Lung adenocarcinoma (LUAD) is a leading cause of cancer-related deaths worldwide. The splicing factor RBM10 is commonly mutated in various cancer types and is strikingly one of the most mutated genes in LUAD (~9-25%). Most RBM10 cancer mutations are loss-of-function that correlate with increased tumorigenesis and poor survival, and limit the efficacy of targeted therapies in EGFR-mutated lung cancer. Notably, exploiting RBM10 deficiency for targeted cancer therapy has not yet been explored, highlighting the urgency of identifying genetic vulnerabilities to RBM10 loss. Prompted by this, we performed a genome-wide CRISPR-Cas9 synthetic lethal (SL) screen in isogenic LUAD cell line harboring RBM10 cancer mutation and identified 262 high-scoring RBM10 SL genes, including Aurora A and WEE1 kinases. We show that pharmacological inhibition of WEE1 selectively sensitizes RBM10-deficient LUAD cells, including patient-derived cells harboring RBM10 cancer mutations, in vitro and in mouse xenograft model. Moreover, the sensitivity of RBM10-deficient cells to WEE1 inhibition is further exacerbated by combined treatment with Aurora kinase A inhibitor. Mechanistically, we demonstrate that the sensitivity to WEE1 inhibition is irrespective of RBM10 splicing activity, and potentiated by DNA damage accumulation, replication stress, and premature mitotic entry. Interestingly, we also reveal an unexpected role of RBM10 in promoting replication fork progression and stress response, at least in part, through its association with replication fork components. Collectively, our data identify DNA replication stress as an SL pathway with RBM10 loss, and provide a repertoire of targets that can be harnessed therapeutically to eradicate RBM10-deficient tumors.