A deep dilated convolutional residual network for predicting interchain contacts of protein homodimers

Abstract

Motivation Deep learning has revolutionized protein tertiary structure prediction recently. The cutting-edge deep learning methods such as AlphaFold can predict high-accuracy tertiary structures for most individual protein chains. However, the accuracy of predicting quaternary structures of protein complexes consisting of multiple chains is still relatively low due to lack of advanced deep learning methods in the field. Because interchain residue-residue contacts can be used as distance restraints to guide quaternary structure modeling, here we develop a deep dilated convolutional residual network method (DRCon) to predict interchain residue-residue contacts in homodimers from residue-residue co-evolutionary signals derived from multiple sequence alignments of monomers, intrachain residue-residue contacts of monomers extracted from true/predicted tertiary structures or predicted by deep learning, and other sequence and structural features. Results Tested on three homodimer test datasets (Homo_std dataset, DeepHomo dataset, and CASP-CAPRI dataset), the precision of DRCon for top L/5 interchain contact predictions (L: length of monomer in a homodimer) is 43.46%, 47.10%, and 33.50% respectively at 6 Å contact threshold, which is substantially better than DeepHomo and DNCON2_inter and similar to Glinter. Moreover, our experiments demonstrate that using predicted tertiary structure or intrachain contacts of monomers in the unbound state as input, DRCon still performs well, even though its accuracy is lower than using true tertiary structures in the bound state are used as input. Finally, our case study shows that good interchain contact predictions can be used to build high-accuracy quaternary structure models of homodimers. Availability The source code of DRCon is available at https://github.com/jianlin-cheng/DRCon.

Enhancing AlphaFold-Multimer-based Protein Complex Structure Prediction with MULTICOM in CASP15

“…However, the accuracy of the protein docking is generally low 3,4 . The recent application of deep learning to inter-protein contact prediction and quaternary structure prediction has started to transform the field [5][6][7][8][9][10] . Particularly, the adaption of the high-accuracy tertiary structure prediction method -AlphaFold2 11 -for quaternary structure prediction as AlphaFold-Multimer 8 has drastically improved the accuracy of quaternary structure prediction for protein assemblies.…”

Multi-head attention-based U-Nets for predicting protein domain boundaries using 1D sequence features and 2D distance maps

“…We use the GPU computing resource on the Summit supercomputer provided by Oak Ridge National Laboratory (ORNL) to train the deep learning network above. The Summit cluster [ 40 , 41 ] provides many compute nodes each having 6 GPUs and 16 GB of memory, which enables the distributed deep learning training. We train 2D U-Net, 1D U-Net, and the multi-head attention layer on three separate GPU nodes.…”

Combining pairwise structural similarity and deep learning interface contact prediction to estimate protein complex model accuracy in CASP15

“…As the tertiary structure prediction problem has been largely solved, the field started to focus more on predicting the quaternary structures of protein complexes and assemblies, which also had a long history of development but did not progress as fast as the tertiary structure prediction 17–19 . However, the situation started to change as more and more deep learning methods were developed to predict inter‐protein contacts and quaternary structures 20–25 . Particularly, adapting AlphaFold2 for protein quaternary structure prediction (i.e., AlphaFold‐Multimer 20 ) substantially improved the accuracy of protein complex/assembly structure prediction.…”