RAPTOR: optimal protein threading by linear programming

Protein remote homology detection and structural alignment using deep learning

Exploiting sequence-structure-function relationships in biotechnology requires improved methods for aligning proteins that have low sequence similarity to previously annotated proteins. We develop two deep learning methods to address this gap, TM-Vec and DeepBLAST. TM-Vec allows searching for structure-structure similarities in large sequence databases. It is trained to accurately predict TM-scores as a metric of structural similarity directly from sequence pairs without the need for intermediate computation or solution of structures. Once structurally similar proteins have been identified, DeepBLAST can structurally align proteins using only sequence information by identifying structurally homologous regions between proteins. It outperforms traditional sequence alignment methods and performs similarly to structure-based alignment methods. We show the merits of TM-Vec and DeepBLAST on a variety of datasets, including better identification of remotely homologous proteins compared with state-of-the-art sequence alignment and structure prediction methods.

Protein Structure Prediction: Challenges, Advances, and the Shift of Research Paradigms

Protein structure prediction is an interdisciplinary research topic that has attracted researchers from multiple fields, including biochemistry, medicine, physics, mathematics, and computer science. These researchers adopt various research paradigms to attack the same structure prediction problem: biochemists and physicists attempt to reveal the principles governing protein folding; mathematicians, especially statisticians, usually start from assuming a probability distribution of protein structures given a target sequence and then find the most likely structure, while computer scientists formulate protein structure prediction as an optimization problem - finding the structural conformation with the lowest energy or minimizing the difference between predicted structure and native structure. These research paradigms fall into the two statistical modeling cultures proposed by Leo Breiman, namely, data modeling and algorithmic modeling. Recently, we have also witnessed the great success of deep learning in protein structure prediction. In this review, we present a survey of the efforts for protein structure prediction. We compare the research paradigms adopted by researchers from different fields, with an emphasis on the shift of research paradigms in the era of deep learning. In short, the algorithmic modeling techniques, especially deep neural networks, have considerably improved the accuracy of protein structure prediction; however, theories interpreting the neural networks and knowledge on protein folding are still highly desired.

Contact-Assisted Threading in Low-Homology Protein Modeling

The ability to successfully predict the three-dimensional structure of a protein from its amino acid sequence has made considerable progress in the recent past. The progress is propelled by the improved accuracy of deep learning-based inter-residue contact map predictors coupled with the rising growth of protein sequence databases. Contact map encodes interatomic interaction information that can be exploited for highly accurate prediction of protein structures via contact map threading even for the query proteins that are not amenable to direct homology modeling. As such, contact-assisted threading has garnered considerable research effort. In this chapter, we provide an overview of existing contact-assisted threading methods while highlighting the recent advances and discussing some of the current limitations and future prospects in the application of contact-assisted threading for improving the accuracy of low-homology protein modeling.

In silico design, production and immunization evaluation of a recombinant bivalent fusion protein candidate vaccine against E. coli O157:H7

In silico techniques are highly suited for both the discovery of new and development of available vaccines. Escherichia coli O157: H7, a main cause of food poisoning can infect humans through the consumption of contaminated water or food. Vaccination is a choice strategy to combat the bacterium. In the present study, we designed, expressed and purified a chimeric protein comprising two antigens of Escherichia coli O157: H7, including intimin and flagellin proteins, as a vaccine candidate and evaluated its immunization ability in mice. Thein silicoresults showed that the proposed antigen has a high antigenicity and conformation to be used as a potent vaccine candidate. The protein was successfully expressed in E. coli expression system with a proper level of expression (0/8g/L). Immunization evaluation showed that the protein is able to evoke the mice's humoral immunity and can confer a protective immunity against E. coli O157:H7, so that 80 % of the immunized animals were survived following the intraperitoneal injection of 100 LD₅₀ of the live bacteria. Shedding analysis also showed the protectivity power of the protein. Bacterial excretion in control animals remained stable at about 10⁸ CFU after 15 days, while the excreted bacteria in the feces of immunized mice's decreased to about 10² after the same time. According to the results, the proposed protein is able to stimulate the immune responses of mice and protect them against E. coli O157:H7.

The Chicken A and E Blood Systems Arise from Genetic Variation in and around the Regulators of Complement Activation Region

The tightly linked A and E blood alloantigen systems are 2 of 13 blood systems identified in chickens. Reported herein are studies showing that the genes encoding A and E alloantigens map within or near to the chicken regulator of complement activation (RCA) gene cluster, a region syntenic with the human RCA. Genome-wide association studies, sequence analysis, and sequence-derived single-nucleotide polymorphism information for known A and/or E system alleles show that the most likely candidate gene for the A blood system is C4BPM gene (complement component 4 binding protein, membrane). Cosegregation of single-nucleotide polymorphism–defined C4BPM haplotypes and blood system A alleles defined by alloantisera provide a link between chicken blood system A and C4BPM. The best match for the E blood system is the avian equivalent of FCAMR (Fc fragment of IgA and IgM receptor). C4BPM is located within the chicken RCA on chicken microchromosome 26 and is separated from FCAMR by 89 kbp. The genetic variation observed at C4BPM and FCAMR could affect the chicken complement system and differentially guide immune responses to infectious diseases.

