Accurate contact predictions using covariation techniques and machine learning

Dietary and lifestyle determinants of vitamin D status in the UK Biobank Cohort study for predictive modeling

Vitamin D (VD) is involved in a wide variety of physiological processes. The high prevalence of VD deficiency in the population requires stronger preventive measures. The aim was to characterize the dietary and lifestyle determinants of VD levels in blood and of VD deficiency to further develop predictive models of these two outcomes. A total of 63,759 participants from the UK Biobank study with available data on dietary intake of VD, assessed via 24-hour recalls, and with measurements of serum 25(OH)D levels were included. Linear and logistic regression models were applied to identify factors associated with VD levels and VD deficiency outcomes, and to evaluate the influence of covariates on the association between VD in serum and VD in the diet. Predictive models for both VD outcomes were constructed using classical regression models and machine learning methods based on penalized likelihood methods. Approximately 10% of the participants had VD deficiency (VD < 25 nmol/L), and 38.9% were at risk of VD inadequacy (VD 25-49 nmol/L). The dietary intake of VD was significantly lower in the VD deficient group. This latter group showed lower engagement in physical activity (22.1%) compared to the non-deficient group (13.4%; P<.001). Also, overweight and obesity (vs normal weight) were related to a greater likelihood of VD deficiency (OR=1.18 and 1.96, respectively). A similar odds of VD deficiency was observed for abdominal obesity (OR=1.83). A weaker association was observed between dietary VD intake, based on participant reports, and VD levels. With regard to sunlight exposure, darker skin tones (OR dark vs fair skin=3.11), season (OR winter vs autumn=3.76) and less outdoor time activities (OR per 1 h increase=0.96) were also related to VD deficiency. Predictive models for both classical regression and machine learning, showed good accuracy (AUC=0.8-0.9 for VD deficiency). In conclusion, while a rich diet in VD boosts its levels, sun exposure plays a more significant role particularly in populations from the UK or Northern Europe. A predictive model including key determinants could effectively assess VD deficiency.

Structure prediction of protein-ligand complexes from sequence information with Umol

Protein-ligand docking is an established tool in drug discovery and development to narrow down potential therapeutics for experimental testing. However, a high-quality protein structure is required and often the protein is treated as fully or partially rigid. Here we develop an AI system that can predict the fully flexible all-atom structure of protein-ligand complexes directly from sequence information. We find that classical docking methods are still superior, but depend upon having crystal structures of the target protein. In addition to predicting flexible all-atom structures, predicted confidence metrics (plDDT) can be used to select accurate predictions as well as to distinguish between strong and weak binders. The advances presented here suggest that the goal of AI-based drug discovery is one step closer, but there is still a way to go to grasp the complexity of protein-ligand interactions fully. Umol is available at: https://github.com/patrickbryant1/Umol .

Improving protein structure prediction with extended sequence similarity searches and deep-learning-based refinement in CASP15

The human predictor team PEZYFoldings got first place with the assessor's formulae (3rd place with Global Distance Test Total Score [GDT-TS]) in the single-domain category and 10th place in the multimer category in Critical Assessment of Structure Prediction 15. In this paper, I describe the exact method used by PEZYFoldings in the competition. As AlphaFold2 and AlphaFold-Multimer, developed by DeepMind, were state-of-the-art structure prediction tools, it was assumed that enhancing the input and output of the tools was an effective strategy to obtain the highest accuracy for structure prediction. Therefore, I used additional tools and databases to collect evolutionarily related sequences and introduced a deep-learning-based model in the refinement step. In addition to these modifications, manual interventions were performed to address various tasks. Detailed analyses were performed after the competition to identify the main contributors to performance. Comparing the number of evolutionarily related sequences I used with those of the other teams that provided AlphaFold2's baseline predictions revealed that an extensive sequence similarity search was one of the main contributors. Nonetheless, there were specific targets for which I could not identify any evolutionarily related sequences, resulting in my inability to construct accurate structures for these targets. Notably, I noticed that I had gained large Z-scores with the subunits of H1137, for which I performed manual domain parsing considering the interfaces between the subunits. This finding implies that the manual intervention contributed to my performance. The influence of the refinement model on the accuracy of structure prediction was minimal. I could have predicted structures with a similar level of accuracy without employing the refinement model. However, from the perspective of accuracy self-estimate, many structures demonstrated improvement after refinement. This improvement likely had a substantial influence on improving my position in the assessor's formulae rankings. These results highlight the opportunities for improvement in (1) multimer prediction, (2) building of larger and more diverse databases, and (3) developing tools to predict structures from primary sequences alone. In addition, transferring the manual intervention process to automation is a future concern.

ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning

Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models (LMs) taken from Natural Language Processing (NLP). These LMs reach for new prediction frontiers at low inference costs. Here, we trained two auto-regressive models (Transformer-XL, XLNet) and four auto-encoder models (BERT, Albert, Electra, T5) on data from UniRef and BFD containing up to 393 billion amino acids. The protein LMs (pLMs) were trained on the Summit supercomputer using 5616 GPUs and TPU Pod up-to 1024 cores. Dimensionality reduction revealed that the raw pLM-embeddings from unlabeled data captured some biophysical features of protein sequences. We validated the advantage of using the embeddings as exclusive input for several subsequent tasks: (1) a per-residue (per-token) prediction of protein secondary structure (3-state accuracy Q3=81%-87%); (2) per-protein (pooling) predictions of protein sub-cellular location (ten-state accuracy: Q10=81%) and membrane versus water-soluble (2-state accuracy Q2=91%). For secondary structure, the most informative embeddings (ProtT5) for the first time outperformed the state-of-the-art without multiple sequence alignments (MSAs) or evolutionary information thereby bypassing expensive database searches. Taken together, the results implied that pLMs learned some of the grammar of the language of life. All our models are available through https://github.com/agemagician/ProtTrans.

ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning

Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models (LMs) taken from Natural Language Processing (NLP). These LMs reach for new prediction frontiers at low inference costs. Here, we trained two auto-regressive models (Transformer-XL, XLNet) and four auto-encoder models (BERT, Albert, Electra, T5) on data from UniRef and BFD containing up to 393 billion amino acids. The protein LMs (pLMs) were trained on the Summit supercomputer using 5616 GPUs and TPU Pod up-to 1024 cores. Dimensionality reduction revealed that the raw pLM-embeddings from unlabeled data captured some biophysical features of protein sequences. We validated the advantage of using the embeddings as exclusive input for several subsequent tasks: (1) a per-residue (per-token) prediction of protein secondary structure (3-state accuracy Q3=81%-87%); (2) per-protein (pooling) predictions of protein sub-cellular location (ten-state accuracy: Q10=81%) and membrane versus water-soluble (2-state accuracy Q2=91%). For secondary structure, the most informative embeddings (ProtT5) for the first time outperformed the state-of-the-art without multiple sequence alignments (MSAs) or evolutionary information thereby bypassing expensive database searches. Taken together, the results implied that pLMs learned some of the grammar of the language of life. All our models are available through https://github.com/agemagician/ProtTrans.

Improved prediction of protein-protein interactions using AlphaFold2

Predicting the structure of interacting protein chains is a fundamental step towards understanding protein function. Unfortunately, no computational method can produce accurate structures of protein complexes. AlphaFold2, has shown unprecedented levels of accuracy in modelling single chain protein structures. Here, we apply AlphaFold2 for the prediction of heterodimeric protein complexes. We find that the AlphaFold2 protocol together with optimised multiple sequence alignments, generate models with acceptable quality (DockQ ≥ 0.23) for 63% of the dimers. From the predicted interfaces we create a simple function to predict the DockQ score which distinguishes acceptable from incorrect models as well as interacting from non-interacting proteins with state-of-art accuracy. We find that, using the predicted DockQ scores, we can identify 51% of all interacting pairs at 1% FPR.

Predicting the structure of protein complexes is extremely difficult. Here, authors apply AlphaFold2 with optimized multiple sequence alignments to model complexes of interacting proteins, enabling prediction of both if and how proteins interact with state-of-art accuracy.

Optimized Elastic Network Models With Direct Characterization of Inter-Residue Cooperativity for Protein Dynamics

The elastic network models (ENMs)are known as representative coarse-grained models to capture essential dynamics of proteins. Due to simple designs of the force constants as a decay with spatial distances of residue pairs in many previous studies, there is still much room for the improvement of ENMs. In this article, we directly computed the force constants with the inverse covariance estimation using a ridge-type operater for the precision matrix estimation (ROPE)on a large-scale set of NMR ensembles. Distance-dependent statistical analyses on the force constants were further comprehensively performed in terms of several paired types of sequence and structural information, including secondary structure, relative solvent accessibility, sequence distance and terminal. Various distinguished distributions of the mean force constants highlight the structural and sequential characteristics coupled with the inter-residue cooperativity beyond the spatial distances. We finally integrated these structural and sequential characteristics to build novel ENM variations using the particle swarm optimization for the parameter estimation. The considerable improvements on the correlation coefficient of the mean-square fluctuation and the mode overlap were achieved by the proposed variations when compared with traditional ENMs. This study opens a novel way to develop more accurate elastic network models for protein dynamics.

Intelligent host engineering for metabolic flux optimisation in biotechnology

Optimising the function of a protein of length N amino acids by directed evolution involves navigating a 'search space' of possible sequences of some 20N. Optimising the expression levels of P proteins that materially affect host performance, each of which might also take 20 (logarithmically spaced) values, implies a similar search space of 20P. In this combinatorial sense, then, the problems of directed protein evolution and of host engineering are broadly equivalent. In practice, however, they have different means for avoiding the inevitable difficulties of implementation. The spare capacity exhibited in metabolic networks implies that host engineering may admit substantial increases in flux to targets of interest. Thus, we rehearse the relevant issues for those wishing to understand and exploit those modern genome-wide host engineering tools and thinking that have been designed and developed to optimise fluxes towards desirable products in biotechnological processes, with a focus on microbial systems. The aim throughput is 'making such biology predictable'. Strategies have been aimed at both transcription and translation, especially for regulatory processes that can affect multiple targets. However, because there is a limit on how much protein a cell can produce, increasing kcat in selected targets may be a better strategy than increasing protein expression levels for optimal host engineering.

