SVMQA: support-vector-machine-based protein single-model quality assessment

Recent advances and challenges in protein complex model accuracy estimation

Estimation of model accuracy plays a crucial role in protein structure prediction, aiming to evaluate the quality of predicted protein structure models accurately and objectively. This process is not only key to screening candidate models that are close to the real structure, but also provides guidance for further optimization of protein structures. With the significant advancements made by AlphaFold2 in monomer structure, the problem of single-domain protein structure prediction has been widely solved. Correspondingly, the importance of assessing the quality of single-domain protein models decreased, and the research focus has shifted to estimation of model accuracy of protein complexes. In this review, our goal is to provide a comprehensive overview of the reference and statistical metrics, as well as representative methods, and the current challenges within four distinct facets (Topology Global Score, Interface Total Score, Interface Residue-Wise Score, and Tertiary Residue-Wise Score) in the field of complex EMA.

ComplexQA: a deep graph learning approach for protein complex structure assessment

MOTIVATION

In recent years, the end-to-end deep learning method for single-chain protein structure prediction has achieved high accuracy. For example, the state-of-the-art method AlphaFold, developed by Google, has largely increased the accuracy of protein structure predictions to near experimental accuracy in some of the cases. At the same time, there are few methods that can evaluate the quality of protein complexes at the residue level. In particular, evaluating the quality of residues at the interface of protein complexes can lead to a wide range of applications, such as protein function analysis and drug design. In this paper, we introduce a new deep graph neural network-based method ComplexQA, to evaluate the local quality of interfaces for protein complexes by utilizing the residue-level structural information in 3D space and the sequence-level constraints.

RESULTS

We benchmark our method to other state-of-the-art quality assessment approaches on the HAF2 and DBM55-AF2 datasets (high-quality structural models predicted by AlphaFold-Multimer), and the BM5 docking dataset. The experimental results show that our proposed method achieves better or similar performance compared with other state-of-the-art methods, especially on difficult targets which only contain a few acceptable models. Our method is able to suggest a score for each interfac e residue, which demonstrates a powerful assessment tool for the ever-increasing number of protein complexes.

AVAILABILITY

https://github.com/Cao-Labs/ComplexQA.git. Contact: caora@plu.edu.

A review of methods for predicting DNA N6-methyladenine sites

Deoxyribonucleic acid(DNA) N6-methyladenine plays a vital role in various biological processes, and the accurate identification of its site can provide a more comprehensive understanding of its biological effects. There are several methods for 6mA site prediction. With the continuous development of technology, traditional techniques with the high costs and low efficiencies are gradually being replaced by computer methods. Computer methods that are widely used can be divided into two categories: traditional machine learning and deep learning methods. We first list some existing experimental methods for predicting the 6mA site, then analyze the general process from sequence input to results in computer methods and review existing model architectures. Finally, the results were summarized and compared to facilitate subsequent researchers in choosing the most suitable method for their work.

Estimation of model accuracy by a unique set of features and tree-based regressor

Computationally generated models of protein structures bridge the gap between the practically negligible price tag of sequencing and the high cost of experimental structure determination. By providing a low-cost (and often free) partial alternative to experimentally determined structures, these models help biologists design and interpret their experiments. Obviously, the more accurate the models the more useful they are. However, methods for protein structure prediction generate many structural models of various qualities, necessitating means for the estimation of their accuracy. In this work we present MESHI_consensus, a new method for the estimation of model accuracy. The method uses a tree-based regressor and a set of structural, target-based, and consensus-based features. The new method achieved high performance in the EMA (Estimation of Model Accuracy) track of the recent CASP14 community-wide experiment (https://predictioncenter.org/casp14/index.cgi). The tertiary structure prediction track of that experiment revealed an unprecedented leap in prediction performance by a single prediction group/method, namely AlphaFold2. This achievement would inevitably have a profound impact on the field of protein structure prediction, including the accuracy estimation sub-task. We conclude this manuscript with some speculations regarding the future role of accuracy estimation in a new era of accurate protein structure prediction.

