Microarray dataset of transgenic rice overexpressing Abp57.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28795104", "kind": "science-record", "revision": 8, "content_hash": "sha256:d77e3dcdc789775d8558a8bb97eae85ab43b1bc647cfa26a7394f5bf60494652", "created_at": "2026-11-01T15:40:27Z", "updated_at": "2026-11-01T22:43:04Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Microarray dataset of transgenic rice overexpressing Abp57.", "doi": "10.1016/j.dib.2017.07.047", "pmid": "28795104", "authors": ["Lay Wen Tan", "Cheng Seng Tan", "Zuraida A Rahman", "Hoe-Han Goh", "Ismanizan Ismail", "Zamri Zainal"], "journal": "Data in brief", "year": 2017, "abstract": "The dataset presented in this article describes microarray experiment of Auxin-binding protein 57, Abp57-overexpressing transgenic rice. The gene expression profiles were generated using Affymetrix GeneChip® Rice (Cn) Gene 1.0 ST Arrays. Total RNA from seedlings tissue of transgenic rice and wildtype, which serve as control were used as starting materials for microarray experiment. Detailed experimental methods and data analysis were described here. The raw and normalized microarray data were deposited into Gene Expression Omnibus (GEO) under accession number GSE99055.", "claims": [{"id": "claim-method", "statement": "The CHP files generated from normalization were subsequently loaded into Transcriptome Analysis Console (TAC) Software for obtaining differential gene expression data using one-way ANOVA (unpaired) and default filter criteria of fold change >|2| with ANOVA p-value of less than 0.05.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28795104", "locator": "sections[6] \"Microarray data normalization and processing\" paragraph 4", "quote": "The CHP files generated from normalization were subsequently loaded into Transcriptome Analysis Console (TAC) Software for obtaining differential gene expression data using one-way ANOVA (unpaired) and default filter criteria of fold change >|2| with ANOVA p-value of less than 0.05."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The raw and processed data are accessible at NCBI GEO DataSets (doi: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE99055).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28795104", "locator": "sections[3] \"Data\" paragraph 2", "quote": "The raw and processed data are accessible at NCBI GEO DataSets (doi: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE99055)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Differential gene expression was assessed using one-way ANOVA (unpaired) with a fold-change filter of >|2| and ANOVA p-value <0.05; the raw and normalized microarray data are available from GEO under accession number GSE99055.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:28795104", "locator": "sections[6] \"Microarray data normalization and processing\" paragraph 4", "quote": "The CHP files generated from normalization were subsequently loaded into Transcriptome Analysis Console (TAC) Software for obtaining differential gene expression data using one-way ANOVA (unpaired) and default filter criteria of fold change >|2| with ANOVA p-value of less than 0.05."}, {"asset": "source:pmid:28795104", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The raw and normalized microarray data were deposited into Gene Expression Omnibus (GEO) under accession number GSE99055."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Differential gene expression was assessed using one-way ANOVA (unpaired) with a fold-change filter of >|2| and ANOVA p-value <0.05; the raw and normalized microarray data are available from GEO under accession number GSE99055.", "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:28795104"], "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:GSE99055"], "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:GSE99055"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28795104", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2017.07.047", "sha256": "sha256:73f9593862b037df12d312aa719c43b6d0726a96d58d481d60d100da27097ef3", "bytes": 6841, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2017.07.047", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5540701", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE99055", "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=GSE99055", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE99055", "version": null, "note": "The raw and processed data are accessible at NCBI GEO DataSets (doi: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE99055).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw and processed data are accessible at NCBI GEO DataSets (doi: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE99055).