Arabidopsis transcriptome dataset of the response of imbibed wild-type and glucosinolate-deficient seeds to nitrogen-containing compounds.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37006386", "kind": "science-record", "revision": 4, "content_hash": "sha256:4145f1757dc821fbbea0174c3c7eb296b562ea321a7a1f525da8d381463f3607", "created_at": "2026-11-01T19:01:39Z", "updated_at": "2026-11-01T22:51:37Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Arabidopsis transcriptome dataset of the response of imbibed wild-type and glucosinolate-deficient seeds to nitrogen-containing compounds.", "doi": "10.1016/j.dib.2023.109047", "pmid": "37006386", "authors": ["Mailen Ortega-Cuadros", "Sophie Aligon", "Nubia Velasquez", "Jerome Verdier", "Philippe Grappin"], "journal": "Data in brief", "year": 2023, "abstract": "The presented RNAseq data were obtained from Arabidopsis seeds dry and 6h imbibed to describe, in wild-type and glucosinolate (GSL)-deficient genotypes, the response at the RNA level to nitrogen compounds, i.e., potassium nitrate (KNO3, 10mM), potassium thiocyanate (KSCN, 8µM). The cyp79B2 cyp79B3 (cyp79B2/B3) double mutant deficient in Indole GSL, the myb28 myb29 (myb28/29) double mutant deficient in aliphatic GSL, the quadruple mutant cyp79B2 cyp79B3 myb28 myb29 (qko) deficient in total GSL in the seed and the WT reference genotype in Col-0 background were used for the transcriptomic analysis. Total ARN was extracted using NucleoSpin® RNA Plant and Fungi kit. Library construction and sequencing were performed with DNBseq™ technology at Beijing Genomics Institute. FastQC was used to check reads quality and mapping analysis were made using a quasi-mapping alignment from Salmon. Gene expression changes in mutant seeds compared to WT were calculated using DESeq2 algorithms. This comparison with the qko, cyp79B2/B3 and myb28/29 mutants made it possible to identify 30220, 36885 and 23807 differentially expressed genes (DEGs), respectively. Mapping rate result was merge into a single report using MultiQC; graphic results were illustrated through Veen diagrams and volcano plots. Fastq raw data and count files from 45 samples are available in the repository Sequence Read Archive (SRA) of the National Center for Biotechnology Information (NCBI) and can be consulted with the data identification number GSE221567 at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE221567.", "claims": [{"id": "claim-method", "statement": "Gene expression changes from comparison between mutant versus wild-type seeds were calculated using the algorithm from DESeq2 [3], and identification of differentially expressed genes (DEGs) was based on log2FC and adjusted p-value thresholds.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37006386", "locator": "sections[6] \"Experimental Design, Materials and Methods\" paragraph 4", "quote": "Gene expression changes from comparison between mutant versus wild-type seeds were calculated using the algorithm from DESeq2 [3], and identification of differentially expressed genes (DEGs) was based on log2FC and adjusted p-value thresholds."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Arabidopsis transcriptome dataset of the response of imbibed wild-type and glucosinolate-deficient seeds to nitrogen-containing compounds (Original data) (Mendeley Data).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37006386", "locator": "sections[11] \"Data Availability\" paragraph 2", "quote": "Arabidopsis transcriptome dataset of the response of imbibed wild-type and glucosinolate-deficient seeds to nitrogen-containing compounds (Original data) (Mendeley Data)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "", "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:37006386"], "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:GSE221567"], "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:GSE221567"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37006386", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2023.109047", "sha256": "sha256:54c68d032fb60339fd76526f7fe8bad3cd04dac270b90a7842fd05dc20d3e46c", "bytes": 16147, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2023.109047", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10051019", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE221567", "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=GSE221567", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE221567", "version": null, "note": "Arabidopsis transcriptome dataset of the response of imbibed wild-type and glucosinolate-deficient seeds to nitrogen-containing compounds (Original data) (Mendeley Data).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Arabidopsis transcriptome dataset of the response of imbibed wild-type and glucosinolate-deficient seeds to nitrogen-containing compounds (Original data) (Mendeley Data).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM6886384", "GSM6886385", "GSM6886386", "GSM6886387", "GSM6886388", "GSM6886389", "GSM6886390", "GSM6886391", "GSM6886392", "GSM6886393", "GSM6886394", "GSM6886395", "GSM6886396", "GSM6886397", "GSM6886398", "GSM6886399", "GSM6886400", "GSM6886401", "GSM6886402", "GSM6886403", "GSM6886404", "GSM6886405", "GSM6886406", "GSM6886407", "GSM6886408", "GSM6886409", "GSM6886410", "GSM6886411", "GSM6886412", "GSM6886413", "GSM6886414", "GSM6886415", "GSM6886416", "GSM6886417", "GSM6886418", "GSM6886419", "GSM6886420", "GSM6886421", "GSM6886422", "GSM6886423", "GSM6886424", "GSM6886425", "GSM6886426", "GSM6886427", "GSM6886428"], "sample_count": 45, "group_sizes": null, "group_sizes_basis": null, "platform": "28290", "taxon": "Arabidopsis thaliana", "title": "Effect of nitrogen compounds on imbibed mutant seeds impaired in glucosinolate biosynthesis", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE221567 not downloaded", "asset:data:geo:GSE221567 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "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": "Gene expression changes from comparison between mutant versus wild-type seeds were calculated using the algorithm from DESeq2 [3], and identification of differentially expressed genes (DEGs) was based on log2FC and adjusted p-value thresholds."}}], "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: deseq2."}, "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": ["GSE221567"], "resolved_accessions": ["GSE221567"], "statements": ["Arabidopsis transcriptome dataset of the response of imbibed wild-type and glucosinolate-deficient seeds to nitrogen-containing compounds (Original data) (Mendeley Data)."], "basis": "The paper names GSE221567 in NCBI GEO 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:37006386", "data:geo:GSE221567"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE221567"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:35:27Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 6000, "completion_tokens": 1920, "cached_tokens": 264}}, "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:37006386", "type": "paper", "label": "pmid:37006386"}, {"id": "source:pmid:37006386", "type": "manuscript", "label": "PMID 37006386 full text"}, {"id": "data:geo:GSE221567", "type": "dataset", "label": "GEO GSE221567"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37006386", "type": "paper", "label": "pmid:37006386"}, {"id": "source:pmid:37006386", "type": "manuscript", "label": "PMID 37006386 full text"}, {"id": "data:geo:GSE221567", "type": "dataset", "label": "GEO GSE221567"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37006386", "type": "extraction", "used": ["source:pmid:37006386"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE221567", "type": "accession_resolution", "used": ["data:geo:GSE221567"], "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:37006386", "parent_hash": "sha256:57efca131d002c7e0bb794562e7cf259aa836edeb2bbf615cf2e10237b0dbf62", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE221567 licence not read", "asset:data:geo:GSE221567 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "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": 0.77, "evidence": ["Agilent Technologies, Santa Clara, CA, USA). cDNA library constructions were performed and paired-end"], "order_basis": "paper_text_order:2726", "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": ["Gene expression changes from comparison between mutant versus wild-type seeds were calculated using the algorithm from DESeq2 [3], and identification of differentially expressed genes (DEGs) was based on log2FC and adjusted p-value thresholds."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}