Whole genome sequence data of Bacillus australimaris strain B28A, isolated from Marine Water in India.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34235237", "kind": "science-record", "revision": 5, "content_hash": "sha256:35c8098822a761470c8e1a25b1ebefe7cdfc703f3337a0a6bba7b7c7b17518c4", "created_at": "2026-11-01T15:41:42Z", "updated_at": "2026-11-01T18:56:02Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Whole genome sequence data of Bacillus australimaris strain B28A, isolated from Marine Water in India.", "doi": "10.1016/j.dib.2021.107240", "pmid": "34235237", "authors": ["Wael Ali Mohammed Hadi", "Boby T Edwin", "Ananthakrishnan Jayakumaran Nair"], "journal": "Data in brief", "year": 2021, "abstract": "Bacillus genus members are dominant in the Eastern Arabian Sea and are known for producing many industrial enzymes. Bacillus australimaris B28A, isolated from seawater, had an enzymatic activity. Here, the whole genome sequence of Bacillus australimaris B28A is reported. The 3,766,107-bp genome, with a GC content of 41.6%, comprised 3936 protein-coding genes, seven ribosomal RNA, and 75 transfer RNA. Several bioactive secondary metabolite genes in the genome, including surfactin, lichenysin, bacillibactin, bacilysin, paenilamicin, fengycin, and carotenoid, were identified using antiSMASH. The 1396 proteins were predicted using RAST, including asparaginase enzyme: an anticancer enzyme. Sequence data have been deposited in the DDBJ/ENA/GenBank database under the accession number JAGQFH000000000. The version described in this paper is JAGQFH000000000.1. The BioProject ID in the GenBank database is PRJNA670955. The raw data is publicly available at \"https://www.ncbi.nlm.nih.gov/sra/SRR14203888\".", "claims": [{"id": "claim-data-access", "statement": "This whole-genome sequencing data have been deposited at DDBJ/EMBL/GenBank under the accession number JAGQFH000000000 (https://www.ncbi.nlm.nih.gov/nuccore/JAGQFH000000000).The sequence data have been deposited in the NCBI SRA database under the accession number SRR14203888.(https://www.ncbi.nlm.nih.gov/sra/SRR14203888)The BioProject ID in GenBank is :PRJNA670955", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34235237", "locator": "sections[1] \"Specifications Table\" paragraph 2", "quote": "This whole-genome sequencing data have been deposited at DDBJ/EMBL/GenBank under the accession number JAGQFH000000000 (https://www.ncbi.nlm.nih.gov/nuccore/JAGQFH000000000).The sequence data have been deposited in the NCBI SRA database under the accession number SRR14203888.(https://www.ncbi.nlm.nih.gov/sra/SRR14203888)The BioProject ID in GenBank is :PRJNA670955"}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "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:34235237"], "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:PRJNA670955"], "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:PRJNA670955"], "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:34235237", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2021.107240", "sha256": "sha256:a62dfb4e085bf42a7603b34773a62c2bc95f386a82ad78e3320ecdf4c3c57896", "bytes": 7467, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2021.107240", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8250166", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PRJNA670955", "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=PRJNA670955", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PRJNA670955", "version": null, "note": "This whole-genome sequencing data have been deposited at DDBJ/EMBL/GenBank under the accession number JAGQFH000000000 (https://www.ncbi.nlm.nih.gov/nuccore/JAGQFH000000000).The sequence data have been deposited in the NCBI SRA database under the accession number SRR14203888.(https://www.ncbi.nlm.nih.gov/sra/SRR14203888)The BioProject ID in GenBank is :PRJNA670955", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This whole-genome sequencing data have been deposited at DDBJ/EMBL/GenBank under the accession number JAGQFH000000000 (https://www.ncbi.nlm.nih.gov/nuccore/JAGQFH000000000).The sequence data have been deposited in the NCBI SRA database under the accession number SRR14203888.(https://www.ncbi.nlm.nih.gov/sra/SRR14203888)The BioProject ID in GenBank is :PRJNA670955", "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": "2026-10-31T18:35:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:SRR14203888", "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=SRR14203888", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRR14203888", "version": null, "note": "This whole-genome sequencing data have been deposited at DDBJ/EMBL/GenBank under the accession number JAGQFH000000000 (https://www.ncbi.nlm.nih.gov/nuccore/JAGQFH000000000).The sequence data have been deposited in the NCBI SRA database under the accession number SRR14203888.(https://www.ncbi.nlm.nih.gov/sra/SRR14203888)The BioProject ID in GenBank is :PRJNA670955", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This whole-genome sequencing data have been deposited at DDBJ/EMBL/GenBank under the accession number JAGQFH000000000 (https://www.ncbi.nlm.nih.gov/nuccore/JAGQFH000000000).The sequence data have been deposited in the NCBI SRA database under the accession number SRR14203888.