DeepCDpred: Inter-residue distance and contact prediction for improved prediction of protein structure

Using Attention-UNet Models to Predict Protein Contact Maps

Proteins are essential to life, and understanding their intrinsic roles requires determining their structure. The field of proteomics has opened up new opportunities by applying deep learning algorithms to large databases of solved protein structures. With the availability of large data sets and advanced machine learning methods, the prediction of protein residue interactions has greatly improved. Protein contact maps provide empirical evidence of the interacting residue pairs within a protein sequence. Template-free protein structure prediction systems rely heavily on this information. This article proposes UNet-CON, an attention-integrated UNet architecture, trained to predict residue-residue contacts in protein sequences. With the predicted contacts being more accurate than state-of-the-art methods on the PDB25 test set, the model paves the way for the development of more powerful deep learning algorithms for predicting protein residue interactions.

Importance of Inter-residue Contacts for Understanding Protein Folding and Unfolding Rates, Remote Homology, and Drug Design

Inter-residue interactions in protein structures provide valuable insights into protein folding and stability. Understanding these interactions can be helpful in many crucial applications, including rational design of therapeutic small molecules and biologics, locating functional protein sites, and predicting protein-protein and protein-ligand interactions. The process of developing machine learning models incorporating inter-residue interactions has been improved recently. This review highlights the theoretical models incorporating inter-residue interactions in predicting folding and unfolding rates of proteins. Utilizing contact maps to depict inter-residue interactions aids researchers in developing computer models for detecting remote homologs and interface residues within protein-protein complexes which, in turn, enhances our knowledge of the relationship between sequence and structure of proteins. Further, the application of contact maps derived from inter-residue interactions is highlighted in the field of drug discovery. Overall, this review presents an extensive assessment of the significant models that use inter-residue interactions to investigate folding rates, unfolding rates, remote homology, and drug development, providing potential future advancements in constructing efficient computational models in structural biology.

Terahertz Photons Inhibit Cancer Cells Long Term by Suppressing Nano Telomerase Activity

Telomeres are nanoscale DNA-protein complexes to protect and stabilize chromosomes. The reexpression of telomerase in cancer cells is a key determinant crucial for the infinite proliferation and long-term survival of most cancer cells. However, the use of telomerase inhibitors for cancer treatment may cause problems such as poor specificity, drug resistance, and cytotoxicity. Here, we discovered a nondrug and noninvasive terahertz modulation strategy capable of the long-term suppression of cancer cells by inhibiting telomerase activity. First, we found that an optimized frequency of 33 THz photon irradiation effectively inhibited the telomerase activity by molecular dynamics simulation and frequency filtering experiments. Moreover, in vitro experiments showed that telomerase activity in 4T1 and MCF-7 cells significantly decreased by 77% and 80% respectively, after 21 days of regular 33 THz irradiation. Furthermore, two kinds of cells were found to undergo aging, apoptosis, and DNA double-strand breaks caused by telomere crisis, which seriously affected the survival of cancer cells. In addition, the tumorigenicity of 4T1 cells irradiated with 33 THz waves for 21 days in in vivo mice decreased by 70%. In summary, this study demonstrates the potential application of THz modulation in nano therapy for cancer.

Toward the assessment of predicted inter-residue distance

MOTIVATION

Significant progress has been achieved in distance-based protein folding, due to improved prediction of inter-residue distance by deep learning. Many efforts are thus made to improve distance prediction in recent years. However, it remains unknown what is the best way of objectively assessing the accuracy of predicted distance.

RESULTS

A total of 19 metrics were proposed to measure the accuracy of predicted distance. These metrics were discussed and compared quantitatively on three benchmark datasets, with distance and structure models predicted by the trRosetta pipeline. The experiments show that a few metrics, such as distance precision, have a high correlation with the model accuracy measure TM-score (Pearson's correlation coefficient >0.7). In addition, the metrics are applied to rank the distance prediction groups in CASP14. The ranking by our metrics coincides largely with the official version. These data suggest that the proposed metrics are effective for measuring distance prediction. We anticipate that this study paves the way for objectively monitoring the progress of inter-residue distance prediction. A web server and a standalone package are provided to implement the proposed metrics.

