The ease of programming CRISPR/Cas9 system for targeting a specific location within the genome has paved way for many clinical and industrial applications. However, its widespread use is still limited owing to its off-target effects. Though this off-target activity has been reported to be dependent on both sgRNA sequence and experimental conditions, a clear understanding of the factors imparting specificity to CRISPR/Cas9 system is important. A machine learning-based computational model has been developed for prediction of off-targets with more likelihood to be cleaved in vivo with an accuracy of 91.49%. The sequence features important for the prediction of positive off-targets were found to be accessibility, mismatches, GC-content and position-specific conservation of nucleotides. The instructions and code to generate the dataset and reproduce the analysis has been made available at http://web.iitd.ac.in/crispcut/off-targets/.

中文翻译：

---

sgRNA 设计工具预测的脱靶评估。

用于靶向基因组内特定位置的 CRISPR/Cas9 系统易于编程，为许多临床和工业应用铺平了道路。然而，由于其脱靶效应，其广泛使用仍然受到限制。尽管据报道这种脱靶活性取决于 sgRNA 序列和实验条件，但清楚地了解赋予 CRISPR/Cas9 系统特异性的因素很重要。已经开发了一种基于机器学习的计算模型，用于预测在体内更有可能被切割的脱靶，准确率为 91.49%。发现对预测阳性脱靶很重要的序列特征是可接近性、错配、GC 含量和核苷酸的位置特异性保守性。