scPOEM: robust co-embedding of peaks and genes revealing peak-gene regulation.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40889281", "kind": "science-record", "revision": 3, "content_hash": "sha256:84091884a770542bebdd44861c276316890fadfca634b0e31534324b9a73d5c2", "created_at": "2026-11-01T20:31:00Z", "updated_at": "2026-11-01T22:14:39Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "scPOEM: robust co-embedding of peaks and genes revealing peak-gene regulation.", "doi": "10.1093/bioinformatics/btaf483", "pmid": "40889281", "authors": ["Yan Zhong", "Yuntong Hou", "Yongjian Yang", "Xinyue Zheng", "James J Cai"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "MOTIVATION: Identifying regulatory elements in various chromosomal regions that influence gene expression is a fundamental challenge in epigenomics, with profound implications for understanding gene regulation and disease mechanisms. The advent of paired single-cell RNA sequencing and single-cell ATAC sequencing has created unprecedented opportunities to address this challenge by enabling simultaneous profiling of gene expression and chromatin accessibility at single-cell resolution. However, the inherent signals between them are weak due to the highly sparse and noisy nature of data.\nRESULTS: This article proposes single-cell meta-Path based Omics Embedding (scPOEM), a novel embedding method that jointly projects chromatin accessibility peaks and expressed genes into a shared low-dimensional space. By integrating the relationships among peak-peak, peak-gene, and gene-gene interactions, scPOEM assigns closer representations in the embedding space to related peak-gene pairs. Our experiments demonstrate that scPOEM generates stable representations of peaks and genes, outperforms existing methods in recovering biologically meaningful peak-gene regulatory relationships and enables new insights in subgroup and differential analysis of gene regulation. These results highlight its potential to uncover gene regulatory mechanisms and enhance the understanding of transcriptional regulation at single-cell resolution.\nAVAILABILITY AND IMPLEMENTATION: The source code of scPOEM is available at https://github.com/Houyt23/scPOEM. The datasets can be obtained from the 10× Genomics (https://www.10xgenomics.com/datasets/pbmc-from-a-healthy-donor-granulocytes-removed-through-cell-sorting-10-k-1-standard-1-0-0) and GEO database under access codes GSE194122 and GSE239916.", "claims": [{"id": "claim-method", "statement": "This article proposes single-cell meta-Path based Omics Embedding (scPOEM), a novel embedding method that jointly projects chromatin accessibility peaks and expressed genes into a shared low-dimensional space.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40889281", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "This article proposes single-cell meta-Path based Omics Embedding (scPOEM), a novel embedding method that jointly projects chromatin accessibility peaks and expressed genes into a shared low-dimensional space."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All the data used in this article are available from public sources, as detailed above in Section 2.6.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40889281", "locator": "sections[27] \"Data availability\" paragraph 2", "quote": "All the data used in this article are available from public sources, as detailed above in Section 2.6."}], "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:40889281"], "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:GSE194122"], "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:GSE194122"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40889281", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf483", "sha256": "sha256:121f4412e2fd08af2b93222a71d08725e9d8d6c8bbf72a7d00b480a9d241a561", "bytes": 41637, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf483", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12449255", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE194122", "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=GSE194122", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE194122", "version": null, "note": "All the data used in this article are available from public sources, as detailed above in Section 2.6.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All the data used in this article are available from public sources, as detailed above in Section 2.6.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5828456", "GSM5828457", "GSM5828458", "GSM5828459", "GSM5828460", "GSM5828461", "GSM5828462", "GSM5828463", "GSM5828464", "GSM5828465", "GSM5828466", "GSM5828467", "GSM5828468", "GSM5828469", "GSM5828470", "GSM5828471", "GSM5828472", "GSM5828473", "GSM5828474", "GSM5828475", "GSM5828476", "GSM5828477", "GSM5828478", "GSM5828479", "GSM5828480", "GSM5828481", "GSM5828482", "GSM5828483", "GSM5828484", "GSM5828485", "GSM5828486", "GSM5828487", "GSM5828488", "GSM5828489", "GSM5828490", "GSM5828491", "GSM5828492", "GSM5828493"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "A sandbox for prediction and integration of DNA, RNA, and proteins in single cells", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE239916", "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=GSE239916", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE239916", "version": null, "note": "All the data used in this article are available from public sources, as detailed above in Section 2.6.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All the data used in this article are available from public sources, as detailed above in Section 2.6.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM7677086", "GSM7677087", "GSM7677088", "GSM7677089", "GSM7677090", "GSM7677091", "GSM7677092", "GSM7677093", "GSM7677094", "GSM7677095", "GSM7677223", "GSM7677224", "GSM7677225", "GSM7677226", "GSM7677227", "GSM7677228", "GSM7677229", "GSM7677230", "GSM7677231", "GSM7677232", "GSM7677372", "GSM7677373", "GSM7677374", "GSM7677375", "GSM7677376", "GSM7677377", "GSM7677378", "GSM7677379", "GSM7677380", "GSM7677381"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Single-cell epigenetic, transcriptional, and protein states of HIV-1-infected cells", "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:GSE194122 not downloaded", "asset:data:geo:GSE194122 licence not read", "asset:data:geo:GSE239916 not downloaded", "asset:data:geo:GSE239916 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "gradient_boosting", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "XGBoost"}}, {"id": "method-2", "family": null, "specific": null, "label": "single-cell meta-Path based Omics Embedding (scPOEM)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "This article proposes single-cell meta-Path based Omics Embedding (scPOEM), a novel embedding method that jointly projects chromatin accessibility peaks and expressed genes into a shared low-dimensional space."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: gradient_boosting."}, "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": ["GSE194122", "GSE239916"], "resolved_accessions": ["GSE194122", "GSE239916"], "statements": ["All the data used in this article are available from public sources, as detailed above in Section 2.6."], "basis": "The paper names GSE194122, GSE239916 in GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "assets": ["source:pmid:40889281", "data:geo:GSE194122"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE194122"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:00:51Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 11412, "completion_tokens": 1658, "cached_tokens": 128}}, "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:40889281", "type": "paper", "label": "pmid:40889281"}, {"id": "source:pmid:40889281", "type": "manuscript", "label": "PMID 40889281 full text"}, {"id": "data:geo:GSE194122", "type": "dataset", "label": "GEO GSE194122"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40889281", "type": "paper", "label": "pmid:40889281"}, {"id": "source:pmid:40889281", "type": "manuscript", "label": "PMID 40889281 full text"}, {"id": "data:geo:GSE194122", "type": "dataset", "label": "GEO GSE194122"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40889281", "type": "extraction", "used": ["source:pmid:40889281"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE194122", "type": "accession_resolution", "used": ["data:geo:GSE194122"], "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:40889281", "parent_hash": "sha256:9bfbb30da3945ffe141a7e9b318273594d69a10df17ec7c176d1e57198d2a2f5", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE194122 licence not read", "asset:data:geo:GSE194122 not downloaded", "asset:data:geo:GSE239916 licence not read", "asset:data:geo:GSE239916 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "scrna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "unsupported", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["and disease mechanisms. The advent of paired single-cell RNA sequencing and single-cell ATAC sequencing has created"], "order_basis": "paper_text_order:289", "id": "assay:1"}, {"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": ["mechanisms. The advent of paired single-cell RNA sequencing and single-cell ATAC sequencing has created"], "order_basis": "paper_text_order:301", "id": "assay:2"}, {"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["XGBoost"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]}