Structural variation-associated expression changes are paralleled by chromatin architecture modifications.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:24265791", "kind": "science-record", "revision": 7, "content_hash": "sha256:f74de4b8acc08131921804d744fea875a025bd32a23f5740602c3ecfefdc15ff", "created_at": "2026-11-01T15:40:03Z", "updated_at": "2026-11-01T21:58:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Structural variation-associated expression changes are paralleled by chromatin architecture modifications.", "doi": "10.1371/journal.pone.0079973", "pmid": "24265791", "authors": ["Nele Gheldof", "Robert M Witwicki", "Eugenia Migliavacca", "Marion Leleu", "Gérard Didelot", "Louise Harewood", "Jacques Rougemont", "Alexandre Reymond"], "journal": "PloS one", "year": 2013, "abstract": "Copy number variants (CNVs) influence the expression of genes that map not only within the rearrangement, but also to its flanks. To assess the possible mechanism(s) underlying this \"neighboring effect\", we compared intrachromosomal interactions and histone modifications in cell lines of patients affected by genomic disorders and control individuals. Using chromosome conformation capture (4C-seq), we observed that a set of genes flanking the Williams-Beuren Syndrome critical region (WBSCR) were often looping together. The newly identified interacting genes include AUTS2, mutations of which are associated with autism and intellectual disabilities. Deletion of the WBSCR disrupts the expression of this group of flanking genes, as well as long-range interactions between them and the rearranged interval. We also pinpointed concomitant changes in histone modifications between samples. We conclude that large genomic rearrangements can lead to chromatin conformation changes that extend far away from the structural variant, thereby possibly modulating expression globally and modifying the phenotype.\nGEO SERIES ACCESSION NUMBER: GSE33784, GSE33867.", "claims": [{"id": "claim-method", "statement": "We then compared the distribution of the (Ctrl+WBS) log counts in these regions versus Bricks outside by a Wilcoxon rank-sum test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:24265791", "locator": "sections[9] \"4C-seq data analysis\" paragraph 2", "quote": "We then compared the distribution of the (Ctrl+WBS) log counts in these regions versus Bricks outside by a Wilcoxon rank-sum test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "GEO Series accession number: GSE33784, GSE33867.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:24265791", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "GEO Series accession number: GSE33784, GSE33867."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Deletion of the WBSCR alters the chromatin conformation and histone modifications of flanking genes, including AUTS2, thereby potentially modulating expression beyond the deleted interval.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:24265791", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Deletion of the WBSCR disrupts the expression of this group of flanking genes, as well as long-range interactions between them and the rearranged interval."}, {"asset": "source:pmid:24265791", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We also pinpointed concomitant changes in histone modifications between samples."}, {"asset": "source:pmid:24265791", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We conclude that large genomic rearrangements can lead to chromatin conformation changes that extend far away from the structural variant, thereby possibly modulating expression globally and modifying the phenotype."}, {"asset": "source:pmid:24265791", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Using chromosome conformation capture (4C-seq), we observed that a set of genes flanking the Williams-Beuren Syndrome critical region (WBSCR) were often looping together."}, {"asset": "source:pmid:24265791", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "GEO Series accession number: GSE33784, GSE33867."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Deletion of the WBSCR alters the chromatin conformation and histone modifications of flanking genes, including AUTS2, thereby potentially modulating expression beyond the deleted interval.", "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:24265791"], "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:GSE33784"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:group_comparison_wilcoxon", "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:GSE33784"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:group_comparison_wilcoxon"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:24265791", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0079973", "sha256": "sha256:a0ffbe66b3911143bdb0ecc51071961763800d90a095f06907fb30eee23d0b19", "bytes": 55401, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0079973", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC3827143", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE33784", "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=GSE33784", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33784", "version": null, "note": "GEO Series accession number: GSE33784, GSE33867.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GEO Series accession number: GSE33784, GSE33867.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM835568", "GSM835569", "GSM835570", "GSM835571", "GSM835572", "GSM835573", "GSM835574", "GSM835575", "GSM835576", "GSM835577"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "10999", "taxon": "Homo sapiens", "title": "Genome-wide maps of chromatin state in Williams-Beuren (WBS), Williams-Beuren Region duplication (WBRdupS), Smith-Magenis (DGS), DiGeorge (DGS) lymphoblastoid cell lines", "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:GSE33867", "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=GSE33867", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33867", "version": null, "note": "GEO Series accession number: GSE33784, GSE33867.