Prediction of potent shRNAs with a sequential classification algorithm

• Published in: Nature biotechnology Vol. 35; no. 4; pp. 350 - 353
• Main Authors: Pelossof, Raphael, Fairchild, Lauren, Huang, Chun-Hao, Widmer, Christian, Sreedharan, Vipin T, Sinha, Nishi, Lai, Dan-Yu, Guan, Yuanzhe, Premsrirut, Prem K, Tschaharganeh, Darjus F, Hoffmann, Thomas, Thapar, Vishal, Xiang, Qing, Garippa, Ralph J, Rätsch, Gunnar, Zuber, Johannes, Lowe, Scott W, Leslie, Christina S, Fellmann, Christof
• Format: Journal Article
• Language: English
• Published: United States Nature Publishing Group 01.04.2017
• Subjects: Algorithms; Analysis; Biology; Cancer; Chromosome Mapping - methods; Classification; Clustered Regularly Interspaced Short Palindromic Repeats - genetics; Computer science; CRISPR-Cas Systems - genetics; Datasets; Gene Silencing; Machine Learning; Methods; MicroRNA; MicroRNAs; Physiological aspects; RNA sequencing; RNA, Small Interfering - genetics; Sequence Analysis, RNA - methods; Software; Support vector machines; New York; United States > US; California
• ISSN: 1087-0156; 1546-1696
• DOI: 10.1038/nbt.3807

We present SplashRNA, a sequential classifier to predict potent microRNA-based short hairpin RNAs (shRNAs). Trained on published and novel data sets, SplashRNA outperforms previous algorithms and reliably predicts the most efficient shRNAs for a given gene. Combined with an optimized miR-E backbone, >90% of high-scoring SplashRNA predictions trigger >85% protein knockdown when expressed from a single genomic integration. SplashRNA can significantly improve the accuracy of loss-of-function genetics studies and facilitates the generation of compact shRNA libraries.