摘要Transcriptional phenotypic drug discovery has achieved great success,and various com-pound perturbation-based data resources,such as connectivity map(CMap)and library of inte-grated network-based cellular signatures(LINCS),have been presented.Computational strategies fully mining these resources for phenotypic drug discovery have been proposed.Among them,the fundamental issue is to define the proper similarity between transcriptional profiles.Tra-ditionally,such similarity has been defined in an unsupervised way.However,due to the high dimensionality and the existence of high noise in high-throughput data,similarity defined in the tra-ditional way lacks robustness and has limited performance.To this end,we present DrSim,which is a learning-based framework that automatically infers similarity rather than defining it.We evalu-ated DrSim on publicly available in vitro and in vivo datasets in drug annotation and repositioning.The results indicated that DrSim outperforms the existing methods.In conclusion,by learning tran-scriptional similarity,DrSim facilitates the broad utility of high-throughput transcriptional pertur-bation data for phenotypic drug discovery.The source code and manual of DrSim are available at https://github.com/bm2-lab/DrSim/.