{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26697344", "kind": "science-record", "revision": 8, "content_hash": "sha256:87401ace55b6a511a2cafb3ff45c5ff67b90f8ca07952f0c0ac6f78f217b4a47", "created_at": "2026-11-01T15:40:14Z", "updated_at": "2026-11-01T22:42:30Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of differentially expressed genes between developing seeds of different soybean cultivars.", "doi": "10.1016/j.gdata.2015.08.005", "pmid": "26697344", "authors": ["Rongshuang Lin", "Jane Glazebrook", "Fumiaki Katagiri", "James H Orf", "Susan I Gibson"], "journal": "Genomics data", "year": 2015, "abstract": "Soybean is a major source of protein and oil and a primary feedstock for biodiesel production. Research on soybean seed composition and yield has revealed that protein, oil and yield are controlled quantitatively and quantitative trait loci (QTL) have been identified for each of these traits. However, very limited information is available regarding the genetic mechanisms controlling seed composition and yield. To help address this deficiency, we used Affymetrix Soybean GeneChips® to identify genes that are differentially expressed between developing seeds of the Minsoy and Archer soybean cultivars, which differ in seed weight, yield, protein content and oil content. A total of 700 probe sets were found to be expressed at significantly different (defined as having an adjusted p-value below or equal to 0.05 and an at least 2-fold difference) levels between the two cultivars at one or more of the three developmental stages and in at least one of the two years assayed. Comparison of data from soybeans collected in two different years revealed that 97 probe sets were expressed at significantly different levels in both years. Functional annotations were assigned to 78% of these 97 probe sets based on the SoyBase Affymetrix™ GeneChip® Soybean Genome Array Annotation. Genes involved in receptor binding/activity and protein binding are overrepresented among the group of 97 probe sets that were differentially expressed in both years assayed. Probe sets involved in growth/development, signal transduction, transcription, defense/stress response and protein and lipid metabolism were also identified among the 97 probe sets and their possible implications in the regulation of agronomic traits are discussed. As the Minsoy and Archer soybean cultivars differ with respect to seed size, yield, protein content and lipid content, some of the differentially expressed probe sets identified in this study may thus play important roles in controlling these traits. Others of these probe sets may be involved in regulation of general seed development or metabolism. All microarray data and expression values after GCRMA are available at the Gene Expression Omnibus (GEO) at NCBI (http://www.ncbi.nlm.nih.gov/geo), under accession number GSE21598.", "claims": [{"id": "claim-method", "statement": "The lmFit function (limma package) [35] was used to fit a linear model to identify differentially expressed genes between the two parental lines and the two RILs at each stage. The empirical Bayes (eBayes) method was used to adjust variances, and Benjamini-Hochberg's False Discovery Rate (FDR) was calculated for multiple test correction [36].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26697344", "locator": "sections[12] \"Analysis of microarray data\" paragraph 4", "quote": "The lmFit function (limma package) [35] was used to fit a linear model to identify differentially expressed genes between the two parental lines and the two RILs at each stage. The empirical Bayes (eBayes) method was used to adjust variances, and Benjamini-Hochberg's False Discovery Rate (FDR) was calculated for multiple test correction [36]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All microarray data and expression values after GCRMA are available at the Gene Expression Omnibus (GEO) at NCBI (http://www.ncbi.nlm.nih.gov/geo), under accession number GSE21598.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26697344", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "All microarray data and expression values after GCRMA are available at the Gene Expression Omnibus (GEO) at NCBI (http://www.ncbi.nlm.nih.gov/geo), under accession number GSE21598."