Whole genome sequencing data of greater burdock (Arctium lappa) naturalized in the United States of America.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40226200", "kind": "science-record", "revision": 1, "content_hash": "sha256:265f28c36c820ae57fd522fd48709f9eba0ad1850a6a05235dcc8eba7ae42c2d", "created_at": "2026-11-01T20:30:23Z", "updated_at": "2026-11-01T20:30:23Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Whole genome sequencing data of greater burdock (Arctium lappa) naturalized in the United States of America.", "doi": "10.1016/j.dib.2025.111508", "pmid": "40226200", "authors": ["Danae Kala Rodriguez Bardaji", "Girish Kumar", "Samantha Tran", "Gabriella Fedus", "Michael A Savka", "Dawn Carter", "André O Hudson"], "journal": "Data in brief", "year": 2025, "abstract": "This dataset comprises whole genome sequencing burdock (Arctium lappa) naturalized in a residential yard in Rochester, New York, USA. Total DNA was extracted from a leaf sample and processed using the Illumina Nextera XT DNA library preparation kit. Sequencing on the NextSeq 2000 platform produced 127.4 GB of raw data, yielding 125.8 GB of high-quality reads after filtering, with an average genome coverage of 75x. The genome was assembled de novo into 792,817 contigs, achieving a total genome length of 1,075,454,921 base pairs with a GC content of 37.03 %. Scaffolding against a Chinese A. lappa reference genome improved genome completeness from 49.1 % to 94.93 %, successfully recovering the majority of protein-coding genes. Variant analysis identified approximately 20.8 million Single Nucleotide Polymorphisms (SNPs) and 1.3 million indels, including functionally significant mutations. The Internal Transcribed Spacer 2 (ITS2) ribosomal region was isolated and compared with global references, revealing significant genetic differentiation between the U.S.A and Chinese populations. This comprehensive genomic dataset has been deposited in publicly accessible repositories, including National Center for Biotechnology Information (NC and Zenodo. The sequencing of this sample provides a valuable resource for comparative genomics, population genetics, and investigations into bioactive compounds with antimicrobial properties, supporting agricultural and pharmaceutical applications. Direct access to the dataset is available at 10.5281/zenodo.14607136.", "claims": [{"id": "claim-data-access", "statement": "ZenodoDataset for Arctium lappa genome (Original data).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40226200", "locator": "sections[17] \"Data Availability\" paragraph 2", "quote": "ZenodoDataset for Arctium lappa genome (Original data)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The genome was assembled de novo into 792,817 contigs, achieving a total genome length of 1,075,454,921 base pairs with a GC content of 37.03 %.", "kind": "quantitative", "target": {"value": 37.03, "unit": "per cent", "tolerance": null, "source": "The genome was assembled de novo into 792,817 contigs, achieving a total genome length of 1,075,454,921 base pairs with a GC content of 37.03 %."}, "evidence": [{"asset": "source:pmid:40226200", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The genome was assembled de novo into 792,817 contigs, achieving a total genome length of 1,075,454,921 base pairs with a GC content of 37.03 %."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The genome was assembled de novo into 792,817 contigs, achieving a total genome length of 1,075,454,921 base pairs with a GC content of 37.03 %.", "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:40226200"], "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:PRJNA1167729"], "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:PRJNA1167729"], "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:40226200", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2025.111508", "sha256": "sha256:7ef94b943fbe90c8cb0785d0980c4dc20b96e2cbe3bfd3c40dad7c05513354d1", "bytes": 15270, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2025.111508", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11986600", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PRJNA1167729", "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=PRJNA1167729", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PRJNA1167729", "version": null, "note": "ZenodoDataset for Arctium lappa genome (Original data).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "ZenodoDataset for Arctium lappa genome (Original data).", "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:PRJNA1167729 not downloaded", "asset:data:geo:PRJNA1167729 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": null, "expected_value": 37.03, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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": ["PRJNA1167729"], "resolved_accessions": [], "statements": ["ZenodoDataset for Arctium lappa genome (Original data)."], "basis": "The paper names PRJNA1167729, 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:40226200", "data:geo:PRJNA1167729"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PRJNA1167729"]}, "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": "2026-11-01T19:50:02Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 5462, "completion_tokens": 1106, "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:40226200", "type": "paper", "label": "pmid:40226200"}, {"id": "source:pmid:40226200", "type": "manuscript", "label": "PMID 40226200 full text"}, {"id": "data:geo:PRJNA1167729", "type": "dataset", "label": "GEO PRJNA1167729"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40226200", "type": "paper", "label": "pmid:40226200"}, {"id": "source:pmid:40226200", "type": "manuscript", "label": "PMID 40226200 full text"}, {"id": "data:geo:PRJNA1167729", "type": "dataset", "label": "GEO PRJNA1167729"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40226200", "type": "extraction", "used": ["source:pmid:40226200"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PRJNA1167729", "type": "accession_resolution", "used": ["data:geo:PRJNA1167729"], "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:PRJNA1167729 licence not read", "asset:data:geo:PRJNA1167729 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"]}