Cryo-electron microscopy (cryo-EM) has become one of important experimental methods in structure determination. However, despite the rapid growth in the number of deposited cryo-EM maps motivated by advances in microscopy instruments and image processing algorithms, building accurate structure models for cryo-EM maps remains a challenge. Protein secondary structure information, which can be extracted from EM maps, is beneficial for cryo-EM structure modeling. Here, we present a novel secondary structure annotation framework for cryo-EM maps at both intermediate and high resolutions, named EMNUSS. EMNUSS adopts a three-dimensional (3D) nested U-net architecture to assign secondary structures for EM maps. Tested on three diverse datasets including simulated maps, middle resolution experimental maps, and high-resolution experimental maps, EMNUSS demonstrated its accuracy and robustness in identifying the secondary structures for cyro-EM maps of various resolutions. Advances in microscopy instruments and image processing algorithms have led to an increasing number of cryo-electron microscopy (cryo-EM) maps [1–3]. The'resolution revolution' in cryo-EM has paved the way for the determination of structures of previously intractable biological systems at unprecedented resolution [4–14]. However, the goal of cryo-EM is not to obtain the 3D maps but to determine the detailed atomic structures [15–25]. It is challenging to build accurate structure models for cryo-EM maps [26]. Rigid fitting and flexible fitting are commonly used methods to fit atomic structures into EM maps, but they are only possible if template structures are available. Without template structures, de novo modeling tools are needed to build full-atom models into EM density maps. However, the application of de novo modeling tools is limited because of their precarious accuracy.

We use two co-evolving neural networks to determine new classes of protein secondary structure which are significantly more predictable from local amino sequence than the conventional secondary structure classification. Accurate prediction of the conventional secondary structure classes: alpha helix, beta strand, and coil, from primary sequence has long been an important problem in computational molecular biology. Neural networks have been a popular method to attempt to predict these conventional secondary structure classes. Accuracy has been disappointingly low. The algorithm presented here uses neural networks to similtaneously examine both sequence and structure data, and to evolve new classes of secondary structure that can be predicted from sequence with significantly higher accuracy than the conventional classes. These new classes have both similarities to, and differences with the conventional alpha helix, beta strand and coil.

We use two co-evolving neural networks to determine new classes of protein secondary structure which are significantly more predictable from local amino sequence than the conventional secondary structure classification. Accurate prediction of the conventional secondary structure classes: alpha helix, beta strand, and coil, from primary sequence has long been an important problem in computational molecular biology. Neural networks have been a popular method to attempt to predict these conventional secondary structure classes. Accuracy has been disappointingly low. The algorithm presented here uses neural networks to similtaneously examine both sequence and structure data, and to evolve new classes of secondary structure that can be predicted from sequence with significantly higher accuracy than the conventional classes. These new classes have both similarities to, and differences with the conventional alpha helix, beta strand and coil.

Alan Lapedes Complex Systems Group (TI3) LANL, MS B213 Los Alamos N.M. 87545 and The Santa Fe Institute, Santa Fe, New Mexico Evan Steeg Department of Computer Science University of Toronto, Toronto, Canada Robert Farber Complex Systems Group (TI3) LANL, MS B213 Los Alamos N.M. 87545 Abstract We use two co-evolving neural networks to determine new classes of protein secondary structure which are significantly more predictable fromlocal amino sequence than the conventional secondary structure classification. Accurate prediction of the conventional secondary structure classes: alpha helix, beta strand, and coil, from primary sequence has long been an important problem in computational molecularbiology. Neural networks have been a popular method to attempt to predict these conventional secondary structure classes.Accuracy has been disappointingly low. The algorithm presentedhere uses neural networks to similtaneously examine both sequence and structure data, and to evolve new classes of secondary structure that can be predicted from sequence with significantly higher accuracy than the conventional classes. These new classes have both similarities to, and differences with the conventional alphahelix, beta strand and coil.