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using an adjusted p-value ≤0.05 and ≥2-fold expression difference, the study identified 700 differentially expressed probe sets, and the microarray data are available through GEO under accession GSE21598.", "kind": "quantitative", "target": {"value": 2.0, "unit": "fold change", "tolerance": null, "source": "A total of 700 probe sets were found to be expressed at significantly different (defined as having an adjusted p-value below or equal to 0.05 and an at least 2-fold difference) levels between the two cultivars at one or more of the three developmental stages and in at least one of the two years assayed. All microarray data and expression values after GCRMA are available at the Gene Expression Omnibus (GEO) at NCBI (http://www.ncbi.nlm.nih.gov/geo), under accession number GSE21598."}, "evidence": [{"asset": "source:pmid:26697344", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "A total of 700 probe sets were found to be expressed at significantly different (defined as having an adjusted p-value below or equal to 0.05 and an at least 2-fold difference) levels between the two cultivars at one or more of the three developmental stages and in at least one of the two years assayed."}, {"asset": "source:pmid:26697344", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "All microarray data and expression values after GCRMA are available at the Gene Expression Omnibus (GEO) at NCBI (http://www.ncbi.nlm.nih.gov/geo), under accession number GSE21598."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Using an adjusted p-value ≤0.05 and ≥2-fold expression difference, the study identified 700 differentially expressed probe sets, and the microarray data are available through GEO under accession GSE21598.", "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:26697344"], "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:GSE21598"], "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": {"fdr_threshold": "and Benjamini-Hochberg false discovery rate correction"}, "inputs": ["data:geo:GSE21598"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26697344", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gdata.2015.08.005", "sha256": "sha256:57ed167abb2d85e26d4ac99e87bbae8b46e3b87dae4de9d0e028c42783698440", "bytes": 45704, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gdata.2015.08.005", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4664686", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE21598", "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=GSE21598", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21598", "version": null, "note": "All microarray data and expression values after GCRMA are available at the Gene Expression Omnibus (GEO) at NCBI (http://www.ncbi.nlm.nih.gov/geo), under accession number GSE21598.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All microarray data and expression values after GCRMA are available at the Gene Expression Omnibus (GEO) at NCBI (http://www.ncbi.nlm.nih.gov/geo), under accession number GSE21598.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM539211", "GSM539212", "GSM539213", "GSM539214", "GSM539215", "GSM539216", "GSM539217", "GSM539218", "GSM539219", "GSM539220", "GSM539221", "GSM539222", "GSM539223", "GSM539224", "GSM539225", "GSM539226", "GSM539227", "GSM539228", "GSM539229", "GSM539230", "GSM539231", "GSM539232", "GSM539233", "GSM539234", "GSM539235", "GSM539236", "GSM539237", "GSM539238", "GSM539239", "GSM539240", "GSM539241", "GSM539242", "GSM539243", "GSM539244", "GSM539245", "GSM539246", "GSM539247", "GSM539248", "GSM539249", "GSM539250", "GSM539251", "GSM539252", "GSM539253", "GSM539254", "GSM539255", "GSM539256", "GSM539257", "GSM539258", "GSM539259", "GSM539260", "GSM539261", "GSM539262", "GSM539263", "GSM539264"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "4592", "taxon": "Glycine max", "title": "Identification of differentially expressed genes between developing seeds of different soybean cultivars", "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:26697344:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6f1d945f6ef3e93d2e2aa77d39e0ab4782a63aa33232c9d5e625cb7a1378b9b0", "bytes": 747, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#t0005", "version": null, "note": "Comparison of seed composition, weight and yield between the Minsoy and Archer cultivars and two recombinant inbred lines (RILs). Data for the two parental lines were taken from published sources [7], [9], [18] and data for the two RILs are based on combined data collected