Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: FoldHSphere: deep hyperspherical embeddings for protein fold recognition

Fig. 1

Overview of the FoldHSphere approach for protein fold recognition. In the first stage a we train a neural network model to map the protein domains into K fold classes using the softmax cross-entropy as loss function. From this trained model, we extract fold class weight vectors \(\mathbf {w}_k, k=1,\dots ,K\) learned in the last classification layer. b We then optimize the position of the \(\mathbf {w}_k\) vectors by our proposed Thomson-based loss, so that they are maximally separated in the angular space. c The resulting hyperspherical prototypes are used as a fixed non-trainable classification matrix \(\mathbf {W}\) in the last layer of the neural network model, which is trained again, but now minimizing the LMCL. The final hyperspherical embeddings are extracted from the fully-connected part of this model. d Finally, the cosine similarity is computed between each two embeddings and a template ranking is performed for each query protein domain (FoldHSphere method). Moreover, template ranking is further improved by using enhanced scores provided by a random forest model trained with additional similarity measures as inputs (FoldHSpherePro method)

Back to article page