Assessing the accuracy of contact and distance predictions in CASP14

We present the results of the assessment of the intramolecular residue-residue contact and distance predictions from groups participating in the 14th round of the CASP experiment. The performance of contact prediction methods was evaluated with the measures used in previous CASPs, while distance predictions were assessed based on a new protocol, which considers individual distance pairs as well as the whole predicted distance matrix, using a graph-based framework. The results of the evaluation indicate that predictions by the tFold framework, TripletRes and DeepPotential were the most accurate in both categories. With regards to progress in method performance, the results of the assessment in contact prediction did not reveal any discernible difference when compared to CASP13. Arguably, this could be due to CASP14 FM targets being more challenging than ever before.

ReFOLD3: refinement of 3D protein models with gradual restraints based on predicted local quality and residue contacts

ReFOLD3 is unique in its application of gradual restraints, calculated from local model quality estimates and contact predictions, which are used to guide the refinement of theoretical 3D protein models towards the native structures. ReFOLD3 achieves improved performance by using an iterative refinement protocol to fix incorrect residue contacts and local errors, including unusual bonds and angles, which are identified in the submitted models by our leading ModFOLD8 model quality assessment method. Following refinement, the likely resulting improvements to the submitted models are recognized by ModFOLD8, which produces both global and local quality estimates. During the CASP14 prediction season (May-Aug 2020), we used the ReFOLD3 protocol to refine hundreds of 3D models, for both the refinement and the main tertiary structure prediction categories. Our group improved the global and local quality scores for numerous starting models in the refinement category, where we ranked in the top 10 according to the official assessment. The ReFOLD3 protocol was also used for the refinement of the SARS-CoV-2 targets as a part of the CASP Commons COVID-19 initiative, and we provided a significant number of the top 10 models. The ReFOLD3 web server is freely available at https://www.reading.ac.uk/bioinf/ReFOLD/.

A fully open-source framework for deep learning protein real-valued distances

As deep learning algorithms drive the progress in protein structure prediction, a lot remains to be studied at this merging superhighway of deep learning and protein structure prediction. Recent findings show that inter-residue distance prediction, a more granular version of the well-known contact prediction problem, is a key to predicting accurate models. However, deep learning methods that predict these distances are still in the early stages of their development. To advance these methods and develop other novel methods, a need exists for a small and representative dataset packaged for faster development and testing. In this work, we introduce protein distance net (PDNET), a framework that consists of one such representative dataset along with the scripts for training and testing deep learning methods. The framework also includes all the scripts that were used to curate the dataset, and generate the input features and distance maps. Deep learning models can also be trained and tested in a web browser using free platforms such as Google Colab. We discuss how PDNET can be used to predict contacts, distance intervals, and real-valued distances.

ConDo: protein domain boundary prediction using coevolutionary information

MOTIVATION

Domain boundary prediction is one of the most important problems in the study of protein structure and function. Many sequence-based domain boundary prediction methods are either template-based or machine learning (ML) based. ML-based methods often perform poorly due to their use of only local (i.e. short-range) features. These conventional features such as sequence profiles, secondary structures and solvent accessibilities are typically restricted to be within 20 residues of the domain boundary candidate.

RESULTS

To address the performance of ML-based methods, we developed a new protein domain boundary prediction method (ConDo) that utilizes novel long-range features such as coevolutionary information in addition to the aforementioned local window features as inputs for ML. Toward this purpose, two types of coevolutionary information were extracted from multiple sequence alignment using direct coupling analysis: (i) partially aligned sequences, and (ii) correlated mutation information. Both the partially aligned sequence information and the modularity of residue-residue couplings possess long-range correlation information.

AVAILABILITY AND IMPLEMENTATION

https://github.com/gicsaw/ConDo.git.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Computationally Aided Discovery of LysEFm5 Variants with Improved Catalytic Activity and Stability

Bacteriophage-derived lysin proteins are potentially effective antimicrobials that would benefit from engineered improvements to their bioavailability and specific activity. Here, the catalytic domain of LysEFm5, a lysin with activity against vancomycin-resistant Enterococcus faecium (VRE), was subjected to site-saturation mutagenesis at positions whose selection was guided by sequence and structural information from homologous proteins. A second-order Potts model with parameters inferred from large sets of homologous sequence information was used to predict the average change in the statistical fitness for mutant libraries with diversity at pairs of sites within the secondary catalytic shell. Guided by the statistical fitness, nine double mutant saturation libraries were created and plated on agar containing autoclaved VRE to quickly identify and segregate catalytically active (halo-forming) and inactive (non-halo-forming) variants. High-throughput DNA sequencing of 873 unique variants showed that the statistical fitness was predictive of the retention or loss of catalytic activity (area under the curve [AUC], 0.840 to 0.894), with the inclusion of more diverse sequences in the starting multiple-sequence alignment improving the classification accuracy when pairwise amino acid couplings (epistasis) were considered. Of eight random halo-forming variants selected for more sensitive testing, one showed a 1.8 (±0.4)-fold improvement in specific activity and an 11.5 ± 0.8°C increase in melting temperature compared to those of the wild type. Our results demonstrate that a computationally informed approach employing homologous protein information coupled with a mid-throughput screening assay allows for the expedited discovery of lysin variants with improved properties.IMPORTANCE Broad-spectrum antibiotics can indiscriminately kill most bacteria, including commensal species that are a part of the normal human flora. This can potentially lead to the proliferation of drug-resistant bacteria upon elimination of competing species and to unwanted autoimmune effects in patients. Bacteriophage-derived lysin proteins are an alternative to conventional antibiotics that have coevolved alongside specific bacterial hosts. Lysins are capable of targeting conserved substrates in the bacterial cell wall essential for its viability. To engineer these proteins to exhibit improved therapeutically relevant properties, homology-guided statistical approaches can be used to identify compelling sites for mutation and to quantify the functional constraints acting on these sites to direct mutagenic library creation. The platform described herein couples this informed approach with a visual plate assay that can be used to simultaneously screen hundreds of mutants for catalytic activity, allowing for the streamlined identification of improved lysin variants.

