Transcriptome-wide association studies (TWASs) utilize gene-expression data to explore the genetic basis of complex traits. A key challenge in TWASs is developing robust imputation models for tissues with limited sample sizes. This paper introduces transfer learning-assisted TWAS (TransferTWAS), a framework that adaptively transfers information from multiple tissues to improve gene-expression prediction in the target tissue. TransferTWAS employs a data-driven strategy that assigns higher weights to genetically similar external tissues. It outperforms other multi-tissue TWAS methods, such as the Unified Test for Molecular Signatures (UTMOST), which neglects tissue similarity, and Joint-Tissue Imputation (JTI), which relies on functional annotations to represent tissue similarity. Simulation studies demonstrate that TransferTWAS achieves the highest imputation accuracy, and analyses using the ROS/MAP and GEUVADIS datasets show a substantial power gain while maintaining control over type-I errors. Furthermore, analysis of the low-density lipoprotein cholesterol GWAS dataset and other complex traits demonstrates that TransferTWAS effectively identifies more associations compared with existing methods.