The high-content image-based assay is commonly leveraged for identifying the pheno-typic impact of genetic perturbations in biology field.However,a persistent issue remains unsolved during experiments:the interferential technical noises caused by systematic errors(e.g.,tempera-ture,reagent concentration,and well location)are always mixed up with the real biological signals,leading to misinterpretation of any conclusion drawn.Here,we reported a mean teacher-based deep learning model(DeepNoise)that can disentangle biological signals from the experimental noises.Specifically,we aimed to classify the phenotypic impact of 1108 different genetic perturbations screened from 125,510 fluorescent microscopy images,which were totally unrecognizable by the human eye.We validated our model by participating in the Recursion Cellular Image Classification Challenge,and DeepNoise achieved an extremely high classification score(accuracy:99.596％),ranking the 2nd place among 866 participating groups.This promising result indicates the success-ful separation of biological and technical factors,which might help decrease the cost of treatment development and expedite the drug discovery process.The source code of DeepNoise is available at .

Tencent AI Lab,Shenzhen 518057,China;Department of Electronic Engineering,The Chinese University of Hong Kong,Hong Kong Special Administrative Region 999077,China;College of Computer Science,Sichuan University,Chengdu 610065,China

[1]Sen Yang;Tao Shen;Yuqi Fang;Xiyue Wang;Jun Zhang;Wei Yang;Junzhou Huang;Xiao Han-.DeepNoise:Signal and Noise Disentanglement Based on Classifying Fluorescent Microscopy Images via Deep Learning)[J].基因组蛋白质组与生物信息学报（英文版）,2022(05):989-1001

DeepNoise,Disentanglement,typic,interferential,misinterpretation,unrecognizable,Recursion

Signal,Based,Classifying,Fluorescent,Microscopy,Images,via,Learning,high,content,assay,commonly,leveraged,identifying,impact,genetic,perturbations,biology,field,However,persistent,issue,remains,unsolved,during,experiments,technical,noises,caused,by,systematic,errors,tempera,ture,reagent,concentration,well,location,are,always,mixed,real,biological,signals,leading,any,conclusion,drawn,Here,reported,mean,teacher,deep,learning,model,that,can,disentangle,from,experimental,Specifically,aimed,classify,phenotypic,different,screened,fluorescent,microscopy,images,which,were,totally,human,eye,We,validated,participating,Cellular,Classification,Challenge,achieved,extremely,classification,score,accuracy,ranking,2nd,place,among,groups,This,promising,result,indicates,success,ful,separation,factors,might,help,decrease,cost,treatment,development,expedite,drug,discovery,process,source,code,available

0.645748