Learning Protein Embedding to Improve Protein Fold Recognition Using Deep Metric Learning

Protein fold recognition refers to predicting the most likely fold type of the query protein and is a critical step of protein structure and function prediction. With the popularity of deep learning in bioinformatics, protein fold recognition has obtained impressive progress. In this study, to extract the fold-specific feature to improve protein fold recognition, we proposed a unified deep metric learning framework based on a joint loss function, termed NPCFold. In addition, we also proposed an integrated machine learning model based on the similarity of proteins in various properties, termed NPCFoldpro. Benchmark experiments show both NPCFold and NPCFoldpro outperform existing protein fold recognition methods at the fold level, indicating that our proposed strategies of fusing loss functions and fusing features could improve the fold recognition level.

SelfAT-Fold: Protein Fold Recognition Based on Residue-Based and Motif-Based Self-Attention Networks

The protein fold recognition is a fundamental and crucial step of tertiary structure determination. In this regard, several computational predictors have been proposed. Recently, the predictive performance has been obviously improved by the fold-specific features generated by deep learning techniques. However, these methods failed to measure the global associations among residues or motifs along the protein sequences. Furthermore, these deep learning techniques are often treated as black boxes without interpretability. Inspired by the similarities between protein sequences and natural language sentences, we applied the self-attention mechanism derived from natural language processing (NLP) field to protein fold recognition. The motif-based self-attention network (MSAN) and the residue-based self-attention network (RSAN) were constructed based on a training set to capture the global associations among the structure motifs and residues along the protein sequences, respectively. The fold-specific attention features trained and generated from the training set were then combined with Support Vector Machines (SVMs) to predict the samples in the widely used LE benchmark dataset, which is fully independent from the training set. Experimental results showed that the proposed two SelfAT-Fold predictors outperformed 34 existing state-of-the-art computational predictors. The two SelfAT-Fold predictors were further tested on an independent dataset SCOP_TEST, and they can achieve stable performance. Furthermore, the fold-specific attention features can be used to analyse the characteristics of protein folds. The trained models and data of SelfAT-Fold can be downloaded from http://bliulab.net/selfAT_fold/.

Performing protein fold recognition by exploiting a stack convolutional neural network with the attention mechanism

Protein fold recognition is a critical step in protein structure and function prediction, and aims to ascertain the most likely fold type of the query protein. As a typical pattern recognition problem, designing a powerful feature extractor and metric function to extract relevant and representative fold-specific features from protein sequences is the key to improving protein fold recognition. In this study, we propose an effective sequence-based approach, called RattnetFold, to identify protein fold types. The basic concept of RattnetFold is to employ a stack convolutional neural network with the attention mechanism that acts as a feature extractor to extract fold-specific features from protein residue-residue contact maps. Moreover, based on the fold-specific features, we leverage metric learning to project fold-specific features into a subspace where similar proteins are closer together and name this approach RattnetFoldPro. Benchmarking experiments illustrate that RattnetFold and RattnetFoldPro enable the convolutional neural networks to efficiently learn the underlying subtle patterns in residue-residue contact maps, thereby improving the performance of protein fold recognition. An online web server of RattnetFold and the benchmark datasets are freely available at http://csbio.njust.edu.cn/bioinf/rattnetfold/.

An analysis of protein language model embeddings for fold prediction

The identification of the protein fold class is a challenging problem in structural biology. Recent computational methods for fold prediction leverage deep learning techniques to extract protein fold-representative embeddings mainly using evolutionary information in the form of multiple sequence alignment (MSA) as input source. In contrast, protein language models (LM) have reshaped the field thanks to their ability to learn efficient protein representations (protein-LM embeddings) from purely sequential information in a self-supervised manner. In this paper, we analyze a framework for protein fold prediction using pre-trained protein-LM embeddings as input to several fine-tuning neural network models, which are supervisedly trained with fold labels. In particular, we compare the performance of six protein-LM embeddings: the long short-term memory-based UniRep and SeqVec, and the transformer-based ESM-1b, ESM-MSA, ProtBERT and ProtT5; as well as three neural networks: Multi-Layer Perceptron, ResCNN-BGRU (RBG) and Light-Attention (LAT). We separately evaluated the pairwise fold recognition (PFR) and direct fold classification (DFC) tasks on well-known benchmark datasets. The results indicate that the combination of transformer-based embeddings, particularly those obtained at amino acid level, with the RBG and LAT fine-tuning models performs remarkably well in both tasks. To further increase prediction accuracy, we propose several ensemble strategies for PFR and DFC, which provide a significant performance boost over the current state-of-the-art results. All this suggests that moving from traditional protein representations to protein-LM embeddings is a very promising approach to protein fold-related tasks.

VHH Structural Modelling Approaches: A Critical Review

V_HH, i.e., VH domains of camelid single-chain antibodies, are very promising therapeutic agents due to their significant physicochemical advantages compared to classical mammalian antibodies. The number of experimentally solved V_HH structures has significantly improved recently, which is of great help, because it offers the ability to directly work on 3D structures to humanise or improve them. Unfortunately, most V_HHs do not have 3D structures. Thus, it is essential to find alternative ways to get structural information. The methods of structure prediction from the primary amino acid sequence appear essential to bypass this limitation. This review presents the most extensive overview of structure prediction methods applied for the 3D modelling of a given V_HH sequence (a total of 21). Besides the historical overview, it aims at showing how model software programs have been shaping the structural predictions of V_HHs. A brief explanation of each methodology is supplied, and pertinent examples of their usage are provided. Finally, we present a structure prediction case study of a recently solved V_HH structure. According to some recent studies and the present analysis, AlphaFold 2 and NanoNet appear to be the best tools to predict a structural model of V_HH from its sequence.