Empirical comparison and analysis of machine learning-based predictors for predicting and analyzing of thermophilic proteins

Thermophilic proteins (TPPs) are critical for basic research and in the food industry due to their ability to maintain a thermodynamically stable fold at extremely high temperatures. Thus, the expeditious identification of novel TPPs through computational models from protein sequences is very desirable. Over the last few decades, a number of computational methods, especially machine learning (ML)-based methods, for in silico prediction of TPPs have been developed. Therefore, it is desirable to revisit these methods and summarize their advantages and disadvantages in order to further develop new computational approaches to achieve more accurate and improved prediction of TPPs. With this goal in mind, we comprehensively investigate a large collection of fourteen state-of-the-art TPP predictors in terms of their dataset size, feature encoding schemes, feature selection strategies, ML algorithms, evaluation strategies and web server/software usability. To the best of our knowledge, this article represents the first comprehensive review on the development of ML-based methods for in silico prediction of TPPs. Among these TPP predictors, they can be classified into two groups according to the interpretability of ML algorithms employed (i.e., computational black-box methods and computational white-box methods). In order to perform the comparative analysis, we conducted a comparative study on several currently available TPP predictors based on two benchmark datasets. Finally, we provide future perspectives for the design and development of new computational models for TPP prediction. We hope that this comprehensive review will facilitate researchers in selecting an appropriate TPP predictor that is the most suitable one to deal with their purposes and provide useful perspectives for the development of more effective and accurate TPP predictors.

Improved Protein Decoy Selection via Non-Negative Matrix Factorization

A central challenge in protein modeling research and protein structure prediction in particular is known as decoy selection. The problem refers to selecting biologically-active/native tertiary structures among a multitude of physically-realistic structures generated by template-free protein structure prediction methods. Research on decoy selection is active. Clustering-based methods are popular, but they fail to identify good/near-native decoys on datasets where near-native decoys are severely under-sampled by a protein structure prediction method. Reasonable progress is reported by methods that additionally take into account the internal energy of a structure and employ it to identify basins in the energy landscape organizing the multitude of decoys. These methods, however, incur significant time costs for extracting basins from the landscape. In this paper, we propose a novel decoy selection method based on non-negative matrix factorization. We demonstrate that our method outperforms energy landscape-based methods. In particular, the proposed method addresses both the time cost issue and the challenge of identifying good decoys in a sparse dataset, successfully recognizing near-native decoys for both easy and hard protein targets.

Using steered molecular dynamic tension for assessing quality of computational protein structure models

The native structures of proteins, except for notable exceptions of intrinsically disordered proteins, in general take their most stable conformation in the physiological condition to maintain their structural framework so that their biological function can be properly carried out. Experimentally, the stability of a protein can be measured by several means, among which the pulling experiment using the atomic force microscope (AFM) stands as a unique method. AFM directly measures the resistance from unfolding, which can be quantified from the observed force-extension profile. It has been shown that key features observed in an AFM pulling experiment can be well reproduced by computational molecular dynamics simulations. Here, we applied computational pulling for estimating the accuracy of computational protein structure models under the hypothesis that the structural stability would positively correlated with the accuracy, i.e. the closeness to the native, of a model. We used in total 4929 structure models for 24 target proteins from the Critical Assessment of Techniques of Structure Prediction (CASP) and investigated if the magnitude of the break force, that is, the force required to rearrange the model's structure, from the force profile was sufficient information for selecting near-native models. We found that near-native models can be successfully selected by examining their break forces suggesting that high break force indeed indicates high stability of models. On the other hand, there were also near-native models that had relatively low peak forces. The mechanisms of the stability exhibited by the break forces were explored and discussed.

DeepUMQA: ultrafast shape recognition-based protein model quality assessment using deep learning

MOTIVATION

Protein model quality assessment is a key component of protein structure prediction. In recent research, the voxelization feature was used to characterize the local structural information of residues, but it may be insufficient for describing residue-level topological information. Design features that can further reflect residue-level topology when combined with deep learning methods are therefore crucial to improve the performance of model quality assessment.

