Continuous learning method and system for biomacromolecular particle recognition of cryoelectron microscope

Abstract

The invention provides a continuous learning method and system for biomacromolecular particle recognition of a cryoelectron microscope. The method comprises the following steps: acquiring to-be-recognized cryoelectron microscope image data; and inputting the to-be-identified cryoelectron microscope image data into a trained network parameter model to obtain an identification result of the biomacromolecular particles, wherein the trained network parameter model is obtained by training a neural network according to example cryoelectron microscope sample image data and cryoelectron microscope sample image data obtained in a historical training process, and the example cryoelectron microscope sample image data and the cryoelectron microscope sample image data are labeled with biological macromolecular particle coordinate tags. The method does not need to store a large amount of old data sets, reduces the single training time, and can continuously enhance the feature recognition range and recognition precision of particle selection.

Description

technical field [0001] The invention relates to the technical field of cryo-electron microscopy, in particular to a continuous learning method and system for identifying biomacromolecular particles in a cryo-electron microscope. Background technique [0002] Cryo-electron microscopy (cryo-EM for short) is a recently developed method for interpreting high-resolution structures of biological macromolecular complexes and cellular tissues. In structure elucidation, it is necessary to be able to identify the biomacromolecular particles of interest in cryo-electron microscopy images before further structural elucidation. [0003] During the use of the cryo-electron microscope system, different biological samples will be processed continuously, thereby continuously generating new data. In each batch of new data, a part needs to be selected for training the network and obtaining a new model. With the use of the electron microscope for a long time, the accumulated training data wil...

AI Technical Summary

Problems solved by technology

However, the amount of data used for joint training will become larger and larger, leading to the following problems. First, it will put pressure on storage and require a long-term maintenance of a large number of training data sets. getting longer

Images