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
Highlights
Proteins interact to form complexes to perform biological functions like gene regulation, signal transduction and enzymatic catalysis (Szklarczyk et al, 2015; Quadir et al, 2021)
We develop DeepComplex, a web server for predicting structures of dimeric protein complexes
The final quality of the complex structures heavily depends on the precision of the predicted contacts and if precision of the contact prediction is over 20%, in most cases good quality quaternary structures can be built by the system
Summary
Proteins interact to form complexes to perform biological functions like gene regulation, signal transduction and enzymatic catalysis (Szklarczyk et al, 2015; Quadir et al, 2021). DeepComplex employs deep learning techniques to predict inter-chain residueresidue contacts from protein sequences first (Quadir et al, 2021; Zeng et al, 2018; Quadir et al, 2020) It utilizes a gradient descent-based optimization method to use the predicted contacts together with physicochemical and geometrical information as restraints to model the quaternary structures of interacting proteins rather accurately (Soltanikazemi et al, 2021). Once the job is scheduled to run, the protein sequence is extracted from the input structure file and is used to generate the multiple sequence alignment from which the residue-residue co-evolution features as well as other features such as secondary structure and solvent accessibility are generated They are used for the deep learning-based inter-chain contact prediction (Quadir et al, 2020). The source code of the deep learning inter-chain contact prediction and the gradient descent optimization used by this web server is available at https://github.com/jianlin-cheng/DeepComplex
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.