A tale of solving two computational challenges in protein science: neoantigen prediction and protein structure prediction

In this article, we review two challenging computational questions in protein science: neoantigen prediction and protein structure prediction. Both topics have seen significant leaps forward by deep learning within the past five years, which immediately unlocked new developments of drugs and immunotherapies. We show that deep learning models offer unique advantages, such as representation learning and multi-layer architecture, which make them an ideal choice to leverage a huge amount of protein sequence and structure data to address those two problems. We also discuss the impact and future possibilities enabled by those two applications, especially how the data-driven approach by deep learning shall accelerate the progress towards personalized biomedicine.

Profiles of Natural and Designed Protein-Like Sequences Effectively Bridge Protein Sequence Gaps: Implications in Distant Homology Detection

Sequence-based approaches are fundamental to guide experimental investigations in obtaining structural and/or functional insights into uncharacterized protein families. Powerful profile-based sequence search methods rely on a sequence space continuum to identify non-trivial relationships through homology detection. The computational design of protein-like sequences that serve as "artificial linkers" is useful in identifying relationships between distant members of a structural fold. Such sequences act as intermediates and guide homology searches between distantly related proteins. Here, we describe an approach that represents natural intermediate sequences and designed protein-like sequences as HMM (Hidden Markov Models) profiles, to improve the sensitivity of existing search methods. Searches made within the "Profile database" were shown to recognize the parent structural fold for 90% of the search queries at query coverage better than 60%. For 1040 protein families with no available structure, fold associations were made through searches in the database of natural and designed sequence profiles. Most of the associations were made with the Alpha-alpha superhelix, Transmembrane beta-barrels, TIM barrel, and Immunoglobulin-like beta-sandwich folds. For 11 domain families of unknown functions, we provide confident fold associations using the profiles of designed sequences and a consensus from other fold recognition methods. For two DUFs (Domain families of Unknown Functions), we performed detailed functional annotation through comparisons with characterized templates of families of known function.

Protein Fold Recognition From Sequences Using Convolutional and Recurrent Neural Networks

The identification of a protein fold type from its amino acid sequence provides important insights about the protein 3D structure. In this paper, we propose a deep learning architecture that can process protein residue-level features to address the protein fold recognition task. Our neural network model combines 1D-convolutional layers with gated recurrent unit (GRU) layers. The GRU cells, as recurrent layers, cope with the processing issues associated to the highly variable protein sequence lengths and so extract a fold-related embedding of fixed size for each protein domain. These embeddings are then used to perform the pairwise fold recognition task, which is based on transferring the fold type of the most similar template structure. We compare our model with several template-based and deep learning-based methods from the state-of-the-art. The evaluation results over the well-known LINDAHL and SCOP_TEST sets, along with a proposed LINDAHL test set updated to SCOP 1.75, show that our embeddings perform significantly better than these methods, specially at the fold level. Supplementary material, which can be found on the Computer Society Digital Library at http://doi.ieeecomputersociety.org/10.1109/TCBB.2020.3012732, source code and trained models are available at http://sigmat.ugr.es/~amelia/CNN-GRU-RF+/.

FoldHSphere: deep hyperspherical embeddings for protein fold recognition

Background

Current state-of-the-art deep learning approaches for protein fold recognition learn protein embeddings that improve prediction performance at the fold level. However, there still exists aperformance gap at the fold level and the (relatively easier) family level, suggesting that it might be possible to learn an embedding space that better represents the protein folds.

Results

In this paper, we propose the FoldHSphere method to learn a better fold embedding space through a two-stage training procedure. We first obtain prototype vectors for each fold class that are maximally separated in hyperspherical space. We then train a neural network by minimizing the angular large margin cosine loss to learn protein embeddings clustered around the corresponding hyperspherical fold prototypes. Our network architectures, ResCNN-GRU and ResCNN-BGRU, process the input protein sequences by applying several residual-convolutional blocks followed by a gated recurrent unit-based recurrent layer. Evaluation results on the LINDAHL dataset indicate that the use of our hyperspherical embeddings effectively bridges the performance gap at the family and fold levels. Furthermore, our FoldHSpherePro ensemble method yields an accuracy of 81.3% at the fold level, outperforming all the state-of-the-art methods.

Conclusions

Our methodology is efficient in learning discriminative and fold-representative embeddings for the protein domains. The proposed hyperspherical embeddings are effective at identifying the protein fold class by pairwise comparison, even when amino acid sequence similarities are low.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04419-7.

FoldRec-C2C: protein fold recognition by combining cluster-to-cluster model and protein similarity network

As a key for studying the protein structures, protein fold recognition is playing an important role in predicting the protein structures associated with COVID-19 and other important structures. However, the existing computational predictors only focus on the protein pairwise similarity or the similarity between two groups of proteins from 2-folds. However, the homology relationship among proteins is in a hierarchical structure. The global protein similarity network will contribute to the performance improvement. In this study, we proposed a predictor called FoldRec-C2C to globally incorporate the interactions among proteins into the prediction. For the FoldRec-C2C predictor, protein fold recognition problem is treated as an information retrieval task in nature language processing. The initial ranking results were generated by a surprised ranking algorithm Learning to Rank, and then three re-ranking algorithms were performed on the ranking lists to adjust the results globally based on the protein similarity network, including seq-to-seq model, seq-to-cluster model and cluster-to-cluster model (C2C). When tested on a widely used and rigorous benchmark dataset LINDAHL dataset, FoldRec-C2C outperforms other 34 state-of-the-art methods in this field. The source code and data of FoldRec-C2C can be downloaded from http://bliulab.net/FoldRec-C2C/download.

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.

