Supplementary Figure 2: Performance of in vitro trained TF models on in vivo data (DREAM5 ChIP-seq) | Nature Biotechnology

Supplementary Figure 2: Performance of in vitro trained TF models on in vivo data (DREAM5 ChIP-seq)

From: Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning

Supplementary Figure 2

(a) All DREAM5 ChIP-seq AUCs used to compute mean performance shown in Figure 3b. The models were trained on the DREAM5 PBM training data only, and evaluated against three different backgrounds22. (b) Cross-validation performance of methods trained directly on ChIP-seq data (sequence length 100), evaluated against a dinucleotide shuffled background (Supplementary Table 1).

Back to article page