Protein localization information is essen-tial for understanding protein functions and their roles in various biological processes.The image-based prediction methods of protein subcellular localization have emerged in recent years because of the advantages of microscopic images in revealing spatial expression and distribution of proteins in cells.However,the image-based prediction is a very challenging task,due to the multi-instance nature of the task and low quality of images.In this paper,we pro-pose a multi-task learning strategy and mask generation to enhance the prediction performance.Furthermore,we also investigate effective multi-instance learning schemes.We collect a large-scale dataset from the Human Protein Atlas database,and the experimental results show that the proposed multi-task multi-instance learning model outperforms both single-instance learning and common multi-instance learning methods by large margins.

ZHANG Pingyue;ZHANG Mengtian;LIU Hui;YANG Yang

Department of Computer Science and Engineering,Shanghai Jiao Tong University,Shanghai 200240,China

电子学报（英文）

[1]ZHANG Pingyue;ZHANG Mengtian;LIU Hui;YANG Yang-.Prediction of Protein Subcellular Localization Based on Microscopic Images via Multi-Task Multi-Instance Learning)[J].电子学报（英文）,2022(05):888-896

Prediction,Protein,Subcellular,Localization,Based,Microscopic,Images,via,Multi,Task,Instance,Learning,localization,information,essen,understanding,functions,their,roles,various,biological,processes,prediction,methods,subcellular,have,emerged,recent,years,because,advantages,microscopic,images,revealing,spatial,expression,distribution,proteins,cells,However,very,challenging,task,due,multi,instance,nature,low,quality,this,paper,learning,strategy,mask,generation,enhance,performance,Furthermore,also,investigate,effective,schemes,We,collect,large,scale,dataset,from,Human,Atlas,database,experimental,results,show,that,proposed,model,outperforms,both,single,common,by,margins

0.629699