Recent Advances in Protein Homology Detection Propelled by Inter-Residue Interaction Map Threading

Sequence-based protein homology detection has emerged as one of the most sensitive and accurate approaches to protein structure prediction. Despite the success, homology detection remains very challenging for weakly homologous proteins with divergent evolutionary profile. Very recently, deep neural network architectures have shown promising progress in mining the coevolutionary signal encoded in multiple sequence alignments, leading to reasonably accurate estimation of inter-residue interaction maps, which serve as a rich source of additional information for improved homology detection. Here, we summarize the latest developments in protein homology detection driven by inter-residue interaction map threading. We highlight the emerging trends in distant-homology protein threading through the alignment of predicted interaction maps at various granularities ranging from binary contact maps to finer-grained distance and orientation maps as well as their combination. We also discuss some of the current limitations and possible future avenues to further enhance the sensitivity of protein homology detection.

ProtFold-DFG: protein fold recognition by combining Directed Fusion Graph and PageRank algorithm

As one of the most important tasks in protein structure prediction, protein fold recognition has attracted more and more attention. In this regard, some computational predictors have been proposed with the development of machine learning and artificial intelligence techniques. However, these existing computational methods are still suffering from some disadvantages. In this regard, we propose a new network-based predictor called ProtFold-DFG for protein fold recognition. We propose the Directed Fusion Graph (DFG) to fuse the ranking lists generated by different methods, which employs the transitive closure to incorporate more relationships among proteins and uses the KL divergence to calculate the relationship between two proteins so as to improve its generalization ability. Finally, the PageRank algorithm is performed on the DFG to accurately recognize the protein folds by considering the global interactions among proteins in the DFG. Tested on a widely used and rigorous benchmark data set, LINDAHL dataset, experimental results show that the ProtFold-DFG outperforms the other 35 competing methods, indicating that ProtFold-DFG will be a useful method for protein fold recognition. The source code and data of ProtFold-DFG can be downloaded from http://bliulab.net/ProtFold-DFG/download.

Machine Learning Approaches for Quality Assessment of Protein Structures

Protein structures play a very important role in biomedical research, especially in drug discovery and design, which require accurate protein structures in advance. However, experimental determinations of protein structure are prohibitively costly and time-consuming, and computational predictions of protein structures have not been perfected. Methods that assess the quality of protein models can help in selecting the most accurate candidates for further work. Driven by this demand, many structural bioinformatics laboratories have developed methods for estimating model accuracy (EMA). In recent years, EMA by machine learning (ML) have consistently ranked among the top-performing methods in the community-wide CASP challenge. Accordingly, we systematically review all the major ML-based EMA methods developed within the past ten years. The methods are grouped by their employed ML approach-support vector machine, artificial neural networks, ensemble learning, or Bayesian learning-and their significances are discussed from a methodology viewpoint. To orient the reader, we also briefly describe the background of EMA, including the CASP challenge and its evaluation metrics, and introduce the major ML/DL techniques. Overall, this review provides an introductory guide to modern research on protein quality assessment and directions for future research in this area.

Evaluating the significance of contact maps in low-homology protein modeling using contact-assisted threading

The development of improved threading algorithms for remote homology modeling is a critical step forward in template-based protein structure prediction. We have recently demonstrated the utility of contact information to boost protein threading by developing a new contact-assisted threading method. However, the nature and extent to which the quality of a predicted contact map impacts the performance of contact-assisted threading remains elusive. Here, we systematically analyze and explore this interdependence by employing our newly-developed contact-assisted threading method over a large-scale benchmark dataset using predicted contact maps from four complementary methods including direct coupling analysis (mfDCA), sparse inverse covariance estimation (PSICOV), classical neural network-based meta approach (MetaPSICOV), and state-of-the-art ultra-deep learning model (RaptorX). Experimental results demonstrate that contact-assisted threading using high-quality contacts having the Matthews Correlation Coefficient (MCC) ≥ 0.5 improves threading performance in nearly 30% cases, while low-quality contacts with MCC <0.35 degrades the performance for 50% cases. This holds true even in CASP13 dataset, where threading using high-quality contacts (MCC ≥ 0.5) significantly improves the performance of 22 instances out of 29. Collectively, our study uncovers the mutual association between the quality of predicted contacts and its possible utility in boosting threading performance for improving low-homology protein modeling.

Fold-LTR-TCP: protein fold recognition based on triadic closure principle

As an important task in protein structure and function studies, protein fold recognition has attracted more and more attention. The existing computational predictors in this field treat this task as a multi-classification problem, ignoring the relationship among proteins in the dataset. However, previous studies showed that their relationship is critical for protein homology analysis. In this study, the protein fold recognition is treated as an information retrieval task. The Learning to Rank model (LTR) was employed to retrieve the query protein against the template proteins to find the template proteins in the same fold with the query protein in a supervised manner. The triadic closure principle (TCP) was performed on the ranking list generated by the LTR to improve its accuracy by considering the relationship among the query protein and the template proteins in the ranking list. Finally, a predictor called Fold-LTR-TCP was proposed. The rigorous test on the LE benchmark dataset showed that the Fold-LTR-TCP predictor achieved an accuracy of 73.2%, outperforming all the other competing methods.