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2631411", "GSM2631412", "GSM2631413", "GSM2631414", "GSM2631415", "GSM2631416"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "19566", "taxon": "Oryza sativa Indica Group; Oryza sativa", "title": "Global gene expression in Abp57-overexpressing transgenic rice", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:28795104:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c9fef8eddabaedbe95a90034e7392f599dadbae92a39ae7c3509531de51c877b", "bytes": 1004, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0010", "version": null, "note": null, "structure": {"pmcid": "PMC5540701", "section_index": 1, "section_title": "Specifications Table", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Biology"], ["More specific subject area", "Gene expression study"], ["Type of data", "Table, visualisation figures"], ["How data was acquired", "Affymetrix GeneChip® Rice (Cn) Gene 1.0 ST Arrays, Robust Multi-Array Average and statistical analyses"], ["Data format", "Raw (CEL.) and normalized (CHP.)"], ["Experimental factors", "Abp57-overexpressing line vs. wildtype (control)"], ["Experimental features", "Total RNA was extracted from whole seedlings of Abp57-overexpressing rice and control. Each sample contains three biological replicates and each replicate consists of three seedlings."], ["Data source location", "The National University of Malaysia, 43600 Bangi, Malaysia (3°16′14.63″ N, 101°41′11.32″ E)"], ["Data accessibility", "Microarray data are available from Gene Expression Omnibus database with GEO accession number GSE99055"]], "row_count": 9, "column_count": 2, "numeric_cells": 5, "header_rows": 0, "locator": "section[1]/table-wrap[1]#t0010"}}, {"id": "asset:table:pmid:28795104:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fec6b6761abe3034e76721ea1ce04eec1afa01d1d9e93e63f3c0a5b865c62cfd", "bytes": 540, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#t0005", "version": null, "note": "Spectrophotometric reading and RIN of RNA samples.", "structure": {"pmcid": "PMC5540701", "section_index": 5, "section_title": "Plant material and RNA extraction", "row_count": 7, "column_count": 5}, "table": {"label": "Table 1", "caption": "Spectrophotometric reading and RIN of RNA samples.", "rows": [["Sample", "Nisbah 260/280", "Nisbah 260/230", "Kepekatan (ng/μL)", "RIN"], ["Control-1", "2.004", "1.880", "222.17", "8.3"], ["Control-2", "1.995", "1.827", "200.68", "8.4"], ["Control-3", "1.976", "1.897", "161.13", "10"], ["OxAbp57-1", "1.997", "1.859", "290.53", "9.2"], ["OxAbp57-2", "1.830", "1.628", "126.72", "8.3"], ["OxAbp57-3", "1.974", "1.981", "259.28", "10"]], "row_count": 7, "column_count": 5, "numeric_cells": 32, "header_rows": 1, "locator": "section[5]/table-wrap[1]#t0005"}}], "gaps": ["asset:data:geo:GSE99055 not downloaded", "asset:data:geo:GSE99055 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": "The CHP files generated from normalization were subsequently loaded into Transcriptome Analysis Console (TAC) Software for obtaining differential gene expression data using one-way ANOVA (unpaired) and default filter criteria of fold change >|2| with ANOVA p-value of less than 0.05."}}], "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": ["GSE99055"], "resolved_accessions": ["GSE99055"], "statements": ["The raw and processed data are accessible at NCBI GEO DataSets (doi: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE99055)."], "basis": "The paper names GSE99055 in Gene Expression Omnibus (GEO) 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:28795104", "data:geo:GSE99055", "asset:table:pmid:28795104:1", "asset:table:pmid:28795104:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE99055"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:31:49Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 17901, "completion_tokens": 2726, "cached_tokens": 5152}}, "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:28795104", "type": "paper", "label": "pmid:28795104"}, {"id": "source:pmid:28795104", "type": "manuscript", "label": "PMID 28795104 full text"}, {"id": "data:geo:GSE99055", "type": "dataset", "label": "GEO GSE99055"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28795104", "type": "paper", "label": "pmid:28795104"}, {"id": "source:pmid:28795104", "type": "manuscript", "label": "PMID 28795104 full text"}, {"id": "data:geo:GSE99055", "type": "dataset", "label": "GEO GSE99055"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28795104", "type": "extraction", "used": ["source:pmid:28795104"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE99055", "type": "accession_resolution", "used": ["data:geo:GSE99055"], "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:28795104", "parent_hash": "sha256:b906a2193770d8453d9d4a8b677ffaeaacd7d3158bb0c04635b849969d846d23", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE99055 licence not read", "asset:data:geo:GSE99055 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 transgenic rice overexpressing Ab", "control were used as starting materials for microarray experiment. Detailed experimental methods an", "were described here. The raw and normalized microarray data were deposited into Gene Expression Omn", "ene expression profiles were generated using Affymetrix GeneChip® Rice (Cn) Gene 1.0 ST Arrays. Tota"], "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": ["The CHP files generated from normalization were subsequently loaded into Transcriptome Analysis Console (TAC) Software for obtaining differential gene expression data using one-way ANOVA (unpaired) and default filter criteria of fold change >|2| with ANOVA p-value of less than 0.05."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}