Figure 1 | Scientific Reports

Figure 1

From: A fully open-source framework for deep learning protein real-valued distances

Figure 1

Comparison of the protein inter-residue distance prediction problem with the ‘depth prediction from a single image problem’ in computer vision. In both problems, the input to the deep learning model is a volume and the output is a 2D matrix. The depth predictions for this specific image (top right corner) were obtained with a pre-trained fully convolutional residual network (FCRN)11.

Back to article page