AJGM: joint learning of heterogeneous gene networks with adaptive graphical model.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40073230", "kind": "science-record", "revision": 2, "content_hash": "sha256:a91ffc71998d8505d8110c093f91a3b77bb5bf26c9762f517556acf490cbf0ec", "created_at": "2026-11-01T20:30:17Z", "updated_at": "2026-11-01T21:34:53Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "AJGM: joint learning of heterogeneous gene networks with adaptive graphical model.", "doi": "10.1093/bioinformatics/btaf096", "pmid": "40073230", "authors": ["Shunqi Yang", "Lingyi Hu", "Pengzhou Chen", "Xiangxiang Zeng", "Shanjun Mao"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "MOTIVATION: Inferring gene networks provides insights into biological pathways and functional relationships among genes. When gene expression samples exhibit heterogeneity, they may originate from unknown subtypes, prompting the utilization of mixture Gaussian graphical model (GGM) for simultaneous subclassification and gene network inference. However, this method overlooks the heterogeneity of network relationships across subtypes and does not sufficiently emphasize shared relationships. Additionally, GGM assumes data follows a multivariate Gaussian distribution, which is often not the case with zero-inflated scRNA-seq data.\nRESULTS: We propose an Adaptive Joint Graphical Model (AJGM) for estimating multiple gene networks from single-cell or bulk data with unknown heterogeneity. In AJGM, an overall network is introduced to capture relationships shared by all samples. The model establishes connections between the subtype networks and the overall network through adaptive weights, enabling it to focus more effectively on gene relationships shared across all networks, thereby enhancing the accuracy of network estimation. On synthetic data, the proposed approach outperforms existing methods in terms of sample classification and network inference, particularly excelling in the identification of shared relationships. Applying this method to gene expression data from triple-negative breast cancer confirms known gene pathways and hub genes, while also revealing novel biological insights.\nAVAILABILITY AND IMPLEMENTATION: The Python code and demonstrations of the proposed approaches are available at https://github.com/yyytim/AJGM, and the software is archived in Zenodo with DOI: 10.5281/zenodo.14740972.", "claims": [{"id": "claim-method", "statement": "We propose an Adaptive Joint Graphical Model (AJGM) for estimating multiple gene networks from single-cell or bulk data with unknown heterogeneity.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40073230", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We propose an Adaptive Joint Graphical Model (AJGM) for estimating multiple gene networks from single-cell or bulk data with unknown heterogeneity."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data underlying this article are available in public repositories as follows: The single-cell RNA sequencing data of triple-negative breast cancer are available in the Gene Expression Omnibus (GEO) with accession number GSE75688. The single-cell RNA sequencing data from Arabidopsis root procambium-type cells are available in GEO with accession number GSE152766. The single-cell RNA sequencing data of mouse embryonic stem cells are available in GEO with accession number GSE65525. The bulk RNA sequencing data of triple-negative breast cancer are available in The Cancer Genome Atlas (TCGA) at https://cancergenome.nih.gov/.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40073230", "locator": "sections[30] \"Data availability\" paragraph 2", "quote": "The data underlying this article are available in public repositories as follows: The single-cell RNA sequencing data of triple-negative breast cancer are available in the Gene Expression Omnibus (GEO) with accession number GSE75688. The single-cell RNA sequencing data from Arabidopsis root procambium-type cells are available in GEO with accession number GSE152766. The single-cell RNA sequencing data of mouse embryonic stem cells are available in GEO with accession number GSE65525. The bulk RNA sequencing data of triple-negative breast cancer are available in The Cancer Genome Atlas (TCGA) at https://cancergenome.nih.gov/."