Swin-cryoEM: Multi-class cryo-electron micrographs single particle mixed detection method

Abstract

Cryo-electron micrograph images have various characteristics such as varying sizes, shapes, and distribution densities of individual particles, severe background noise, high levels of impurities, irregular shapes, blurred edges, and similar color to the background. How to demonstrate good adaptability in the field of image vision by picking up single particles from multiple types of cryo-electron micrographs is currently a challenge in the field of cryo-electron micrographs. This paper combines the characteristics of the MixUp hybrid enhancement algorithm, enhances the image feature information in the pre-processing stage, builds a feature perception network based on the channel self-attention mechanism in the forward network of the Swin Transformer model network, achieving adaptive adjustment of self-attention mechanism between different single particles, increasing the network's tolerance to noise, Incorporating PReLU activation function to enhance information exchange between pixel blocks of different single particles, and combining the Cross-Entropy function with the softmax function to construct a classification network based on Swin Transformer suitable for cryo-electron micrograph single particle detection model (Swin-cryoEM), achieving mixed detection of multiple types of single particles. Swin-cryoEM algorithm can better solve the problem of good adaptability in picking single particles of many types of cryo-electron micrographs, improve the accuracy and generalization ability of the single particle picking method, and provide high-quality data support for the three-dimensional reconstruction of a single particle. In this paper, ablation experiments and comparison experiments were designed to evaluate and compare Swin-cryoEM algorithms in detail and comprehensively on multiple datasets. The Average Precision is an important evaluation index of the evaluation model, and the optimal Average Precision reached 95.5% in the training stage Swin-cryoEM, and the single particle picking performance was also superior in the prediction stage. This model inherits the advantages of the Swin Transformer detection model and is superior to mainstream models such as Faster R-CNN and YOLOv5 in terms of the single particle detection capability of cryo-electron micrographs.

Fig 1. Swin-cryoEM model structure.

Fig 2

Comparison diagram before and after noise suppression: (a)original; (b)noise suppression.

Fig 3

Comparison histogram equalization between multiple categories: (a)EMPIAR-10153; (b) EMPIAR-10017;(c) EMPIAR-10088; (d)EMPIAR-10089; (1)Original;(2)Histogram equalization;(3)expression (1) histogram curve;(4)expression(2) histogram curve.

Fig 4. Pipeline process of Swin-cryoEM model.

Fig 5. Flow chart of feature extraction and detection methods based on channel attention mechanism.

Fig 6

The trend of IOU value AP between the Swin-cryoEM model and Swin Transformer model: (a) IOU = 0.5;(b) IOU = 0.75.

Fig 7. Comparison of AR between the Swin-cryoEM model and Swin Transformer model.

Fig 8. Swin-cryoEM model acc,cls_Loss, and loss analysis.

Fig 9

Test results of different types of particles in EMPIAR-10153 and EMPIAR-10017: (a) dataset human ribosomes (EMPIAR-10153); (b) Data set b-galactosidase (EMPIAR-10017).