from plants grown during 2000 in Becker, MN and during 2001 in Waseca, MN (unpublished data).", "structure": {"pmcid": "PMC4664686", "section_index": 4, "section_title": "Introduction", "row_count": 5, "column_count": 5}, "table": {"label": "Table 1", "caption": "Comparison of seed composition, weight and yield between the Minsoy and Archer cultivars and two recombinant inbred lines (RILs). Data for the two parental lines were taken from published sources [7], [9], [18] and data for the two RILs are based on combined data collected from plants grown during 2000 in Becker, MN and during 2001 in Waseca, MN (unpublished data).", "rows": [["Trait", "RIL 6049-273", "RIL 6049-32", "Archer", "Minsoy"], ["Yield (bu/a)", "66.1", "33.5", "49", "29"], ["Oil (g/kg)", "166", "162", "187", "178"], ["Protein (g/kg)", "344", "366", "340", "353"], ["Seed weight (mg/seed)", "188", "142", "161", "123"]], "row_count": 5, "column_count": 5, "numeric_cells": 18, "header_rows": 1, "locator": "section[4]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:26697344:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:58032ebf86ead7834cc6def65af0b9ca16051bbf67954cd75cd6815bcb767485", "bytes": 1068, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#t0010", "version": null, "note": "Comparison of number of differentially expressed transcripts between Minsoy and Archer and two recombinant inbred lines (RILs). The significant cutoff value is q-value = 0.05 and 2-fold change in expression values. The two RILs are LY (lower yield) line 6049–32 and HY (higher yield) line 6049-273.", "structure": {"pmcid": "PMC4664686", "section_index": 6, "section_title": "Identification of differentially expressed probe sets", "row_count": 10, "column_count": 5}, "table": {"label": "Table 2", "caption": "Comparison of number of differentially expressed transcripts between Minsoy and Archer and two recombinant inbred lines (RILs). The significant cutoff value is q-value = 0.05 and 2-fold change in expression values. The two RILs are LY (lower yield) line 6049–32 and HY (higher yield) line 6049-273.", "rows": [["Affymetrix probe sets", "Stage 1", "Stage 2", "Stage 3", "Total in all stages combineda"], ["Higher in Minsoy in 2007", "117", "120", "167", "273"], ["Higher in Archer in 2007", "172", "140", "135", "301"], ["Total different between Minsoy and Archer in 2007", "289", "260", "302", "574"], ["Higher in Minsoy in 2008", "62", "67", "73", "104"], ["Higher in Archer in 2008", "89", "76", "97", "128"], ["Total different between Minsoy and Archer in 2008", "151", "143", "170", "232"], ["Higher in LY RIL in 2007", "74", "6", "0", "78"], ["Higher in HY RIL in 2007", "55", "14", "0", "66"], ["Total different between LY and HY RILs in 2007", "129", "20", "0", "144"]], "row_count": 10, "column_count": 5, "numeric_cells": 48, "header_rows": 1, "locator": "section[6]/table-wrap[1]#t0010"}}, {"id": "asset:table:pmid:26697344:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d86bcac6397cf6281b40d7a41e829854ee48a7aea800667faa0ee9e6b5cee82a", "bytes": 2069, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#t0015", "version": null, "note": "Probe sets potentially involved in seed growth/development and signal transduction. Probe sets that were found to be expressed at significantly different levels between Minsoy and Archer in one or more developmental stages during 2007 and 2008 were searched for those predicted by their GO assignments to be involved in seed growth/development/signal transduction. Significant differences in transcript levels are defined as having a q-value ≤ 0.05 and fold difference ≥ 2. The developmental stage(s) and year(s) in which significant differences in transcript levels were detected for a particular gene are indicated. The cultivar that has higher expression values is also indicated. S1, S2, S3 represent developmental stage 1 (2 mm seeds), stage 2 (3.5 mm seeds) and stage 3 (5–6 mm seeds), respectively. (07) and (08) refer to 2007 and 2008, respectively.", "structure": {"pmcid": "PMC4664686", "section_index": 7, "section_title": "Functional categories of differentially expressed probe sets", "row_count": 12, "column_count": 4}, "table": {"label": "Table 3", "caption": "Probe sets potentially involved in seed growth/development and signal transduction. Probe sets that were found to be expressed at significantly different levels between Minsoy and Archer in one or more developmental stages