Federating Structural Models and Data: Outcomes from A Workshop on Archiving Integrative Structures

Structures of biomolecular systems are increasingly computed by integrative modeling. In this approach, a structural model is constructed by combining information from multiple sources, including varied experimental methods and prior models. In 2019, a Workshop was held as a Biophysical Society Satellite Meeting to assess progress and discuss further requirements for archiving integrative structures. The primary goal of the Workshop was to build consensus for addressing the challenges involved in creating common data standards, building methods for federated data exchange, and developing mechanisms for validating integrative structures. The summary of the Workshop and the recommendations that emerged are presented here.

Structural complementarity of distance constraints obtained from chemical cross-linking and amino acid coevolution

The analysis of amino acid coevolution has emerged as a practical method for protein structural modeling by providing structural contact information from alignments of amino acid sequences. In parallel, chemical cross-linking/mass spectrometry (XLMS) has gained attention as a universally applicable method for obtaining low-resolution distance constraints to model the quaternary arrangements of proteins, and more recently even protein tertiary structures. Here, we show that the structural information obtained by XLMS and coevolutionary analysis are effectively complementary: the distance constraints obtained by each method are almost exclusively associated with non-coincident pairs of residues, and modeling results obtained by the combination of both sets are improved relative to considering the same total number of constraints of a single type. The structural rationale behind the complementarity of the distance constraints is discussed and illustrated for a representative set of proteins with different sizes and folds.

Critical assessment of methods of protein structure prediction (CASP)-Round XIII

CASP (critical assessment of structure prediction) assesses the state of the art in modeling protein structure from amino acid sequence. The most recent experiment (CASP13 held in 2018) saw dramatic progress in structure modeling without use of structural templates (historically "ab initio" modeling). Progress was driven by the successful application of deep learning techniques to predict inter-residue distances. In turn, these results drove dramatic improvements in three-dimensional structure accuracy: With the proviso that there are an adequate number of sequences known for the protein family, the new methods essentially solve the long-standing problem of predicting the fold topology of monomeric proteins. Further, the number of sequences required in the alignment has fallen substantially. There is also substantial improvement in the accuracy of template-based models. Other areas-model refinement, accuracy estimation, and the structure of protein assemblies-have again yielded interesting results. CASP13 placed increased emphasis on the use of sparse data together with modeling and chemical crosslinking, SAXS, and NMR all yielded more mature results. This paper summarizes the key outcomes of CASP13. The special issue of PROTEINS contains papers describing the CASP13 assessments in each modeling category and contributions from the participants.

Prediction of interresidue contacts with DeepMetaPSICOV in CASP13

In this article, we describe our efforts in contact prediction in the CASP13 experiment. We employed a new deep learning‐based contact prediction tool, DeepMetaPSICOV (or DMP for short), together with new methods and data sources for alignment generation. DMP evolved from MetaPSICOV and DeepCov and combines the input feature sets used by these methods as input to a deep, fully convolutional residual neural network. We also improved our method for multiple sequence alignment generation and included metagenomic sequences in the search. We discuss successes and failures of our approach and identify areas where further improvements may be possible. DMP is freely available at: https://github.com/psipred/DeepMetaPSICOV.

Protein Inter-Residue Contacts Prediction: Methods, Performances and Applications

Background:

Protein inter-residue contacts prediction play an important role in the field of protein structure and function research. As a low-dimensional representation of protein tertiary structure, protein inter-residue contacts could greatly help de novo protein structure prediction methods to reduce the conformational search space. Over the past two decades, various methods have been developed for protein inter-residue contacts prediction.

Objective:

We provide a comprehensive and systematic review of protein inter-residue contacts prediction methods.

Results:

Protein inter-residue contacts prediction methods are roughly classified into five categories: correlated mutations methods, machine-learning methods, fusion methods, templatebased methods and 3D model-based methods. In this paper, firstly we describe the common definition of protein inter-residue contacts and show the typical application of protein inter-residue contacts. Then, we present a comprehensive review of the three main categories for protein interresidue contacts prediction: correlated mutations methods, machine-learning methods and fusion methods. Besides, we analyze the constraints for each category. Furthermore, we compare several representative methods on the CASP11 dataset and discuss performances of these methods in detail.

Conclusion:

Correlated mutations methods achieve better performances for long-range contacts, while the machine-learning method performs well for short-range contacts. Fusion methods could take advantage of the machine-learning and correlated mutations methods. Employing more effective fusion strategy could be helpful to further improve the performances of fusion methods.

DNCON2: improved protein contact prediction using two-level deep convolutional neural networks

Motivation

Significant improvements in the prediction of protein residue–residue contacts are observed in the recent years. These contacts, predicted using a variety of coevolution-based and machine learning methods, are the key contributors to the recent progress in ab initio protein structure prediction, as demonstrated in the recent CASP experiments. Continuing the development of new methods to reliably predict contact maps is essential to further improve ab initio structure prediction.

