PuSH - Publication Server of Helmholtz Zentrum München

DeMeo, B.* ; Nesbitt, C.* ; Miller, S.A.* ; Burkhardt, D.B.* ; Lipchina, I.* ; Fu, D.* ; Holderreith, P.* ; Kim, D.* ; Kolchenko, S.* ; Szalata, A. ; Gupta, I.* ; Kerr, C.* ; Pfefer, T.J.* ; Rojas-Rodriguez, R.* ; Kuppassani, S.* ; Kruidenier, L.* ; Doshi, P.B.* ; Zamanighomi, M.* ; Collins, J.J.* ; Shalek, A.K.* ; Theis, F.J. ; Cortes, M.*

Active learning framework leveraging transcriptomics identifies modulators of disease phenotypes.

Science 390:eadi8577 (2025)
DOI PMC
Closed: Publ. Version/Full Text online available 10/2026
Phenotypic drug screening remains constrained by the vastness of chemical space and technical challenges scaling experimental workflows. To overcome these barriers, computational methods have been developed to prioritize compounds, but they rely on either single-task models lacking generalizability or heuristic-based genomic proxies that resist optimization. We designed an active deep-learning framework that leverages omics to enable scalable, optimizable identification of compounds that induce complex phenotypes. Our generalizable algorithm outperformed state-of-the-art models on classical recall, translating to a 13-17x increase in phenotypic hit-rate across two hematological discovery campaigns. Combining this algorithm with a lab-in-the-loop signature refinement step, we achieved an additional two-fold increase in hit-rate and molecular insights. In sum, our framework enables efficient phenotypic hit identification campaigns, with broad potential to accelerate drug discovery.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
ISSN (print) / ISBN 0036-8075
e-ISSN 1095-9203
Journal Science
Quellenangaben Volume: 390, Issue: 6776, Pages: , Article Number: eadi8577 Supplement: ,
Publisher American Association for the Advancement of Science (AAAS)
Reviewing status Peer reviewed
Institute(s) Institute of Computational Biology (ICB)