during 2007 and 2008 were searched for those predicted by their GO assignments to be involved in seed growth/development/signal transduction. Significant differences in transcript levels are defined as having a q-value ≤ 0.05 and fold difference ≥ 2. The developmental stage(s) and year(s) in which significant differences in transcript levels were detected for a particular gene are indicated. The cultivar that has higher expression values is also indicated. S1, S2, S3 represent developmental stage 1 (2 mm seeds), stage 2 (3.5 mm seeds) and stage 3 (5–6 mm seeds), respectively. (07) and (08) refer to 2007 and 2008, respectively.", "rows": [["Affymetrix probe set ID", "Gene description", "Stage (year)", "Higher expression"], ["Gma.1471.2.S1_at", "Suppressor of PHYA-105 1 (SPA1)", "S1,2 (07);S1,2,3 (08)", "Archer"], ["Gma.12643.1.A1_at", "Light repressible receptor protein kinase", "S1 (07);S1,2,3 (08)", "Minsoy"], ["GmaAffx.88161.1.S1_at", "Phytochrome (PHYA)", "S1 (07);S1,2,3 (08)", "Archer"], ["Gma.7387.1.A1_at", "Pseudo-response regulator 7 (PRR7)", "S1,2,3 (07,08)", "Minsoy"], ["GmaAffx.77896.1.S1_at", "Suppressor of auxin resistance 3 (SAR3)", "S1,2,3 (07,08)", "Archer"], ["GmaAffx.90343.1.S1_at", "GAST1 protein homolog 4 (GASA4)", "S1,2 (07);S2,3 (08)", "Minsoy"], ["GmaAffx.90343.1.S1_s_at", "GAST1 protein homolog 4 (GASA4)", "S1,2 (07);S2,3 (08)", "Minsoy"], ["Gma.473.1.A1_at", "Retinoblastoma-related 1 (RBR1)", "S1 (07);S1,2,3 (08)", "Archer"], ["GmaAffx.21668.1.A1_at", "COBRA (COB)", "S1,2,3 (07,08)", "Archer"], ["GmaAffx.28349.1.S1_at", "Ankyrin repeat_containing 2B (AKR2B)", "S1,2 (07);S1,2,3 (08)", "Archer"], ["GmaAffx.7290.1.A1_at", "alpha-N-acetylglucosaminidase family/NAGLU family", "S3 (07,08)", "Archer"]], "row_count": 12, "column_count": 4, "numeric_cells": 29, "header_rows": 1, "locator": "section[7]/table-wrap[1]#t0015"}}, {"id": "asset:table:pmid:26697344:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e270d2cb687a3b32d697ca0523a3565715308bba8e146cf131f6a35fa285beaf", "bytes": 2409, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[2]#t0020", "version": null, "note": "Probe sets potentially involved in defense and stress responses. Probe sets predicted to be involved in defense and/or stress response and that exhibit significant differences in transcript levels between Minsoy and Archer were identified. See Table 3 legend for additional information.", "structure": {"pmcid": "PMC4664686", "section_index": 7, "section_title": "Functional categories of differentially expressed probe sets", "row_count": 21, "column_count": 4}, "table": {"label": "Table 4", "caption": "Probe sets potentially involved in defense and stress responses. Probe sets predicted to be involved in defense and/or stress response and that exhibit significant differences in transcript levels between Minsoy and Archer were identified. See Table 3 legend for additional information.", "rows": [["Affymetrix probe set ID", "Gene description", "Stage (year)", "Higher expression"], ["Gma.1034.4.S1_s_atb", "Caffeoyl-CoA 3-O-methyltransferase, putative", "S3 (07);S1,3 (08)", "Minsoy"], ["Gma.11082.2.A1_s_atb", "Caffeoyl-CoA 3-O-methyltransferase, putative", "S3 (07);S1,3 (08)", "Minsoy"], ["Gma.11344.1.S1_at", "Disease resistance gene (R gene)", "S1,2,3 (07,08)", "Archer"], ["Gma.13012.1.A1_at", "Disease resistance protein (TIR-NBS-LRR class), putative", "S1,2,3 (07,08)", "Archer"], ["Gma.17871.1.S1_at", "Disease resistance protein (TIR-NBS-LRR class), putative", "S1 (07);S1,2,3 (08)", "Archer"], ["Gma.13036.1.S1_at", "Inducer of CBF expression 1 (ICE1)", "S1,2,3 (07,08)", "Minsoy"], ["Gma.1464.1.S1_at", "Rotamase FKBP 1 (ROF1)", "S1,2 (07);S1,2,3 (08)", "Archer"], ["Gma.1571.1.S1_at", "ALDH10A8, 3-chloroallyl aldehyde dehydrogenase/oxidoreductase", "S1,2 (07);S2,3 (08)", "Minsoy"], ["Gma.16586.1.S1_at", "Harpin-induced 1", "S1,2,3 (07);S3 (08)", "Minsoy"], ["Gma.2628.1.A1_at", "Arabidopsis thaliana peptide-N-glycanase 1 (AtPNG1)", "S1,2 (07,08)", "Archer"], ["Gma.4155.1.S1_ata", "RAP2.12,ERF/AP2 transcription factor family", "S1,2,3 (07,08)", "Minsoy"], ["Gma.4155.2.S1_s_ata", "RAP2.12,ERF/AP2 transcription factor family", "S1,2,3 (07,08)", "Minsoy"], ["GmaAffx.14960.1.S1_s_ata", "RAP2.12,ERF/AP2 transcription factor family", "S1 (07);S1,2,3 (08)", "Minsoy"], ["Gma.7716.1.A1_at", "Zinc induced facilitator 1 (ZIF1)", "S2 (07);S1,2,3 (08)", "Minsoy"], ["Gma.8522.1.S1_at", "Major latex