Adversarial attack of sequence-free enhancer prediction identifies chromatin architecture.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40581823", "kind": "science-record", "revision": 4, "content_hash": "sha256:385875f537f114159536250c6261bdfc513a413b80e22fdb4399caecbec399df", "created_at": "2026-11-01T20:30:40Z", "updated_at": "2026-11-01T22:56:43Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Adversarial attack of sequence-free enhancer prediction identifies chromatin architecture.", "doi": "10.1093/bioinformatics/btaf371", "pmid": "40581823", "authors": ["Jamil Gafur", "Olivia W Lang", "William K M Lai"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "MOTIVATION: The wide range of cellular complexity created by multicellular organisms is due in large part to the intricate and synergistic interplay of regulatory complexes throughout the eukaryotic genome. These regulatory elements \"enhance\" specific gene programs and have been shown to operate in diverse networks that are distinct across cell states of the same organism. Attempts to characterize and predict enhancers have typically focused on leveraging information-dense DNA sequence in parallel with epigenomic assays. We examined the viability of enhancer prediction using only a minimal set of epigenomic datasets without direct DNA information.\nRESULTS: We demonstrate that chromatin datasets are sufficient to identify enhancers genome-wide with high accuracy. By training networks leveraging data from multiple cell types simultaneously, we generated a cell-type invariant enhancer prediction platform that utilized only the patterns of protein binding for inference. We also showed the utility of swarm-based adversarial attacks [adversarial particle swarm optimization (APSO)] to deconvolute trained genomic neural networks for the first time. Critically, unlike saliency mapping or other game-theory based approaches, APSO is completely network-architecture independent and can be applied to any prediction engine to derive the features that drive inference.\nAVAILABILITY AND IMPLEMENTATION: All software and code for data downloading, processing, enhancer inference, eXplainable AI (XAI), and complete figure generation are publicly available on GitHub at https://github.com/EpiGenomicsCode/ChromEnhancer and Zenodo at https://doi.org/10.5281/zenodo.15652797.", "claims": [{"id": "claim-method", "statement": "Network performance was measured by calculating auROC and auPRC based on the networks’ accuracy in predicting enhancers in the held-out chromosomes, ranking each 1 kb window (Fig. 2B and C).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40581823", "locator": "sections[12] \"3.1 Model performance\" paragraph 3", "quote": "Network performance was measured by calculating auROC and auPRC based on the networks’ accuracy in predicting enhancers in the held-out chromosomes, ranking each 1 kb window (Fig. 2B and C)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Supplementary data are available at Bioinformatics online.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40581823", "locator": "sections[20] \"Supplementary data\" paragraph 2", "quote": "Supplementary data are available at Bioinformatics online."}], "state": "complete"}, {"id": "claim-target-result", "statement": "In contrast, model 5 (2D CNN) performed the best with a median auROC and auPRC of 0.924 and 0.206, respectively.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40581823", "locator": "sections[12] \"3.1 Model performance\" paragraph 4", "quote": "In contrast, model 5 (2D CNN) performed the best with a median auROC and auPRC of 0.924 and 0.206, respectively."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "In contrast, model 5 (2D CNN) performed the best with a median auROC and auPRC of 0.924 and 0.206, respectively.", "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:40581823"], "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:40581823", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf371", "sha256": "sha256:57b0a24ce58d98bdbfc1f72c50ebf87e8e1c9e55efa6d7f418c429a83f9469ce", "bytes": 44091, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf371", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12240468", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Network performance was measured by calculating auROC and auPRC based on the networks’ accuracy in predicting enhancers in the held-out chromosomes, ranking each 1 kb window (Fig. 2B and C)."}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: roc."}, "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": ["Supplementary data are available at Bioinformatics online."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "assets": ["source:pmid:40581823"], "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": "2026-11-01T19:55:31Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 11584, "completion_tokens": 2729, "cached_tokens": 256}}, "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:40581823", "type": "paper", "label": "pmid:40581823"}, {"id": "source:pmid:40581823", "type": "manuscript", "label": "PMID 40581823 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40581823", "type": "paper", "label": "pmid:40581823"}, {"id": "source:pmid:40581823", "type": "manuscript", "label": "PMID 40581823 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40581823", "type": "extraction", "used": ["source:pmid:40581823"], "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:40581823", "parent_hash": "sha256:1a9703c3384766755df832e610e7247cd1c4dbcab390b68338334a497d2aed39", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "diagnostic_evaluation", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Network performance was measured by calculating auROC and auPRC based on the networks’ accuracy in predicting enhancers in the held-out chromosomes, ranking each 1 kb window (Fig. 2B and C)."], "order_basis": "analysis_only", "id": "assay:1"}]}