MotifCNN-fold: protein fold recognition based on fold-specific features extracted by motif-based convolutional neural networks

Protein fold recognition is one of the most critical tasks to explore the structures and functions of the proteins based on their primary sequence information. The existing protein fold recognition approaches rely on features reflecting the characteristics of protein folds. However, the feature extraction methods are still the bottleneck of the performance improvement of these methods. In this paper, we proposed two new feature extraction methods called MotifCNN and MotifDCNN to extract more discriminative fold-specific features based on structural motif kernels to construct the motif-based convolutional neural networks (CNNs). The pairwise sequence similarity scores calculated based on fold-specific features are then fed into support vector machines to construct the predictor for fold recognition, and a predictor called MotifCNN-fold has been proposed. Experimental results on the benchmark dataset showed that MotifCNN-fold obviously outperformed all the other competing methods. In particular, the fold-specific features extracted by MotifCNN and MotifDCNN are more discriminative than the fold-specific features extracted by other deep learning techniques, indicating that incorporating the structural motifs into the CNN is able to capture the characteristics of protein folds.

Enhanced GROMACS: toward a better numerical simulation framework

The GROMACS software package represented a promising direction toward the molecular dynamic simulation and there is ongoing interest to extend it. In this study, we introduce a new component into the conventional package with the goal being to facilitate the process of finding the native structure of proteins with minimal free-energy value. We achieved this through incorporating a wide range of metaheuristic optimization algorithms and force fields, leading up to the EGROMACS molecular simulation toolkit. Compared with other programs, the EGROMACS supports all standard force fields as well as new minimization algorithms and Hybrid MPI/OpenMP parallelization. We applied the proposed EGROMACS framework to minimize the structure of several target sequences. The obtained results showed comparative performance of the introduced framework to current well-known molecular simulation algorithms. This extension to the GROMACS, however, uses metaheuristic algorithms to address the problem.

DeepSVM-fold: protein fold recognition by combining support vector machines and pairwise sequence similarity scores generated by deep learning networks

Protein fold recognition is critical for studying the structures and functions of proteins. The existing protein fold recognition approaches failed to efficiently calculate the pairwise sequence similarity scores of the proteins in the same fold sharing low sequence similarities. Furthermore, the existing feature vectorization strategies are not able to measure the global relationships among proteins from different protein folds. In this article, we proposed a new computational predictor called DeepSVM-fold for protein fold recognition by introducing a new feature vector based on the pairwise sequence similarity scores calculated from the fold-specific features extracted by deep learning networks. The feature vectors are then fed into a support vector machine to construct the predictor. Experimental results on the benchmark dataset (LE) show that DeepSVM-fold obviously outperforms all the other competing methods.

Protein threading using residue co-variation and deep learning

Motivation

Template-based modeling, including homology modeling and protein threading, is a popular method for protein 3D structure prediction. However, alignment generation and template selection for protein sequences without close templates remain very challenging.

Results

We present a new method called DeepThreader to improve protein threading, including both alignment generation and template selection, by making use of deep learning (DL) and residue co-variation information. Our method first employs DL to predict inter-residue distance distribution from residue co-variation and sequential information (e.g. sequence profile and predicted secondary structure), and then builds sequence-template alignment by integrating predicted distance information and sequential features through an ADMM algorithm. Experimental results suggest that predicted inter-residue distance is helpful to both protein alignment and template selection especially for protein sequences without very close templates, and that our method outperforms currently popular homology modeling method HHpred and threading method CNFpred by a large margin and greatly outperforms the latest contact-assisted protein threading method EigenTHREADER.

Availability and implementation

http://raptorx.uchicago.edu/

Supplementary information

Supplementary data are available at Bioinformatics online.

Does inclusion of residue-residue contact information boost protein threading?

Template-based modeling is considered as one of the most successful approaches for protein structure prediction. However, reliably and accurately selecting optimal template proteins from a library of known protein structures having similar folds as the target protein and making correct alignments between the target sequence and the template structures, a template-based modeling technique known as threading, remains challenging, particularly for non- or distantly-homologous protein targets. With the recent advancement in protein residue-residue contact map prediction powered by sequence co-evolution and machine learning, here we systematically analyze the effect of inclusion of residue-residue contact information in improving the accuracy and reliability of protein threading. We develop a new threading algorithm by incorporating various sequential and structural features, and subsequently integrate residue-residue contact information as an additional scoring term for threading template selection. We show that the inclusion of contact information attains statistically significantly better threading performance compared to a baseline threading algorithm that does not utilize contact information when everything else remains the same. Experimental results demonstrate that our contact based threading approach outperforms popular threading method MUSTER, contact-assisted ab initio folding method CONFOLD2, and recent state-of-the-art contact-assisted protein threading methods EigenTHREADER and map_align on several benchmarks. Our study illustrates that the inclusion of contact maps is a promising avenue in protein threading to ultimately help to improve the accuracy of protein structure prediction.

Study of specific nanoenvironments containing α-helices in all-α and (α+β)+(α/β) proteins