protein-related/MLP-related", "S1,2 (07);S1,2,3 (08)", "Archer"], ["GmaAffx.21668.1.A1_at", "COBRA (COB)", "S1,2,3 (07,08)", "Archer"], ["GmaAffx.59014.1.S1_s_at", "Dehydrin family protein", "S1,2 (07);S1 (08)", "Archer"], ["GmaAffx.66290.1.S1_at", "Disease resistance protein (CC-NBS class), putative", "S1,2 (07);S1,2,3 (08)", "Archer"], ["GmaAffx.77896.1.S1_at", "Suppressor of auxin resistance 3 (SAR3), nucleoporin", "S1,2,3 (07,08)", "Archer"], ["GmaAffx.93642.1.S1_s_at", "Secretory protein, putative", "S2 (07);S1,2 (08)", "Archer"]], "row_count": 21, "column_count": 4, "numeric_cells": 52, "header_rows": 1, "locator": "section[7]/table-wrap[2]#t0020"}}, {"id": "asset:table:pmid:26697344:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:60d0f3dbf82d5991c0765e3346955883912746f12ef3b8f964ad2d84472c3499", "bytes": 1037, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[3]#t0025", "version": null, "note": "Probe sets potentially related to protein metabolism. Probe sets predicted to be involved in protein metabolism and that exhibit significant differences in transcript levels between Minsoy and Archer were identified. See Table 3 legend for additional information.", "structure": {"pmcid": "PMC4664686", "section_index": 7, "section_title": "Functional categories of differentially expressed probe sets", "row_count": 7, "column_count": 4}, "table": {"label": "Table 5", "caption": "Probe sets potentially related to protein metabolism. Probe sets predicted to be involved in protein metabolism and that exhibit significant differences in transcript levels between Minsoy and Archer were identified. See Table 3 legend for additional information.", "rows": [["Affymetrix probe set ID", "Gene description", "Stage (year)", "Higher expression"], ["Gma.13070.2.A1_at", "Ribosomal protein L25", "S1,2,3 (07,08)", "Minsoy"], ["Gma.2628.1.A1_at", "Arabidopsis thaliana peptide-N-glycanase 1 (AtPNG1)", "S1,2 (07)", "Archer"], ["Gma.7719.1.A1_at", "TIF3H1, translation initiation factor", "S1 (07);S1,2,3 (08)", "Archer"], ["GmaAffx.16360.1.S1_at", "Glyoxylate/hydroxypyruvate reductase", "S2 (07);S1,2,3 (08)", "Archer"], ["GmaAffx.20624.1.S1_at", "PUB14, ubiquitin-protein ligase", "S1 (07,08)", "Archer"], ["GmaAffx.93183.1.S1_at", "S-adenosylmethionine decarboxylase (SAMDC)", "S1,2 (07);S1,2,3 (08)", "Archer"]], "row_count": 7, "column_count": 4, "numeric_cells": 15, "header_rows": 1, "locator": "section[7]/table-wrap[3]#t0025"}}, {"id": "asset:table:pmid:26697344:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bb47d081b337d8a23471031b0e0f5dfd0e455b75c269b76651cd3aca3184bf83", "bytes": 1300, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[4]#t0030", "version": null, "note": "Probe sets potentially involved in lipid metabolism. Probe sets predicted to be involved in lipid metabolism and that exhibit significant differences in transcript levels between Minsoy and Archer were identified. Gene function was predicted both on the basis of SoyBase Affymetrix ™ GeneChip® Soybean Genome Array Annotation and the Arabidopsis lipid gene database [14] (http://www.plantbiology.msu.edu/lipids/genesurvey/index.htm). See Table 3 legend for additional information.", "structure": {"pmcid": "PMC4664686", "section_index": 7, "section_title": "Functional categories of differentially expressed probe sets", "row_count": 8, "column_count": 4}, "table": {"label": "Table 6", "caption": "Probe sets potentially involved in lipid metabolism. Probe sets predicted to be involved in lipid metabolism and that exhibit significant differences in transcript levels between Minsoy and Archer were identified. Gene function was predicted both on the basis of SoyBase Affymetrix ™ GeneChip® Soybean Genome Array Annotation and the Arabidopsis lipid gene database [14] (http://www.plantbiology.msu.edu/lipids/genesurvey/index.htm). See Table 3 legend for additional information.", "rows": [["AffyID", "Gene description", "Stage (year)", "Higher expression"], ["Gma.13043.1.S1_at", "Arabidopsis thaliana carboxyesterase 20 (AtCXE20)", "S1,2,3 (07);S3 (08)", "Minsoy"], ["Gma.13216.2.S1_ata", "Ceramidase family protein", "S1,2,3 (07,08)", "Archer"], ["Gma.4488.1.A1_s_ata", "Ceramidase family protein", "S1,2,3 (07,08)", "Archer"], ["Gma.6802.1.A1_at", "GLIP5, carboxylesterase/lipase", "S1,3 (07);S1,2,3 (08)", "Minsoy"], ["GmaAffx.18905.1.S1_at", "Esterase/lipase/thioesterase", "S1,2 (07,08)", "Minsoy"], ["GmaAffx.37987.1.S1_at", "Diacylglycerol