Buccaneer model building with neural network fragment selection

Tracing the backbone is a critical step in protein model building, as incorrect tracing leads to poor protein models. Here, a neural network trained to identify unfavourable fragments and remove them from the model-building process in order to improve backbone tracing is presented. Moreover, a decision tree was trained to select an optimal threshold to eliminate unfavourable fragments. The neural network was tested on experimental phasing data sets from the Joint Center for Structural Genomics (JCSG), recently deposited experimental phasing data sets (from 2015 to 2021) and molecular-replacement data sets. The experimental results show that using the neural network in the Buccaneer protein-model-building software can produce significantly more complete protein models than those built using Buccaneer alone. In particular, Buccaneer with the neural network built protein models with a completeness that was at least 5% higher for 25% and 50% of the original and truncated resolution JCSG experimental phasing data sets, respectively, for 28% of the recently collected experimental phasing data sets and for 43% of the molecular-replacement data sets.

Current approaches for automated model building into cryo-EM maps using Buccaneer with CCP-EM

This work focuses on the use of the existing protein-model-building software Buccaneer to provide structural interpretation of electron cryo-microscopy (cryo-EM) maps. Originally developed for application to X-ray crystallography, the necessary steps to optimise the usage of Buccaneer with cryo-EM maps are shown. This approach has been applied to the data sets of 208 cryo-EM maps with resolutions of better than 4 Å. The results obtained also show an evident improvement in the sequencing step when the initial reference map and model used for crystallographic cases are replaced by a cryo-EM reference. All other necessary changes to settings in Buccaneer are implemented in the model-building pipeline from within the CCP-EM interface (as of version 1.4.0).

CAB: a cyclic automatic model-building procedure

The program Buccaneer, a well known fast and efficient automatic model-building program, is also a tool for phase refinement: indeed, input phases are used to calculate electron-density maps that are interpreted in terms of a molecular model, from which new phase estimates may be obtained. This specific property is shared by all other automatic model-building programs and allows their cyclic use, as is usually performed in other phase-refinement methods (for example electron-density modification techniques). Buccaneer has been included in a cyclic procedure, called CAB, aimed at increasing the rate of success of Buccaneer and the quality of the molecular models provided. CAB has been tested on 81 protein structures that were solved via molecular-replacement, anomalous dispersion and ab initio methods. The corresponding phases were submitted to a phase-refinement process that synergically combines current phase-refinement techniques and out-of-mainstream refinement methods [Burla et al. (2017), Acta Cryst. D73, 877-888]. The phases thus obtained were used as input for CAB. The experimental results were compared with those obtained by the sole use of Buccaneer: it is shown that CAB improves the Buccaneer results, both in completeness and in accuracy.