Protein secondary structure elements (PSSEs) such as α-helices, β-strands, and turns are the primary building blocks of the tertiary protein structure. Our primary interest here is to reveal the characteristics of the nanoenvironment formed by both PSSEs and their surrounding amino acid residues (AARs), which might contribute to the general understanding of how proteins fold. The characteristics of such nanoenvironments must be specific to each secondary structure element, and we have set our goal here to gather the fullest possible description of the α-helical nanoenvironment. In general, this postulate (the existence of specific nanoenvironments for specific protein substructures/neighbourhoods/regions with distinct functionality) was already successfully explored and confirmed for some protein regions, such as protein-protein interfaces and enzyme catalytic sites. Consequently, PSSEs were the obvious next choice for additional work for further evidence showing that specific nanoenvironments (having characteristics fully describable by means of structural and physical chemical descriptors) do exist for the corresponding and determined intraprotein regions. The nanoenvironment of α-helices (nEoαH) is defined as any region of the protein where this secondary structure element type is detected. The nEoαH, therefore, includes not only the α-helix amino acid residues but also the residues immediately around the α-helix. The hypothesis that motivated this work is that it might in fact be possible to detect a postulated "signal" or "signature" that distinguishes the specific location of α-helices. This "signal" must be discernible by tracking differences in the values of physical, chemical, physicochemical, structural and geometric descriptors immediately before (or after) the PSSE from those in the region along the α-helices. The search for this specific nanoenvironment "signal" was made possible by aligning previously selected α-helices of equal length. Afterward, we calculated the average value, standard deviation and mean square error at each aligned residue position for each selected descriptor. We applied Student's t-test, the Kolmogorov-Smirnov test and MANOVA statistical tests to the dataset constructed as described above, and the results confirmed that the hypothesized "signal"/"signature" is both existing/identifiable and capable of distinguishing the presence of an α-helix inside the specific nanoenvironment, contextualized as a specific region within the whole protein. However, such conclusion might rarely be reached if only one descriptor is considered at a time. A more accurate signal with broader coverage is achieved only if one applies multivariate analysis, which means that several descriptors (usually approximately 10 descriptors) should be considered at the same time. To a limited extent (up to a maximum of 15% of cases), such conclusion is also possible with only a single descriptor, and the conclusion is also possible in general for up to 50-80% of cases when no less than 5 nonlinear descriptors are selected and considered. Using all the descriptors considered in this work, provided all assumptions about data characteristics for this analysis are met, multivariate analysis regularly reached a coverage and accuracy above 90%. Understanding how secondary structure elements are formed and maintained within a protein structure could enable a more detailed understanding of how proteins reach their final 3D structure and consequently, their function. Likewise, this knowledge may also improve the tools used to determine how good a structure is by means of comparing the "signal" around a selected PSSE with the one obtained from the best (resolution and quality wise) protein structures available.

Use of designed sequences in protein structure recognition

Background

Knowledge of the protein structure is a pre-requisite for improved understanding of molecular function. The gap in the sequence-structure space has increased in the post-genomic era. Grouping related protein sequences into families can aid in narrowing the gap. In the Pfam database, structure description is provided for part or full-length proteins of 7726 families. For the remaining 52% of the families, information on 3-D structure is not yet available. We use the computationally designed sequences that are intermediately related to two protein domain families, which are already known to share the same fold. These strategically designed sequences enable detection of distant relationships and here, we have employed them for the purpose of structure recognition of protein families of yet unknown structure.

Results

We first measured the success rate of our approach using a dataset of protein families of known fold and achieved a success rate of 88%. Next, for 1392 families of yet unknown structure, we made structural assignments for part/full length of the proteins. Fold association for 423 domains of unknown function (DUFs) are provided as a step towards functional annotation.

Conclusion

The results indicate that knowledge-based filling of gaps in protein sequence space is a lucrative approach for structure recognition. Such sequences assist in traversal through protein sequence space and effectively function as ‘linkers’, where natural linkers between distant proteins are unavailable.

Reviewers

This article was reviewed by Oliviero Carugo, Christine Orengo and Srikrishna Subramanian.

Electronic supplementary material

The online version of this article (10.1186/s13062-018-0209-6) contains supplementary material, which is available to authorized users.

Computational Approaches for Revealing the Structure of Membrane Transporters: Case Study on Bilitranslocase

The structural and functional details of transmembrane proteins are vastly underexplored, mostly due to experimental difficulties regarding their solubility and stability. Currently, the majority of transmembrane protein structures are still unknown and this present a huge experimental and computational challenge. Nowadays, thanks to X-ray crystallography or NMR spectroscopy over 3000 structures of membrane proteins have been solved, among them only a few hundred unique ones. Due to the vast biological and pharmaceutical interest in the elucidation of the structure and the functional mechanisms of transmembrane proteins, several computational methods have been developed to overcome the experimental gap. If combined with experimental data the computational information enables rapid, low cost and successful predictions of the molecular structure of unsolved proteins. The reliability of the predictions depends on the availability and accuracy of experimental data associated with structural information. In this review, the following methods are proposed for in silico structure elucidation: sequence-dependent predictions of transmembrane regions, predictions of transmembrane helix–helix interactions, helix arrangements in membrane models, and testing their stability with molecular dynamics simulations. We also demonstrate the usage of the computational methods listed above by proposing a model for the molecular structure of the transmembrane protein bilitranslocase. Bilitranslocase is bilirubin membrane transporter, which shares similar tissue distribution and functional properties with some of the members of the Organic Anion Transporter family and is the only member classified in the Bilirubin Transporter Family. Regarding its unique properties, bilitranslocase is a potentially interesting drug target.

Structural predictions for curli amyloid fibril subunits CsgA and CsgB

CsgA are the building blocks of curli fibrils.

Comparative Protein Structure Modeling Using MODELLER

Comparative protein structure modeling predicts the three-dimensional structure of a given protein sequence (target) based primarily on its alignment to one or more proteins of known structure (templates). The prediction process consists of fold assignment, target-template alignment, model building, and model evaluation. This unit describes how to calculate comparative models using the program MODELLER and how to use the ModBase database of such models, and discusses all four steps of comparative modeling, frequently observed errors, and some applications. Modeling lactate dehydrogenase from Trichomonas vaginalis (TvLDH) is described as an example. The download and installation of the MODELLER software is also described. © 2016 by John Wiley & Sons, Inc.

Why Is There a Glass Ceiling for Threading Based Protein Structure Prediction Methods?