acyltransferase family", "S1 (07,08)", "Archer"], ["GmaAffx.6790.1.S1_at", "Epoxide hydrolase, putative", "S1,2,3 (07);S1 (08)", "Minsoy"]], "row_count": 8, "column_count": 4, "numeric_cells": 15, "header_rows": 1, "locator": "section[7]/table-wrap[4]#t0030"}}], "gaps": ["asset:data:geo:GSE21598 not downloaded", "asset:data:geo:GSE21598 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {"fdr_threshold": "and Benjamini-Hochberg false discovery rate correction"}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The lmFit function (limma package) [35] was used to fit a linear model to identify differentially expressed genes between the two parental lines and the two RILs at each stage. The empirical Bayes (eBayes) method was used to adjust variances, and Benjamini-Hochberg's False Discovery Rate (FDR) was calculated for multiple test correction [36]."}}, {"id": "method-2", "family": "genetic_association", "specific": "linkage", "label": "Genetic association (GWAS / linkage / MR)", "dsl_operations": ["gwas_locus_scan", "mr_estimate", "linkage_scan"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["genotype_phenotype_table"], "evidence": {"score": 0.7, "band": "medium", "quote": "QTL"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "differential_expression_fit", "expected_value": 2.0, "unit": "fold change", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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: limma_voom."}, "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": ["GSE21598"], "resolved_accessions": ["GSE21598"], "statements": ["All microarray data and expression values after GCRMA are available at the Gene Expression Omnibus (GEO) at NCBI (http://www.ncbi.nlm.nih.gov/geo), under accession number GSE21598."], "basis": "The paper names GSE21598 in Gene Expression Omnibus (GEO) at NCBI 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:26697344", "data:geo:GSE21598", "asset:table:pmid:26697344:1", "asset:table:pmid:26697344:2", "asset:table:pmid:26697344:3", "asset:table:pmid:26697344:4", "asset:table:pmid:26697344:5", "asset:table:pmid:26697344:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE21598"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:26:39Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 86943, "completion_tokens": 2874, "cached_tokens": 11776}}, "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:26697344", "type": "paper", "label": "pmid:26697344"}, {"id": "source:pmid:26697344", "type": "manuscript", "label": "PMID 26697344 full text"}, {"id": "data:geo:GSE21598", "type": "dataset", "label": "GEO GSE21598"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26697344", "type": "paper", "label": "pmid:26697344"}, {"id": "source:pmid:26697344", "type": "manuscript", "label": "PMID 26697344 full text"}, {"id": "data:geo:GSE21598", "type": "dataset", "label": "GEO GSE21598"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26697344", "type": "extraction", "used": ["source:pmid:26697344"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE21598", "type": "accession_resolution", "used": ["data:geo:GSE21598"], "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:26697344", "parent_hash": "sha256:37a9e93a4e4795a2029126fdb166e2ca73721cf3b76659e05e6188ffe2f7037b", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE21598 licence not read", "asset:data:geo:GSE21598 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": ["general seed development or metabolism. All microarray data and expression values after GCRMA are a", "ld. To help address this deficiency, we used Affymetrix Soybean GeneChips® to identify genes that ar", "of these 97 probe sets based on the SoyBase Affymetrix™ GeneChip® Soybean Genome Array Annotation.", "to − 80 °C until RNA extraction. Analysis of microarray data The Affymetrix Soybean GeneChip® contai"], "order_basis": "paper_text_order:516", "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 lmFit function (limma package) [35] was used to fit a linear model to identify differentially expressed genes between the two parental lines and the two RILs at each stage. The empirical Bayes (eBayes) method was used to adjust variances, and Benjamini-Hochberg's False Discovery Rate (FDR) was calculated for multiple test correction [36]."], "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":"2026-11-04T03:17:21+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}}}