Un enfoque para desarrollar conjuntos de datos de referencia para la segmentación de estructuras secundarias de...

More and more deep learning approaches have been proposed to segment secondary structures from cryo-electron density maps at medium resolution range (5-10Å). Although the deep learning approaches show great potential, only a few small experimental data sets have been used to test the approaches. There is limited understanding about potential factors, in data, that affect the performance of segmentation. We propose an approach to generate data sets with desired specifications in three potential factors - the protein sequence identity, structural contents, and data quality. The approach was implemented and has generated a test set and various training sets to study the effect of secondary structure content and data quality on the performance of DeepSSETracer, a deep learning method that segments regions of protein secondary structures from cryo-EM map components. Results show that various content levels in the secondary structure and data quality influence the performance of segmentation for DeepSSETracer.