AVAILABILITY AND IMPLEMENTATION

http://yanglab.nankai.edu.cn/APD.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Enhancing protein inter-residue real distance prediction by scrutinising deep learning models

Protein structure prediction (PSP) has achieved significant progress lately via prediction of inter-residue distances using deep learning models and exploitation of the predictions during conformational search. In this context, prediction of large inter-residue distances and also prediction of distances between residues separated largely in the protein sequence remain challenging. To deal with these challenges, state-of-the-art inter-residue distance prediction algorithms have used large sets of coevolutionary and non-coevolutionary features. In this paper, we argue that the more the types of features used, the more the kinds of noises introduced and then the deep learning model has to overcome the noises to improve the accuracy of the predictions. Also, multiple features capturing similar underlying characteristics might not necessarily have significantly better cumulative effect. So we scrutinise the feature space to reduce the types of features to be used, but at the same time, we strive to improve the prediction accuracy. Consequently, for inter-residue real distance prediction, in this paper, we propose a deep learning model named scrutinised distance predictor (SDP), which uses only 2 coevolutionary and 3 non-coevolutionary features. On several sets of benchmark proteins, our proposed SDP method improves mean Local Distance Different Test (LDDT) scores at least by 10% over existing state-of-the-art methods. The SDP program along with its data is available from the website https://gitlab.com/mahnewton/sdp .

Evaluation of Deep Neural Network ProSPr for Accurate Protein Distance Predictions on CASP14 Targets

The field of protein structure prediction has recently been revolutionized through the introduction of deep learning. The current state-of-the-art tool AlphaFold2 can predict highly accurate structures; however, it has a prohibitively long inference time for applications that require the folding of hundreds of sequences. The prediction of protein structure annotations, such as amino acid distances, can be achieved at a higher speed with existing tools, such as the ProSPr network. Here, we report on important updates to the ProSPr network, its performance in the recent Critical Assessment of Techniques for Protein Structure Prediction (CASP14) competition, and an evaluation of its accuracy dependency on sequence length and multiple sequence alignment depth. We also provide a detailed description of the architecture and the training process, accompanied by reusable code. This work is anticipated to provide a solid foundation for the further development of protein distance prediction tools.

Perturbation of ACE2 Structural Ensembles by SARS-CoV-2 Spike Protein Binding

The human ACE2 enzyme serves as a critical first recognition point of coronaviruses, including SARS-CoV-2. In particular, the extracellular domain of ACE2 interacts directly with the S1 tailspike protein of the SARS-CoV-2 virion through a broad protein-protein interface. Although this interaction has been characterized by X-ray crystallography, these structures do not reveal significant differences in the ACE2 structure upon S1 protein binding. In this work, using several all-atom molecular dynamics simulations, we show persistent differences in the ACE2 structure upon binding. These differences are determined with the linear discriminant analysis (LDA) machine learning method and validated using independent training and testing datasets, including long trajectories generated by D. E. Shaw Research on the Anton 2 supercomputer. In addition, long trajectories for 78 potent ACE2-binding compounds, also generated by D. E. Shaw Research, were projected onto the LDA classification vector in order to determine whether the ligand-bound ACE2 structures were compatible with S1 protein binding. This allows us to predict which compounds are "apo-like" versus "complex-like" and to pinpoint long-range ligand-induced allosteric changes in the ACE2 structure.

Recent Applications of Deep Learning Methods on Evolution- and Contact-Based Protein Structure Prediction

The new advances in deep learning methods have influenced many aspects of scientific research, including the study of the protein system. The prediction of proteins' 3D structural components is now heavily dependent on machine learning techniques that interpret how protein sequences and their homology govern the inter-residue contacts and structural organization. Especially, methods employing deep neural networks have had a significant impact on recent CASP13 and CASP14 competition. Here, we explore the recent applications of deep learning methods in the protein structure prediction area. We also look at the potential opportunities for deep learning methods to identify unknown protein structures and functions to be discovered and help guide drug-target interactions. Although significant problems still need to be addressed, we expect these techniques in the near future to play crucial roles in protein structural bioinformatics as well as in drug discovery.