Results

In this paper we discuss DNCON2, an improved protein contact map predictor based on two-level deep convolutional neural networks. It consists of six convolutional neural networks—the first five predict contacts at 6, 7.5, 8, 8.5 and 10 Å distance thresholds, and the last one uses these five predictions as additional features to predict final contact maps. On the free-modeling datasets in CASP10, 11 and 12 experiments, DNCON2 achieves mean precisions of 35, 50 and 53.4%, respectively, higher than 30.6% by MetaPSICOV on CASP10 dataset, 34% by MetaPSICOV on CASP11 dataset and 46.3% by Raptor-X on CASP12 dataset, when top L/5 long-range contacts are evaluated. We attribute the improved performance of DNCON2 to the inclusion of short- and medium-range contacts into training, two-level approach to prediction, use of the state-of-the-art optimization and activation functions, and a novel deep learning architecture that allows each filter in a convolutional layer to access all the input features of a protein of arbitrary length.

Availability and implementation

The web server of DNCON2 is at http://sysbio.rnet.missouri.edu/dncon2/ where training and testing datasets as well as the predictions for CASP10, 11 and 12 free-modeling datasets can also be downloaded. Its source code is available at https://github.com/multicom-toolbox/DNCON2/.

Supplementary information

Supplementary data are available at Bioinformatics online.

Numerical Encodings of Amino Acids in Multivariate Gaussian Modeling of Protein Multiple Sequence Alignments

Residues in proteins that are in close spatial proximity are more prone to covariate as their interactions are likely to be preserved due to structural and evolutionary constraints. If we can detect and quantify such covariation, physical contacts may then be predicted in the structure of a protein solely from the sequences that decorate it. To carry out such predictions, and following the work of others, we have implemented a multivariate Gaussian model to analyze correlation in multiple sequence alignments. We have explored and tested several numerical encodings of amino acids within this model. We have shown that 1D encodings based on amino acid biochemical and biophysical properties, as well as higher dimensional encodings computed from the principal components of experimentally derived mutation/substitution matrices, do not perform as well as a simple twenty dimensional encoding with each amino acid represented with a vector of one along its own dimension and zero elsewhere. The optimum obtained from representations based on substitution matrices is reached by using 10 to 12 principal components; the corresponding performance is less than the performance obtained with the 20-dimensional binary encoding. We highlight also the importance of the prior when constructing the multivariate Gaussian model of a multiple sequence alignment.

Co-Evolution of Intrinsically Disordered Proteins with Folded Partners Witnessed by Evolutionary Couplings

Although improved strategies for the detection and analysis of evolutionary couplings (ECs) between protein residues already enable the prediction of protein structures and interactions, they are mostly restricted to conserved and well-folded proteins. Whereas intrinsically disordered proteins (IDPs) are central to cellular interaction networks, due to the lack of strict structural constraints, they undergo faster evolutionary changes than folded domains. This makes the reliable identification and alignment of IDP homologs difficult, which led to IDPs being omitted in most large-scale residue co-variation analyses. By preforming a dedicated analysis of phylogenetically widespread bacterial IDP–partner interactions, here we demonstrate that partner binding imposes constraints on IDP sequences that manifest in detectable interprotein ECs. These ECs were not detected for interactions mediated by short motifs, rather for those with larger IDP–partner interfaces. Most identified coupled residue pairs reside close (<10 Å) to each other on the interface, with a third of them forming multiple direct atomic contacts. EC-carrying interfaces of IDPs are enriched in negatively charged residues, and the EC residues of both IDPs and partners preferentially reside in helices. Our analysis brings hope that IDP–partner interactions difficult to study could soon be successfully dissected through residue co-variation analysis.

Recent advances in sequence-based protein structure prediction

The most accurate characterizations of the structure of proteins are provided by structural biology experiments. However, because of the high cost and labor-intensive nature of the structural experiments, the gap between the number of protein sequences and solved structures is widening rapidly. Development of computational methods to accurately model protein structures from sequences is becoming increasingly important to the biological community. In this article, we highlight some important progress in the field of protein structure prediction, especially those related to free modeling (FM) methods that generate structure models without using homologous templates. We also provide a short synopsis of some of the recent advances in FM approaches as demonstrated in the recent Computational Assessment of Structure Prediction competition as well as recent trends and outlook for FM approaches in protein structure prediction.

Finding the needle in the haystack: towards solving the protein-folding problem computationally

Prediction of protein tertiary structures from amino acid sequence and understanding the mechanisms of how proteins fold, collectively known as "the protein folding problem," has been a grand challenge in molecular biology for over half a century. Theories have been developed that provide us with an unprecedented understanding of protein folding mechanisms. However, computational simulation of protein folding is still difficult, and prediction of protein tertiary structure from amino acid sequence is an unsolved problem. Progress toward a satisfying solution has been slow due to challenges in sampling the vast conformational space and deriving sufficiently accurate energy functions. Nevertheless, several techniques and algorithms have been adopted to overcome these challenges, and the last two decades have seen exciting advances in enhanced sampling algorithms, computational power and tertiary structure prediction methodologies. This review aims at summarizing these computational techniques, specifically conformational sampling algorithms and energy approximations that have been frequently used to study protein-folding mechanisms or to de novo predict protein tertiary structures. We hope that this review can serve as an overview on how the protein-folding problem can be studied computationally and, in cases where experimental approaches are prohibitive, help the researcher choose the most relevant computational approach for the problem at hand. We conclude with a summary of current challenges faced and an outlook on potential future directions.