RESULTS

We developed a deep-learning method, DeepUMQA, based on Ultrafast Shape Recognition (USR) for the residue-level single-model quality assessment. In the framework of the deep residual neural network, the residue-level USR feature was introduced to describe the topological relationship between the residue and overall structure by calculating the first moment of a set of residue distance sets and then combined with 1D, 2D and voxelization features to assess the quality of the model. Experimental results on the CASP13, CASP14 test datasets and CAMEO blind test show that USR could supplement the voxelization features to comprehensively characterize residue structure information and significantly improve model assessment accuracy. The performance of DeepUMQA ranks among the top during the state-of-the-art single-model quality assessment methods, including ProQ2, ProQ3, ProQ3D, Ornate, VoroMQA, ProteinGCN, ResNetQA, QDeep, GraphQA, ModFOLD6, ModFOLD7, ModFOLD8, QMEAN3, QMEANDisCo3 and DeepAccNet.

AVAILABILITY AND IMPLEMENTATION

The DeepUMQA server is freely available at http://zhanglab-bioinf.com/DeepUMQA/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

ZoomQA: residue-level protein model accuracy estimation with machine learning on sequential and 3D structural features

MOTIVATION

The Estimation of Model Accuracy problem is a cornerstone problem in the field of Bioinformatics. As of CASP14, there are 79 global QA methods, and a minority of 39 residue-level QA methods with very few of them working on protein complexes. Here, we introduce ZoomQA, a novel, single-model method for assessing the accuracy of a tertiary protein structure/complex prediction at residue level, which have many applications such as drug discovery. ZoomQA differs from others by considering the change in chemical and physical features of a fragment structure (a portion of a protein within a radius $r$ of the target amino acid) as the radius of contact increases. Fourteen physical and chemical properties of amino acids are used to build a comprehensive representation of every residue within a protein and grade their placement within the protein as a whole. Moreover, we have shown the potential of ZoomQA to identify problematic regions of the SARS-CoV-2 protein complex.

RESULTS

We benchmark ZoomQA on CASP14, and it outperforms other state-of-the-art local QA methods and rivals state of the art QA methods in global prediction metrics. Our experiment shows the efficacy of these new features and shows that our method is able to match the performance of other state-of-the-art methods without the use of homology searching against databases or PSSM matrices.

AVAILABILITY

http://zoomQA.renzhitech.com.

ProFitFun: a protein tertiary structure fitness function for quantifying the accuracies of model structures

MOTIVATION

An accurate estimation of the quality of protein model structures typifies as a cornerstone in protein structure prediction regimes. Despite the recent groundbreaking success in the field of protein structure prediction, there are certain prospects for the improvement in model quality estimation at multiple stages of protein structure prediction and thus, to further push the prediction accuracy. Here, a novel approach, named ProFitFun, for assessing the quality of protein models is proposed by harnessing the sequence and structural features of experimental protein structures in terms of the preferences of backbone dihedral angles and relative surface accessibility of their amino acid residues at the tripeptide level. The proposed approach leverages upon the backbone dihedral angle and surface accessibility preferences of the residues by accounting for its N-terminal and C-terminal neighbors in the protein structure. These preferences are used to evaluate protein structures through a machine learning approach and tested on an extensive dataset of diverse proteins.

RESULTS

The approach was extensively validated on a large test dataset (n = 25 005) of protein structures, comprising 23 661 models of 82 non-homologous proteins and 1344 non-homologous experimental structures. In addition, an external dataset of 40 000 models of 200 non-homologous proteins was also used for the validation of the proposed method. Both datasets were further used for benchmarking the proposed method with four different state-of-the-art methods for protein structure quality assessment. In the benchmarking, the proposed method outperformed some state-of-the-art methods in terms of Spearman's and Pearson's correlation coefficients, average GDT-TS loss, sum of z-scores and average absolute difference of predictions over corresponding observed values. The high accuracy of the proposed approach promises a potential use of the sequence and structural features in computational protein design.

