{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:24398116", "kind": "science-record", "revision": 4, "content_hash": "sha256:b748e8ec1f03bb69f5eaf9cc9f1444866698f6c8998daddb22b760716f30f38d", "created_at": "2026-11-01T15:40:04Z", "updated_at": "2026-11-01T21:19:45Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Development of a microarray for two rice subspecies: characterization and validation of gene expression in rice tissues.", "doi": "10.1186/1756-0500-7-15", "pmid": "24398116", "authors": ["Jia-Shing Chen", "Shang-Chi Lin", "Chia-Ying Chen", "Yen-Ting Hsieh", "Ping-Hui Pai", "Long-Kung Chen", "Shengwan Lee"], "journal": "BMC research notes", "year": 2014, "abstract": "BACKGROUND: Rice is one of the major crop species in the world helping to sustain approximately half of the global population's diet especially in Asia. However, due to the impact of extreme climate change and global warming, rice crop production and yields may be adversely affected resulting in a world food crisis. Researchers have been keen to understand the effects of drought, temperature and other environmental stress factors on rice plant growth and development. Gene expression microarray technology represents a key strategy for the identification of genes and their associated expression patterns in response to stress. Here, we report on the development of the rice OneArray® microarray platform which is suitable for two major rice subspecies, japonica and indica.\nRESULTS: The rice OneArray® 60-mer, oligonucleotide microarray consists of a total of 21,179 probes covering 20,806 genes of japonica and 13,683 genes of indica. Through a validation study, total RNA isolated from rice shoots and roots were used for comparison of gene expression profiles via microarray examination. The results were submitted to NCBI's Gene Expression Omnibus (GEO). Data can be found under the GEO accession number GSE50844 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE50844). A list of significantly differentially expressed genes was generated; 438 shoot-specific genes were identified among 3,138 up-regulated genes, and 463 root-specific genes were found among 3,845 down-regulated genes. GO enrichment analysis demonstrates these results are in agreement with the known physiological processes of the different organs/tissues. Furthermore, qRT-PCR validation was performed on 66 genes, and found to significantly correlate with the microarray results (R = 0.95, p < 0.001***).\nCONCLUSION: The rice OneArray® 22 K microarray, the first rice microarray, covering both japonica and indica subspecies was designed and validated in a comprehensive study of gene expression in rice tissues. The rice OneArray® microarray platform revealed high specificity and sensitivity. Additional information for the rice OneArray® microarray can be found at http://www.phalanx.com.tw/index.php.", "claims": [{"id": "claim-method", "statement": "Gene set analysis was performed using Gene Ontology terms with functional annotation, as described in DAVID Bioinformatics Resources 6.7 (http://david.abcc.ncifcrf.gov/) [9,10].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:24398116", "locator": "sections[6] \"Comparison of gene expression in rice root and shoot using gene ontology analysis\" paragraph 2", "quote": "Gene set analysis was performed using Gene Ontology terms with functional annotation, as described in DAVID Bioinformatics Resources 6.7 (http://david.abcc.ncifcrf.gov/) [9,10]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All normalized and raw data were submitted to NCBI’s Gene Expression Omnibus (GEO) for others to examine. The data are accessible via GEO Series accession number GSE50844 http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE50844.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:24398116", "locator": "sections[5] \"Rice OneArray® microarray technical performance\" paragraph 3", "quote": "All normalized and raw data were submitted to NCBI’s Gene Expression Omnibus (GEO) for others to examine. The data are accessible via GEO Series accession number GSE50844 http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE50844."