Identification of genome-specific transcripts in wheat-rye translocation lines.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26484243", "kind": "science-record", "revision": 8, "content_hash": "sha256:28436e9db5dd495e708ae39a1aa1be5276d93be866e7007372011e6fd9a72c05", "created_at": "2026-11-01T15:40:12Z", "updated_at": "2026-11-01T22:42:24Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of genome-specific transcripts in wheat-rye translocation lines.", "doi": "10.1016/j.gdata.2015.05.045", "pmid": "26484243", "authors": ["Tong Geon Lee", "Yong Weon Seo"], "journal": "Genomics data", "year": 2015, "abstract": "Studying gene expression in wheat-rye translocation lines is complicated due to the presence of homeologs in hexaploid wheat and high levels of synteny between wheat and rye genomes (Naranjo and Fernandez-Rueda, 1991 [1]; Devos et al., 1995 [2]; Lee et al., 2010 [3]; Lee et al., 2013 [4]). To overcome limitations of current gene expression studies on wheat-rye translocation lines and identify genome-specific transcripts, we developed a custom Roche NimbleGen Gene Expression microarray that contains probes derived from the sequence of hexaploid wheat, diploid rye and diploid progenitors of hexaploid wheat genome (Lee et al., 2014). Using the array developed, we identified genome-specific transcripts in a wheat-rye translocation line (Lee et al., 2014). Expression data are deposited in the NCBI Gene Expression Omnibus (GEO) under accession number GSE58678. Here we report the details of the methods used in the array workflow and data analysis.", "claims": [{"id": "claim-method", "statement": "Multiple analyses were performed with LIMMA package in R software environment. A threshold of 0.05 (false discovery rate; FDR) was applied.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26484243", "locator": "sections[7] \"Data analysis\" paragraph 2", "quote": "Multiple analyses were performed with LIMMA package in R software environment. A threshold of 0.05 (false discovery rate; FDR) was applied."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Expression data are deposited in the NCBI Gene Expression Omnibus (GEO) under accession number GSE58678.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26484243", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Expression data are deposited in the NCBI Gene Expression Omnibus (GEO) under accession number GSE58678."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper reports the methods used in the custom array workflow and data analysis, and states that the expression data are deposited in NCBI Gene Expression Omnibus under accession number GSE58678.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:26484243", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Here we report the details of the methods used in the array workflow and data analysis."}, {"asset": "source:pmid:26484243", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Expression data are deposited in the NCBI Gene Expression Omnibus (GEO) under accession number GSE58678."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper reports the methods used in the custom array workflow and data analysis, and states that the expression data are deposited in NCBI Gene Expression Omnibus under accession number GSE58678.", "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:26484243"], "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:GSE58678"], "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:GSE58678"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26484243", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gdata.2015.05.045", "sha256": "sha256:2f48b727f19eea09b41856d5357ac51b8a30b25ab399408815b372b083fb9910", "bytes": 8448, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gdata.2015.05.045", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4583666", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE58678", "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=GSE58678", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE58678", "version": null, "note": "Expression data are deposited in the NCBI Gene Expression Omnibus (GEO) under accession number GSE58678.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Expression data are deposited in the NCBI Gene Expression Omnibus (GEO) under accession number GSE58678.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1416760", "GSM1416761", "GSM1416762", "GSM1416763", "GSM1416764", "GSM1416765", "GSM1416766", "GSM1416767", "GSM1416768", "GSM1416769", "GSM1416770", "GSM1416771"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "18847", "taxon": "Triticum aestivum; Triticum urartu; Aegilops speltoides; Aegilops tauschii; Secale cereale", "title": "Expression analysis of individual homoeologous wheat genome- and rye genome-specific transcripts in a 2BS.2RL wheat-rye translocation", "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:26484243:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:42840d46f9b1208b0eaf2a90b81264f6f7996895b74c2f27434256d324edcc83", "bytes": 778, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0010", "version": null, "note": null, "structure": {"pmcid": "PMC4583666", "section_index": 1, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Specifications"], ["Organism/cell line/tissue", "Aegilops speltoides, Aegilops squarrosa, Aegilops tauschii, Secale cereale, Triticum aestivum, Triticum monococcum, Triticum urartu"], ["Sex", "Not applicable"], ["Sequencer or array type", "Roche NimbleGen Gene Expression microarray 135K"], ["Data format", "normalized data: SOFT, MINiML, and TXT"], ["Experimental factors", "Unstressed and drought-stressed plants"], ["Experimental features", "A technical possibility for designing genome-specific probes to detect gene expression in wheat–rye translocation lines"], ["Consent", "Not applicable"], ["Sample source location", "Not applicable"]], "row_count": 9, "column_count": 2, "numeric_cells": 1, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0010"}}], "gaps": ["asset:data:geo:GSE58678 not downloaded", "asset:data:geo:GSE58678 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": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Multiple analyses were performed with LIMMA package in R software environment. A threshold of 0.05 (false discovery rate; FDR) was applied."}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: 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": ["GSE58678"], "resolved_accessions": ["GSE58678"], "statements": ["Expression data are deposited in the NCBI Gene Expression Omnibus (GEO) under accession number GSE58678."], "basis": "The paper names GSE58678 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:26484243", "data:geo:GSE58678", "asset:table:pmid:26484243:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE58678"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:25:46Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 22109, "completion_tokens": 2440, "cached_tokens": 2104}}, "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:26484243", "type": "paper", "label": "pmid:26484243"}, {"id": "source:pmid:26484243", "type": "manuscript", "label": "PMID 26484243 full text"}, {"id": "data:geo:GSE58678", "type": "dataset", "label": "GEO GSE58678"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26484243", "type": "paper", "label": "pmid:26484243"}, {"id": "source:pmid:26484243", "type": "manuscript", "label": "PMID 26484243 full text"}, {"id": "data:geo:GSE58678", "type": "dataset", "label": "GEO GSE58678"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26484243", "type": "extraction", "used": ["source:pmid:26484243"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE58678", "type": "accession_resolution", "used": ["data:geo:GSE58678"], "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:26484243", "parent_hash": "sha256:4b261c463d5bcb263903e529c91489d083e9edfbed47a0674479d45bbcee6173", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE58678 licence not read", "asset:data:geo:GSE58678 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": 0.93, "evidence": ["ped a custom Roche NimbleGen Gene Expression microarray that contains probes derived from the sequen"], "order_basis": "paper_text_order:514", "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": ["Multiple analyses were performed with LIMMA package in R software environment. A threshold of 0.05 (false discovery rate; FDR) was applied."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}