Protein Structure Prediction: Conventional and Deep Learning Perspectives

Protein structure prediction is a way to bridge the sequence-structure gap, one of the main challenges in computational biology and chemistry. Predicting any protein's accurate structure is of paramount importance for the scientific community, as these structures govern their function. Moreover, this is one of the complicated optimization problems that computational biologists have ever faced. Experimental protein structure determination methods include X-ray crystallography, Nuclear Magnetic Resonance Spectroscopy and Electron Microscopy. All of these are tedious and time-consuming procedures that require expertise. To make the process less cumbersome, scientists use predictive tools as part of computational methods, using data consolidated in the protein repositories. In recent years, machine learning approaches have raised the interest of the structure prediction community. Most of the machine learning approaches for protein structure prediction are centred on co-evolution based methods. The accuracy of these approaches depends on the number of homologous protein sequences available in the databases. The prediction problem becomes challenging for many proteins, especially those without enough sequence homologs. Deep learning methods allow for the extraction of intricate features from protein sequence data without making any intuitions. Accurately predicted protein structures are employed for drug discovery, antibody designs, understanding protein-protein interactions, and interactions with other molecules. This article provides a review of conventional and deep learning approaches in protein structure prediction. We conclude this review by outlining a few publicly available datasets and deep learning architectures currently employed for protein structure prediction tasks.

Deep Learning-Based Advances in Protein Structure Prediction

Obtaining an accurate description of protein structure is a fundamental step toward understanding the underpinning of biology. Although recent advances in experimental approaches have greatly enhanced our capabilities to experimentally determine protein structures, the gap between the number of protein sequences and known protein structures is ever increasing. Computational protein structure prediction is one of the ways to fill this gap. Recently, the protein structure prediction field has witnessed a lot of advances due to Deep Learning (DL)-based approaches as evidenced by the success of AlphaFold2 in the most recent Critical Assessment of protein Structure Prediction (CASP14). In this article, we highlight important milestones and progresses in the field of protein structure prediction due to DL-based methods as observed in CASP experiments. We describe advances in various steps of protein structure prediction pipeline viz. protein contact map prediction, protein distogram prediction, protein real-valued distance prediction, and Quality Assessment/refinement. We also highlight some end-to-end DL-based approaches for protein structure prediction approaches. Additionally, as there have been some recent DL-based advances in protein structure determination using Cryo-Electron (Cryo-EM) microscopy based, we also highlight some of the important progress in the field. Finally, we provide an outlook and possible future research directions for DL-based approaches in the protein structure prediction arena.

Evaluation of residue-residue contact prediction methods: From retrospective to prospective

Sequence-based residue contact prediction plays a crucial role in protein structure reconstruction. In recent years, the combination of evolutionary coupling analysis (ECA) and deep learning (DL) techniques has made tremendous progress for residue contact prediction, thus a comprehensive assessment of current methods based on a large-scale benchmark data set is very needed. In this study, we evaluate 18 contact predictors on 610 non-redundant proteins and 32 CASP13 targets according to a wide range of perspectives. The results show that different methods have different application scenarios: (1) DL methods based on multi-categories of inputs and large training sets are the best choices for low-contact-density proteins such as the intrinsically disordered ones and proteins with shallow multi-sequence alignments (MSAs). (2) With at least 5L (L is sequence length) effective sequences in the MSA, all the methods show the best performance, and methods that rely only on MSA as input can reach comparable achievements as methods that adopt multi-source inputs. (3) For top L/5 and L/2 predictions, DL methods can predict more hydrophobic interactions while ECA methods predict more salt bridges and disulfide bonds. (4) ECA methods can detect more secondary structure interactions, while DL methods can accurately excavate more contact patterns and prune isolated false positives. In general, multi-input DL methods with large training sets dominate current approaches with the best overall performance. Despite the great success of current DL methods must be stated the fact that there is still much room left for further improvement: (1) With shallow MSAs, the performance will be greatly affected. (2) Current methods show lower precisions for inter-domain compared with intra-domain contact predictions, as well as very high imbalances in precisions between intra-domains. (3) Strong prediction similarities between DL methods indicating more feature types and diversified models need to be developed. (4) The runtime of most methods can be further optimized.

