{"scope":{"layer":"general","tissue_scope":"unknown","species":"unknown","system":"unknown","evidence_level":"preprint","importance":"","importance_reason":""},"id":"VC0166","type":"preprint","title":"PIE: Generalizing perturbation effects across unseen perturbations, contexts and datasets","authors_or_org":"Verma R, Adduri A, Bevilacqua B, Eraslan B, Burke D, Goodarzi H, Roohani Y.","date":"2026-10-05","year":"2026","venue":"bioRxiv (preprint, not peer-reviewed)","url":"https://doi.org/10.64898/2026.10.02.756297","doi":"10.64898/2026.10.02.756297","pmid":"","brain_tumor_focus":"no","tags":["perturbation","benchmark","zero-shot","arc"],"tag_slugs":["perturbation","benchmark","zero-shot","arc"],"tag_labels":["Perturbation","Benchmark & validation","Zero-shot","Arc Institute"],"tag_labels_zh":["扰动","基准评测与验证","零样本","Arc 研究所"],"unmapped_tags":[],"one_line_summary_en":"Preprint (not peer-reviewed): Verma et al. (Arc Institute) introduce PIE, which reformulates perturbation-response learning around population-level effects and directly predicts differentially expressed genes and expression changes for each (context, perturbation) pair from external biological knowledge, baseline expression and observed responses, including genes unseen in training. The authors report state-of-the-art performance on most metrics on the Replogle–Nadig dataset across all tested generalization settings, and 1.2 to 3.2 times the DEG AUPRC of the strongest baseline in each setting (unseen contexts, perturbations, datasets, and jointly unseen contexts and perturbations). Self-reported; no independent evaluation yet.","one_line_summary_zh":"预印本（未经同行评审）：Verma 等（Arc 研究所）提出 PIE，将扰动响应学习改写为群体层面效应预测，利用外部生物知识、基线表达与已观测响应，直接预测每个（细胞语境，扰动）组合的差异表达基因与表达变化，并可预测训练中未见的基因。作者报告：在 Replogle–Nadig 数据集上，所有测试的泛化设置中多数指标达到当前最佳；各设置（未见语境、未见扰动、未见数据集、语境与扰动均未见）下差异基因 AUPRC 为最强基线的 1.2–3.2 倍。为作者自报结果，尚无独立评测。","verified":"yes","verification_source":"bioRxiv API details (title, 7 authors, posted 2026-10-05, v1, new results, CC BY, corresponding institution Arc Institute, abstract) fetched 2026-10-20; full text not read; KB id VC0166 (renumbered 2026-10-20)","page_url":"https://gliostate.com/library/VC0166/","api_url":"https://gliostate.com/api/items/VC0166.json","sameAs":["https://doi.org/10.64898/2026.10.02.756297"],"is_preprint":true,"facets":{"type":"https://gliostate.com/library/type/preprint/","year":"https://gliostate.com/library/year/2026/","tags":["https://gliostate.com/library/tag/perturbation/","https://gliostate.com/library/tag/benchmark/","https://gliostate.com/library/tag/zero-shot/","https://gliostate.com/library/tag/arc/"]},"cited_by":[],"related":[{"id":"VC0143","title":"Generating high-quality Perturb-seq data for the 2026 Virtual Cell Challenge","shared_tags":["arc","benchmark","zero-shot"],"page_url":"https://gliostate.com/library/VC0143/","api_url":"https://gliostate.com/api/items/VC0143.json"},{"id":"VC0169","title":"Benchmarking single-cell foundation models reveals an advantage in the low-data regime for cell-type and disease-state prediction","shared_tags":["benchmark","zero-shot"],"page_url":"https://gliostate.com/library/VC0169/","api_url":"https://gliostate.com/api/items/VC0169.json"},{"id":"VC0058","title":"Virtual Cell Challenge 2026: Benchmarking zero-shot generalization across cellular contexts.","shared_tags":["benchmark","zero-shot"],"page_url":"https://gliostate.com/library/VC0058/","api_url":"https://gliostate.com/api/items/VC0058.json"},{"id":"VC0050","title":"Zero-shot evaluation reveals limitations of single-cell foundation models.","shared_tags":["benchmark","zero-shot"],"page_url":"https://gliostate.com/library/VC0050/","api_url":"https://gliostate.com/api/items/VC0050.json"},{"id":"VC0107","title":"Virtual Cell Challenge 2026 (zero-shot, 6 unseen cell lines)","shared_tags":["zero-shot"],"page_url":"https://gliostate.com/library/VC0107/","api_url":"https://gliostate.com/api/items/VC0107.json"},{"id":"VC0002","title":"Virtual Cell Challenge: Toward a Turing test for the virtual cell.","shared_tags":["benchmark","arc"],"page_url":"https://gliostate.com/library/VC0002/","api_url":"https://gliostate.com/api/items/VC0002.json"}]}