}], "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:40073230"], "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:GSE152766"], "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:GSE152766"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40073230", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf096", "sha256": "sha256:54751b56db715d1e60fc51507d32eba8948aee651c3ab570a0d96f8b76657d5a", "bytes": 45557, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf096", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11937957", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE152766", "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=GSE152766", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE152766", "version": null, "note": "The data underlying this article are available in public repositories as follows: The single-cell RNA sequencing data of triple-negative breast cancer are available in the Gene Expression Omnibus (GEO) with accession number GSE75688. The single-cell RNA sequencing data from Arabidopsis root procambium-type cells are available in GEO with accession number GSE152766. The single-cell RNA sequencing data of mouse embryonic stem cells are available in GEO with accession number GSE65525. The bulk RNA sequencing data of triple-negative breast cancer are available in The Cancer Genome Atlas (TCGA) at https://cancergenome.nih.gov/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data underlying this article are available in public repositories as follows: The single-cell RNA sequencing data of triple-negative breast cancer are available in the Gene Expression Omnibus (GEO) with accession number GSE75688. The single-cell RNA sequencing data from Arabidopsis root procambium-type cells are available in GEO with accession number GSE152766. The single-cell RNA sequencing data of mouse embryonic stem cells are available in GEO with accession number GSE65525. The bulk RNA sequencing data of triple-negative breast cancer are available in The Cancer Genome Atlas (TCGA) at https://cancergenome.nih.gov/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4625993", "GSM4625994", "GSM4625995", "GSM4625996", "GSM4625997", "GSM4625998", "GSM4625999", "GSM4626000", "GSM4626001", "GSM4626002", "GSM4626003", "GSM4626004", "GSM4626005", "GSM4626006", "GSM4626007", "GSM4626008", "GSM4626009", "GSM4626010", "GSM4626011"], "sample_count": 19, "group_sizes": null, "group_sizes_basis": null, "platform": "26208", "taxon": "Arabidopsis thaliana", "title": "Single-cell RNA-seq data of Arabidopsis root", "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:GSE65525", "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=GSE65525", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE65525", "version": null, "note": "The data underlying this article are available in public repositories as follows: The single-cell RNA sequencing data of triple-negative breast cancer are available in the Gene Expression Omnibus (GEO) with accession number GSE75688. The single-cell RNA sequencing data from Arabidopsis root procambium-type cells are available in GEO with accession number GSE152766. The single-cell RNA sequencing data of mouse embryonic stem cells are available in GEO with accession number GSE65525. The bulk RNA sequencing data of triple-negative breast cancer are available in The Cancer Genome Atlas (TCGA) at https://cancergenome.nih.gov/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data underlying this article are available in public repositories as follows: The single-cell RNA sequencing data of triple-negative breast cancer are available in the Gene Expression Omnibus (GEO) with accession number GSE75688. The single-cell RNA sequencing data from Arabidopsis root procambium-type cells are available in GEO with accession number GSE152766. The single-cell RNA sequencing data of mouse embryonic stem cells are available in GEO with accession number GSE65525. The bulk RNA sequencing data of triple-negative breast cancer are available in The Cancer Genome Atlas (TCGA) at https://cancergenome.nih.gov/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1599494", "GSM1599495", "GSM1599496", "GSM1599497", "GSM1599498", "GSM1599499", "GSM1599500", "GSM1599501"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "16417;17021;18573;19057;16791", "taxon": "Homo sapiens; Mus