The amino acid sequence of a protein ultimately determines its tertiary structure, and the tertiary structure determines its function(s) and plays a key role in understanding biological processes and disease pathogenesis. Protein tertiary structure can be determined using experimental techniques such as cryo-electron microscopy, nuclear magnetic resonance and X-ray crystallography, which are very expensive and time-consuming. As an alternative, researchers are trying to use in silico methods to predict the 3D structures. Residue contact-assisted protein folding paves an avenue for sequence-based protein structure prediction and therefore has become one of the most challenging and promising problems in structural bioinformatics. Over the past years, contact prediction has undergone continuous evolution in techniques. Through a retrospective analysis of traditional machine learning /evolutionary coupling analysis methods/ consensus machine learning methods and a multi-perspective study on recently developed deep learning methods, we explore the most advanced contact predictors, pursue application scenarios for different methods, and seek prospective directions for further improvement. We anticipate that our study will serve as a practical and useful guide for the development of future approaches to contact prediction.

The whole is greater than its parts: ensembling improves protein contact prediction

The prediction of amino acid contacts from protein sequence is an important problem, as protein contacts are a vital step towards the prediction of folded protein structures. We propose that a powerful concept from deep learning, called ensembling, can increase the accuracy of protein contact predictions by combining the outputs of different neural network models. We show that ensembling the predictions made by different groups at the recent Critical Assessment of Protein Structure Prediction (CASP13) outperforms all individual groups. Further, we show that contacts derived from the distance predictions of three additional deep neural networks-AlphaFold, trRosetta, and ProSPr-can be substantially improved by ensembling all three networks. We also show that ensembling these recent deep neural networks with the best CASP13 group creates a superior contact prediction tool. Finally, we demonstrate that two ensembled networks can successfully differentiate between the folds of two highly homologous sequences. In order to build further on these findings, we propose the creation of a better protein contact benchmark set and additional open-source contact prediction methods.

Homology modeling in the time of collective and artificial intelligence

Homology modeling is a method for building protein 3D structures using protein primary sequence and utilizing prior knowledge gained from structural similarities with other proteins. The homology modeling process is done in sequential steps where sequence/structure alignment is optimized, then a backbone is built and later, side-chains are added. Once the low-homology loops are modeled, the whole 3D structure is optimized and validated. In the past three decades, a few collective and collaborative initiatives allowed for continuous progress in both homology and ab initio modeling. Critical Assessment of protein Structure Prediction (CASP) is a worldwide community experiment that has historically recorded the progress in this field. Folding@Home and Rosetta@Home are examples of crowd-sourcing initiatives where the community is sharing computational resources, whereas RosettaCommons is an example of an initiative where a community is sharing a codebase for the development of computational algorithms. Foldit is another initiative where participants compete with each other in a protein folding video game to predict 3D structure. In the past few years, contact maps deep machine learning was introduced to the 3D structure prediction process, adding more information and increasing the accuracy of models significantly. In this review, we will take the reader in a journey of exploration from the beginnings to the most recent turnabouts, which have revolutionized the field of homology modeling. Moreover, we discuss the new trends emerging in this rapidly growing field.

Protein Secondary Structure Prediction: A Review of Progress and Directions

Background:

Over the last few decades, a search for the theory of protein folding has grown into a full-fledged research field at the intersection of biology, chemistry and informatics. Despite enormous effort, there are still open questions and challenges, like understanding the rules by which amino acid sequence determines protein secondary structure.

