Abstract
Protein structure prediction has been greatly improved by deep learning, but most efforts are devoted to template-free modeling. But very few deep learning methods are developed for TBM (template-based modeling), a popular technique for protein structure prediction. TBM has been studied extensively in the past, but its accuracy is not satisfactory when highly similar templates are not available. This paper presents a new method NDThreader (New Deep-learning Threader) to address the challenges of TBM. NDThreader first employs DRNF (deep convolutional residual neural fields), which is an integration of deep ResNet (convolutional residue neural networks) and CRF (conditional random fields), to align a query protein to templates without using any distance information. Then NDThreader uses ADMM (alternating direction method of multipliers) and DRNF to further improve sequence-template alignments by making use of predicted distance potential. Finally, NDThreader builds 3D models from a sequence-template alignment by feeding it and sequence coevolution information into a deep ResNet to predict inter-atom distance distribution, which is then fed into PyRosetta for 3D model construction. Our experimental results show that NDThreader greatly outperforms existing methods such as CNFpred, HHpred, DeepThreader and CEthreader. NDThreader was blindly tested in CASP14 as a part of RaptorX server, which obtained the best average GDT score among all CASP14 servers on the 58 TBM targets.
Highlights
Predicting protein structure from its amino acid sequence is one of the most challenging problems in the field of computational biology
NDThreader first employs DRNF, which is an integration of deep residual neural network (ResNet) and CRF, to align a query protein to templates without using any distance information
NDThreader builds 3D models from a sequence-template alignment by feeding it and sequence coevolution information into a deep ResNet to predict inter-atom distance distribution, which is fed into PyRosetta for 3D model construction
Summary
Predicting protein structure from its amino acid sequence is one of the most challenging problems in the field of computational biology. Template-based modeling (TBM), including protein threading and homology modeling, is a popular method for protein tertiary structure prediction. TBM predicts the structure of a query protein (called target) by aligning it to one or multiple templates with solved structures. Along with the growth of the PDB (Protein Data Bank), TBM is able to predict structures for a good percentage of proteins [1]. In CASP13 67 out of 112 test domains and in CASP14 58 out of 107 test domains have reasonable templates in PDB. When a protein under prediction does not have highly similar templates, TBM faces three major challenges: selection of the best templates, building an accurate sequence-template alignment, and constructing 3D models from the alignment
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
