Integrating 5hmC and gene expression data to infer regulatory mechanisms.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29220513", "kind": "science-record", "revision": 2, "content_hash": "sha256:4578e1ff5160c30f5e5acea94d393875016140afda9e0bb52c1aaea943edcf56", "created_at": "2026-11-01T15:40:30Z", "updated_at": "2026-11-01T18:49:07Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Integrating 5hmC and gene expression data to infer regulatory mechanisms.", "doi": "10.1093/bioinformatics/btx777", "pmid": "29220513", "authors": ["Cristina Mitrea", "Priyanga Wijesinghe", "Greg Dyson", "Adéle Kruger", "Douglas M Ruden", "Sorin Draghici", "Aliccia Bollig-Fischer"], "journal": "Bioinformatics (Oxford, England)", "year": 2018, "abstract": "Motivation: Epigenetic mechanisms are known to play a major role in breast cancer. However, the role of 5-hydroxymethylcytosine (5hmC) remains understudied. We hypothesize that 5hmC mediates redox regulation of gene expression in an aggressive subtype known as triple negative breast cancer (TNBC). To address this, our objective was to highlight genes that may be the target of this process by identifying redox-regulated, antioxidant-sensitive, gene-localized 5hmC changes associated with mRNA changes in TNBC cells.\nResults: We proceeded to develop an approach to integrate novel Pvu-sequencing and RNA-sequencing data. The result of our approach to merge genome-wide, high-throughput TNBC cell line datasets to identify significant, concordant 5hmC and mRNA changes in response to antioxidant treatment produced a gene set with relevance to cancer stem cell function. Moreover, we have established a method that will be useful for continued research of 5hmC in TNBC cells and tissue samples.\nAvailability and implementation: Data are available at Gene Expression Omnibus (GEO) under accession number GSE103850.\nContact: bollig@karmanos.org.", "claims": [{"id": "claim-target-result", "statement": "The study integrated novel Pvu-sequencing and RNA-sequencing datasets to identify concordant 5hmC and mRNA changes after antioxidant treatment, producing a gene set relevant to cancer stem cell function; the source data are available from GEO accession GSE103850.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:29220513", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We proceeded to develop an approach to integrate novel Pvu-sequencing and RNA-sequencing data."}, {"asset": "source:pmid:29220513", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "The result of our approach to merge genome-wide, high-throughput TNBC cell line datasets to identify significant, concordant 5hmC and mRNA changes in response to antioxidant treatment produced a gene set with relevance to cancer stem cell function."}, {"asset": "source:pmid:29220513", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Data are available at Gene Expression Omnibus (GEO) under accession number GSE103850."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The study integrated novel Pvu-sequencing and RNA-sequencing datasets to identify concordant 5hmC and mRNA changes after antioxidant treatment, producing a gene set relevant to cancer stem cell function; the source data are available from GEO accession GSE103850.", "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:29220513"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29220513", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btx777", "sha256": "sha256:cae96af5ccbd167ef0b33f6c644fefad787a76d15e565518668937e89fb4813a", "bytes": 1073, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btx777", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5925763", "source": "ncbi_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), 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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": [], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:29220513"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:32:57Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 2, "usage": {"prompt_tokens": 1458, "completion_tokens": 584, "cached_tokens": 768}}, "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:29220513", "type": "paper", "label": "pmid:29220513"}, {"id": "source:pmid:29220513", "type": "manuscript", "label": "PMID 29220513 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29220513", "type": "paper", "label": "pmid:29220513"}, {"id": "source:pmid:29220513", "type": "manuscript", "label": "PMID 29220513 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29220513", "type": "extraction", "used": ["source:pmid:29220513"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:29220513", "parent_hash": "sha256:cc44fcd87c65597835249ab4d1ce5577fe5e47321adccca13feeb1c9c2ed4f11", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["proach to integrate novel Pvu-sequencing and RNA-sequencing data. The result of our approach to merge ge"], "order_basis": "paper_text_order:631", "id": "assay:1"}]}