CDACHIE: chromatin domain annotation by integrating chromatin interaction and epigenomic data with contrastive learning.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40845158", "kind": "science-record", "revision": 2, "content_hash": "sha256:b9e6439fc35afe43962da68abe5b96d7fee5ff9cd6e1c7b09cd6b6c976ce27e8", "created_at": "2026-11-01T20:30:57Z", "updated_at": "2026-11-01T21:35:40Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "CDACHIE: chromatin domain annotation by integrating chromatin interaction and epigenomic data with contrastive learning.", "doi": "10.1093/bioinformatics/btaf464", "pmid": "40845158", "authors": ["Asato Yoshinaga", "Osamu Maruyama"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "MOTIVATION: Chromatin domain annotation identifies functional genomic regions, such as active and inactive zones, based on epigenomic features like histone modifications, DNA methylation, and chromatin accessibility. While recent methods have utilized both chromatin interaction data (e.g. Hi-C) and epigenomic data, they often overlook the direct relationship between these data types.\nRESULTS: In this study, we introduce Chromatin Domain Annotation using Contrastive Learning for Hi-C and Epigenomic Data (CDACHIE), a method for identifying chromatin domains from Hi-C and epigenomic data. Our approach leverages contrastive learning to generate aligned representative vectors for both data types at each genomic bin. The concatenated vectors are then clustered using K-means to classify distinct chromatin domain types. CDACHIE achieves superior performance in Variance Explained, evaluated across gene expression, replication timing, and ChIA-PET data. This highlights its robust ability to integrate semantic associations between Hi-C and epigenomic features within the embedding space.\nAVAILABILITY AND IMPLEMENTATION: The source code is available at GitHub: https://github.com/maruyama-lab-design/CDACHIE. An archival snapshot of the code used in this study is available on Zenodo: https://doi.org/10.5281/zenodo.15751780.", "claims": [{"id": "claim-method", "statement": "Our approach leverages contrastive learning to generate aligned representative vectors for both data types at each genomic bin. The concatenated vectors are then clustered using K-means to classify distinct chromatin domain types.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40845158", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Our approach leverages contrastive learning to generate aligned representative vectors for both data types at each genomic bin. The concatenated vectors are then clustered using K-means to classify distinct chromatin domain types."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data underlying this article are available in its online supplementary material.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40845158", "locator": "sections[17] \"Data availability\" paragraph 2", "quote": "The data underlying this article are available in its online supplementary material."}], "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:40845158"], "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:GSE63525"], "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:GSE63525"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40845158", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf464", "sha256": "sha256:2a11ccfdd5465450d61ae97fb9b98ae56fede3fa84ebee64582e65ea735a1ea6", "bytes": 29667, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf464", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12422559", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE63525", "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=GSE63525", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63525", "version": null, "note": "The data underlying this article are available in its online supplementary material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data underlying this article are available in its online supplementary material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1551550", "GSM1551551", "GSM1551552", "GSM1551553", "GSM1551554", "GSM1551555", "GSM1551556", "GSM1551557", "GSM1551558", "GSM1551559", "GSM1551560", "GSM1551561", "GSM1551562", "GSM1551563", "GSM1551564", "GSM1551565", "GSM1551566", "GSM1551567", "GSM1551568", "GSM1551569", "GSM1551570", "GSM1551571", "GSM1551572", "GSM1551573", "GSM1551574", "GSM1551575", "GSM1551576", "GSM1551577", "GSM1551578", "GSM1551579", "GSM1551580", "GSM1551581", "GSM1551582", "GSM1551583", "GSM1551584", "GSM1551585", "GSM1551586", "GSM1551587", "GSM1551588", "GSM1551589", "GSM1551590", "GSM1551591", "GSM1551592", "GSM1551593", "GSM1551594", "GSM1551595", "GSM1551596", "GSM1551597", "GSM1551598", "GSM1551599", "GSM1551600", "GSM1551601", "GSM1551602", "GSM1551603", "GSM1551604", "GSM1551605", "GSM1551606", "GSM1551607", "GSM1551608", "GSM1551609", "GSM1551610", "GSM1551611", "GSM1551612", "GSM1551613", "GSM1551614", "GSM1551615", "GSM1551616", "GSM1551617", "GSM1551618", "GSM1551619", "GSM1551620", "GSM1551621", "GSM1551622", "GSM1551623", "GSM