TY - JOUR
T1 - AI virtual cells for drug discovery and pharmacology
AU - Wang, Shihang
AU - Zhang, Yang
AU - Wang, Dong
AU - Liu, Huanxiang
AU - Yao, Xiaojun
N1 - Publisher Copyright:
© 2026 Elsevier Ltd
PY - 2026/10
Y1 - 2026/10
N2 - Drug discovery relies on cellular assays to determine whether a candidate produces a desired response, reveals its mechanism, or causes toxicity, but only a small fraction of compound–dose–time–context combinations can be measured experimentally. Recent perturbation atlases, single-cell and imaging technologies, and intervention-conditioned AI models now make prediction of unmeasured cellular responses a testable objective. AI virtual cells could therefore complement conventional discovery by prioritizing compounds, contexts, and follow-up experiments rather than replacing laboratory assays. Here, we review the resources and modeling advances supporting this capability, assess their value for mechanism-of-action analysis, efficacy, safety, resistance, and combination studies, and define evidence requirements for pharmacological use. Data coverage makes oncology, including immuno-oncology, plausible early proving grounds, with safety assessment as a crosscutting use case; broader deployment requires perturbation-specific, mechanistic, and decision-level validation.
AB - Drug discovery relies on cellular assays to determine whether a candidate produces a desired response, reveals its mechanism, or causes toxicity, but only a small fraction of compound–dose–time–context combinations can be measured experimentally. Recent perturbation atlases, single-cell and imaging technologies, and intervention-conditioned AI models now make prediction of unmeasured cellular responses a testable objective. AI virtual cells could therefore complement conventional discovery by prioritizing compounds, contexts, and follow-up experiments rather than replacing laboratory assays. Here, we review the resources and modeling advances supporting this capability, assess their value for mechanism-of-action analysis, efficacy, safety, resistance, and combination studies, and define evidence requirements for pharmacological use. Data coverage makes oncology, including immuno-oncology, plausible early proving grounds, with safety assessment as a crosscutting use case; broader deployment requires perturbation-specific, mechanistic, and decision-level validation.
KW - AI virtual cells
KW - drug discovery
KW - perturbation biology
KW - phenotypic profiling
KW - single-cell modeling
KW - virtual pharmacology
UR - https://www.scopus.com/pages/publications/105050658947
U2 - 10.1016/j.tips.2026.08.006
DO - 10.1016/j.tips.2026.08.006
M3 - Review article
C2 - 42716878
AN - SCOPUS:105050658947
SN - 0165-6147
VL - 47
SP - 1085
EP - 1098
JO - Trends in Pharmacological Sciences
JF - Trends in Pharmacological Sciences
IS - 10
ER -