}], "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:24398116"], "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:GSE50844"], "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:GSE50844"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:24398116", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/1756-0500-7-15", "sha256": "sha256:1f6a5f72a12a98a0f6110552c179eca0f62646a3786f69cb98a9c4c867729e77", "bytes": 26340, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/1756-0500-7-15", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC3891988", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE50844", "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=GSE50844", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE50844", "version": null, "note": "All normalized and raw data were submitted to NCBI’s Gene Expression Omnibus (GEO) for others to examine. The data are accessible via GEO Series accession number GSE50844 http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE50844.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All normalized and raw data were submitted to NCBI’s Gene Expression Omnibus (GEO) for others to examine. The data are accessible via GEO Series accession number GSE50844 http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE50844.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1231066", "GSM1231067", "GSM1231068", "GSM1231069", "GSM1231070", "GSM1231071", "GSM1231072", "GSM1231073", "GSM1231074", "GSM1231075"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "13702", "taxon": "Oryza sativa Japonica Group; Oryza sativa", "title": "Characterization of Gene Expression in Rice Shoot and Root", "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:24398116:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:df7fb35a60a917fc1a157090a17efc403647ca52f8cc0ef8a8ca81243d98e168", "bytes": 1022, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#T1", "version": null, "note": "The correlation between technique repeats of rice shoot and root", "structure": {"pmcid": "PMC3891988", "section_index": 5, "section_title": "Rice OneArray® microarray technical performance", "row_count": 12, "column_count": 12}, "table": {"label": "Table 1", "caption": "The correlation between technique repeats of rice shoot and root", "rows": [["", "", "", "", "Shoot", "", "", "", "", "Root", "", ""], ["", "", "H01", "H02", "H03", "H04", "H05", "H06", "H07", "H08", "H09", "H10"], ["", "H01", "1.000", "0.989", "0.987", "0.986", "0.985", "0.670", "0.673", "0.674", "0.675", "0.672"], ["", "H02", "", "1.000", "0.991", "0.985", "0.988", "0.678", "0.678", "0.681", "0.682", "0.678"], ["Shoot", "H03", "", "", "1.000", "0.987", "0.988", "0.681", "0.679", "0.683", "0.681", "0.678"], ["", "H04", "", "", "", "1.000", "0.983", "0.667", "0.673", "0.671", "0.675", "0.671"], ["", "H05", "", "", "", "", "1.000", "0.674", "0.679", "0.677", "0.681", "0.677"], ["", "H06", "", "", "", "", "", "1.000", "0.984", "0.994", "0.987", "0.983"], ["", "H07", "", "", "", "", "", "", "1.000", "0.987", "0.993", "0.985"], ["Root", "H08", "", "", "", "", "", "", "", "1.000", "0.990", "0.985"], ["", "H09", "", "", "", "", "", "", "", "", "1.000", "0.986"], ["", "H10", "", "", "", "", "", "", "", "", "", "1.000"]], "row_count": 12, "column_count": 12, "numeric_cells": 75, "header_rows": 1, "locator": "section[5]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:24398116:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8d84727702f5a5727bc2a4344fc00fb51d8051201d7c8b99c3ad6b39e6e258b1", "bytes": 1726, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#T2", "version": null, "note": "Go term significantly represented in up-regulated and shoot-specific gene clusters", "structure": {"pmcid": "PMC3891988", "section_index": 6, "section_title": "Comparison of gene expression in rice root and shoot using gene ontology analysis", "row_count": 25, "column_count": 5}, "table": {"label": "Table 2", "caption": "Go term significantly represented in up-regulated and shoot-specific gene clusters", "rows": [["", "Term (biological process)", "Count", "Percentage", "P-value"], ["Up-regulated genes: 3138 (shoot vs. root)", "Oxidation reduction", "136", "4.33%", "1.10E-17"], ["", "Photosynthesis", "36", "1.15%", "1.56E-15"], ["", "Photosynthesis, light harvesting", "10", "0.32%", "2.70E-07"], ["", "Pigment metabolic process", "13", "0.41%", "6.27E-06"], ["", "Pigment biosynthetic process", "12", "0.38%", "9.67E-06"], ["", "Photosynthesis, light reaction", "12", "0.38%", "1.30E-05"], ["", "Generation of precursor metabolites and energy", "36", "1.15%", "5.09E-05"], ["", "Fatty