DeepCpf1: Deep learning-based prediction ofCRISPR-Cpf1 activity at endogenous sites

We developed Seq-deepCpf1, a deep learning-based algorithm trained on a data set of AsCpf1 (Cpf1 from Acidaminococcus sp.BV3L6)-induced indel frequencies at 15,000 target sequences, which outperformed conventional machine learning-based algorithms.Subsequent fine-tuning of Seq-deepCpf1 using data sets of AsCpf1induced indel frequencies at endogenous target sites with chromatin accessibility information enabled the development of DeepCpf1.We provide DeepCpf1 as a web tool, which predicts AsCpf1 activities at endogenous target sites with unprecedentedly high accuracy.