TransCell:In Silico Characterization of Genomic Landscape and Cellular Responses by Deep Transfer Learning

作     者：Shan-Ju Yeh Shreya Paithankar Ruoqiao Chen Jing Xing Mengying Sun Ke Liu Jiayu Zhou Bin Chen 

作者机构：Department of Pediatrics and Human DevelopmentMichigan State UniversityGrand RapidsMI 49503USA Department of Pharmacology and ToxicologyMichigan State UniversityGrand RapidsMI 49503USA Department of Computer Science and EngineeringMichigan State UniversityEast LansingMI 48824USA 

出 版 物：《Genomics, Proteomics & Bioinformatics》 (基因组蛋白质组与生物信息学报（英文版）)

年 卷 期：2024年第22卷第2期

页      面：157-170页

核心收录：

学科分类：0710[理学-生物学] 07[理学] 08[工学] 09[农学] 071007[理学-遗传学] 0901[农学-作物学] 0836[工学-生物工程] 090102[农学-作物遗传育种] 

基　　金：supported by the National Institute of Health(Grant Nos.R01GM134307 and K01 ES028047) the MSU Global Impact Initiative,USA 

主　　题：Genomics Transcriptomics Cancer dependency Drug repurposing Transfer learning 

摘      要：Gene expression profiling of new or modified cell lines becomes routine today;however,obtaining comprehensive molecular characterization and cellular responses for a variety of cell lines,including those derived from underrepresented groups,is not trivial when resources are *** gene expression to predict other measurements has been actively explored;however,systematic investigation of its predictive power in various measurements has not been well ***,we evaluated commonly used machine learning methods and presented TransCell,a two-step deep transfer learning framework that utilized the knowledge derived from pan-cancer tumor samples to predict molecular features and *** these models,TransCell had the best performance in predicting metabolite,gene effect score(or genetic dependency),and drug sensitivity,and had comparable performance in predicting mutation,copy number variation,and protein ***,TransCell improved the performance by over 50%in drug sensitivity prediction and achieved a correlation of 0.7 in gene effect score ***,predicted drug sensitivities revealed potential repurposing candidates for new 100 pediatric cancer cell lines,and predicted gene effect scores reflected BRAF resistance in melanoma cell ***,we investigated the predictive power of gene expression in six molecular measurement types and developed a web portal(http://***/transcell/)that enables the prediction of 352,000 genomic and cellular response features solely from gene expression profiles.