Despite their different implementations, comparison of the best threading approaches to the prediction of evolutionary distant protein structures reveals that they tend to succeed or fail on the same protein targets. This is true despite the fact that the structural template library has good templates for all cases. Thus, a key question is why are certain protein structures threadable while others are not. Comparison with threading results on a set of artificial sequences selected for stability further argues that the failure of threading is due to the nature of the protein structures themselves. Using a new contact map based alignment algorithm, we demonstrate that certain folds are highly degenerate in that they can have very similar coarse grained fractions of native contacts aligned and yet differ significantly from the native structure. For threadable proteins, this is not the case. Thus, contemporary threading approaches appear to have reached a plateau, and new approaches to structure prediction are required.

ProFold: Protein Fold Classification with Additional Structural Features and a Novel Ensemble Classifier

Protein fold classification plays an important role in both protein functional analysis and drug design. The number of proteins in PDB is very large, but only a very small part is categorized and stored in the SCOPe database. Therefore, it is necessary to develop an efficient method for protein fold classification. In recent years, a variety of classification methods have been used in many protein fold classification studies. In this study, we propose a novel classification method called proFold. We import protein tertiary structure in the period of feature extraction and employ a novel ensemble strategy in the period of classifier training. Compared with existing similar ensemble classifiers using the same widely used dataset (DD-dataset), proFold achieves 76.2% overall accuracy. Another two commonly used datasets, EDD-dataset and TG-dataset, are also tested, of which the accuracies are 93.2% and 94.3%, higher than the existing methods. ProFold is available to the public as a web-server.

Comparative Protein Structure Modeling Using MODELLER

Comparative protein structure modeling predicts the three-dimensional structure of a given protein sequence (target) based primarily on its alignment to one or more proteins of known structure (templates). The prediction process consists of fold assignment, target-template alignment, model building, and model evaluation. This unit describes how to calculate comparative models using the program MODELLER and how to use the ModBase database of such models, and discusses all four steps of comparative modeling, frequently observed errors, and some applications. Modeling lactate dehydrogenase from Trichomonas vaginalis (TvLDH) is described as an example. The download and installation of the MODELLER software is also described. © 2016 by John Wiley & Sons, Inc.

A neural network learning approach for improving the prediction of residue depth based on sequence-derived features

Residue depth is a solvent exposure measure that quantitatively describes the depth of a residue from the protein surface.

Improving Protein Fold Recognition by Deep Learning Networks

For accurate recognition of protein folds, a deep learning network method (DN-Fold) was developed to predict if a given query-template protein pair belongs to the same structural fold. The input used stemmed from the protein sequence and structural features extracted from the protein pair. We evaluated the performance of DN-Fold along with 18 different methods on Lindahl’s benchmark dataset and on a large benchmark set extracted from SCOP 1.75 consisting of about one million protein pairs, at three different levels of fold recognition (i.e., protein family, superfamily, and fold) depending on the evolutionary distance between protein sequences. The correct recognition rate of ensembled DN-Fold for Top 1 predictions is 84.5%, 61.5%, and 33.6% and for Top 5 is 91.2%, 76.5%, and 60.7% at family, superfamily, and fold levels, respectively. We also evaluated the performance of single DN-Fold (DN-FoldS), which showed the comparable results at the level of family and superfamily, compared to ensemble DN-Fold. Finally, we extended the binary classification problem of fold recognition to real-value regression task, which also show a promising performance. DN-Fold is freely available through a web server at http://iris.rnet.missouri.edu/dnfold.

FALCON@home: a high-throughput protein structure prediction server based on remote homologue recognition

SUMMARY

The protein structure prediction approaches can be categorized into template-based modeling (including homology modeling and threading) and free modeling. However, the existing threading tools perform poorly on remote homologous proteins. Thus, improving fold recognition for remote homologous proteins remains a challenge. Besides, the proteome-wide structure prediction poses another challenge of increasing prediction throughput. In this study, we presented FALCON@home as a protein structure prediction server focusing on remote homologue identification. The design of FALCON@home is based on the observation that a structural template, especially for remote homologous proteins, consists of conserved regions interweaved with highly variable regions. The highly variable regions lead to vague alignments in threading approaches. Thus, FALCON@home first extracts conserved regions from each template and then aligns a query protein with conserved regions only rather than the full-length template directly. This helps avoid the vague alignments rooted in highly variable regions, improving remote homologue identification. We implemented FALCON@home using the Berkeley Open Infrastructure of Network Computing (BOINC) volunteer computing protocol. With computation power donated from over 20,000 volunteer CPUs, FALCON@home shows a throughput as high as processing of over 1000 proteins per day. In the Critical Assessment of protein Structure Prediction (CASP11), the FALCON@home-based prediction was ranked the 12th in the template-based modeling category. As an application, the structures of 880 mouse mitochondria proteins were predicted, which revealed the significant correlation between protein half-lives and protein structural factors.

AVAILABILITY AND IMPLEMENTATION

FALCON@home is freely available at http://protein.ict.ac.cn/FALCON/.

CONTACT

shuaicli@cityu.edu.hk, dbu@ict.ac.cn

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Refinement by shifting secondary structure elements improves sequence alignments

Constructing a model of a query protein based on its alignment to a homolog with experimentally determined spatial structure (the template) is still the most reliable approach to structure prediction. Alignment errors are the main bottleneck for homology modeling when the query is distantly related to the template. Alignment methods often misalign secondary structural elements by a few residues. Therefore, better alignment solutions can be found within a limited set of local shifts of secondary structures. We present a refinement method to improve pairwise sequence alignments by evaluating alignment variants generated by local shifts of template-defined secondary structures. Our method SFESA is based on a novel scoring function that combines the profile-based sequence score and the structure score derived from residue contacts in a template. Such a combined score frequently selects a better alignment variant among a set of candidate alignments generated by local shifts and leads to overall increase in alignment accuracy. Evaluation of several benchmarks shows that our refinement method significantly improves alignments made by automatic methods such as PROMALS, HHpred and CNFpred. The web server is available at http://prodata.swmed.edu/sfesa.