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GEO Series accession number: GSE33784, GSE33867.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1153763", "GSM838190", "GSM838191", "GSM838192", "GSM838193", "GSM838194", "GSM838195"], "sample_count": 7, "group_sizes": null, "group_sizes_basis": null, "platform": "10999", "taxon": "Homo sapiens", "title": "Structural variation-induced changes of chromatin architecture and gene expression", "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:24265791:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:89535ea5928095692c7737dd74b5441c4f44e5d5d44a3ec0c79f2d77b9aa6d4d", "bytes": 1467, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#pone-0079973-t001", "version": null, "note": "Expression changes and chromatin architecture modifications in WBS cells.", "structure": {"pmcid": "PMC3827143", "section_index": 3, "section_title": "Outlining the chromatin architecture of the WBS region", "row_count": 13, "column_count": 12}, "table": {"label": "Table 1", "caption": "Expression changes and chromatin architecture modifications in WBS cells.", "rows": [["", "", "Expression (this work)", "Expression (ref 16)", "H4K20me1 changes *", "H3K27me3 changes"], ["Gene", "Category", "Ctrl", "WBS", "WBS/Ctrl", "WBS/Ctrl", "", ""], ["", "", "AREL", "SD", "AREL", "SD", "AREL ratio", "t Test P", "AREL ratio", "t Test P", "", ""], ["GBAS", "viewpoint", "0.874", "0.095", "0.431", "0.010", "0.493", "0.014", "0.74", "0.02", "−0.67", "NS"], ["ASL", "viewpoint", "0.033", "0.005", "0.046", "0.004", "1.424", "0.029", "1.59", "0.004", "1", "NS"], ["KCTD7", "viewpoint", "0.067", "0.006", "0.061", "0.003", "0.922", "0.272", "0.39", "0.004", "−0.1", "NS"], ["HIP1", "viewpoint", "0.119", "0.019", "0.048", "0.013", "0.403", "0.009", "0.47", "0.02", "0.81", "1.38"], ["POR", "viewpoint", "0.241", "0.064", "0.201", "0.029", "0.833", "0.401", "0.89", "0.37", "−0.73", "NS"], ["MDH2", "viewpoint", "9.229", "0.321", "12.32", "0.195", "1.335", "0.0004", "1.23", "0.002", "−0.22", "NS"], ["ZNF107", "control viewpoint", "20.90", "2.717", "21.87", "1.701", "1.046", "0.633", "0.85", "0.24", "−0.96", "NS"], ["AUTS2", "novel interactor", "2.739", "0.101", "0.680", "0.006", "0.248", "0.001", "0.35", "0.06", "−1.55", "2.58"], ["CALN1", "novel interactor", "BDL", "", "BDL", "", "", "", "BDL", "", "−0.45", "0.77"], ["WBSCR22", "positive control", "0.277", "0.031", "0.125", "0.024", "0.451", "0.003", "0.43", "0.0003", "−1.67", "NS"]], "row_count": 13, "column_count": 12, "numeric_cells": 90, "header_rows": 3, "locator": "section[3]/table-wrap[1]#pone-0079973-t001"}}], "gaps": ["asset:data:geo:GSE33784 not downloaded", "asset:data:geo:GSE33784 licence not read", "asset:data:geo:GSE33867 not downloaded", "asset:data:geo:GSE33867 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We then compared the distribution of the (Ctrl+WBS) log counts in these regions versus Bricks outside by a Wilcoxon rank-sum test."}}, {"id": "method-2", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson correlation"}}], "targets": [], "gaps": ["method.group_comparison_wilcoxon"]}, "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": false, "required_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: wilcoxon."}, "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": ["GSE33784", "GSE33867"], "resolved_accessions": ["GSE33784", "GSE33867"], "statements": ["GEO Series accession number: GSE33784, GSE33867."], "basis": "The paper names GSE33784, GSE33867 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:24265791", "data:geo:GSE33784", "asset:table:pmid:24265791:1"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_wilcoxon", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE33784"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:43Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 108477, "completion_tokens": 3312, "cached_tokens": 54944}}, "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:24265791", "type": "paper", "label": "pmid:24265791"}, {"id": "source:pmid:24265791", "type": "manuscript", "label": "PMID 24265791 full text"}, {"id": "data:geo:GSE33784", "type": "dataset", "label": "GEO GSE33784"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:24265791", "type": "paper", "label": "pmid:24265791"}, {"id": "source:pmid:24265791", "type": "manuscript", "label": "PMID 24265791 full text"}, {"id": "data:geo:GSE33784", "type": "dataset", "label": "GEO GSE33784"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-24265791", "type": "extraction", "used": ["source:pmid:24265791"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE33784", "type": "accession_resolution", "used": ["data:geo:GSE33784"], "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:24265791", "parent_hash": "sha256:185bcb199494f81acfebf28a81ba9e8476bb1f9b7beefabb00d7b0a9410679f9", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE33784 licence not read", "asset:data:geo:GSE33784 not downloaded", "asset:data:geo:GSE33867 licence not read", "asset:data:geo:GSE33867 not downloaded", "execution.not_run", "method.group_comparison_wilcoxon", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:group_comparison_wilcoxon"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["We then compared the distribution of the (Ctrl+WBS) log counts in these regions versus Bricks outside by a Wilcoxon rank-sum test."], "order_basis": "analysis_only", "id": "assay:1"}]}