AVAILABILITY AND IMPLEMENTATION

http://github.com/KYZ-LSB/ProTerS-FitFun.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Recent development of machine learning methods in sumoylation sites prediction

Sumoylation of proteins is an important reversible post-translational modification of proteins and mediates a variety of cellular processes. Sumo-modified proteins can change their subcellular localization, activity and stability. In addition, it also plays an important role in various cellular processes such as transcriptional regulation and signal transduction. The abnormal sumoylation is involved in many diseases, including neurodegeneration and immune-related diseases, as well as the development of cancer. Therefore, identification of the sumoylation site (SUMO site) is fundamental to understanding their molecular mechanisms and regulatory roles. In contrast to labor-intensive and costly experimental approaches, computational prediction of sumoylation sites in silico also attracted much attention for its accuracy, convenience and speed. At present, many computational prediction models have been used to identify SUMO sites, but these contents have not been comprehensively summarized and reviewed. Therefore, the research progress of relevant models is summarized and discussed in this paper. We will briefly summarize the development of bioinformatics methods on sumoylation site prediction. We will mainly focus on the benchmark dataset construction, feature extraction, machine learning method, published results and online tools. We hope the review will provide more help for wet-experimental scholars.

Improved estimation of model quality using predicted inter-residue distance

MOTIVATION

Protein model quality assessment (QA) is an essential component in protein structure prediction, which aims to estimate the quality of a structure model and/or select the most accurate model out from a pool of structure models, without knowing the native structure. QA remains a challenging task in protein structure prediction.

RESULTS

Based on the inter-residue distance predicted by the recent deep learning-based structure prediction algorithm trRosetta, we developed QDistance, a new approach to the estimation of both global and local qualities. QDistance works for both single-model and multi-models inputs. We designed several distance-based features to assess the agreement between the predicted and model-derived inter-residue distances. Together with a few widely used features, they are fed into a simple yet powerful linear regression model to infer the global QA scores. The local QA scores for each structure model are predicted based on a comparative analysis with a set of selected reference models. For multi-models input, the reference models are selected from the input based on the predicted global QA scores. For single-model input, the reference models are predicted by trRosetta. With the informative distance-based features, QDistance can predict the global quality with satisfactory accuracy. Benchmark tests on the CASP13 and the CAMEO structure models suggested that QDistance was competitive other methods. Blind tests in the CASP14 experiments showed that QDistance was robust and ranked among the top predictors. Especially, QDistance was the top 3 local QA method and made the most accurate local QA prediction for unreliable local region. Analysis showed that this superior performance can be attributed to the inclusion of the predicted inter-residue distance.

AVAILABILITY AND IMPLEMENTATION

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

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Empirical comparison and analysis of web-based cell-penetrating peptide prediction tools

Cell-penetrating peptides (CPPs) facilitate the delivery of therapeutically relevant molecules, including DNA, proteins and oligonucleotides, into cells both in vitro and in vivo. This unique ability explores the possibility of CPPs as therapeutic delivery and its potential applications in clinical therapy. Over the last few decades, a number of machine learning (ML)-based prediction tools have been developed, and some of them are freely available as web portals. However, the predictions produced by various tools are difficult to quantify and compare. In particular, there is no systematic comparison of the web-based prediction tools in performance, especially in practical applications. In this work, we provide a comprehensive review on the biological importance of CPPs, CPP database and existing ML-based methods for CPP prediction. To evaluate current prediction tools, we conducted a comparative study and analyzed a total of 12 models from 6 publicly available CPP prediction tools on 2 benchmark validation sets of CPPs and non-CPPs. Our benchmarking results demonstrated that a model from the KELM-CPPpred, namely KELM-hybrid-AAC, showed a significant improvement in overall performance, when compared to the other 11 prediction models. Moreover, through a length-dependency analysis, we find that existing prediction tools tend to more accurately predict CPPs and non-CPPs with the length of 20-25 residues long than peptides in other length ranges.