acid biosynthetic process", "14", "0.45%", "0.00286"], ["", "Fatty acid metabolic process", "15", "0.48%", "0.004194"], ["", "Electron transport chain", "14", "0.45%", "0.006286"], ["", "Aminoglycan metabolic process", "7", "0.22%", "0.006382"], ["", "Lipid biosynthetic process", "21", "0.67%", "0.007102"], ["", "Cellular aldehyde metabolic process", "4", "0.13%", "0.007622"], ["", "Lipid transport", "12", "0.38%", "0.009804"], ["", "Lipid localization", "12", "0.38%", "0.009804"], ["Shoot-specific genes: 438", "Oxidation reduction", "40", "9.13%", "3.40E-07"], ["", "Fatty acid metabolic process", "8", "1.83%", "1.30E-03"], ["", "Recognition of pollen", "6", "1.37%", "2.70E-03"], ["", "Pollination", "6", "1.37%", "2.70E-03"], ["", "Cell recognition", "6", "1.37%", "2.70E-03"], ["", "Pollen-pistil interaction", "6", "1.37%", "2.70E-03"], ["", "Fatty acid biosynthetic process", "7", "1.60%", "2.80E-03"], ["", "Reproductive cellular process", "6", "1.37%", "2.90E-03"], ["", "Regulation of transcription", "30", "6.85%", "1.10E-02"]], "row_count": 25, "column_count": 5, "numeric_cells": 74, "header_rows": 1, "locator": "section[6]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:24398116:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c29c21a7efcbfad4f02c304ef0a23dafa85f1d2603eef6865d279e1008d252f2", "bytes": 1508, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[2]#T3", "version": null, "note": "Go term significantly represented in down-regulated and root-specific gene clusters", "structure": {"pmcid": "PMC3891988", "section_index": 6, "section_title": "Comparison of gene expression in rice root and shoot using gene ontology analysis", "row_count": 20, "column_count": 5}, "table": {"label": "Table 3", "caption": "Go term significantly represented in down-regulated and root-specific gene clusters", "rows": [["", "Term (biological process)", "Count", "Percentage", "P-value"], ["Down-regulated genes: 3845 (shoot vs. root)", "Regulation of transcription", "110", "2.86%", "6.28E-13"], ["", "Regulation of transcription, NA-dependent", "71", "1.85%", "1.20E-10"], ["", "Regulation of RNA metabolic process", "71", "1.85%", "1.48E-10"], ["", "Transcription", "65", "1.69%", "8.87E-10"], ["", "Response to oxidative stress", "27", "0.70%", "1.93E-08"], ["", "Oxidation reduction", "81", "2.11%", "1.21E-05"], ["", "Cell wall polysaccharide metabolic process", "5", "0.13%", "0.008210995"], ["", "Oxylipin metabolic process", "5", "0.13%", "0.008210995"], ["", "Xylan metabolic process", "5", "0.13%", "0.008210995"], ["", "Xylan catabolic process", "5", "0.13%", "0.008210995"], ["", "Oxylipin biosynthetic process", "5", "0.13%", "0.008210995"], ["Shoot-specific genes: 438", "Response to oxidative stress", "11", "2.51%", "4.30E-05"], ["", "Oxidation reduction", "27", "6.16%", "1.30E-03"], ["", "Cell wall polysaccharide metabolic process", "4", "0.91%", "1.50E-03"], ["", "Xylan metabolic process", "4", "0.91%", "1.50E-03"], ["", "Hemicellulose metabolic process", "4", "0.91%", "1.50E-03"], ["", "Xylan catabolic process", "4", "0.91%", "1.50E-03"], ["", "Regulation of transcription", "27", "6.16%", "5.30E-03"], ["", "Polysaccharide metabolic process", "8", "1.83%", "6.90E-03"]], "row_count": 20, "column_count": 5, "numeric_cells": 59, "header_rows": 1, "locator": "section[6]/table-wrap[2]#T3"}}, {"id": "asset:table:pmid:24398116:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:45e2844883a66fb0f5819a5a41c72cbfc2b1649c63a02eb329f22486360720bd", "bytes": 6011, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#T4", "version": null, "note": "Comparison of expression levels (log2 ration) from qRT-PCR and microarray for selected target genes", "structure": {"pmcid": "PMC3891988", "section_index": 7, "section_title": "qRT-PCR validation", "row_count": 68, "column_count": 4}, "table": {"label": "Table 4", "caption": "Comparison of expression levels (log2 ration) from qRT-PCR and microarray for selected target genes", "rows": [["Target gene", "MSU Gene ID", "Microarray value", "qRT-PCR value"], ["", "", "(log2ratio)", "(log2ratio)"], ["Zinc finger, C3HC4 type, domain containing protein, expressed", "Os07g29600", "0.73", "0.14"], ["bZIP transcription factor domain containing protein, expressed", "Os07g48180", "−0.04", "−0.7"], ["Ankyrin repeat-rich protein, putative, expressed", "Os08g15840", "−0.99", "−0.66"], ["bZIP