1551624", "GSM1551625", "GSM1551626", "GSM1551627", "GSM1551628", "GSM1551629", "GSM1551630", "GSM1551631", "GSM1551632", "GSM1551633", "GSM1551634", "GSM1551635", "GSM1551636", "GSM1551637", "GSM1551638", "GSM1551639", "GSM1551640", "GSM1551641", "GSM1551642", "GSM1551643", "GSM1551644", "GSM1551645", "GSM1551646", "GSM1551647", "GSM1551648", "GSM1551649", "GSM1551650", "GSM1551651", "GSM1551652", "GSM1551653", "GSM1551654", "GSM1551655", "GSM1551656", "GSM1551657", "GSM1551658", "GSM1551659", "GSM1551660", "GSM1551661", "GSM1551662", "GSM1551663", "GSM1551664", "GSM1551665", "GSM1551666", "GSM1551667", "GSM1551668", "GSM1551669", "GSM1551670", "GSM1551671", "GSM1551672", "GSM1551673", "GSM1551674", "GSM1551675", "GSM1551676", "GSM1551677", "GSM1551678", "GSM1551679", "GSM1551680", "GSM1551681", "GSM1551682", "GSM1551683", "GSM1551684", "GSM1551685", "GSM1551686", "GSM1551687", "GSM1551688", "GSM1551689", "GSM1551690", "GSM1551691", "GSM1551692", "GSM1551693", "GSM1551694", "GSM1551695", "GSM1551696", "GSM1551697", "GSM1551698", "GSM1551699", "GSM1551700", "GSM1551701", "GSM1551702", "GSM1551703", "GSM1551704", "GSM1551705", "GSM1551706", "GSM1551707", "GSM1551708", "GSM1551709", "GSM1551710", "GSM1551711", "GSM1551712", "GSM1551713", "GSM1551714", "GSM1551715", "GSM1551716", "GSM1551717", "GSM1551718", "GSM1551719", "GSM1551720", "GSM1551721", "GSM1551722", "GSM1551723", "GSM1551724", "GSM1551725", "GSM1551726", "GSM1551727", "GSM1551728", "GSM1551729", "GSM1551730", "GSM1551731", "GSM1551732", "GSM1551733", "GSM1551734", "GSM1551735", "GSM1551736", "GSM1551737", "GSM1551738", "GSM1551739", "GSM1551740", "GSM1551741", "GSM1551742", "GSM1551743", "GSM1551744", "GSM1551745", "GSM1551746", "GSM1551747", "GSM1551748", "GSM1551749"], "sample_count": 200, "group_sizes": null, "group_sizes_basis": null, "platform": "16791;15520;13112;11154;17021", "taxon": "Homo sapiens; Mus musculus", "title": "A three-dimensional map of the human genome at kilobase resolution reveals prinicples of chromatin looping", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE63525 not downloaded", "asset:data:geo:GSE63525 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "clustering", "specific": "kmeans", "label": "Clustering", "dsl_operations": ["kmeans_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Our approach leverages contrastive learning to generate aligned representative vectors for both data types at each genomic bin. The concatenated vectors are then clustered using K-means to classify distinct chromatin domain types."}}], "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": ["kmeans_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kmeans."}, "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": ["GSE63525"], "resolved_accessions": ["GSE63525"], "statements": ["The data underlying this article are available in its online supplementary material."], "basis": "The paper names GSE63525 in GSE63525 and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["kmeans_fit"], "assets": ["source:pmid:40845158", "data:geo:GSE63525"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE63525"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:00:13Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8933, "completion_tokens": 1938, "cached_tokens": 264}}, "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:40845158", "type": "paper", "label": "pmid:40845158"}, {"id": "source:pmid:40845158", "type": "manuscript", "label": "PMID 40845158 full text"}, {"id": "data:geo:GSE63525", "type": "dataset", "label": "GEO GSE63525"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40845158", "type": "paper", "label": "pmid:40845158"}, {"id": "source:pmid:40845158", "type": "manuscript", "label": "PMID 40845158 full text"}, {"id": "data:geo:GSE63525", "type": "dataset", "label": "GEO GSE63525"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40845158", "type": "extraction", "used": ["source:pmid:40845158"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE63525", "type": "accession_resolution", "used": ["data:geo:GSE63525"], "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:40845158", "parent_hash": "sha256:ad5e9cf0989422ce798721599c15506ee525f645843aaa4594f7ecf9f36dd30b", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE63525 licence not read", "asset:data:geo:GSE63525 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["nal and structural features. Analysis of the K562 cell line data (Fig. 9, available as supplem", "s superior integration strategy. Analysis of K562 cell line data (Fig. 10, available as supple"], "order_basis": "paper_text_order:3891", "id": "assay:1"}, {"role": "analysis", "definition_id": "clustering", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["kmeans_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Our approach leverages contrastive learning to generate aligned representative vectors for both data types at each genomic bin. The concatenated vectors are then clustered using K-means to classify distinct chromatin domain types."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}