Review and comparative analysis of machine learning-based predictors for predicting and analyzing of anti-angiogenic peptides

Cancer is one of the leading causes of death worldwide and underlying this is angiogenesis that represents one of the hallmarks of cancer. Ongoing effort is already under way in the discovery of anti-angiogenic peptides (AAPs) as a promising therapeutic route by tackling the formation of new blood vessels. As such, the identification of AAPs constitutes a viable path for understanding their mechanistic properties pertinent for the discovery of new anti-cancer drugs. In spite of the abundance of peptide sequences in public databases, experimental efforts in the identification of anti-angiogenic peptides have progressed very slowly owing to its high expenditures and laborious nature. Owing to its inherent ability to make sense of large volumes of data, machine learning (ML) represents a lucrative technique that can be harnessed for peptide-based drug discovery. In this review, we conducted a comprehensive and comparative analysis of ML-based AAP predictors in terms of their employed feature descriptors, ML algorithms, cross-validation methods and prediction performance. Moreover, the common framework of these AAP predictors and their inherent weaknesses are also discussed. Particularly, we explore future perspectives for improving the prediction accuracy and model interpretability, which represents an interesting avenue for overcoming some of the inherent weaknesses of existing AAP predictors. We anticipate that this review would assist researchers in the rapid screening and identification of promising AAPs for clinical use.

Machine Learning Methods in Prediction of Protein Palmitoylation Sites: A Brief Review

Protein palmitoylation is a fundamental and reversible post-translational lipid modification that involves a series of biological processes. Although a large number of experimental studies have explored the molecular mechanism behind the palmitoylation process, the computational methods has attracted much attention for its good performance in predicting palmitoylation sites compared with expensive and time-consuming biochemical experiments. The prediction of protein palmitoylation sites is helpful to reveal its biological mechanism. Therefore, the research on the application of machine learning methods to predict palmitoylation sites has become a hot topic in bioinformatics and promoted the development in the related fields. In this review, we briefly introduced the recent development in predicting protein palmitoylation sites by using machine learningbased methods and discussed their benefits and drawbacks. The perspective of machine learning-based methods in predicting palmitoylation sites was also provided. We hope the review could provide a guide in related fields.

In Silico Approaches for the Prediction and Analysis of Antiviral Peptides: A Review

In light of the growing resistance toward current antiviral drugs, efforts to discover novel and effective antiviral therapeutic agents remain a pressing scientific effort. Antiviral peptides (AVPs) represent promising therapeutic agents due to their extraordinary advantages in terms of potency, efficacy and pharmacokinetic properties. The growing volume of newly discovered peptide sequences in the post-genomic era requires computational approaches for timely and accurate identification of AVPs. Machine learning (ML) methods such as random forest and support vector machine represent robust learning algorithms that are instrumental in successful peptide-based drug discovery. Therefore, this review summarizes the current state-of-the-art application of ML methods for identifying AVPs directly from the sequence information. We compare the efficiency of these methods in terms of the underlying characteristics of the dataset used along with feature encoding methods, ML algorithms, cross-validation methods and prediction performance. Finally, guidelines for the development of robust AVP models are also discussed. It is anticipated that this review will serve as a useful guide for the design and development of robust AVP and related therapeutic peptide predictors in the future.

Recent development of bioinformatics tools for microRNA target prediction

MicroRNAs (miRNAs) are central players that regulate the post-transcriptional processes of gene expression. Binding of miRNAs to target mRNAs can repress their translation by inducing the degradation or by inhibiting the translation of the target mRNAs. High-throughput experimental approaches for miRNA target identification are costly and time-consuming, depending on various factors. It is vitally important to develop the bioinformatics methods for accurately predicting miRNA targets. With the increase of RNA sequences in the post-genomic era, bioinformatics methods are being developed for miRNA studies specially for miRNA target prediction. This review summarizes the current development of state-of-the-art bioinformatics tools for miRNA target prediction, points out the progress and limitations of the available miRNA databases, and their working principles. Finally, we discuss the caveat and perspectives of the next-generation algorithms for the prediction of miRNA targets.

iDNA6mA-Rice-DL: A local web server for identifying DNA N6-methyladenine sites in rice genome by deep learning method

