paper✓ VerifiedVC0008
Cui H, Wang C, Maan H, Pang K, Luo F, Duan N, Wang B. · Nature methods · 2024-02-26
scGPT: generative pretrained transformer on 33M cells (Bo Wang lab).
DOIPubMed
paper✓ VerifiedVC0152
Coudray A, Forey R, Bejar Haro B, Martins F, Carlevaro-Fita J, Sheppard S, Offner SE, La Manno G, Obozinski G, Trono D. · PLOS Computational Biology · 2026-10-16
Coudray et al. (PLOS Comput Biol 2026): CLIMB and CLIFF deconvolve bulk RNA-seq into cell-type composition and bulk drug-sensitivity data into cell-subtype/single-cell profiles; validated on leukemic cell-line mixtures and pseudo-bulk data, applied to the beatAML ex vivo screen (121 compounds). Focus is acute myeloid leukemia; no brain-tumor application stated in the abstract.
DOIPubMed
preprintBrain tumor✓ VerifiedVC0176
Huang X, Qiao Y, Black GS, Sederman CR, Yang H, Musci T, Ludwick A, He G, Youssef O, Gutierrez M, Yang J, Chan PP, Memmott TH, Whipple NS, Bruggers CS, Quinlan A, Moos PJ, Cheshier SH, Marth GT. · bioRxiv (preprint, not peer-reviewed) · 2026-10-14
Preprint (not peer-reviewed): Huang et al. (University of Utah; senior authors Cheshier SH and Marth GT) describe a tiered framework combining deep whole-genome sequencing, scRNA-seq and ex vivo functional drug screening, applied to 17 children with malignant CNS tumors. Functional screening gave every patient at least one high-confidence targeted-therapy or chemotherapy nomination; scRNA-seq identified on average 37 druggable gene targets per patient, a fourfold increase in high-confidence targeted-therapy recommendations. In an exploratory analysis, functional classifications were directionally consistent with outcomes in 8 of 10 evaluable cases, but combination treatments and radiation precluded causal attribution.
DOI
paperBrain tumor✓ VerifiedVC0132
Suter et al. · Nature Communications · 2026-01-07
scFOCAL/ISOSCELES links GBM cell states to L1000 signatures; predicts state-specific sensitivity and OLIG2i+Depatux-M combo.
DOI
preprint✓ VerifiedVC0138
Yu et al. · bioRxiv · 2026-08-12
PerturbLDM: Tahoe-100M-pretrained latent diffusion for conditional sc response generation across drug/dose/cell-line.
DOI
preprintBrain tumor✓ VerifiedVC0147
Zhang X, Wu H, Liu H (aiPTO TechBio GmbH; Liu also DKFZ) · bioRxiv (preprint; v1 2026-07-06, v2 2026-09-17) · 2026-07-06
Preprint (not peer reviewed; no independent replication found) from aiPTO TechBio authors: DELPHAI trains a fitness network and an optimal-transport network jointly and, at inference,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.
DOI