DeepComplex: A Web Server of Predicting Protein Complex Structures by Deep Learning Inter-chain Contact Prediction and Distance-Based Modelling

Abstract

Proteins interact to form complexes. Predicting the quaternary structure of protein complexes is useful for protein function analysis, protein engineering, and drug design. However, few user-friendly tools leveraging the latest deep learning technology for inter-chain contact prediction and the distance-based modelling to predict protein quaternary structures are available. To address this gap, we develop DeepComplex, a web server for predicting structures of dimeric protein complexes. It uses deep learning to predict inter-chain contacts in a homodimer or heterodimer. The predicted contacts are then used to construct a quaternary structure of the dimer by the distance-based modelling, which can be interactively viewed and analysed. The web server is freely accessible and requires no registration. It can be easily used by providing a job name and an email address along with the tertiary structure for one chain of a homodimer or two chains of a heterodimer. The output webpage provides the multiple sequence alignment, predicted inter-chain residue-residue contact map, and predicted quaternary structure of the dimer. DeepComplex web server is freely available at http://tulip.rnet.missouri.edu/deepcomplex/web_index.html.

Keywords: deep learning; distance-based modeling; inter-chain contact prediction; protein complex structure prediction; protein interaction; protein quaternary structure prediction.

FIGURE 1

The workflow of DeepComplex illustrating the input, validation, prediction and output.

FIGURE 2

The input and output interface of DeepComplex. Step 1 is the landing page; Steps 2A and 3A are input/output pages for homodimers; and Steps 2B and 3B are input/output pages for heterodimers. In Step 2A, homodimer is selected and the tertiary structure information for one chain is provided; and the output webpage is displayed on Step 3A. Similarly for heterodimer in Step 2B, heterodimer is selected and tertiary structures of the two interacting proteins are provided; and the output is displayed on Step 3B.