Plant and fungus transcriptomic data from grapevine berries undergoing artificially-induced noble rot caused by Botrytis cinerea.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31304217", "kind": "science-record", "revision": 8, "content_hash": "sha256:2ee600ae1a0cfe79110a39261275b462f91c9edd981741824b1fc38ac3832725", "created_at": "2026-11-01T15:40:47Z", "updated_at": "2026-11-01T22:44:05Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Plant and fungus transcriptomic data from grapevine berries undergoing artificially-induced noble rot caused by Botrytis cinerea.", "doi": "10.1016/j.dib.2019.104150", "pmid": "31304217", "authors": ["Arianna Lovato", "Sara Zenoni", "Giovanni Battista Tornielli", "Teresa Colombo", "Elodie Vandelle", "Annalisa Polverari"], "journal": "Data in brief", "year": 2019, "abstract": "Noble rot is a latent infection of grape berries caused by the necrotrophic fungus Botrytis cinerea, which develops under specific climatic conditions. The infected berries undergo biochemical and metabolic changes, associated with a rapid withering, which altogether offer interesting organoleptic features to sweet white wines. In this paper, we provide RNAseq datasets (raw and normalized counts as well as differentially expressed genes lists) of the transcriptome profiles of both grapevine berries (Vitis vinifera cv. Garganega) and B. cinerea during the establishment of noble rot, artificially induced in controlled conditions. The sequencing data are available in the NCBI GEO database under accession number GSE116741. These data were exploited in a comprehensive meta-analysis of gene expression during noble rot infection, gray mold and post-harvest withering. This highlighted an important common transcriptional reprogramming in different botrytized grape berry varieties and led to the identification of key genes specifically modulated during noble rot infection, which are described in the article entitled \"Specific molecular interactions between Vitis vinifera and Botrytis cinerea are required for noble rot development in grape berries\" Lovato et al., 2019.", "claims": [{"id": "claim-method", "statement": "The gene-level count matrix was used for differential expression analysis with edgeR [10].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31304217", "locator": "sections[9] \"RNA-Seq analysis\" paragraph 5", "quote": "The gene-level count matrix was used for differential expression analysis with edgeR [10]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The sequencing data are available in the NCBI GEO database under accession number GSE116741.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31304217", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The sequencing data are available in the NCBI GEO database under accession number GSE116741."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "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:31304217"], "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": "complete", "blocked_on": null, "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:GSE116741"], "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:GSE116741"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31304217", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2019.104150", "sha256": "sha256:781116e792e24745d890c658f25d1e8b54ca08f969087ea348cddafe223d86cc", "bytes": 17427, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2019.104150", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6603817", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE116741", "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=GSE116741", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE116741", "version": null, "note": "The sequencing data are available in the NCBI GEO database under accession number GSE116741.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The sequencing data are available in the NCBI GEO database under accession number GSE116741.