Tsbrowse: an interactive browser for ancestral recombination graphs.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40650922", "kind": "science-record", "revision": 1, "content_hash": "sha256:c5ae22a4c2f6402166533a03fe07b9389f00dd4ec72b6c12432860b724c50596", "created_at": "2026-11-01T20:30:44Z", "updated_at": "2026-11-01T20:30:44Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Tsbrowse: an interactive browser for ancestral recombination graphs.", "doi": "10.1093/bioinformatics/btaf393", "pmid": "40650922", "authors": ["Savita Karthikeyan", "Ben Jeffery", "Duncan Mbuli-Robertson", "Jerome Kelleher"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "SUMMARY: Ancestral recombination graphs (ARGs) represent the interwoven paths of genetic ancestry of a set of recombining sequences. The ability to capture the evolutionary history of samples makes ARGs valuable in a wide range of applications in population and statistical genetics. ARG-based approaches are increasingly becoming a part of genetic data analysis pipelines due to breakthroughs enabling ARG inference at biobank-scale. However, there is a lack of visualization tools, which are crucial for validating inferences and generating hypotheses. We present tsbrowse, an open-source, web-based Python application for the interactive visualization of the fundamental building blocks of ARGs, i.e. nodes, edges and mutations. We demonstrate the application of tsbrowse to various data sources and scenarios, and highlight its key features of browsability along the genome, user interactivity, and scalability to very large sample sizes.\nAVAILABILITY AND IMPLEMENTATION: Tsbrowse is installed as a Python package from PyPI (https://pypi.org/project/tsbrowse/), while a development version is maintained at https://github.com/tskit-dev/tsbrowse. Documentation is available at https://tskit.dev/tsbrowse/docs/. Source code is archived on Zenodo with DOI, https://doi.org/10.5281/zenodo.15683039.", "claims": [{"id": "claim-data-access", "statement": "The data underlying this article are available in https://github.com/savitakartik/tsbrowse-paper with DOI: https://doi.org/10.5281/zenodo.16615378", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40650922", "locator": "sections[14] \"Data availability\" paragraph 2", "quote": "The data underlying this article are available in https://github.com/savitakartik/tsbrowse-paper with DOI: https://doi.org/10.5281/zenodo.16615378"}], "state": "complete"}, {"id": "claim-target-result", "statement": "We present tsbrowse, an open-source, web-based Python application for the interactive visualization of the fundamental building blocks of ARGs, i.e. nodes, edges and mutations.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40650922", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We present tsbrowse, an open-source, web-based Python application for the interactive visualization of the fundamental building blocks of ARGs, i.e. nodes, edges and mutations."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "We present tsbrowse, an open-source, web-based Python application for the interactive visualization of the fundamental building blocks of ARGs, i.e. nodes, edges and mutations.", "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:40650922"], "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:40650922", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf393", "sha256": "sha256:b1415d9508a6f28c109582d9610f17277c77cee72662219f15f2c5d86bb168a3", "bytes": 24623, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf393", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12342996", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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 (not named), 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": ["The data underlying this article are available in https://github.com/savitakartik/tsbrowse-paper with DOI: https://doi.org/10.5281/zenodo.16615378"], "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:40650922"], "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": "2026-11-01T19:56:38Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 7987, "completion_tokens": 983, "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:40650922", "type": "paper", "label": "pmid:40650922"}, {"id": "source:pmid:40650922", "type": "manuscript", "label": "PMID 40650922 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40650922", "type": "paper", "label": "pmid:40650922"}, {"id": "source:pmid:40650922", "type": "manuscript", "label": "PMID 40650922 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40650922", "type": "extraction", "used": ["source:pmid:40650922"], "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": null, "parent_hash": null, "fork_of": null, "generation": 0}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}