transcription factor domain containing protein, expressed", "Os08g26880", "1.42", "1.19"], ["Zinc finger family protein, putative, expressed", "Os08g03310", "4.58", "4.99"], ["MYB family transcription factor, putative, expressed", "Os08g33660", "3.93", "2.8"], ["B-box zinc finger family protein, putative, expressed", "Os09g35880", "0.93", "0.97"], ["Zinc finger, C3HC4 type domain containing protein, expressed", "Os09g33670", "−0.13", "−0.12"], ["MYB family transcription factor, putative, expressed", "Os09g36250", "0.75", "0.2"], ["OsWRKY80 - Superfamily of TFs having WRKY and zinc finger domains, expressed", "Os09g30400", "−0.17", "−0.48"], ["BHLH transcription factor, putative, expressed", "Os09g32510", "2.66", "1.73"], ["Zinc finger, C3HC4 type domain containing protein, expressed", "Os09g26400", "−0.17", "−0.53"], ["Dof zinc finger domain containing protein, putative, expressed", "Os09g29960", "2.57", "2.71"], ["Auxin response factor 18, putative, expressed", "Os10g33940", "−1.11", "−0.32"], ["Transcription factor, putative, expressed", "Os12g13170", "−0.08", "0.66"], ["ZOS12-05 - C2H2 zinc finger protein, expressed", "Os12g31840", "−0.45", "−0.38"], ["OsRR4 type-A response regulator, expressed", "Os01g72330", "2.53", "2.42"], ["Inducer of CBF expression 2, putative, expressed", "Os01g70310", "4.86", "4.05"], ["PHD finger protein, putative, expressed", "Os01g66420", "0.02", "−0.28"], ["SNF2 family N-terminal domain containing protein, expressed", "Os02g02290", "0.14", "0.11"], ["MYB family transcription factor, putative, expressed", "Os01g59660", "−1.41", "−0.76"], ["No apical meristem protein, putative, expressed", "Os01g48130", "0.31", "−0.02"], ["GATA transcription factor 25, putative, expressed", "Os02g05510", "−0.53", "−0.09"], ["PHD finger protein, putative, expressed", "Os02g35600", "2.08", "0.74"], ["AP2 domain containing protein, expressed", "Os02g29550", "0.42", "1.23"], ["Two-component response regulator, putative, expressed", "Os02g55320", "0.84", "0.46"], ["OsMADS22 - MADS-box family gene with MIKCc type-box, expressed", "Os02g52340", "2.78", "2.13"], ["Histidine kinase, putative, expressed", "Os02g50480", "0.12", "0.49"], ["DIRP family protein, putative, expressed", "Os03g43800", "−0.18", "0.21"], ["OsWRKY55 - Superfamily of TFs having WRKY and zinc finger domains, expressed", "Os03g20550", "−2.11", "−2.45"], ["ZOS3-23 - C2H2 zinc finger protein, expressed", "Os03g61640", "−0.64", "0.3"], ["NAC domain-containing protein 67, putative, expressed", "Os03g60080", "−4.04", "−4.17"], ["MYB family transcription factor, putative, expressed", "Os04g49450", "−2.27", "−2.01"], ["Auxin response factor, putative, expressed", "Os04g57610", "1.17", "1.13"], ["MYB_Al protein, putative, expressed", "Os04g58020", "0.1", "−0.12"], ["Zinc RING finger protein, putative, expressed", "Os06g03580", "−2.82", "−2.41"], ["bHelix-loop-helix transcription factor, putative, expressed", "Os05g46370", "−0.55", "−0.81"], ["Transcription factor, putative, expressed", "Os05g37170", "−2.58", "−1.44"], ["myb-like DNA-binding domain containing protein, expressed", "Os06g24070", "4.09", "4.63"], ["Zinc finger protein, putative, expressed", "Os06g33810", "0.27", "−0.25"], ["N-terminal asparagine amidohydrolase, putative, expressed", "Os06g41390", "−0.6", "−0.02"], ["TIP41, putative, expressed", "Os03g55270", "−0.73", "−0.5"], ["B3 DNA binding domain containing protein, expressed", "Os01g04800", "−3.02", "−2.99"], ["ZOS1-03 - C2H2 zinc finger protein, expressed", "Os01g04120", "−3.41", "−4.35"], ["TCP family transcription factor, putative, expressed", "Os01g11550", "2.09", "3"], ["RNA-binding zinc finger protein, putative, expressed", "Os07g48410", "0.68", "0.85"], ["GRAS family transcription factor domain containing protein, expressed", "Os07g38030", "1.77", "1.44"], ["Response regulator receiver domain containing protein, expressed", "Os07g49460", "−1.54", "−0.69"], ["Auxin response factor, putative, expressed", "Os08g40900", "−0.82", "0.55"], ["Homeobox associated leucine zipper, putative, expressed", "Os09g21180", "1.06", "0.23"], ["No apical meristem protein, putative, expressed", "Os10g42130", "−0.03", "−0.19"], ["MYB family transcription factor, putative, expressed", "Os01g74410", "−4.45", "−3.84"], ["bZIP transcription factor domain containing protein, expressed", "Os01g55150", "0.18", "0.15"], ["OsWRKY71 - Superfamily of TFs