🏠 Home

A collection of general pretrained networks for cellular cryoET

Trained on a large and curated body of cryoET datasets, easymode provides pretrained networks for feature detection in cellular cryoET. Our models are hosted via Hugging Face and automatically distributed for inference – meaning you don't need to worry about downloading model weights.

Simply call easymode segment ribosome, point to your data, and easymode will do the rest. Or microtubule. Or mitochondrion. Or npc. Or tric. Or check out the full model library.

easymode ecosystem

easymode was built on top of Ais, inspired by Membrain, and designed for use within Warp/Relion/M pipelines. By growing the easymode model library, our eventual goal is to enable Pom's tricks - context-aware particle picking, area selective template matching, and representing datasets as searchable databases - without requiring any training at all.