CONFOLD2: improved contact-driven ab initio protein structure modeling

Background

Contact-guided protein structure prediction methods are becoming more and more successful because of the latest advances in residue-residue contact prediction. To support contact-driven structure prediction, effective tools that can quickly build tertiary structural models of good quality from predicted contacts need to be developed.

Results

We develop an improved contact-driven protein modelling method, CONFOLD2, and study how it may be effectively used for ab initio protein structure prediction with predicted contacts as input. It builds models using various subsets of input contacts to explore the fold space under the guidance of a soft square energy function, and then clusters the models to obtain the top five models. CONFOLD2 obtains an average reconstruction accuracy of 0.57 TM-score for the 150 proteins in the PSICOV contact prediction dataset. When benchmarked on the CASP11 contacts predicted using CONSIP2 and CASP12 contacts predicted using Raptor-X, CONFOLD2 achieves a mean TM-score of 0.41 on both datasets.

Conclusion

CONFOLD2 allows to quickly generate top five structural models for a protein sequence when its secondary structures and contacts predictions at hand. The source code of CONFOLD2 is publicly available at https://github.com/multicom-toolbox/CONFOLD2/.

Electronic supplementary material

The online version of this article (10.1186/s12859-018-2032-6) contains supplementary material, which is available to authorized users.

Protein contact prediction by integrating deep multiple sequence alignments, coevolution and machine learning

In this study, we report the evaluation of the residue-residue contacts predicted by our three different methods in the CASP12 experiment, focusing on studying the impact of multiple sequence alignment, residue coevolution, and machine learning on contact prediction. The first method (MULTICOM-NOVEL) uses only traditional features (sequence profile, secondary structure, and solvent accessibility) with deep learning to predict contacts and serves as a baseline. The second method (MULTICOM-CONSTRUCT) uses our new alignment algorithm to generate deep multiple sequence alignment to derive coevolution-based features, which are integrated by a neural network method to predict contacts. The third method (MULTICOM-CLUSTER) is a consensus combination of the predictions of the first two methods. We evaluated our methods on 94 CASP12 domains. On a subset of 38 free-modeling domains, our methods achieved an average precision of up to 41.7% for top L/5 long-range contact predictions. The comparison of the three methods shows that the quality and effective depth of multiple sequence alignments, coevolution-based features, and machine learning integration of coevolution-based features and traditional features drive the quality of predicted protein contacts. On the full CASP12 dataset, the coevolution-based features alone can improve the average precision from 28.4% to 41.6%, and the machine learning integration of all the features further raises the precision to 56.3%, when top L/5 predicted long-range contacts are evaluated. And the correlation between the precision of contact prediction and the logarithm of the number of effective sequences in alignments is 0.66.

Improved protein contact predictions with the MetaPSICOV2 server in CASP12

In this paper, we present the results for the MetaPSICOV2 contact prediction server in the CASP12 community experiment (http://predictioncenter.org). Over the 35 assessed Free Modelling target domains the MetaPSICOV2 server achieved a mean precision of 43.27%, a substantial increase relative to the server's performance in the CASP11 experiment. In the following paper, we discuss improvements to the MetaPSICOV2 server, covering both changes to the neural network and attempts to integrate contact predictions on a domain basis into the prediction pipeline. We also discuss some limitations in the CASP12 assessment which may have overestimated the performance of our method.

RRCRank: a fusion method using rank strategy for residue-residue contact prediction

Background

In structural biology area, protein residue-residue contacts play a crucial role in protein structure prediction. Some researchers have found that the predicted residue-residue contacts could effectively constrain the conformational search space, which is significant for de novo protein structure prediction. In the last few decades, related researchers have developed various methods to predict residue-residue contacts, especially, significant performance has been achieved by using fusion methods in recent years. In this work, a novel fusion method based on rank strategy has been proposed to predict contacts. Unlike the traditional regression or classification strategies, the contact prediction task is regarded as a ranking task. First, two kinds of features are extracted from correlated mutations methods and ensemble machine-learning classifiers, and then the proposed method uses the learning-to-rank algorithm to predict contact probability of each residue pair.

Results

First, we perform two benchmark tests for the proposed fusion method (RRCRank) on CASP11 dataset and CASP12 dataset respectively. The test results show that the RRCRank method outperforms other well-developed methods, especially for medium and short range contacts. Second, in order to verify the superiority of ranking strategy, we predict contacts by using the traditional regression and classification strategies based on the same features as ranking strategy. Compared with these two traditional strategies, the proposed ranking strategy shows better performance for three contact types, in particular for long range contacts. Third, the proposed RRCRank has been compared with several state-of-the-art methods in CASP11 and CASP12. The results show that the RRCRank could achieve comparable prediction precisions and is better than three methods in most assessment metrics.

Conclusions

The learning-to-rank algorithm is introduced to develop a novel rank-based method for the residue-residue contact prediction of proteins, which achieves state-of-the-art performance based on the extensive assessment.

Electronic supplementary material

The online version of this article (10.1186/s12859-017-1811-9) contains supplementary material, which is available to authorized users.