having WRKY and zinc finger domains, expressed", "Os02g08440", "−5.14", "−2.75"], ["Ethylene-responsive transcription factor, putative, expressed", "Os02g43790", "−4.02", "−1.47"], ["TCP family transcription factor, putative, expressed", "Os02g42380", "4.84", "4.24"], ["RING-H2 finger protein, putative, expressed", "Os02g54830", "0.35", "−0.04"], ["Dof zinc finger domain containing protein, putative, expressed", "Os02g47810", "2.99", "1.97"], ["Ethylene-responsive transcription factor, putative, expressed", "Os03g09170", "−5.3", "−3.76"], ["Homeobox associated leucine zipper, putative, expressed", "Os03g08960", "3.17", "2.13"], ["TCP-domain protein, putative, expressed", "Os02g51280", "0.05", "0.4"], ["Response regulator receiver domain containing protein, expressed", "Os03g17570", "−1.86", "−1.42"], ["ZOS3-21 - C2H2 zinc finger protein, expressed", "Os03g60560", "−5.18", "−6.27"], ["MYB family transcription factor, putative, expressed", "Os05g04820", "0.68", "0.7"], ["Actin, putative, expressed", "Os05g36290", "−0.97", "0"], ["TCP-domain protein, putative, expressed", "Os06g12230", "0.89", "0.29"]], "row_count": 68, "column_count": 4, "numeric_cells": 211, "header_rows": 2, "locator": "section[7]/table-wrap[1]#T4"}}], "gaps": ["asset:data:geo:GSE50844 not downloaded", "asset:data:geo:GSE50844 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "GO enrichment"}}, {"id": "method-2", "family": null, "specific": null, "label": "Gene Ontology enrichment analysis using DAVID Bioinformatics Resources 6.7", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Gene set analysis was performed using Gene Ontology terms with functional annotation, as described in DAVID Bioinformatics Resources 6.7 (http://david.abcc.ncifcrf.gov/) [9,10]."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": ["pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pathway_enrichment."}, "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": ["GSE50844"], "resolved_accessions": ["GSE50844"], "statements": ["All normalized and raw data were submitted to NCBI’s Gene Expression Omnibus (GEO) for others to examine. The data are accessible via GEO Series accession number GSE50844 http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE50844."], "basis": "The paper names GSE50844 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pathway_enrich"], "assets": ["source:pmid:24398116", "data:geo:GSE50844", "asset:table:pmid:24398116:1", "asset:table:pmid:24398116:2", "asset:table:pmid:24398116:3", "asset:table:pmid:24398116:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE50844"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": null, "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 0, "usage": {}}, "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:24398116", "type": "paper", "label": "pmid:24398116"}, {"id": "source:pmid:24398116", "type": "manuscript", "label": "PMID 24398116 full text"}, {"id": "data:geo:GSE50844", "type": "dataset", "label": "GEO GSE50844"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:24398116", "type": "paper", "label": "pmid:24398116"}, {"id": "source:pmid:24398116", "type": "manuscript", "label": "PMID 24398116 full text"}, {"id": "data:geo:GSE50844", "type": "dataset", "label": "GEO GSE50844"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-24398116", "type": "extraction", "used": ["source:pmid:24398116"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE50844", "type": "accession_resolution", "used": ["data:geo:GSE50844"], "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:24398116", "parent_hash": "sha256:5c21a8a4a3be4f965d8d2bd871a37e2585960b9fafb6c078035c5fd9488ad9da", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE50844 licence not read", "asset:data:geo:GSE50844 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": ["Development of a microarray for two rice subspecies: characterization an", "lant growth and development. Gene expression microarray technology represents a key strategy for the", "ort on the development of the rice OneArray® microarray platform which is suitable for two major ric", ": The rice OneArray® 60-mer, oligonucleotide microarray consists of a total of 21,179 probes coverin"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["GO enrichment"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:45:46+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}