Fungal pathogens cause fatal plant diseases, contributing to up to 20% loss in annual crop yield. These pathogens accomplish this using an arsenal of secreted effectors that can target the plant apoplast or be translocated into the plant to affect cellular functions and disrupt host defences. Identification of fungal effectors is a crucial step, not only to advance our understanding of plant–pathogen interactions, but also to assist in developing novel disease prevention strategies to ultimately to mitigate crop losses and improve food safety. However, the fast evolving nature of fungal effectors, coupled with the limited number of known fungal effectors, complicates efforts to reliably distinguish them from non-effectors.

Here, we introduce Fungtion (Fungal effector prediction), a toolkit leveraging a hybrid framework to accurately predict and visualize fungal effectors. By combining global patterns learned from pretrained protein language models with refined information from known effectors, Fungtion achieves state-of-the-art prediction performance. Additionally, the interactive visualizations we have developed enable researchers to explore relationships between the predicted and known effectors, facilitating effector function discovery, annotation, and hypothesis formulation regarding plant-pathogen interactions. We anticipate Fungtion to be a valuable resource for biologists seeking deeper insights into fungal effector functions and for computational biologists aiming to develop future methodologies for fungal effector prediction.