(https://www.ncbi.nlm.nih.gov/sra/SRR14203888)The BioProject ID in GenBank is :PRJNA670955", "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": "2026-10-31T18:35:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:34235237:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c1c0ad90d7903cec2997eedbcc49a37d12671ec9804d0a77c29b8dc64821d34e", "bytes": 1374, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#utbl0001", "version": null, "note": null, "structure": {"pmcid": "PMC8250166", "section_index": 1, "section_title": "Specifications Table", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject", "Microbiology"], ["Specific subject area", "Marine Biology and genomics"], ["Type of data", "Genome sequence data in FASTA and FASTQ format"], ["How data were acquired", "Genome sequencing with Illumina HiSeq 4000 at MACROGEN Inc. South Korea"], ["Data format", "Raw, Filtered, and Analysed genome sequences."], ["Parameters for data collection", "Bacterial genomic DNA was extracted from a pure culture of Bacillus australimaris B28A"], ["Description of data collection", "Genome features (Table 1), genome map (Fig. 1a), Whole genome sequencing, raw, assembly, and annotation"], ["Data source location", "Bacillus australimaris B28 was obtained from marine water in the city of Thiruvananthapuram, Kerala, India. (GPS: 8.554185N 76.849609E). The isolated sample 16srRNA accession number is MT010836. The BioSample ID is SAMN18571126"], ["Data accessibility", "This whole-genome sequencing data have been deposited at DDBJ/EMBL/GenBank under the accession number JAGQFH000000000 (https://www.ncbi.nlm.nih.gov/nuccore/JAGQFH000000000).The sequence data have been deposited in the NCBI SRA database under the accession number SRR14203888.(https://www.ncbi.nlm.nih.gov/sra/SRR14203888)The BioProject ID in GenBank is :PRJNA670955"]], "row_count": 9, "column_count": 2, "numeric_cells": 5, "header_rows": 0, "locator": "section[1]/table-wrap[1]#utbl0001"}}, {"id": "asset:table:pmid:34235237:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f2ff339f09dd5f78a4e1529c5651d5d017dd20184256c9a74a6b995ff214c92c", "bytes": 416, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#tbl0001", "version": null, "note": "Genome feature of Bacillus australimaris B28.", "structure": {"pmcid": "PMC8250166", "section_index": 3, "section_title": "Data Description", "row_count": 9, "column_count": 2}, "table": {"label": "Table 1", "caption": "Genome feature of Bacillus australimaris B28.", "rows": [["Genome feature", "Value"], ["Genome size", "3,766,107"], ["G+C content", "41.6"], ["Number of rRNA genes", "7"], ["Number of tRNA genes", "75"], ["Number of ORFs", "3936"], ["Number of contigs", "58"], ["N50", "339274"], ["L50", "3"]], "row_count": 9, "column_count": 2, "numeric_cells": 10, "header_rows": 1, "locator": "section[3]/table-wrap[1]#tbl0001"}}], "gaps": ["asset:data:geo:PRJNA670955 not downloaded", "asset:data:geo:PRJNA670955 licence not read", "asset:data:geo:SRR14203888 not downloaded", "asset:data:geo:SRR14203888 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": ["SRR14203888", "PRJNA670955"], "resolved_accessions": [], "statements": ["This whole-genome sequencing data have been deposited at DDBJ/EMBL/GenBank under the accession number JAGQFH000000000 (https://www.ncbi.nlm.nih.gov/nuccore/JAGQFH000000000).The sequence data have been deposited in the NCBI SRA database under the accession number SRR14203888.(https://www.ncbi.nlm.nih.gov/sra/SRR14203888)The BioProject ID in GenBank is :PRJNA670955"], "basis": "The paper names SRR14203888, PRJNA670955, but the accession does not resolve in the repository (not_in_ncbi_sra, 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:34235237", "data:geo:PRJNA670955", "asset:table:pmid:34235237:1", "asset:table:pmid:34235237:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PRJNA670955"]}, "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": "2026-10-31T18:31:56Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 7398, "completion_tokens": 1147, "cached_tokens": 792}}, "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:34235237", "type": "paper", "label": "pmid:34235237"}, {"id": "source:pmid:34235237", "type": "manuscript", "label": "PMID 34235237 full text"}, {"id": "data:geo:PRJNA670955", "type": "dataset", "label": "GEO PRJNA670955"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34235237", "type": "paper", "label": "pmid:34235237"}, {"id": "source:pmid:34235237", "type": "manuscript", "label": "PMID 34235237 full text"}, {"id": "data:geo:PRJNA670955", "type": "dataset", "label": "GEO PRJNA670955"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34235237", "type": "extraction", "used": ["source:pmid:34235237"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PRJNA670955", "type": "accession_resolution", "used": ["data:geo:PRJNA670955"], "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:34235237", "parent_hash": "sha256:0242f52e28621b52e156254b3a8a4533ba1156a4f0b752b76f38f9e99031c959", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:PRJNA670955 licence not read", "asset:data:geo:PRJNA670955 not downloaded", "asset:data:geo:SRR14203888 licence not read", "asset:data:geo:SRR14203888 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"], "assays": [{"role": "data_generation", "definition_id": "amplicon_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["was previously isolated and identified with 16SrRNA with GenBank accession number MT010836. Geno"], "order_basis": "paper_text_order:1175", "id": "assay:1"}]}