Fig. 3: Evaluation and application of the DeepMVP for PTM site prediction. | Nature Methods

Fig. 3: Evaluation and application of the DeepMVP for PTM site prediction.

From: DeepMVP: deep learning models trained on high-quality data accurately predict PTM sites and variant-induced alterations

Fig. 3

a–h, Performance comparison between DeepMVP and other models for site prediction for six PTM types, evaluated on the basis of AUROC. i, Proportion of PTM sites nominated in this study in the human proteome for the six PTM types and their classification into three confidence levels. j, Comparison between S/T phosphosite prediction results against phosphosites detected in two phosphoproteomic experiments, and the whole proteome of SARS-CoV-2.

Source data

Back to article page