A multi-scale multi-model deep neural network via ensemble strategy on high-throughput microscopy image for protein subcellular localization

作者：

Highlights：

• A multi-scale multi-model DNN for protein subcellular localization through images.

• The multi-model structure can consider features of different abstraction levels.

• SE block is added to the network to emphasize more informative features.

• An ensemble method is used to fuse the classification results from different models.

摘要

•A multi-scale multi-model DNN for protein subcellular localization through images.•The multi-model structure can consider features of different abstraction levels.•SE block is added to the network to emphasize more informative features.•An ensemble method is used to fuse the classification results from different models.

论文关键词：Protein subcellular localization,Deep learning,Multi-scale multi-model,Ensemble learning,Yeast cell image

论文评审过程：Received 1 July 2021, Revised 17 May 2022, Accepted 30 August 2022, Available online 5 September 2022, Version of Record 15 September 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118744