Improved protein structure reconstruction using secondary structures, contacts at higher distance thresholds, and non-contacts

Background

Residue-residue contacts are key features for accurate de novo protein structure prediction. For the optimal utilization of these predicted contacts in folding proteins accurately, it is important to study the challenges of reconstructing protein structures using true contacts. Because contact-guided protein modeling approach is valuable for predicting the folds of proteins that do not have structural templates, it is necessary for reconstruction studies to focus on hard-to-predict protein structures.

Results

Using a data set consisting of 496 structural domains released in recent CASP experiments and a dataset of 150 representative protein structures, in this work, we discuss three techniques to improve the reconstruction accuracy using true contacts – adding secondary structures, increasing contact distance thresholds, and adding non-contacts. We find that reconstruction using secondary structures and contacts can deliver accuracy higher than using full contact maps. Similarly, we demonstrate that non-contacts can improve reconstruction accuracy not only when the used non-contacts are true but also when they are predicted. On the dataset consisting of 150 proteins, we find that by simply using low ranked predicted contacts as non-contacts and adding them as additional restraints, can increase the reconstruction accuracy by 5% when the reconstructed models are evaluated using TM-score.

Conclusions

Our findings suggest that secondary structures are invaluable companions of contacts for accurate reconstruction. Confirming some earlier findings, we also find that larger distance thresholds are useful for folding many protein structures which cannot be folded using the standard definition of contacts. Our findings also suggest that for more accurate reconstruction using predicted contacts it is useful to predict contacts at higher distance thresholds (beyond 8 Å) and predict non-contacts.

Electronic supplementary material

The online version of this article (10.1186/s12859-017-1807-5) contains supplementary material, which is available to authorized users.

An overview of comparative modelling and resources dedicated to large-scale modelling of genome sequences

Computational modelling of proteins has been a major catalyst in structural biology. Bioinformatics groups have exploited the repositories of known structures to predict high-quality structural models with high efficiency at low cost. This article provides an overview of comparative modelling, reviews recent developments and describes resources dedicated to large-scale comparative modelling of genome sequences. The value of subclustering protein domain superfamilies to guide the template-selection process is investigated. Some recent cases in which structural modelling has aided experimental work to determine very large macromolecular complexes are also cited.

Predictions of Backbone Dynamics in Intrinsically Disordered Proteins Using De Novo Fragment-Based Protein Structure Predictions

Intrinsically disordaered proteins (IDPs) are a prevalent phenomenon with over 30% of human proteins estimated to have long disordered regions. Computational methods are widely used to study IDPs, however, nearly all treat disorder in a binary fashion, not accounting for the structural heterogeneity present in disordered regions. Here, we present a new de novo method, FRAGFOLD-IDP, which addresses this problem. Using 200 protein structural ensembles derived from NMR, we show that FRAGFOLD-IDP achieves superior results compared to methods which can predict related data (NMR order parameter, or crystallographic B-factor). FRAGFOLD-IDP produces very good predictions for 33.5% of cases and helps to get a better insight into the dynamics of the disordered ensembles. The results also show it is not necessary to predict the correct fold of the protein to reliably predict per-residue fluctuations. It implies that disorder is a local property and it does not depend on the fold. Our results are orthogonal to DynaMine, the only other method significantly better than the naïve prediction. We therefore combine these two using a neural network. FRAGFOLD-IDP enables better insight into backbone dynamics in IDPs and opens exciting possibilities for the design of disordered ensembles, disorder-to-order transitions, or design for protein dynamics.

Applications of contact predictions to structural biology

Evolutionary pressure on residue interactions, intramolecular or intermolecular, that are important for protein structure or function can lead to covariance between the two positions. Recent methodological advances allow much more accurate contact predictions to be derived from this evolutionary covariance signal. The practical application of contact predictions has largely been confined to structural bioinformatics, yet, as this work seeks to demonstrate, the data can be of enormous value to the structural biologist working in X-ray crystallo-graphy, cryo-EM or NMR. Integrative structural bioinformatics packages such as Rosetta can already exploit contact predictions in a variety of ways. The contribution of contact predictions begins at construct design, where structural domains may need to be expressed separately and contact predictions can help to predict domain limits. Structure solution by molecular replacement (MR) benefits from contact predictions in diverse ways: in difficult cases, more accurate search models can be constructed using ab initio modelling when predictions are available, while intermolecular contact predictions can allow the construction of larger, oligomeric search models. Furthermore, MR using supersecondary motifs or large-scale screens against the PDB can exploit information, such as the parallel or antiparallel nature of any β-strand pairing in the target, that can be inferred from contact predictions. Contact information will be particularly valuable in the determination of lower resolution structures by helping to assign sequence register. In large complexes, contact information may allow the identity of a protein responsible for a certain region of density to be determined and then assist in the orientation of an available model within that density. In NMR, predicted contacts can provide long-range information to extend the upper size limit of the technique in a manner analogous but complementary to experimental methods. Finally, predicted contacts can distinguish between biologically relevant interfaces and mere lattice contacts in a final crystal structure, and have potential in the identification of functionally important regions and in foreseeing the consequences of mutations.

