Protein structure prediction using AI and quantum computers

This work seeks to combine the combined advantage of leveraging these emerging areas of Artificial Intelligence and quantum computing in applying it to solve the specific biological problem of protein structure prediction using Quantum Machine Learning algorithms. The CASP dataset from ProteinNet was downloaded which is a standardized data set for machine learning of protein structure. Its large and standardized dataset of PDB entries contains the coordinates of the backbone atoms, corresponding to the sequential chain of N, C_alpha, and C' atoms. This dataset was used to train a quantum-classical hybrid Keras deep neural network model to predict the structure of the proteins. To visually qualify the quality of the predicted versus the actual protein structure, protein contact maps were generated with the experimental and predicted protein structure data and qualified. Therefore this model is recommended for the use of protein structure prediction using AI leveraging the power of quantum computers. The code is provided in the following Github repository https://github.com/bengeof/Protein-structure-prediction-using-AI-and-quantum-computers.

Protein contact map prediction using multiple sequence alignment dropout and consistency learning for sequences with less homologs

The prediction of protein contact map needs enough normalized number of effective sequence (Nf) in multiple sequence alignment (MSA). When Nf is small, the predicted contact maps are often not satisfactory. To solve this problem, we randomly selected a small part of sequence homologs for proteins with large Nf to generate MSAs with small Nf. From these MSAs, input features were generated and were passed through a consistency learning network, aiming to get the same results when using the features generated from the MSA with large Nf. The results showed that this method effectively improves the prediction accuracy of protein contact maps with small Nf.

Deducing high-accuracy protein contact-maps from a triplet of coevolutionary matrices through deep residual convolutional networks

The topology of protein folds can be specified by the inter-residue contact-maps and accurate contact-map prediction can help ab initio structure folding. We developed TripletRes to deduce protein contact-maps from discretized distance profiles by end-to-end training of deep residual neural-networks. Compared to previous approaches, the major advantage of TripletRes is in its ability to learn and directly fuse a triplet of coevolutionary matrices extracted from the whole-genome and metagenome databases and therefore minimize the information loss during the course of contact model training. TripletRes was tested on a large set of 245 non-homologous proteins from CASP 11&12 and CAMEO experiments and outperformed other top methods from CASP12 by at least 58.4% for the CASP 11&12 targets and 44.4% for the CAMEO targets in the top-L long-range contact precision. On the 31 FM targets from the latest CASP13 challenge, TripletRes achieved the highest precision (71.6%) for the top-L/5 long-range contact predictions. It was also shown that a simple re-training of the TripletRes model with more proteins can lead to further improvement with precisions comparable to state-of-the-art methods developed after CASP13. These results demonstrate a novel efficient approach to extend the power of deep convolutional networks for high-accuracy medium- and long-range protein contact-map predictions starting from primary sequences, which are critical for constructing 3D structure of proteins that lack homologous templates in the PDB library.

ConPlot: web-based application for the visualization of protein contact maps integrated with other data

Summary Covariance-based predictions of residue contacts and inter-residue distances are an increasingly popular data type in protein bioinformatics. Here we present ConPlot, a web-based application for convenient display and analysis of contact maps and distograms. Integration of predicted contact data with other predictions is often required to facilitate inference of structural features. ConPlot can therefore use the empty space near the contact map diagonal to display multiple coloured tracks representing other sequence-based predictions. Popular file formats are natively read and bespoke data can also be flexibly displayed. This novel visualization will enable easier interpretation of predicted contact maps. Availability and implementation available online at www.conplot.org, along with documentation and examples. Alternatively, ConPlot can be installed and used locally using the docker image from the project’s Docker Hub repository. ConPlot is licensed under the BSD 3-Clause. Supplementary information Supplementary data are available at Bioinformatics online.