musculus", "title": "Droplet barcoding for single cell transcriptomics applied to embryonic stem cells", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE75688", "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=GSE75688", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE75688", "version": null, "note": "The data underlying this article are available in public repositories as follows: The single-cell RNA sequencing data of triple-negative breast cancer are available in the Gene Expression Omnibus (GEO) with accession number GSE75688. The single-cell RNA sequencing data from Arabidopsis root procambium-type cells are available in GEO with accession number GSE152766. The single-cell RNA sequencing data of mouse embryonic stem cells are available in GEO with accession number GSE65525. The bulk RNA sequencing data of triple-negative breast cancer are available in The Cancer Genome Atlas (TCGA) at https://cancergenome.nih.gov/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data underlying this article are available in public repositories as follows: The single-cell RNA sequencing data of triple-negative breast cancer are available in the Gene Expression Omnibus (GEO) with accession number GSE75688. The single-cell RNA sequencing data from Arabidopsis root procambium-type cells are available in GEO with accession number GSE152766. The single-cell RNA sequencing data of mouse embryonic stem cells are available in GEO with accession number GSE65525. The bulk RNA sequencing data of triple-negative breast cancer are available in The Cancer Genome Atlas (TCGA) at https://cancergenome.nih.gov/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1963742", "GSM1963743", "GSM1963744", "GSM1963745", "GSM1963746", "GSM1963747", "GSM1963748", "GSM1963749", "GSM1963750", "GSM1963751", "GSM1963752", "GSM1963753", "GSM1963754", "GSM1963755", "GSM1963756", "GSM1963757", "GSM1963758", "GSM1963759", "GSM1963760", "GSM1963761", "GSM1963762", "GSM1963763", "GSM1963764", "GSM1963765", "GSM1963766", "GSM1963767", "GSM1963768", "GSM1963769", "GSM1963770", "GSM1963771", "GSM1963772", "GSM1963773", "GSM1963774", "GSM1963775", "GSM1963776", "GSM1963777", "GSM1963778", "GSM1963779", "GSM1963780", "GSM1963781", "GSM1963782", "GSM1963783", "GSM1963784", "GSM1963785", "GSM1963786", "GSM1963787", "GSM1963788", "GSM1963789", "GSM1963790", "GSM1963791", "GSM1963792", "GSM1963793", "GSM1963794", "GSM1963795", "GSM1963796", "GSM1963797", "GSM1963798", "GSM1963799", "GSM1963800", "GSM1963801", "GSM1963802", "GSM1963803", "GSM1963804", "GSM1963805", "GSM1963806", "GSM1963807", "GSM1963808", "GSM1963809", "GSM1963810", "GSM1963811", "GSM1963812", "GSM1963813", "GSM1963814", "GSM1963815", "GSM1963816", "GSM1963817", "GSM1963818", "GSM1963819", "GSM1963820", "GSM1963821", "GSM1963822", "GSM1963823", "GSM1963824", "GSM1963825", "GSM1963826", "GSM1963827", "GSM1963828", "GSM1963829", "GSM1963830", "GSM1963831", "GSM1963832", "GSM1963833", "GSM1963834", "GSM1963835", "GSM1963836", "GSM1963837", "GSM1963838", "GSM1963839", "GSM1963840", "GSM1963841", "GSM1963842", "GSM1963843", "GSM1963844", "GSM1963845", "GSM1963846", "GSM1963847", "GSM1963848", "GSM1963849", "GSM1963850", "GSM1963851", "GSM1963852", "GSM1963853", "GSM1963854", "GSM1963855", "GSM1963856", "GSM1963857", "GSM1963858", "GSM1963859", "GSM1963860", "GSM1963861", "GSM1963862", "GSM1963863", "GSM1963864", "GSM1963865", "GSM1963866", "GSM1963867", "GSM1963868", "GSM1963869", "GSM1963870", "GSM1963871", "GSM1963872", "GSM1963873", "GSM1963874", "GSM1963875", "GSM1963876", "GSM1963877", "GSM1963878", "GSM1963879", "GSM1963880", "GSM1963881", "GSM1963882", "GSM1963883", "GSM1963884", "GSM1963885", "GSM1963886", "GSM1963887", "GSM1963888", "GSM1963889", "GSM1963890", "GSM1963891", "GSM1963892", "GSM1963893", "GSM1963894", "GSM1963895", "GSM1963896", "GSM1963897", "GSM1963898", "GSM1963899", "GSM1963900", "GSM1963901", "GSM1963902", "GSM1963903", "GSM1963904", "GSM1963905", "GSM1963906", "GSM1963907", "GSM1963908", "GSM1963909", "GSM1963910", "GSM1963911", "GSM1963912", "GSM1963913", "GSM1963914", "GSM1963915", "GSM1963916", "GSM1963917", "GSM1963918", "GSM1963919", "GSM1963920", "GSM1963921", "GSM1963922", "GSM1963923", "GSM1963924", "GSM1963925", "GSM1963926", "GSM1963927", "GSM1963928", "GSM1963929", "GSM1963930", "GSM1963931", "GSM1963932