{"id":"VC0147","type":"preprint","title":"DELPHAI predicts heterogeneous perturbation responses with learned single-cell fitness","authors_or_org":"Zhang X, Wu H, Liu H (aiPTO TechBio GmbH; Liu also DKFZ)","date":"2026-07-06","year":"2026","venue":"bioRxiv (preprint; v1 2026-07-06, v2 2026-09-17)","url":"https://doi.org/10.64898/2026.07.01.735965","doi":"10.64898/2026.07.01.735965","pmid":"","brain_tumor_focus":"yes","tags":["perturbation","benchmark","drug-response","virtual-tumor"],"tag_slugs":["perturbation","benchmark","drug-response","digital-twin"],"tag_labels":["Perturbation","Benchmark & validation","Drug response","Digital twin"],"tag_labels_zh":["扰动","基准评测与验证","药物反应","数字孪生"],"unmapped_tags":[],"one_line_summary_en":"Preprint (not peer reviewed; no independent replication found) from aiPTO TechBio authors: DELPHAI trains a fitness network and an optimal-transport network jointly and, at inference, applies fitness-gated transport with direct gene-space retrieval. The abstract self-reports ranking first on differentially expressed gene prediction across two benchmark frameworks. Authors are affiliated with aiPTO. Same-name successor of VC0129 (2025 preprint) but a different method.","one_line_summary_zh":"预印本（未经同行评审；未见独立复现），作者来自 aiPTO TechBio：DELPHAI 联合训练适应度（fitness）网络与最优传输网络，推理时采用适应度门控传输并直接在基因空间检索。摘要自述在两个基准框架中差异表达基因预测排名第一。作者隶属于 aiPTO。与 VC0129（2025 年预印本）同名，但方法不同，可视为同名后继。","verified":"yes","verification_source":"Crossref API + bioRxiv API (title, authors, affiliations, v1 date 2026-07-06, v2 date 2026-09-17, DOI, abstract) checked 2026-10-17; full text and competing-interest statement not read","page_url":"https://gliostate.com/library/VC0147/","api_url":"https://gliostate.com/api/items/VC0147.json","sameAs":["https://doi.org/10.64898/2026.07.01.735965"],"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/drug-response/","https://gliostate.com/library/tag/digital-twin/"]},"cited_by":[],"related":[{"id":"VC0148","title":"AI-Driven Precision Oncology Startup aiPTO Unveils #1-Ranked DELPHAI Model, Bridging the \"Scale Gap\" From Virtual Cells to Virtual Tumors","shared_tags":["perturbation","digital-twin"],"page_url":"https://gliostate.com/library/VC0148/","api_url":"https://gliostate.com/api/items/VC0148.json"},{"id":"VC0138","title":"PerturbLDM: conditional latent diffusion for modelling single-cell perturbation responses","shared_tags":["drug-response","perturbation"],"page_url":"https://gliostate.com/library/VC0138/","api_url":"https://gliostate.com/api/items/VC0138.json"},{"id":"VC0129","title":"DELPHAI, AI Agent for Predicting Drug Response and Resistance","shared_tags":["perturbation","drug-response"],"page_url":"https://gliostate.com/library/VC0129/","api_url":"https://gliostate.com/api/items/VC0129.json"},{"id":"VC0014","title":"Predicting cellular responses to complex perturbations in high-throughput screens.","shared_tags":["perturbation","drug-response"],"page_url":"https://gliostate.com/library/VC0014/","api_url":"https://gliostate.com/api/items/VC0014.json"},{"id":"VC0077","title":"Generative AI for spatial tumor growth on MRI: a proof-of-principle study in pediatric diffuse midline glioma.","shared_tags":["digital-twin"],"page_url":"https://gliostate.com/library/VC0077/","api_url":"https://gliostate.com/api/items/VC0077.json"},{"id":"VC0134","title":"TumorTwin: a Python framework for patient-specific digital twins in oncology","shared_tags":["digital-twin"],"page_url":"https://gliostate.com/library/VC0134/","api_url":"https://gliostate.com/api/items/VC0134.json"}]}