There are many new and potential drug targets in G protein-coupled receptors(GPCRs)without sufficient ligand associations,and accurately predicting and interpreting ligand bioactivities is vital for screening and optimizing hit compo-unds targeting these GPCRs.To efficiently address the lack of labeled training samples,we proposed a multi-task regression learning with incoherent sparse and low-rank patterns(MTR-ISLR)to model ligand bioactivities and identify their key substructures associated with these GPCRs targets.That is,MTR-ISLR intends to enhance the performance and interpre-tability of models under a small size of available training data by introducing homologous GPCR tasks.Meanwhile,the low-rank constraint term encourages to catch the underlying relationship among homologous GPCR tasks for greater model generalization,and the entry-wise sparse regularization term ensures to recognize essential discriminative substructures from each task for explanative modeling.We examined MTR-ISLR on a set of 31 important human GPCRs datasets from 9 subfamilies,each with less than 400 ligand associations.The results show that MTR-ISLR reaches better performance when compared with traditional single-task learning,deep multi-task learning and multi-task learning with joint feature learning-based models on most cases,where MTR-ISLR obtains an average improvement of 7％in correlation coefficient(r2)and 12％in root mean square error(RMSE)against the runner-up predictors.The MTR-ISLR web server appends freely all source codes and data for academic usages.1)

Jiansheng WU;Chuangchuang LAN;Xuelin YE;Jiale DENG;Wanqing HUANG;Xueni YANG;Yanxiang ZHU;Haifeng HU

School of Geographic and Biologic Information,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Department of Statistics,University of Warwick,Coventry CV47AL,United Kingdom;Modern Economics&Management College,Jiangxi University of Finance and Economics,Nanchang 330013,China;School of Telecommunication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Verimake Research,Nanjing Qujike Info-tech Co.,Ltd.,Nanjing 210088,China

计算机科学前沿

[1]Jiansheng WU;Chuangchuang LAN;Xuelin YE;Jiale DENG;Wanqing HUANG;Xueni YANG;Yanxiang ZHU;Haifeng HU-.Disclosing incoherent sparse and low-rank patterns inside homologous GPCR tasks for better modelling of ligand bioactivities)[J].计算机科学前沿,2022(04):88-99

Disclosing,unds,interpre,tability,explanative,appends

incoherent,sparse,low,rank,patterns,inside,homologous,tasks,better,modelling,ligand,bioactivities,There,many,new,potential,drug,targets,protein,coupled,receptors,GPCRs,without,sufficient,associations,accurately,predicting,interpreting,vital,screening,optimizing,hit,compo,targeting,these,To,efficiently,address,lack,labeled,training,samples,proposed,multi,regression,learning,MTR,ISLR,identify,their,key,substructures,associated,That,intends,enhance,performance,models,small,size,available,by,introducing,Meanwhile,constraint,term,encourages,catch,underlying,relationship,among,greater,generalization,entry,wise,regularization,ensures,recognize,essential,discriminative,from,modeling,We,examined,important,human,datasets,subfamilies,less,than,results,show,that,reaches,when,compared,traditional,single,deep,joint,feature,most,cases,where,obtains,average,improvement,correlation,coefficient,r2,root,mean,square,error,RMSE,against,runner,predictors,web,server,freely,source,codes,academic,usages

0.537022