1 Abstract
The cryo-EM resolution revolution enables the development of algorithms for direct de-novo modelling of protein structures from given cryo-EM density maps. Deep Learning tools have been applied to locate structure patterns, such as rotamers, secondary structures and Cα atoms. We present a deep neural network (nicknamed SegmA) for the residue type segmentation of a cryo-EM density map. The network labels voxels in a cryo-EM map by the residue type (amino acid type or nucleic acid) of the sampled macromolecular structure. It also provides a visual representation of the density map by coloring the different types of voxels by their assgned colors. SegmA’s algorithm combines a rotation equivariant group convolutional network with a traditional U-net network in a cascade. In addition SegmA estimates the labeling accuracy and reports only labels assigned with high confidence. At resolution of 3Å SegmAs accuracy is 80% for nucleotides. Amino acids which can be seen by eye, such as LEU, ARG and PHE, are detected by Segma with about 70% accuracy.
A web server of the application is under development at https://dev.dcsh7cbr3o89e.amplifyapp.com. The SegmA open code is available at https://github.com/Mark-Rozanov/SegmA_3A/tree/master
Competing Interest Statement
The authors have declared no competing interest.