Department of Computer Science, University of York, Heslington, York YO10 5GH, United Kingdom.
Department of Chemistry, University of York, Heslington, York YO10 5DD, United Kingdom.
Acta Crystallogr D Struct Biol. 2023 Apr 1;79(Pt 4):326-338. doi: 10.1107/S205979832300181X. Epub 2023 Mar 28.
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.
追踪骨架是蛋白质模型构建的关键步骤，因为不正确的追踪会导致较差的蛋白质模型。在这里，提出了一种经过训练可识别不良片段并将其从模型构建过程中去除以改善骨架追踪的神经网络。此外，还训练了一个决策树来选择最佳阈值以消除不良片段。该神经网络在联合结构基因组学中心（JCSG）的实验相数据集、最近提交的实验相数据集（2015 年至 2021 年）和分子置换数据集上进行了测试。实验结果表明，在 Buccaneer 蛋白质建模软件中使用神经网络可以产生比单独使用 Buccaneer 更完整的蛋白质模型。特别是，对于 JCSG 原始和截断分辨率实验相数据集的 25%和 50%，对于最近收集的实验相数据集的 28%以及对于分子置换数据集的 43%，Buccaneer 与神经网络构建的蛋白质模型的完整性至少提高了 5%。
