PNNL

Abstract

A pre-trained convolutional neural network was fine-tuned for three separate classification tasks, distinguishing 2D images of: 1) single amino acids, 2) protein structural ball and stick images of metalloproteins, and 3) protein structural ball and stick images of metalloenzymes with the metal cofactors removed. The average recall for all tasks was above 95%, demonstrating this technique as a facile method for identifying potential metal binding sites.