Complete genome sequence data describing the biosynthetic potential of kanosamine and bacilysin in Bacillus subtilis AMFE023/7 from Thai fermented fish (Pla Ra).

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40718143", "kind": "science-record", "revision": 2, "content_hash": "sha256:31f544f0113ba7f7272a020215a8cc670e883045b871243d736032893804cfd1", "created_at": "2026-11-01T20:30:48Z", "updated_at": "2026-11-01T21:35:31Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Complete genome sequence data describing the biosynthetic potential of kanosamine and bacilysin in Bacillus subtilis AMFE023/7 from Thai fermented fish (Pla Ra).", "doi": "10.1016/j.dib.2025.111860", "pmid": "40718143", "authors": ["Montri Yasawong", "Thunwarat Songngamsuk", "Manassanan Phatcharaharikarn", "Parweenuch Santaweesuk", "Prapimpun Wongchitrat", "Prasit Palittapongarnpim", "Wongwarut Boonyanugomol", "Arunee Thong-On", "Sasalux Kaewbutra", "Kamolchanok Rukseree"], "journal": "Data in brief", "year": 2025, "abstract": "Bacillus subtilis AMFE023/7, a Gram-positive bacterium with aciditolerans and halotolerant properties, was isolated from Pla Ra, a traditional fermented fish product popular in Thai cuisine. The sample was obtained from a local morning market in Amnat Charoen, Thailand. The complete genome was assembled through the integration of complementary sequencing platforms, specifically Illumina and PacBio. The genome spans 4132,147 base pairs with a GC content of 43.87 %. Comparison with the reference strain B. subtilis ATCC 6051T using digital DNA-DNA hybridisation confirmed the identity of the isolate with 89.3 % similarity. The genome analysis revealed gene clusters responsible for producing potentially useful compounds such as kanosamine and bacilysin, which have antimicrobial properties. This genome sequence provides valuable data for researchers studying microbial communities in fermented foods, those conducting comparative genomics, and scientists searching for new bioactive compounds. The complete genome sequence data has been made publicly available through NCBI under BioProject accession number PRJNA1253417.", "claims": [{"id": "claim-method", "statement": "The taxonomic placement was determined via digital DNA-DNA hybridisation (dDDH) analysis using the Type (Strain) Genome Server (TYGS) [18].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40718143", "locator": "sections[9] \"Taxonomic identification of strains\" paragraph 2", "quote": "The taxonomic placement was determined via digital DNA-DNA hybridisation (dDDH) analysis using the Type (Strain) Genome Server (TYGS) [18]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Original dataComplete genome sequence data describing the biosynthetic potential of kanosamine and bacilysin in Bacillus subtilis AMFE023/7 from Thai fermented fish (Pla Ra) (Original data) (GenBank).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40718143", "locator": "sections[17] \"Data Availability\" paragraph 2", "quote": "Original dataComplete genome sequence data describing the biosynthetic potential of kanosamine and bacilysin in Bacillus subtilis AMFE023/7 from Thai fermented fish (Pla Ra) (Original data) (GenBank)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Digital DNA-DNA hybridisation confirmed AMFE023/7 as a B. subtilis species with 89.3% similarity to the type strain B. subtilis ATCC 6051T.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40718143", "locator": "sections[4] \"Data Description\" paragraph 6", "quote": "Genomic relatedness assessment through digital DNA-DNA hybridisation (dDDH) revealed a value of 89.3 % between strain AMFE023/7 and the type strain B. subtilis ATCC 6051T, substantially exceeding the 70 % threshold for species delineation [1] and thereby confirming the taxonomic assignment of AMFE023/7 as a B. subtilis species."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Digital DNA-DNA hybridisation confirmed AMFE023/7 as a B. subtilis species with 89.3% similarity to the type strain B. subtilis ATCC 6051T.", "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:40718143"], "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:PRJNA1253417"], "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:PRJNA1253417"], "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:40718143", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2025.111860", "sha256": "sha256:c9e58ab248c9699fbc48c7bf70493e7a5191f54b12431419355746e73e68be4f", "bytes": 20495, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2025.111860", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12296536", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PRJNA1253417", "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=PRJNA1253417", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PRJNA1253417", "version": null, "note": "Original dataComplete genome sequence data describing the biosynthetic potential of kanosamine and bacilysin in Bacillus subtilis AMFE023/7 from Thai fermented fish (Pla Ra) (Original data) (GenBank).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Original dataComplete genome sequence data describing the biosynthetic potential of kanosamine and bacilysin in Bacillus subtilis AMFE023/7 from Thai fermented fish (Pla Ra) (Original data) (GenBank).", "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:PRJNA1253417 not downloaded", "asset:data:geo:PRJNA1253417 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "digital DNA-DNA hybridisation (dDDH) analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The taxonomic placement was determined via digital DNA-DNA hybridisation (dDDH) analysis using the Type (Strain) Genome Server (TYGS) [18]."}}], "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 (digital DNA-DNA hybridisation (dDDH) analysis), 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": ["PRJNA1253417"], "resolved_accessions": [], "statements": ["Original dataComplete genome sequence data describing the biosynthetic potential of kanosamine and bacilysin in Bacillus subtilis AMFE023/7 from Thai fermented fish (Pla Ra) (Original data) (GenBank)."], "basis": "The paper names PRJNA1253417, 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:40718143", "data:geo:PRJNA1253417"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PRJNA1253417"]}, "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": "2026-11-01T19:57:47Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 6911, "completion_tokens": 1639, "cached_tokens": 256}}, "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:40718143", "type": "paper", "label": "pmid:40718143"}, {"id": "source:pmid:40718143", "type": "manuscript", "label": "PMID 40718143 full text"}, {"id": "data:geo:PRJNA1253417", "type": "dataset", "label": "GEO PRJNA1253417"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40718143", "type": "paper", "label": "pmid:40718143"}, {"id": "source:pmid:40718143", "type": "manuscript", "label": "PMID 40718143 full text"}, {"id": "data:geo:PRJNA1253417", "type": "dataset", "label": "GEO PRJNA1253417"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40718143", "type": "extraction", "used": ["source:pmid:40718143"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PRJNA1253417", "type": "accession_resolution", "used": ["data:geo:PRJNA1253417"], "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:40718143", "parent_hash": "sha256:b28a857a201d16fd3df07991d9da2e3a7bf70e6b1805d5749d205b4e77a28512", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:PRJNA1253417 licence not read", "asset:data:geo:PRJNA1253417 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_unresolved"]}