New encouraging developments in contact prediction: Assessment of the CASP11 results

This article provides a report on the state-of-the-art in the prediction of intra-molecular residue-residue contacts in proteins based on the assessment of the predictions submitted to the CASP11 experiment. The assessment emphasis is placed on the accuracy in predicting long-range contacts. Twenty-nine groups participated in contact prediction in CASP11. At least eight of them used the recently developed evolutionary coupling techniques, with the top group (CONSIP2) reaching precision of 27% on target proteins that could not be modeled by homology. This result indicates a breakthrough in the development of methods based on the correlated mutation approach. Successful prediction of contacts was shown to be practically helpful in modeling three-dimensional structures; in particular target T0806 was modeled exceedingly well with accuracy not yet seen for ab initio targets of this size (>250 residues). Proteins 2016; 84(Suppl 1):131-144. © 2015 Wiley Periodicals, Inc.

KScons: a Bayesian approach for protein residue contact prediction using the knob-socket model of protein tertiary structure

MOTIVATION

By simplifying the many-bodied complexity of residue packing into patterns of simple pairwise secondary structure interactions between a single knob residue with a three-residue socket, the knob-socket construct allows a more direct incorporation of structural information into the prediction of residue contacts. By modeling the preferences between the amino acid composition of a socket and knob, we undertake an investigation of the knob-socket construct's ability to improve the prediction of residue contacts. The statistical model considers three priors and two posterior estimations to better understand how the input data affects predictions. This produces six implementations of KScons that are tested on three sets: PSICOV, CASP10 and CASP11. We compare against the current leading contact prediction methods.

RESULTS

The results demonstrate the usefulness as well as the limits of knob-socket based structural modeling of protein contacts. The construct is able to extract good predictions from known structural homologs, while its performance degrades when no homologs exist. Among our six implementations, KScons MST-MP (which uses the multiple structure alignment prior and marginal posterior incorporating structural homolog information) performs the best in all three prediction sets. An analysis of recall and precision finds that KScons MST-MP improves accuracy not only by improving identification of true positives, but also by decreasing the number of false positives. Over the CASP10 and CASP11 sets, KScons MST-MP performs better than the leading methods using only evolutionary coupling data, but not quite as well as the supervised learning methods of MetaPSICOV and CoinDCA-NN that incorporate a large set of structural features.

CONTACT

qiwei.li@rice.eduSupplementary information: Supplementary data are available at Bioinformatics online.

Residue contacts predicted by evolutionary covariance extend the application of ab initio molecular replacement to larger and more challenging protein folds

For many protein families, the deluge of new sequence information together with new statistical protocols now allow the accurate prediction of contacting residues from sequence information alone. This offers the possibility of more accurate ab initio (non-homology-based) structure prediction. Such models can be used in structure solution by molecular replacement (MR) where the target fold is novel or is only distantly related to known structures. Here, AMPLE, an MR pipeline that assembles search-model ensembles from ab initio structure predictions ('decoys'), is employed to assess the value of contact-assisted ab initio models to the crystallographer. It is demonstrated that evolutionary covariance-derived residue-residue contact predictions improve the quality of ab initio models and, consequently, the success rate of MR using search models derived from them. For targets containing β-structure, decoy quality and MR performance were further improved by the use of a β-strand contact-filtering protocol. Such contact-guided decoys achieved 14 structure solutions from 21 attempted protein targets, compared with nine for simple Rosetta decoys. Previously encountered limitations were superseded in two key respects. Firstly, much larger targets of up to 221 residues in length were solved, which is far larger than the previously benchmarked threshold of 120 residues. Secondly, contact-guided decoys significantly improved success with β-sheet-rich proteins. Overall, the improved performance of contact-guided decoys suggests that MR is now applicable to a significantly wider range of protein targets than were previously tractable, and points to a direct benefit to structural biology from the recent remarkable advances in sequencing.

UniCon3D: de novo protein structure prediction using united-residue conformational search via stepwise, probabilistic sampling

MOTIVATION

Recent experimental studies have suggested that proteins fold via stepwise assembly of structural units named 'foldons' through the process of sequential stabilization. Alongside, latest developments on computational side based on probabilistic modeling have shown promising direction to perform de novo protein conformational sampling from continuous space. However, existing computational approaches for de novo protein structure prediction often randomly sample protein conformational space as opposed to experimentally suggested stepwise sampling.

RESULTS

Here, we develop a novel generative, probabilistic model that simultaneously captures local structural preferences of backbone and side chain conformational space of polypeptide chains in a united-residue representation and performs experimentally motivated conditional conformational sampling via stepwise synthesis and assembly of foldon units that minimizes a composite physics and knowledge-based energy function for de novo protein structure prediction. The proposed method, UniCon3D, has been found to (i) sample lower energy conformations with higher accuracy than traditional random sampling in a small benchmark of 6 proteins; (ii) perform comparably with the top five automated methods on 30 difficult target domains from the 11th Critical Assessment of Protein Structure Prediction (CASP) experiment and on 15 difficult target domains from the 10th CASP experiment; and (iii) outperform two state-of-the-art approaches and a baseline counterpart of UniCon3D that performs traditional random sampling for protein modeling aided by predicted residue-residue contacts on 45 targets from the 10th edition of CASP.

AVAILABILITY AND IMPLEMENTATION

Source code, executable versions, manuals and example data of UniCon3D for Linux and OSX are freely available to non-commercial users at http://sysbio.rnet.missouri.edu/UniCon3D/ CONTACT: chengji@missouri.edu

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.