Genome-wide epigenetic cross-talk between DNA methylation and H3K27me3 in zebrafish embryos.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26697317", "kind": "science-record", "revision": 6, "content_hash": "sha256:81b9eb61be8aaaf3063111da58a7e9cc727c418c367a4b5b0b25453a79c39300", "created_at": "2026-11-01T15:40:14Z", "updated_at": "2026-11-01T21:20:19Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Genome-wide epigenetic cross-talk between DNA methylation and H3K27me3 in zebrafish embryos.", "doi": "10.1016/j.gdata.2015.07.020", "pmid": "26697317", "authors": ["Elisa de la Calle Mustienes", "Jose Luis Gómez-Skarmeta", "Ozren Bogdanović"], "journal": "Genomics data", "year": 2015, "abstract": "DNA methylation and histone modifications are epigenetic marks implicated in the complex regulation of vertebrate embryogenesis. The cross-talk between DNA methylation and Polycomb-dependent H3K27me3 histone mark has been reported in a number of organisms [1], [2], [3], [4], [5], [6], [7] and both marks are known to be required for proper developmental progression. Here we provide genome-wide DNA methylation (MethylCap-seq) and H3K27me3 (ChIP-seq) maps for three stages (dome, 24 hpf and 48 hpf) of zebrafish (Danio rerio) embryogenesis, as well as all analytical and methodological details associated with the generation of this dataset. We observe a strong antagonism between the two epigenetic marks present in CpG islands and their compatibility throughout the bulk of the genome, as previously reported in mammalian ESC lines (Brinkman et al., 2012). Next generation sequencing data linked to this project have been deposited in the Gene Expression Omnibus (GEO) database under accession numbers GSE35050 and GSE70847.", "claims": [{"id": "claim-method", "statement": "The statistical significance of differences in size distributions was assessed by a Kruskal–Wallis test and Dunn's multiple comparison test, (P < 0.05).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26697317", "locator": "sections[6] \"Peak calling\" paragraph 3", "quote": "The statistical significance of differences in size distributions was assessed by a Kruskal–Wallis test and Dunn's multiple comparison test, (P < 0.05)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Next generation sequencing data linked to this project have been deposited in the Gene Expression Omnibus (GEO) database under accession numbers GSE35050 and GSE70847.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26697317", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Next generation sequencing data linked to this project have been deposited in the Gene Expression Omnibus (GEO) database under accession numbers GSE35050 and GSE70847."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "", "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:26697317"], "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:GSE35050"], "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:GSE35050"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26697317", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gdata.2015.07.020", "sha256": "sha256:4a83896a956a6cc70d56159daf90ad10c07d88264b32b6e75bde2280fbbdb32a", "bytes": 11599, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gdata.2015.07.020", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4664660", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE35050", "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=GSE35050", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE35050", "version": null, "note": "Next generation sequencing data linked to this project have been deposited in the Gene Expression Omnibus (GEO) database under accession numbers GSE35050 and GSE70847.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Next generation sequencing data linked to this project have been deposited in the Gene Expression Omnibus (GEO) database under accession numbers GSE35050 and GSE70847.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM861348"], "sample_count": 1, "group_sizes": null, "group_sizes_basis": null, "platform": "10164", "taxon": "Danio rerio", "title": "Extensive conservation of ancient microsynteny across metazoans", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE70847", "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=GSE70847", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE70847", "version": null, "note": "Next generation sequencing data linked to this project have been deposited in the Gene Expression Omnibus (GEO) database under accession numbers GSE35050 and GSE70847.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Next generation sequencing data linked to this project have been deposited in the Gene Expression Omnibus (GEO) database under accession numbers GSE35050 and GSE70847.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1820450", "GSM1820451", "GSM1820452", "GSM1820453", "GSM1820454"], "sample_count": 5, "group_sizes": null, "group_sizes_basis": null, "platform": "14875", "taxon": "Danio rerio", "title": "Genome-wide epigenetic cross-talk between DNA methylation and H3K27me3 in zebrafish embryos", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE35050 not downloaded", "asset:data:geo:GSE35050 licence not read", "asset:data:geo:GSE70847 not downloaded", "asset:data:geo:GSE70847 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Kruskal–Wallis test with Dunn's multiple comparison test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The statistical significance of differences in size distributions was assessed by a Kruskal–Wallis test and Dunn's multiple comparison test, (P < 0.05)."}}], "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": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Kruskal–Wallis test with Dunn's multiple comparison test), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["GSE35050", "GSE70847"], "resolved_accessions": ["GSE35050", "GSE70847"], "statements": ["Next generation sequencing data linked to this project have been deposited in the Gene Expression Omnibus (GEO) database under accession numbers GSE35050 and GSE70847."], "basis": "The paper names GSE35050, GSE70847 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:26697317", "data:geo:GSE35050"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE35050"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:26:31Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 31535, "completion_tokens": 4395, "cached_tokens": 12312}}, "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:26697317", "type": "paper", "label": "pmid:26697317"}, {"id": "source:pmid:26697317", "type": "manuscript", "label": "PMID 26697317 full text"}, {"id": "data:geo:GSE35050", "type": "dataset", "label": "GEO GSE35050"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26697317", "type": "paper", "label": "pmid:26697317"}, {"id": "source:pmid:26697317", "type": "manuscript", "label": "PMID 26697317 full text"}, {"id": "data:geo:GSE35050", "type": "dataset", "label": "GEO GSE35050"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26697317", "type": "extraction", "used": ["source:pmid:26697317"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE35050", "type": "accession_resolution", "used": ["data:geo:GSE35050"], "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:26697317", "parent_hash": "sha256:7b661fff4bc058abb8d0bf49a68e761a68131063617ed0d2a3667dff89a963f8", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE35050 licence not read", "asset:data:geo:GSE35050 not downloaded", "asset:data:geo:GSE70847 licence not read", "asset:data:geo:GSE70847 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "chip_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["NA methylation (MethylCap-seq) and H3K27me3 (ChIP-seq) maps for three stages (dome, 24 hpf and 48", "gnment and data processing MethylCap-seq and ChIP-seq libraries were sequenced on a HiSeq 2000 Seq", "ng efficiency for MethylCap-seq and H3K27me3 ChIP-seq data expressed as N reads (× 106). Animal pr"], "order_basis": "paper_text_order:490", "id": "assay:1"}]}