Microarray dataset of after-ripening induced mRNA oxidation in wheat seeds.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30417044", "kind": "science-record", "revision": 8, "content_hash": "sha256:047c478f46788ad4a0fe10f063794b7cb0bd138366df3435dd264ae195d4a70c", "created_at": "2026-11-01T15:40:38Z", "updated_at": "2026-11-01T22:43:37Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Microarray dataset of after-ripening induced mRNA oxidation in wheat seeds.", "doi": "10.1016/j.dib.2018.10.036", "pmid": "30417044", "authors": ["Feng Gao", "Mark C Jordan", "Belay T Ayele"], "journal": "Data in brief", "year": 2018, "abstract": "The dataset presented here profiles oxidative modification of mRNAs in wheat seeds in response to after-ripening, a treatment that releases seeds from the state of dormancy. The level of dormancy in wheat seeds is closely associated with preharvest sprouting, defined as the germination of seeds while they are on the mother plant, which negatively affects wheat yield and quality. Understanding the molecular mechanisms involved in the control of seed dormancy is critical for improving the tolerance of wheat seeds to preharvest sprouting. The dataset were generated using oxidized mRNA samples derived from three independent biological replicates of dormant and after-ripened (non-dormant) wheat seeds and a microarray based experimental procedures that involved the use of Affymetrix GeneChip Wheat Genome Array. The raw and normalized data are available in NCBI׳s Gene Expression Ominbus (GEO) database with accession number GSE41949, and a related research article has been published in Plant Biotechnology Journal (Gao et al., 2013).", "claims": [{"id": "claim-method", "statement": "Identification of probesets that are differentially oxidized between dormant and after-ripened seeds was performed by analysis of variance (ANOVA) using FlexArray software [5].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30417044", "locator": "sections[8] \"Data analysis\" paragraph 2", "quote": "Identification of probesets that are differentially oxidized between dormant and after-ripened seeds was performed by analysis of variance (ANOVA) using FlexArray software [5]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The raw and normalized files of the data are available at NCBI׳s Gene Expression Ominbus database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41949). Detailed description of the data can be found in Gao et al. [1].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30417044", "locator": "sections[3] \"Data\" paragraph 2", "quote": "The raw and normalized files of the data are available at NCBI׳s Gene Expression Ominbus database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41949). Detailed description of the data can be found in Gao et al. [1]."}], "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:30417044"], "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:GSE41949"], "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:GSE41949"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30417044", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2018.10.036", "sha256": "sha256:fde20dd0a3db3b99d8991cb9bcd0628afb3d2f8cb400b341d7abd71b9b86b731", "bytes": 7153, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2018.10.036", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6218628", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE41949", "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=GSE41949", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE41949", "version": null, "note": "The raw and normalized files of the data are available at NCBI׳s Gene Expression Ominbus database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41949). Detailed description of the data can be found in Gao et al. [1].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw and normalized files of the data are available at NCBI׳s Gene Expression Ominbus database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41949). Detailed description of the data can be found in Gao et al. [1].", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1028084", "GSM1028085", "GSM1028086", "GSM1028087", "GSM1028088", "GSM1028089"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "3802", "taxon": "Triticum aestivum", "title": "mRNA oxidation data from dry dormant and after-ripened wheat seeds", "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:30417044:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:347bc8df095bc09640a4a3852519096af6f0faddfdfd830f834b94c4b6471e15", "bytes": 823, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0005", "version": null, "note": null, "structure": {"pmcid": "PMC6218628", "section_index": 1, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Biology"], ["More specific subject area", "Oxidative modification of mRNAs"], ["Type of data", "Data Table in Excel and CEL files"], ["How data was acquired", "Affymetrix GeneChip Wheat Genome Array"], ["Data format", "Raw and normalized data"], ["Experimental factors", "Dormant seeds vs. after-ripened (non-dormant) seeds"], ["Experimental features", "Isolation of oxidized mRNAs, large scale analysis of oxidative modification of seed stored mRNAs"], ["Data source location", "University of Manitoba, Winnipeg, Canada"], ["Data accessibility", "The raw and normalized data are available from NCBI׳s Gene Expression Ominbus (GEO) database with accession number GSE41949."]], "row_count": 9, "column_count": 2, "numeric_cells": 1, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:30417044:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:347bc8df095bc09640a4a3852519096af6f0faddfdfd830f834b94c4b6471e15", "bytes": 823, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0005", "version": null, "note": null, "structure": {"pmcid": "PMC6218628", "section_index": 2, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Biology"], ["More specific subject area", "Oxidative modification of mRNAs"], ["Type of data", "Data Table in Excel and CEL files"], ["How data was acquired", "Affymetrix GeneChip Wheat Genome Array"], ["Data format", "Raw and normalized data"], ["Experimental factors", "Dormant seeds vs. after-ripened (non-dormant) seeds"], ["Experimental features", "Isolation of oxidized mRNAs, large scale analysis of oxidative modification of seed stored mRNAs"], ["Data source location", "University of Manitoba, Winnipeg, Canada"], ["Data accessibility", "The raw and normalized data are available from NCBI׳s Gene Expression Ominbus (GEO) database with accession number GSE41949."]], "row_count": 9, "column_count": 2, "numeric_cells": 1, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0005"}}], "gaps": ["asset:data:geo:GSE41949 not downloaded", "asset:data:geo:GSE41949 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Identification of probesets that are differentially oxidized between dormant and after-ripened seeds was performed by analysis of variance (ANOVA) using FlexArray software [5]."}}], "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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE41949"], "resolved_accessions": ["GSE41949"], "statements": ["The raw and normalized files of the data are available at NCBI׳s Gene Expression Ominbus database (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41949). Detailed description of the data can be found in Gao et al. [1]."], "basis": "The paper names GSE41949 in NCBI׳s Gene Expression Ominbus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:30417044", "data:geo:GSE41949", "asset:table:pmid:30417044:1", "asset:table:pmid:30417044:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE41949"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:12:49Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 6713, "completion_tokens": 1053, "cached_tokens": 656}}, "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:30417044", "type": "paper", "label": "pmid:30417044"}, {"id": "source:pmid:30417044", "type": "manuscript", "label": "PMID 30417044 full text"}, {"id": "data:geo:GSE41949", "type": "dataset", "label": "GEO GSE41949"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30417044", "type": "paper", "label": "pmid:30417044"}, {"id": "source:pmid:30417044", "type": "manuscript", "label": "PMID 30417044 full text"}, {"id": "data:geo:GSE41949", "type": "dataset", "label": "GEO GSE41949"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30417044", "type": "extraction", "used": ["source:pmid:30417044"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE41949", "type": "accession_resolution", "used": ["data:geo:GSE41949"], "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:30417044", "parent_hash": "sha256:db24425a0f317bf220a0f221a595ed11f7fdacc74cc5d1679531d475d22fc212", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE41949 licence not read", "asset:data:geo:GSE41949 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Microarray dataset of after-ripening induced mRNA oxida", "fter-ripened (non-dormant) wheat seeds and a microarray based experimental procedures that involved", "rimental procedures that involved the use of Affymetrix GeneChip Wheat Genome Array. The raw and nor"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Identification of probesets that are differentially oxidized between dormant and after-ripened seeds was performed by analysis of variance (ANOVA) using FlexArray software [5]."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}