Active learning framework leveraging transcriptomics identifies modulators of disease phenotypes

Phenotypic drug screening remains constrained by the vastness of chemical space and the technical challenges of 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- to 17-fold 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 twofold increase in hit rate along with molecular insights. In sum, our framework enables efficient phenotypic hit identification campaigns, with broad potential to accelerate drug discovery.

Authors

Institutions

Publication Details

Journal
Science
Published
2025-10-23
DOI
https://doi.org/10.1126/science.adi8577
Citations
10
Primary Topic
Genomics and Phylogenetic Studies
Type
article
Field-Weighted Citation Impact
8.06
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Active learning framework leveraging transcriptomics identifies modulators of disease phenotypes

Samuel A. Miller, Raziel Rojas-Rodriguez, T. Joshua Pfefer, Inna Lipchina et al.
10 citations
Science
Genomics and Phylogenetic Studies
8.06
article

Active learning framework leveraging transcriptomics identifies modulators of disease phenotypes

Samuel A. Miller, Raziel Rojas-Rodriguez, T. Joshua Pfefer, Inna Lipchina, Mahdi Zamanighomi, David Kim, Christine Kerr, Artur Szałata, James J. Collins, Daniel B. Burkhardt, Fabian Joachim Theis, Alex K. Shalek, Benjamin DeMeo, Doris Fu, Ishan Gupta, Mauricio Cortes, Laurens Kruidenier, Sunil Kuppassani, Parul B. Doshi, Charlotte Nesbitt, Peter Holderreith, Sergey Kolchenko
article en
10 citations

Abstract

Phenotypic drug screening remains constrained by the vastness of chemical space and the technical challenges of 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- to 17-fold 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 twofold increase in hit rate along with molecular insights. In sum, our framework enables efficient phenotypic hit identification campaigns, with broad potential to accelerate drug discovery.

ScienceVol. 390(6776)
Broad Institute (US), Harvard University (US), Somerville Hospital (US), Ragon Institute of MGH, MIT and Harvard (US), Helmholtz Zentrum München (DE), IIT@MIT (US), Technical University of Munich (DE), Massachusetts Institute of Technology (US)
Openalex Percentile: Top 2%
Genomics and Phylogenetic Studies
8.06
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.