcore-research/kg-topology-toolbox/tree/main/the_role_of_graph_topology_paper and archived on Zenodo, at https://doi.org/10.5281/zenodo.12097376."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:41056421"], "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": "2026-11-01T20:02:38Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 10823, "completion_tokens": 1593, "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:41056421", "type": "paper", "label": "pmid:41056421"}, {"id": "source:pmid:41056421", "type": "manuscript", "label": "PMID 41056421 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41056421", "type": "paper", "label": "pmid:41056421"}, {"id": "source:pmid:41056421", "type": "manuscript", "label": "PMID 41056421 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41056421", "type": "extraction", "used": ["source:pmid:41056421"], "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:41056421", "parent_hash": "sha256:7c44b2a26b14918048a322492ae7d6683f0704816d4e4903d42a5b606ec2c8ad", "fork_of": null, "generation": 1}, "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"]}