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3223561", "GSM3223562", "GSM3223563", "GSM3223564", "GSM3223565", "GSM3223566", "GSM3223567", "GSM3223568", "GSM3223569", "GSM3259664", "GSM3259665", "GSM3259666", "GSM3259667", "GSM3259668", "GSM3259669", "GSM3259670", "GSM3259671", "GSM3259672", "GSM3259673", "GSM3259674", "GSM3259675", "GSM3259676", "GSM3259677", "GSM3259678"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "24368;25248;24810;22427", "taxon": "Botrytis cinerea; Vitis vinifera", "title": "Whole-transcriptome analysis of grapevine-Botrytis cinerea interaction during latent infection of berries", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31304217:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:877d25e49ed030b74aca2440b15bdd4119457d5efa2510f108479242df4a3fa8", "bytes": 1349, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#tbl1", "version": null, "note": "Statistics on Vitis vinifera and Botrytis cinerea TruSeq sequencing.", "structure": {"pmcid": "PMC6603817", "section_index": 3, "section_title": "Data", "row_count": 10, "column_count": 7}, "table": {"label": "Table 1", "caption": "Statistics on Vitis vinifera and Botrytis cinerea TruSeq sequencing.", "rows": [["Samples", "# of sequences in fastq files", "# of sequences in filtered fastq files [IlluQC.pl - NGS QC Toolkit]", "% of High Quality reads [i.e.: passing filtering]", "# of Aligned Pairs", "% of AlignedPairs"], ["1)", "Botrytis cinerea biol. repl. 1", "51.596.498", "48.464.674", "93,93%", "44.728.327", "92,30%"], ["2)", "Botrytis cinerea biol. repl. 2", "48.796.078", "45.945.913", "94,16%", "42.621.946", "92,80%"], ["3)", "Botrytis cinerea biol. repl. 3", "57.657.830", "54.115.696", "93,86%", "50.145.232", "92,70%"], ["4)", "B. cinerea-infected berries biol. repl. 1", "47.398.134", "44.179.114", "93,21%", "30.345.824", "68,50%"], ["5)", "B. cinerea-infected berries biol. repl. 2", "58.054.526", "54.322.693", "93,57%", "35.755.979", "65,60%"], ["6)", "B. cinerea-infected berries biol. repl. 3", "68.936.519", "64.588.098", "93,69%", "45.693.676", "70,50%"], ["7)", "Water-injected berries biol. repl. 1", "65.333.494", "60.514.894", "92,62%", "44.998.907", "74,20%"], ["8)", "Water-injected berries biol. repl. 2", "65.244.803", "61.257.338", "93,89%", "46.173.353", "75,20%"], ["9)", "Water-injected berries biol. repl. 3", "70.761.848", "65.929.242", "93,17%", "48.576.393", "73,50%"]], "row_count": 10, "column_count": 7, "numeric_cells": 63, "header_rows": 1, "locator": "section[3]/table-wrap[1]#tbl1"}}], "gaps": ["asset:data:geo:GSE116741 not downloaded", "asset:data:geo:GSE116741 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "edger", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The gene-level count matrix was used for differential expression analysis with edgeR [10]."}}], "targets": [], "gaps": []}, "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: edger."}, "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": "R1", "reachable": true, "accessions": ["GSE116741"], "resolved_accessions": ["GSE116741"], "statements": ["The sequencing data are available in the NCBI GEO database under accession number GSE116741."], "basis": "The paper names GSE116741 in NCBI GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:31304217", "data:geo:GSE116741", "asset:table:pmid:31304217:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE116741"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:15:26Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 15136, "completion_tokens": 854, "cached_tokens": 640}}, "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:31304217", "type": "paper", "label": "pmid:31304217"}, {"id": "source:pmid:31304217", "type": "manuscript", "label": "PMID 31304217 full text"}, {"id": "data:geo:GSE116741", "type": "dataset", "label": "GEO GSE116741"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31304217", "type": "paper", "label": "pmid:31304217"}, {"id": "source:pmid:31304217", "type": "manuscript", "label": "PMID 31304217 full text"}, {"id": "data:geo:GSE116741", "type": "dataset", "label": "GEO GSE116741"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31304217", "type": "extraction", "used": ["source:pmid:31304217"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE116741", "type": "accession_resolution", "used": ["data:geo:GSE116741"], "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:31304217", "parent_hash": "sha256:e920fcc0a501c9fc9bc3faf6922c7dff00621c47cf393326f3163568c636317e", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE116741 licence not read", "asset:data:geo:GSE116741 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "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": ["Plant and fungus transcriptomic data from grapevine berries undergoing artif", "differentially expressed genes lists) of the transcriptome profiles of both grapevine berries (Vitis vi", "sweet white wines. In this paper, we provide RNAseq datasets (raw and normalized counts as well"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The gene-level count matrix was used for differential expression analysis with edgeR [10]."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}