MRFy: Remote Homology Detection for Beta-Structural Proteins Using Markov Random Fields and Stochastic Search

We introduce MRFy, a tool for protein remote homology detection that captures beta-strand dependencies in the Markov random field. Over a set of 11 SCOP beta-structural superfamilies, MRFy shows a 14 percent improvement in mean Area Under the Curve for the motif recognition problem as compared to HMMER, 25 percent improvement as compared to RAPTOR, 14 percent improvement as compared to HHPred, and a 18 percent improvement as compared to CNFPred and RaptorX. MRFy was implemented in the Haskell functional programming language, and parallelizes well on multi-core systems. MRFy is available, as source code as well as an executable, from http://mrfy.cs.tufts.edu/.

Improving protein fold recognition by random forest

BACKGROUND

Recognizing the correct structural fold among known template protein structures for a target protein (i.e. fold recognition) is essential for template-based protein structure modeling. Since the fold recognition problem can be defined as a binary classification problem of predicting whether or not the unknown fold of a target protein is similar to an already known template protein structure in a library, machine learning methods have been effectively applied to tackle this problem. In our work, we developed RF-Fold that uses random forest - one of the most powerful and scalable machine learning classification methods - to recognize protein folds.

RESULTS

RF-Fold consists of hundreds of decision trees that can be trained efficiently on very large datasets to make accurate predictions on a highly imbalanced dataset. We evaluated RF-Fold on the standard Lindahl's benchmark dataset comprised of 976 × 975 target-template protein pairs through cross-validation. Compared with 17 different fold recognition methods, the performance of RF-Fold is generally comparable to the best performance in fold recognition of different difficulty ranging from the easiest family level, the medium-hard superfamily level, and to the hardest fold level. Based on the top-one template protein ranked by RF-Fold, the correct recognition rate is 84.5%, 63.4%, and 40.8% at family, superfamily, and fold levels, respectively. Based on the top-five template protein folds ranked by RF-Fold, the correct recognition rate increases to 91.5%, 79.3% and 58.3% at family, superfamily, and fold levels.

CONCLUSIONS

The good performance achieved by the RF-Fold demonstrates the random forest's effectiveness for protein fold recognition.

Comparative Protein Structure Modeling Using MODELLER

Functional characterization of a protein sequence is one of the most frequent problems in biology. This task is usually facilitated by accurate three-dimensional (3-D) structure of the studied protein. In the absence of an experimentally determined structure, comparative or homology modeling can sometimes provide a useful 3-D model for a protein that is related to at least one known protein structure. Comparative modeling predicts the 3-D structure of a given protein sequence (target) based primarily on its alignment to one or more proteins of known structure (templates). The prediction process consists of fold assignment, target-template alignment, model building, and model evaluation. This unit describes how to calculate comparative models using the program MODELLER and discusses all four steps of comparative modeling, frequently observed errors, and some applications. Modeling lactate dehydrogenase from Trichomonas vaginalis (TvLDH) is described as an example. The download and installation of the MODELLER software is also described.

Dystroglycan binding to α-neurexin competes with neurexophilin-1 and neuroligin in the brain

α-Neurexins (α-Nrxn) are mostly presynaptic cell surface molecules essential for neurotransmission that are linked to neuro-developmental disorders as autism or schizophrenia. Several interaction partners of α-Nrxn are identified that depend on alternative splicing, including neuroligins (Nlgn) and dystroglycan (αDAG). The trans-synaptic complex with Nlgn1 was extensively characterized and shown to partially mediate α-Nrxn function. However, the interactions of α-Nrxn with αDAG, neurexophilins (Nxph1) and Nlgn2, ligands that occur specifically at inhibitory synapses, are incompletely understood. Using site-directed mutagenesis, we demonstrate the exact binding epitopes of αDAG and Nxph1 on Nrxn1α and show that their binding is mutually exclusive. Identification of an unusual cysteine bridge pattern and complex type glycans in Nxph1 ensure binding to the second laminin/neurexin/sex hormone binding (LNS2) domain of Nrxn1α, but this association does not interfere with Nlgn binding at LNS6. αDAG, in contrast, interacts with both LNS2 and LNS6 domains without inserts in splice sites SS#2 or SS#4 mostly via LARGE (like-acetylglucosaminyltransferase)-dependent glycans attached to the mucin region. Unexpectedly, binding of αDAG at LNS2 prevents interaction of Nlgn at LNS6 with or without splice insert in SS#4, presumably by sterically hindering each other in the u-form conformation of α-Nrxn. Thus, expression of αDAG and Nxph1 together with alternative splicing in Nrxn1α may prevent or facilitate formation of distinct trans-synaptic Nrxn·Nlgn complexes, revealing an unanticipated way to contribute to the identity of synaptic subpopulations.

10 years for the Journal of Bioinformatics and Computational Biology (2003-2013) -- a retrospective

The Journal of Bioinformatics and Computational Biology (JBCB) started publishing scientific articles in 2003. It has established itself as home for solid research articles in the field (~ 60 per year) that are surprisingly well cited. JBCB has an important function as alternative publishing channel in addition to other, bigger journals.