The application of machine learning in sciences has seen exciting advances in recent years. As a widely applicable technique, anomaly detection has been long studied in the machine learning community. Especially, deep neural nets-based out-of-distribution detection has made great progress for high-dimensional data. Recently, these techniques have been showing their potential in scientific disciplines. We take a critical look at their applicative prospects including data universality, experimental protocols, model robustness, etc. We discuss examples that display transferable practices and domain-specific challenges simultaneously, providing a starting point for establishing a novel interdisciplinary research paradigm in the near future.