", "GSM1963933", "GSM1963934", "GSM1963935", "GSM1963936", "GSM1963937", "GSM1963938", "GSM1963939", "GSM1963940", "GSM1963941", "GSM1963942", "GSM1963943", "GSM1963944", "GSM1963945", "GSM1963946", "GSM1963947", "GSM1963948", "GSM1963949", "GSM1963950", "GSM1963951", "GSM1963952", "GSM1963953", "GSM1963954", "GSM1963955", "GSM1963956", "GSM1963957", "GSM1963958", "GSM1963959", "GSM1963960", "GSM1963961", "GSM1963962", "GSM1963963", "GSM1963964", "GSM1963965", "GSM1963966", "GSM1963967", "GSM1963968", "GSM1963969", "GSM1963970", "GSM1963971", "GSM1963972", "GSM1963973", "GSM1963974", "GSM1963975", "GSM1963976", "GSM1963977", "GSM1963978", "GSM1963979", "GSM1963980", "GSM1963981", "GSM1963982", "GSM1963983", "GSM1963984", "GSM1963985", "GSM1963986", "GSM1963987", "GSM1963988", "GSM1963989", "GSM1963990", "GSM1963991", "GSM1963992", "GSM1963993", "GSM1963994", "GSM1963995", "GSM1963996", "GSM1963997", "GSM1963998", "GSM1963999", "GSM1964000", "GSM1964001", "GSM1964002", "GSM1964003", "GSM1964004", "GSM1964005", "GSM2391843", "GSM2391844", "GSM2391845", "GSM2391846", "GSM2391847", "GSM2391848", "GSM2391849", "GSM2391850", "GSM2391851", "GSM2391852", "GSM2391853", "GSM2391854", "GSM2391855", "GSM2391856", "GSM2391857", "GSM2391858", "GSM2391859", "GSM2391860", "GSM2391861", "GSM2391862", "GSM2391863", "GSM2391864", "GSM2391865", "GSM2391866", "GSM2391867", "GSM2391868", "GSM2391869", "GSM2391870", "GSM2391871", "GSM2391872", "GSM2391873", "GSM2391874", "GSM2391875", "GSM2391876", "GSM2391877", "GSM2391878", "GSM2391879", "GSM2391880", "GSM2391881", "GSM2391882", "GSM2391883", "GSM2391884", "GSM2391885", "GSM2391886", "GSM2391887", "GSM2391888", "GSM2391889", "GSM2391890", "GSM2391891", "GSM2391892", "GSM2391893", "GSM2391894", "GSM2391895", "GSM2391896", "GSM2391897", "GSM2391898", "GSM2391899", "GSM2391900", "GSM2391901", "GSM2391902", "GSM2391903", "GSM2391904", "GSM2391905", "GSM2391906", "GSM2391907", "GSM2391908", "GSM2391909", "GSM2391910", "GSM2391911", "GSM2391912", "GSM2391913", "GSM2391914", "GSM2391915", "GSM2391916", "GSM2391917", "GSM2391918", "GSM2391919", "GSM2391920", "GSM2391921", "GSM2391922", "GSM2391923", "GSM2391924", "GSM2391925", "GSM2391926", "GSM2391927", "GSM2391928", "GSM2391929", "GSM2391930", "GSM2391931", "GSM2391932", "GSM2391933", "GSM2391934", "GSM2391935", "GSM2391936", "GSM2391937", "GSM2391938", "GSM2391939", "GSM2391940", "GSM2391941", "GSM2391942", "GSM2391943", "GSM2391944", "GSM2391945", "GSM2391946", "GSM2391947", "GSM2391948", "GSM2391949", "GSM2391950", "GSM2391951", "GSM2391952", "GSM2391953", "GSM2391954", "GSM2391955", "GSM2391956", "GSM2391957", "GSM2391958", "GSM2391959", "GSM2391960", "GSM2391961", "GSM2391962", "GSM2391963", "GSM2391964", "GSM2391965", "GSM2391966", "GSM2391967", "GSM2391968", "GSM2391969", "GSM2391970", "GSM2391971", "GSM2391972", "GSM2391973", "GSM2391974", "GSM2391975", "GSM2391976", "GSM2391977", "GSM2391978", "GSM2391979", "GSM2391980", "GSM2391981", "GSM2391982", "GSM2391983", "GSM2391984", "GSM2391985", "GSM2391986", "GSM2391987", "GSM2391988", "GSM2391989", "GSM2391990", "GSM2391991", "GSM2391992", "GSM2391993", "GSM2391994", "GSM2391995", "GSM2391996", "GSM2391997", "GSM2391998", "GSM2391999", "GSM2392000", "GSM2392001", "GSM2392002", "GSM2392003", "GSM2392004", "GSM2392005", "GSM2392006", "GSM2392007", "GSM2392008", "GSM2392009", "GSM2392010", "GSM2392011", "GSM2392012", "GSM2392013", "GSM2392014", "GSM2392015", "GSM2392016", "GSM2392017", "GSM2392018", "GSM2392019", "GSM2392020", "GSM2392021", "GSM2392022", "GSM2392023", "GSM2392024", "GSM2392025", "GSM2392026", "GSM2392027", "GSM2392028", "GSM2392029", "GSM2392030", "GSM2392031", "GSM2392032", "GSM2392033", "GSM2392034", "GSM2392035", "GSM2392036", "GSM2392037", "GSM2392038", "GSM2392039", "GSM2392040", "GSM2392041", "GSM2392042", "GSM2392043", "GSM2392044", "GSM2392045", "GSM2392046", "GSM2392047", "GSM2392048", "GSM2392049", "GSM2392050", "GSM2392051", "GSM2392052", "GSM2392053", "GSM2392054", "GSM2392055", "GSM2392056", "GSM2392057", "GSM2392058", "GSM2392059", "GSM2392060", "GSM2392061", "GSM2392062", "GSM2392063", "GSM2392064", "GSM2392065", "GSM2392066", "GSM2392067", "GSM2392068", "GSM2392069", "GSM2392070", "GSM2392071", "GSM2392072", "GSM2392073", "GSM2392074", "GSM2392075", "GSM2392076", "GSM2392077", "GSM2392078", "GSM2392079", "GSM2392080", "GSM2392081", "GSM2392082", "GSM2392083", "GSM2392084", "GSM2392085", "GSM2392086", "GSM2392087", "GSM2392088", "GSM2392089", "GSM2392090", "GSM2392091", "GSM2392092", "GSM2392093", "GSM2392094", "GSM2392095", "GSM2392096", "GSM2392097", "GSM2392098", "GSM2392099", "GSM2392100", "GSM2392101", "GSM2392102", "GSM2392103", "GSM2392104", "GSM2392105", "GSM2392106", "GSM2392107", "GSM2392108", "GSM2392109", "GSM2392110", "GSM2392111", "GSM2392112", "GSM2392113", "GSM2392114", "GSM2392115", "GSM2392116", "GSM2392117", "GSM2392118", "GSM2392119", "GSM2392120", "GSM2392121", "GSM2392122", "GSM2392123", "GSM2392124", "GSM2392125", "GSM2392126", "GSM2392127", "GSM2392128", "GSM2392129", "GSM2392130", "GSM2392131", "GSM2392132", "GSM2392133", "GSM2392134", "GSM2392135", "GSM2392136", "GSM2392137", "GSM2392138", "GSM2392139", "GSM2392140", "GSM2392141"], "sample_count": 563, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "Single cell RNA sequencing of primary breast cancer.", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE152766 not downloaded", "asset:data:geo:GSE152766 licence not read", "asset:data:geo:GSE65525 not downloaded", "asset:data:geo:GSE65525 licence not read", "asset:data:geo:GSE75688 not downloaded", "asset:data:geo:GSE75688 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Adaptive Joint Graphical Model (AJGM)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We propose an Adaptive Joint Graphical Model (AJGM) for estimating multiple gene networks from single-cell or bulk data with unknown heterogeneity."}}], "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": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Adaptive Joint Graphical Model (AJGM)), 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": "R1", "reachable": true, "accessions": ["GSE75688", "GSE152766", "GSE65525"], "resolved_accessions": ["GSE75688", "GSE152766", "GSE65525"], "statements": ["The data underlying this article are available in public repositories as follows: The single-cell RNA sequencing data of triple-negative breast cancer are available in the Gene Expression Omnibus (GEO) with accession number GSE75688. The single-cell RNA sequencing data from Arabidopsis root procambium-type cells are available in GEO with accession number GSE152766. The single-cell RNA sequencing data of mouse embryonic stem cells are available in GEO with accession number GSE65525. The bulk RNA sequencing data of triple-negative breast cancer are available in The Cancer Genome Atlas (TCGA) at https://cancergenome.nih.gov/."], "basis": "The paper names GSE75688, GSE152766, GSE65525 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40073230", "data:geo:GSE152766"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE152766"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:48:33Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 12093, "completion_tokens": 1629, "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:40073230", "type": "paper", "label": "pmid:40073230"}, {"id": "source:pmid:40073230", "type": "manuscript", "label": "PMID 40073230 full text"}, {"id": "data:geo:GSE152766", "type": "dataset", "label": "GEO GSE152766"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40073230", "type": "paper", "label": "pmid:40073230"}, {"id": "source:pmid:40073230", "type": "manuscript", "label": "PMID 40073230 full text"}, {"id": "data:geo:GSE152766", "type": "dataset", "label": "GEO GSE152766"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40073230", "type": "extraction", "used": ["source:pmid:40073230"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE152766", "type": "accession_resolution", "used": ["data:geo:GSE152766"], "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:40073230", "parent_hash": "sha256:ea0bd5e1a637dbdab007a9ea6802d6f7d0b7e5b7acb6b7a6e6723f39fd1639c1", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE152766 licence not read", "asset:data:geo:GSE152766 not downloaded", "asset:data:geo:GSE65525 licence not read", "asset:data:geo:GSE65525 not downloaded", "asset:data:geo:GSE75688 licence not read", "asset:data:geo:GSE75688 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": ["ich is often not the case with zero-inflated scRNA-seq data. RESULTS: We propose an Adaptive Joint"], "order_basis": "paper_text_order:656", "id": "assay:1"}]}