Skip to main content
. 2023 Jun 30;39(Suppl 1):i318–i325. doi: 10.1093/bioinformatics/btad208

Figure 1.

Figure 1.

The protein function prediction pipeline of TransFun. The pipeline is divided into two main components, feature preprocessing (left) and neural network model (right). The input is a protein sequence. The output is the predicted probabilities of the GO terms for the protein.