SVbyEye: a visual tool to characterize structural variation among whole-genome assemblies.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40478668", "kind": "science-record", "revision": 1, "content_hash": "sha256:5c3154f9a9301af666b039223c9bf4493e10bda481c97dd5e09caff3f4a8d5e8", "created_at": "2026-11-01T20:30:35Z", "updated_at": "2026-11-01T20:30:35Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "SVbyEye: a visual tool to characterize structural variation among whole-genome assemblies.", "doi": "10.1093/bioinformatics/btaf332", "pmid": "40478668", "authors": ["David Porubsky", "Xavi Guitart", "DongAhn Yoo", "Philip C Dishuck", "William T Harvey", "Evan E Eichler"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "MOTIVATION: We are now in the era of being able to routinely generate highly contiguous (near telomere-to-telomere) genome assemblies of human and nonhuman species. Complex structural variation and regions of rapid evolutionary turnover are being discovered for the first time. Thus, efficient and informative visualization tools are needed to evaluate and directly observe structural differences between two or more genomes.\nRESULTS: We developed SVbyEye, an open-source R package to visualize and annotate sequence-to-sequence alignments along with various functionalities to process these alignments. The tool facilitates the characterization of complex structural variants in the context of sequence homology helping resolve the mechanisms underlying their formation.\nAVAILABILITY AND IMPLEMENTATION: SVbyEye is available on GitHub (https://github.com/daewoooo/SVbyEye) and via Zenodo (https://doi.org/10.5281/zenodo.15303553).", "claims": [{"id": "claim-data-access", "statement": "The phased genome assembly for human sample HG01457 used in this study is available via NCBI at https://www.ncbi.nlm.nih.gov and can be accessed with the accession number PRJEB76276 (Logsdon et al., 2024).\nThe phased genome assembly for chimpanzee sample AG18354 used in this study is available via GenBank Nucleotide Database at https://www.ncbi.nlm.nih.gov/genbank/ and can be accessed with the accession number GCA_028858775.2 (Yoo et al. 2025).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40478668", "locator": "sections[12] \"Data availability\" paragraphs 1-3", "quote": "The phased genome assembly for human sample HG01457 used in this study is available via NCBI at https://www.ncbi.nlm.nih.gov and can be accessed with the accession number PRJEB76276 (Logsdon et al., 2024).\nThe phased genome assembly for chimpanzee sample AG18354 used in this study is available via GenBank Nucleotide Database at https://www.ncbi.nlm.nih.gov/genbank/ and can be accessed with the accession number GCA_028858775.2 (Yoo et al. 2025)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We developed SVbyEye, an open-source R package to visualize and annotate sequence-to-sequence alignments along with various functionalities to process these alignments.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40478668", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We developed SVbyEye, an open-source R package to visualize and annotate sequence-to-sequence alignments along with various functionalities to process these alignments."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "We developed SVbyEye, an open-source R package to visualize and annotate sequence-to-sequence alignments along with various functionalities to process these alignments.", "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:40478668"], "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_unresolved", "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:PRJEB76276"], "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:PRJEB76276"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_unresolved"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40478668", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf332", "sha256": "sha256:0aeb51cdf6fbb43454726e0f5320f9480838850a2af8e8011221a73eaa8f8ef3", "bytes": 17313, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf332", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12198750", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PRJEB76276", "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=PRJEB76276", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PRJEB76276", "version": null, "note": "The phased genome assembly for human sample HG01457 used in this study is available via NCBI at https://www.ncbi.nlm.nih.gov and can be accessed with the accession number PRJEB76276 (Logsdon et al., 2024).\nThe phased genome assembly for chimpanzee sample AG18354 used in this study is available via GenBank Nucleotide Database at https://www.ncbi.nlm.nih.gov/genbank/ and can be accessed with the accession number GCA_028858775.2 (Yoo et al. 2025).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The phased genome assembly for human sample HG01457 used in this study is available via NCBI at https://www.ncbi.nlm.nih.gov and can be accessed with the accession number PRJEB76276 (Logsdon et al., 2024).\nThe phased genome assembly for chimpanzee sample AG18354 used in this study is available via GenBank Nucleotide Database at https://www.ncbi.nlm.nih.gov/genbank/ and can be accessed with the accession number GCA_028858775.2 (Yoo et al. 2025).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-11-01T20:16:20Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PRJEB76276 not downloaded", "asset:data:geo:PRJEB76276 licence not read"]}, "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": ["PRJEB76276"], "resolved_accessions": [], "statements": ["The phased genome assembly for human sample HG01457 used in this study is available via NCBI at https://www.ncbi.nlm.nih.gov and can be accessed with the accession number PRJEB76276 (Logsdon et al., 2024).\nThe phased genome assembly for chimpanzee sample AG18354 used in this study is available via GenBank Nucleotide Database at https://www.ncbi.nlm.nih.gov/genbank/ and can be accessed with the accession number GCA_028858775.2 (Yoo et al. 2025)."], "basis": "The paper names PRJEB76276, but the accession does not resolve in the repository (not_in_ncbi_bioproject), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40478668", "data:geo:PRJEB76276"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PRJEB76276"]}, "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": "2026-11-01T19:53:50Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 5859, "completion_tokens": 1109, "cached_tokens": 128}}, "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:40478668", "type": "paper", "label": "pmid:40478668"}, {"id": "source:pmid:40478668", "type": "manuscript", "label": "PMID 40478668 full text"}, {"id": "data:geo:PRJEB76276", "type": "dataset", "label": "GEO PRJEB76276"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40478668", "type": "paper", "label": "pmid:40478668"}, {"id": "source:pmid:40478668", "type": "manuscript", "label": "PMID 40478668 full text"}, {"id": "data:geo:PRJEB76276", "type": "dataset", "label": "GEO PRJEB76276"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40478668", "type": "extraction", "used": ["source:pmid:40478668"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PRJEB76276", "type": "accession_resolution", "used": ["data:geo:PRJEB76276"], "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": ["asset:data:geo:PRJEB76276 licence not read", "asset:data:geo:PRJEB76276 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_unresolved"]}