RISK: a next-generation tool for biological network annotation and visualization.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41423796", "kind": "science-record", "revision": 3, "content_hash": "sha256:b31ae1d9fb9ce9a6ce5daaf9be22803c8eafd7d41ca6440d2897fd1fda06f111", "created_at": "2026-11-01T20:31:25Z", "updated_at": "2026-11-01T22:15:11Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "RISK: a next-generation tool for biological network annotation and visualization.", "doi": "10.1093/bioinformatics/btaf669", "pmid": "41423796", "authors": ["Ira Horecka", "Hannes Röst"], "journal": "Bioinformatics (Oxford, England)", "year": 2026, "abstract": "SUMMARY: Analyzing biological networks demands scalable annotation tools, yet existing methods fall short in clustering power, statistical flexibility, and broad data compatibility. We introduce Regional Inference of Significant Kinships (RISK), a next-generation tool that overcomes these challenges by integrating community detection algorithms, rigorous overrepresentation analysis, and a modular architecture that supports diverse network types. RISK identifies biologically coherent relationships within networks and generates publication-ready visualizations, as demonstrated by its ability to resolve compact functional modules in Saccharomyces cerevisiae protein-protein interaction and genetic interaction networks. Its application to a high-energy physics citation network reveals structured relationships among research subfields, highlighting its versatility beyond biological systems. As biological and interdisciplinary networks increase in size and complexity, RISK's scalability and adaptability make it a powerful solution for modern network analysis.\nAVAILABILITY AND IMPLEMENTATION: RISK is compatible with Python 3.8 or later, supports all major operating systems, and can be installed via pip. The software is open source under the GPLv3 license on GitHub (https://github.com/riskportal/risk) and archived on Zenodo (https://doi.org/10.5281/zenodo.17257418). Documentation and a step-by-step Jupyter notebook tutorial are available at https://github.com/riskportal/risk-docs.", "claims": [{"id": "claim-method", "statement": "RISK’s chi-squared test scaled to networks with 500 000 edges (250 000 nodes), whereas SAFE’s hypergeometric method experienced memory limitations beyond 50 000 edges (Fig. 8, available as supplementary data at Bioinformatics online).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41423796", "locator": "sections[9] \"3.3 Computational performance and scalability\" paragraph 3", "quote": "RISK’s chi-squared test scaled to networks with 500 000 edges (250 000 nodes), whereas SAFE’s hypergeometric method experienced memory limitations beyond 50 000 edges (Fig. 8, available as supplementary data at Bioinformatics online)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data supporting this study are available in publicly accessible repositories. The RISK Documentation repository (https://github.com/riskportal/risk-docs) provides documentation and a step-by-step Jupyter notebook tutorial for using the RISK software with the Saccharomyces cerevisiae protein–protein interaction network. The RISK Publication repository (https://github.com/riskportal/risk-publication) includes processed datasets, analysis scripts, and workflows for generating all figures presented in this study. Please contact the corresponding author for further inquiries regarding the data or analysis methods.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41423796", "locator": "sections[16] \"Data availability\" paragraph 2", "quote": "All data supporting this study are available in publicly accessible repositories. The RISK Documentation repository (https://github.com/riskportal/risk-docs) provides documentation and a step-by-step Jupyter notebook tutorial for using the RISK software with the Saccharomyces cerevisiae protein–protein interaction network. The RISK Publication repository (https://github.com/riskportal/risk-publication) includes processed datasets, analysis scripts, and workflows for generating all figures presented in this study. Please contact the corresponding author for further inquiries regarding the data or analysis methods."}], "state": "complete"}, {"id": "claim-target-result", "statement": "RISK’s chi-squared test scaled to networks with 500 000 edges (250 000 nodes), whereas SAFE’s hypergeometric method experienced memory limitations beyond 50 000 edges.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41423796", "locator": "sections[9] \"3.3 Computational performance and scalability\" paragraph 3", "quote": "RISK’s chi-squared test scaled to networks with 500 000 edges (250 000 nodes), whereas SAFE’s hypergeometric method experienced memory limitations beyond 50 000 edges (Fig. 8, available as supplementary data at Bioinformatics online)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "RISK’s chi-squared test scaled to networks with 500 000 edges (250 000 nodes), whereas SAFE’s hypergeometric method experienced memory limitations beyond 50 000 edges.", "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:41423796"], "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:41423796", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf669", "sha256": "sha256:570e3f847eb115baaac604d83d853930b31e968562f04fbecffe9f78775fd084", "bytes": 22001, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf669", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12766918", "source": "europe_pmc_fulltext", "coverage": "whole_body", "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": "chi-squared test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "RISK’s chi-squared test scaled to networks with 500 000 edges (250 000 nodes), whereas SAFE’s hypergeometric method experienced memory limitations beyond 50 000 edges (Fig. 8, available as supplementary data at Bioinformatics online)."}}], "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": ["All data supporting this study are available in publicly accessible repositories. The RISK Documentation repository (https://github.com/riskportal/risk-docs) provides documentation and a step-by-step Jupyter notebook tutorial for using the RISK software with the Saccharomyces cerevisiae protein–protein interaction network. The RISK Publication repository (https://github.com/riskportal/risk-publication) includes processed datasets, analysis scripts, and workflows for generating all figures presented in this study. Please contact the corresponding author for further inquiries regarding the data or analysis methods."], "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:41423796"], "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": "2026-11-01T20:08:29Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 6857, "completion_tokens": 1353, "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:41423796", "type": "paper", "label": "pmid:41423796"}, {"id": "source:pmid:41423796", "type": "manuscript", "label": "PMID 41423796 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41423796", "type": "paper", "label": "pmid:41423796"}, {"id": "source:pmid:41423796", "type": "manuscript", "label": "PMID 41423796 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41423796", "type": "extraction", "used": ["source:pmid:41423796"], "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:41423796", "parent_hash": "sha256:f9555f268271d25e3d66ea74060ed0db7675738439a95305949b470d470fce2a", "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"}]}