Objective:

In this review, we depict the progress of the prediction methods over the years and identify sources of improvement.

Methods:

The protein secondary structure prediction problem is described followed by the discussion on theoretical limitations, description of the commonly used data sets, features and a review of three generations of methods with the focus on the most recent advances. Additionally, methods with available online servers are assessed on the independent data set.

Results:

The state-of-the-art methods are currently reaching almost 88% for 3-class prediction and 76.5% for an 8-class prediction.

Conclusion:

This review summarizes recent advances and outlines further research directions.

Deep learning methods in protein structure prediction

Protein Structure Prediction is a central topic in Structural Bioinformatics. Since the '60s statistical methods, followed by increasingly complex Machine Learning and recently Deep Learning methods, have been employed to predict protein structural information at various levels of detail. In this review, we briefly introduce the problem of protein structure prediction and essential elements of Deep Learning (such as Convolutional Neural Networks, Recurrent Neural Networks and basic feed-forward Neural Networks they are founded on), after which we discuss the evolution of predictive methods for one-dimensional and two-dimensional Protein Structure Annotations, from the simple statistical methods of the early days, to the computationally intensive highly-sophisticated Deep Learning algorithms of the last decade. In the process, we review the growth of the databases these algorithms are based on, and how this has impacted our ability to leverage knowledge about evolution and co-evolution to achieve improved predictions. We conclude this review outlining the current role of Deep Learning techniques within the wider pipelines to predict protein structures and trying to anticipate what challenges and opportunities may arise next.

Introduction of a bounded penalty function in contact-assisted simulations of protein structures to omit false restraints

Contact-assisted simulations, the contacts being predicted or determined experimentally, have become very important in the determination of the structures of proteins and other biological macromolecules. In this work, the effect of contact-distance restraints on the simulated structures was investigated with the use of multiplexed replica exchange simulations with the coarse-grained UNRES force field. A modified bounded flat-bottom restraint function that does not generate a gradient when a restraint cannot be satisfied was implemented. Calculations were run with (i) a set of four small proteins, with contact restraints derived from experimental structures, and (ii) selected CASP11 and CASP12 targets, with restraints as used at prediction time. The bounded penalty function largely omitted false contacts, which were usually inconsistent. It was found that at least 20% of correct contacts must be present in the restraint set to improve model quality with respect to unrestrained simulations. © 2019 Wiley Periodicals, Inc.

Structure of SPH (self-incompatibility protein homologue) proteins: a widespread family of small, highly stable, secreted proteins

SPH (self-incompatibility protein homologue) proteins are a large family of small, disulfide-bonded, secreted proteins, initially found in the self-incompatibility response in the field poppy (Papaver rhoeas), but now known to be widely distributed in plants, many containing multiple members of this protein family. Using the Origami strain of Escherichia coli, we expressed one member of this family, SPH15 from Arabidopsis thaliana, as a folded thioredoxin fusion protein and purified it from the cytosol. The fusion protein was cleaved and characterised by analytical ultracentrifugation, circular dichroism and nuclear magnetic resonance (NMR) spectroscopy. This showed that SPH15 is monomeric and temperature stable, with a β-sandwich structure. The four strands in each sheet have the same topology as the unrelated proteins: human transthyretin, bacterial TssJ and pneumolysin, with no discernible sequence similarity. The NMR-derived structure was compared with a de novo model, made using a new deep learning algorithm based on co-evolution/correlated mutations, DeepCDPred, validating the method. The DeepCDPred de novo method and homology modelling to SPH15 were then both used to derive models of the 3D structure of the three known PrsS proteins from P. rhoeas, which have only 15-18% sequence homology to SPH15. The DeepCDPred method gave models with lower discreet optimised protein energy scores than the homology models. Three loops at one end of the poppy structures are postulated to interact with their respective pollen receptors to instigate programmed cell death in pollen tubes.