{"scope":{"layer":"general","tissue_scope":"unknown","species":"multi_species","system":"unknown","evidence_level":"preprint","importance":"","importance_reason":""},"id":"VC0185","type":"preprint","title":"Predicting cell-state-specific gene regulation from DNA across species","authors_or_org":"Liu H, Mao S, Gallent T, Chen Y, Yan Z, Vogel I, Traunmuller L, Zhang R, Buenrostro JD, Zhou J, Greenberg ME.","date":"2026-10-20","year":"2026","venue":"bioRxiv (preprint, not peer-reviewed)","url":"https://doi.org/10.64898/2026.10.19.760026","doi":"10.64898/2026.10.19.760026","pmid":"","brain_tumor_focus":"no","tags":["foundation-model","grn","cross-species","generative"],"tag_slugs":["foundation-model","grn","cross-species","generative"],"tag_labels":["Foundation model","Gene regulatory network","Cross-species","Generative AI & diffusion"],"tag_labels_zh":["基础模型","基因调控网络","跨物种","生成式 AI 与扩散模型"],"unmapped_tags":[],"one_line_summary_en":"Preprint (not peer-reviewed): Liu et al. (corresponding institution Arc Institute; senior author Greenberg ME) present Bolero, a sequence-to-function model whose parameters condition on atlas-scale cell-state embeddings and other biological variables to predict cell-state-specific chromatin accessibility and transcript abundance from DNA. Trained on 10.7 million cells from 33 datasets across six mammals, it is reported to match or exceed specialised models; the authors report that extrapolating cell-state embeddings extended predictions to cell states absent from training, that an AP-1 activity score as a conditioning axis predicted activity-regulated chromatin changes without stimulation data, and that it predicted cell-type-specific accessibility in species excluded from training. Self-reported; no independent evaluation yet.","one_line_summary_zh":"预印本（未经同行评审）：Liu 等（通讯单位 Arc 研究所；资深作者 Greenberg ME）提出 Bolero，一种以图谱级细胞状态嵌入及其他生物学变量为条件的“序列到功能”模型，可从 DNA 序列预测细胞状态特异的染色质可及性与转录本丰度。模型在 6 种哺乳动物、33 个数据集的 1070 万个细胞上训练，作者报告其表现与专用模型相当或更好；外推细胞状态嵌入可将预测扩展到训练中未出现的细胞状态；以 AP-1 活性评分作为条件轴，可在无刺激数据时预测活动依赖的染色质变化；并可预测训练中排除物种的细胞类型特异可及性。为作者自报结果，尚无独立评测。","verified":"yes","verification_source":"bioRxiv API details (title, 11 authors, posted 2026-10-20, v1, new results, genomics, CC BY-NC, corresponding institution Arc Institute, abstract) + Crossref posted-content record; doi.org resolves to biorxiv.org (10.64898 is bioRxiv's current DOI prefix) fetched 2026-10-21; full text not read","page_url":"https://gliostate.com/library/VC0185/","api_url":"https://gliostate.com/api/items/VC0185.json","sameAs":["https://doi.org/10.64898/2026.10.19.760026"],"is_preprint":true,"facets":{"type":"https://gliostate.com/library/type/preprint/","year":"https://gliostate.com/library/year/2026/","tags":["https://gliostate.com/library/tag/foundation-model/","https://gliostate.com/library/tag/grn/","https://gliostate.com/library/tag/cross-species/","https://gliostate.com/library/tag/generative/"]},"cited_by":[],"related":[{"id":"VC0029","title":"GeneCompass: deciphering universal gene regulatory mechanisms with a knowledge-informed cross-species foundation model.","shared_tags":["foundation-model","cross-species","grn"],"page_url":"https://gliostate.com/library/VC0029/","api_url":"https://gliostate.com/api/items/VC0029.json"},{"id":"VC0021","title":"A Cross-Species Generative Cell Atlas Across 1.5 Billion Years of Evolution: The TranscriptFormer Single-cell Model","shared_tags":["foundation-model","cross-species"],"page_url":"https://gliostate.com/library/VC0021/","api_url":"https://gliostate.com/api/items/VC0021.json"},{"id":"VC0012","title":"Universal Cell Embeddings: A Foundation Model for Cell Biology","shared_tags":["foundation-model","cross-species"],"page_url":"https://gliostate.com/library/VC0012/","api_url":"https://gliostate.com/api/items/VC0012.json"},{"id":"VC0102","title":"TranscriptFormer model overview (blog)","shared_tags":["cross-species"],"page_url":"https://gliostate.com/library/VC0102/","api_url":"https://gliostate.com/api/items/VC0102.json"},{"id":"VC0126","title":"Keystone: AI and Gene Regulation Across Scales","shared_tags":["grn"],"page_url":"https://gliostate.com/library/VC0126/","api_url":"https://gliostate.com/api/items/VC0126.json"},{"id":"VC0184","title":"AI and computational methods for reconstructing cell-state-specific gene regulatory networks from single-cell transcriptome and chromatin accessibility data in cancer: methods, applications, and perspectives","shared_tags":["grn"],"page_url":"https://gliostate.com/library/VC0184/","api_url":"https://gliostate.com/api/items/VC0184.json"}]}