Dataset of de novo assembly and functional annotation of the transcriptome of blueberry (Vaccinium spp.).

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31497632", "kind": "science-record", "revision": 5, "content_hash": "sha256:62fed9ce9c04a148d8f7607bde56a4fe808cf7785c27ad1f174b9e9b99750ffc", "created_at": "2026-11-01T15:40:49Z", "updated_at": "2026-11-01T18:51:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dataset of de novo assembly and functional annotation of the transcriptome of blueberry (Vaccinium spp.).", "doi": "10.1016/j.dib.2019.104390", "pmid": "31497632", "authors": ["Xinpeng Qi", "Elizabeth L Ogden", "Mark K Ehlenfeldt", "Lisa J Rowland"], "journal": "Data in brief", "year": 2019, "abstract": "Blueberry is an economically important berry crop. Both production and consumption of blueberries have increased sharply worldwide in recent years at least partly due to their known health benefits. The development of improved genomic resources for blueberry, such as a well-assembled genome and transcriptome, could accelerate breeding through genomic-assisted approaches. To enrich available transcriptome data and identify genes potentially involved in fruit quality, RNA sequencing was performed on fruit tissue from two northern-adapted hybrid blueberry breeding populations. RNA-seq was carried out using the Illumina HiSeqTM 2500 platform. Because of the absence of a reference-grade genome for blueberry, a transcriptome was de novo assembled from this RNA-seq data and other publicly available transcriptome data from blueberry downloaded from the National Center for Biotechnology Information (NCBI) Short Read Archive (SRA) using Trinity. After removing redundancy, this resulted in a dataset of 91,861 blueberry unigenes. This unigene dataset was functionally annotated using the NCBI-Nr protein database. All raw reads from the breeding populations were deposited in the NCBI SRA with accession numbers SRR6281886, SRR6281887, SRR6281888, and SRR6281889. The de novo transcriptome assembly was deposited at NCBI Transcriptome Shotgun Assembly (TSA) database with accession number GGAB00000000. These data will provide real expression evidence for the blueberry genome gene prediction and gene functional annotation and a reference transcriptome for future gene expression studies involving blueberry fruit.", "claims": [{"id": "claim-data-access", "statement": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31497632", "locator": "sections[1] \"p\" paragraph 1", "quote": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly"}], "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:31497632"], "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:SRR6281886"], "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:SRR6281886"], "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:31497632", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2019.104390", "sha256": "sha256:f7e910ea83f044f61ea5f18cf789de655a9b801d4f1952096ace6e4ddf7baea0", "bytes": 10117, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2019.104390", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6718820", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:SRR6281886", "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=SRR6281886", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRR6281886", "version": null, "note": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "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:SRR6281887", "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=SRR6281887", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRR6281887", "version": null, "note": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "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:SRR6281888", "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=SRR6281888", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRR6281888", "version": null, "note": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "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:SRR6281889", "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=SRR6281889", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRR6281889", "version": null, "note": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "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:31497632:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ca80133e3994803ed94e1682426df16757caa296881f76581cb9d72303ff514e", "bytes": 1876, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#undtbl1", "version": null, "note": "Specifications Table", "structure": {"pmcid": "PMC6718820", "section_index": 1, "section_title": "p", "row_count": 10, "column_count": 2}, "table": {"label": null, "caption": "Specifications Table", "rows": [["Subject area", "Biology"], ["More specific subject area", "Transcriptomics"], ["Type of data", "Transcriptome sequences"], ["How data was acquired", "Illumina HiSeqTM 2500 sequencing platform"], ["Data format", "Raw and analyzed"], ["Experimental factors", "Ripe fruit was collected from two field-grown blueberry breeding populations segregating for the waxy coating on fruit"], ["Experimental features", "Total RNA was extracted from bulked waxy and non-waxy fruit tissue from two blueberry breeding populations segregating for the waxy coating on fruit. RNA was used for cDNA library construction. Paired-end RNA-seq data was generated using the Illumina HiSeqTM 2500 sequencing platform. Trinity software was used to perform de novo assembly of clean reads from this data and other blueberry transcriptome data downloaded from NCBI SRA. The unigene dataset was functionally annotated using NCBI-Nr protein database."], ["Data source location", "USDA-ARS, Genetic Improvement of Fruits and Vegetables Laboratory, Beltsville, MD 20705, USA"], ["Data accessibility", "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly"], ["Related research article", "Xinpeng Qi, Elizabeth L. Ogden, Mark K. Ehlenfeldt, and Lisa J. Rowland. Transcriptome analysis identifies genes related to the waxy coating on blueberry fruit in two northern-adapted rabbiteye breeding populations, “under review”."]], "row_count": 10, "column_count": 2, "numeric_cells": 4, "header_rows": 0, "locator": "section[1]/table-wrap[1]#undtbl1"}}, {"id": "asset:table:pmid:31497632:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b92d1d6a1a0f2f59522d4d600575524d102040bf63e367241c75a253d607d87d", "bytes": 947, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[2]#undtbl2", "version": null, "note": null, "structure": {"pmcid": "PMC6718820", "section_index": 1, "section_title": "p", "row_count": 1, "column_count": 1}, "table": {"label": null, "caption": null, "rows": [["Value of the Data1.The RNA-seq and assembled transcriptome datasets provide real expression evidence for use to the scientific research community in gene prediction and functional annotation of the emerging blueberry genome.2.The RNA-seq dataset is useful to scientists in identifying differentially expressed genes between blueberry fruit with and without the waxy coating and, thus, genes associated with wax accumulation in berry fruit.3.The expression profiles are available as raw sequence reads that can be further processed and analyzed by researchers using their own bioinformatic algorithms.4.The de novo assembled transcriptome is useful as a reference transcriptome to other scientists working to identify differentially expressed genes in blueberry and in related Vaccinium species."]], "row_count": 1, "column_count": 1, "numeric_cells": 1, "header_rows": 0, "locator": "section[1]/table-wrap[2]#undtbl2"}}, {"id": "asset:table:pmid:31497632:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:878d54a943595bbd757fb9ef9dc394cf98f530bfef8b63df27cde387fcc33ff6", "bytes": 503, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#tbl1", "version": null, "note": "RNA-seq of two northern-adapted rabbiteye hybrid blueberry breeding populations.", "structure": {"pmcid": "PMC6718820", "section_index": 2, "section_title": "Data", "row_count": 5, "column_count": 3}, "table": {"label": "Table 1", "caption": "RNA-seq of two northern-adapted rabbiteye hybrid blueberry breeding populations.", "rows": [["Library", "Number of plants in bulk", "Number of clean reads"], ["‘Nocturne’ x T 300 non-waxy", "9", "69,318,222"], ["‘Nocturne’ x T 300 waxy", "10", "97,629,788"], ["‘Nocturne’ x US 1212 non-waxy", "10", "68,222,558"], ["‘Nocturne’ x US 1212 waxy", "13", "81,404,420"]], "row_count": 5, "column_count": 3, "numeric_cells": 12, "header_rows": 1, "locator": "section[2]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:31497632:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9930d6c3982ea50f1b483a87743013b46540f39334a49bd84b5f806bacfe47bc", "bytes": 722, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[2]#tbl2", "version": null, "note": "Statistics of the blueberry transcriptome raw assembly, quality assessment, and redundancy elimination.", "structure": {"pmcid": "PMC6718820", "section_index": 2, "section_title": "Data", "row_count": 11, "column_count": 2}, "table": {"label": "Table 2", "caption": "Statistics of the blueberry transcriptome raw assembly, quality assessment, and redundancy elimination.", "rows": [["Total “genes” from Trinity assembly", "251,974"], ["Assembly N50 length", "806"], ["Total assembled bases", "208,124,831"], ["‘Nocturne’ x T 300 non-waxy (%)", "87.16a"], ["‘Nocturne’ x T 300 waxy (%)", "92.00a"], ["‘Nocturne’ x US 1212 non-waxy (%)", "93.36a"], ["‘Nocturne’ x US 1212 waxy (%)", "91.63a"], ["Total full-length SwissProt protein hits", "9909"], ["Total unigene number", "91,861"], ["Unigene N50 length", "1144"], ["Total unigene bases", "66,642,205"]], "row_count": 11, "column_count": 2, "numeric_cells": 17, "header_rows": 0, "locator": "section[2]/table-wrap[2]#tbl2"}}], "gaps": ["asset:data:geo:SRR6281886 not downloaded", "asset:data:geo:SRR6281886 licence not read", "asset:data:geo:SRR6281887 not downloaded", "asset:data:geo:SRR6281887 licence not read", "asset:data:geo:SRR6281888 not downloaded", "asset:data:geo:SRR6281888 licence not read", "asset:data:geo:SRR6281889 not downloaded", "asset:data:geo:SRR6281889 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": ["SRR6281886", "SRR6281887", "SRR6281888", "SRR6281889"], "resolved_accessions": [], "statements": ["NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly"], "basis": "The paper names SRR6281886, SRR6281887, SRR6281888, SRR6281889, but the accession does not resolve in the repository (not_in_ncbi_sra, not_in_ncbi_sra, not_in_ncbi_sra, not_in_ncbi_sra), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:31497632", "data:geo:SRR6281886", "asset:table:pmid:31497632:1", "asset:table:pmid:31497632:2", "asset:table:pmid:31497632:3", "asset:table:pmid:31497632:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:SRR6281886"]}, "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": "2026-10-31T18:16:10Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 9076, "completion_tokens": 2442, "cached_tokens": 528}}, "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:31497632", "type": "paper", "label": "pmid:31497632"}, {"id": "source:pmid:31497632", "type": "manuscript", "label": "PMID 31497632 full text"}, {"id": "data:geo:SRR6281886", "type": "dataset", "label": "GEO SRR6281886"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31497632", "type": "paper", "label": "pmid:31497632"}, {"id": "source:pmid:31497632", "type": "manuscript", "label": "PMID 31497632 full text"}, {"id": "data:geo:SRR6281886", "type": "dataset", "label": "GEO SRR6281886"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31497632", "type": "extraction", "used": ["source:pmid:31497632"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-SRR6281886", "type": "accession_resolution", "used": ["data:geo:SRR6281886"], "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:31497632", "parent_hash": "sha256:573733412da0739fe14df29240c0bc3ca39fcbb0d1364d5114bacf9c17156a60", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:SRR6281886 licence not read", "asset:data:geo:SRR6281886 not downloaded", "asset:data:geo:SRR6281887 licence not read", "asset:data:geo:SRR6281887 not downloaded", "asset:data:geo:SRR6281888 licence not read", "asset:data:geo:SRR6281888 not downloaded", "asset:data:geo:SRR6281889 licence not read", "asset:data:geo:SRR6281889 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": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["vo assembly and functional annotation of the transcriptome of blueberry (Vaccinium spp.).", "ueberry, such as a well-assembled genome and transcriptome, could accelerate breeding through genomic-a", "mic-assisted approaches. To enrich available transcriptome data and identify genes potentially involved", "of a reference-grade genome for blueberry, a transcriptome was de novo assembled from this RNA-seq data"], "order_basis": "paper_text_order:16", "id": "assay:1"}]}