Deducing high-accuracy protein contact-maps from a triplet of coevolutionary matrices through deep residual convolutional networks

The topology of protein folds can be specified by the inter-residue contact-maps and accurate contact-map prediction can help ab initio structure folding. We developed TripletRes to deduce protein contact-maps from discretized distance profiles by end-to-end training of deep residual neural-networks. Compared to previous approaches, the major advantage of TripletRes is in its ability to learn and directly fuse a triplet of coevolutionary matrices extracted from the whole-genome and metagenome databases and therefore minimize the information loss during the course of contact model training. TripletRes was tested on a large set of 245 non-homologous proteins from CASP and CAMEO experiments, and outperformed other state-of-the-art methods by at least 58.4% for the CASP 11&12 and 44.4% for the CAMEO targets in the top-L long-range contact precision. On the 31 FM targets from the latest CASP13 challenge, TripletRes achieved the highest precision (71.6%) for the top-L/5 long-range contact predictions. These results demonstrate a novel efficient approach to extend the power of deep convolutional networks for high-accuracy medium- and long-range protein contact-map predictions starting from primary sequences, which are critical for constructing 3D structure of proteins that lack homologous templates in the PDB library.AvailabilityThe training and testing data, standalone package, and the online server for TripletRes are available at https://zhanglab.ccmb.med.umich.edu/TripletRes/.Author SummaryAb initio protein folding has been a major unsolved problem in computational biology for more than half a century. Recent community-wide Critical Assessment of Structure Prediction (CASP) experiments have witnessed exciting progress on ab initio structure prediction, which was mainly powered by the boosting of contact-map prediction as the latter can be used as constraints to guide ab initio folding simulations. In this work, we proposed a new open-source deep-learning architecture, TripletRes, built on the residual convolutional neural networks for high-accuracy contact prediction. The large-scale benchmark and blind test results demonstrate significant advancement of the proposed methods over other approaches in predicting medium- and long-range contact-maps that are critical for guiding protein folding simulations. Detailed data analyses showed that the major advantage of TripletRes lies in the unique protocol to fuse multiple evolutionary feature matrices which are directly extracted from whole-genome and metagenome databases and therefore minimize the information loss during the contact model training.

CoCoNet: Boosting RNA contact prediction by convolutional neural networks

Physics-based co-evolutionary models such as direct coupling analysis (DCA) in combination with machine learning (ML) techniques based on deep neural networks are able to predict protein contact maps with astonishing accuracy. Such contacts can be used as constraints in structure prediction and massively increase prediction accuracy. Unfortunately, the same ML methods cannot readily be applied to RNA as they rely on large structural datasets only available for proteins but not for RNAs. Here, we demonstrate how the small amount of data available for RNA can be used to significantly improve prediction of RNA contact maps. We introduce an algorithm called CoCoNet that is based on a combination of a Coevolutionary model and a shallow Convolutional Neural Network. Despite its simplicity and the small number of trained parameters, the method boosts the contact prediction accuracy by about 70% with respect to straightforward DCA as tested by cross-validation on a dataset of about sixty RNA structures. Both our extensive robustness tests and the limited number of parameters allow the generalization properties of our model. Finally, applications to other RNAs highlight the power of our approach. CoCoNet is freely available and can be found at https://github.com/KIT-MBS/coconet.

Patch-DCA: Improved Protein Interface Prediction by utilizing Structural Information and Clustering DCA scores

Over the past decade there have been impressive advances in determining the 3D structures of protein complexes. However, there are still many complexes with unknown structures, even when the structures of the individual proteins are known. The advent of protein sequence information provides an opportunity to leverage evolutionary information to enhance the accuracy of protein-protein interface prediction. To this end, several statistical and machine learning methods have been proposed. In particular, direct coupling analysis has recently emerged as a promising approach for identification of protein contact maps from sequential information. However, the ability of these methods to detect protein-protein inter-residue contacts remains relatively limited.In this work, we propose a method to integrate sequential and co-evolution information with structural and functional information to increase the performance of protein-protein interface prediction. Further, we present a post-processing clustering method that improves the average relative F1 score by 70 % and 24 % and the precision by 80 % and 36 % in comparison with two state-of-the-art methods PSICOV and GREMLIN.