Accurate detection of N6-methyladenine (6mA) sites by biochemical experiments will help to reveal their biological functions, still, these wet experiments are laborious and expensive. Therefore, it is necessary to introduce a powerful computational model to identify the 6mA sites on a genomic scale, especially for plant genomes. In view of this, we proposed a model called iDNA6mA-Rice-DL for the effective identification of 6mA sites in rice genome, which is an intelligent computing model based on deep learning method. Traditional machine learning methods assume the preparation of the features for analysis. However, our proposed model automatically encodes and extracts key DNA features through an embedded layer and several groups of dense layers. We use an independent dataset to evaluate the generalization ability of our model. An area under the receiver operating characteristic curve (auROC) of 0.98 with an accuracy of 95.96% was obtained. The experiment results demonstrate that our model had good performance in predicting 6mA sites in the rice genome. A user-friendly local web server has been established. The Docker image of the local web server can be freely downloaded at https://hub.docker.com/r/his1server/idna6ma-rice-dl.

Improved barnacles mating optimizer algorithm for feature selection and support vector machine optimization

With the rapid development of computer technology, data collection becomes easier, and data object presents more complex. Data analysis method based on machine learning is an important, active, and multi-disciplinarily research field. Support vector machine (SVM) is one of the most powerful and fast classification models. The main challenges SVM faces are the selection of feature subset and the setting of kernel parameters. To improve the performance of SVM, a metaheuristic algorithm is used to optimize them simultaneously. This paper first proposes a novel classification model called IBMO-SVM, which hybridizes an improved barnacle mating optimizer (IBMO) with SVM. Three strategies, including Gaussian mutation, logistic model, and refraction-learning, are used to improve the performance of BMO from different perspectives. Through 23 classical benchmark functions, the impact of control parameters and the effectiveness of introduced strategies are analyzed. The convergence accuracy and stability are the main gains, and exploration and exploitation phases are more properly balanced. We apply IBMO-SVM to 20 real-world datasets, including 4 extremely high-dimensional datasets. Experimental results are compared with 6 state-of-the-art methods in the literature. The final statistical results show that the proposed IBMO-SVM achieves a better performance than the standard BMO-SVM and other compared methods, especially on high-dimensional datasets. In addition, the proposed model also shows significant superiority compared with 4 other classifiers.

Representations of protein structure for exploring the conformational space: A speed-accuracy trade-off

•

We compare ten structural representations, either atomistic or coarse-grained.

•

Thus, ten distance-dependent statistical potentials of mean force (PMF) were built.

•

The Cβ-only and Cα + Cβ representations provide the best speed–accuracy trade-off.

•

Including glycines through Cα, in a Cβ-only representation, yields a higher accuracy.

•

We generalize the conclusions to the total information gain (TIG) scoring function.

The recent breakthrough in the field of protein structure prediction shows the relevance of using knowledge-based based scoring functions in combination with a low-resolution 3D representation of protein macromolecules. The choice of not using all atoms is barely supported by any data in the literature, and is mostly motivated by empirical and practical reasons, such as the computational cost of assessing the numerous folds of the protein conformational space. Here, we present a comprehensive study, carried on a large and balanced benchmark of predicted protein structures, to see how different types of structural representations rank in either accuracy or calculation speed, and which ones offer the best compromise between these two criteria. We tested ten representations, including low-resolution, high-resolution, and coarse-grained approaches. We also investigated the generalization of the findings to other formalisms than the widely-used “potential of mean force” (PMF) method. Thus, we observed that representing protein structures by their β carbons—combined or not with Cα—provides the best speed–accuracy trade-off, when using a “total information gain” scoring function. For statistical PMFs, using MARTINI backbone and side-chains beads is the best option. Finally, we also demonstrated the necessity of training the reference state on all atom types, and of including the Cα atoms of glycine residues, in a Cβ-based representation.

QDeep: distance-based protein model quality estimation by residue-level ensemble error classifications using stacked deep residual neural networks

MOTIVATION

Protein model quality estimation, in many ways, informs protein structure prediction. Despite their tight coupling, existing model quality estimation methods do not leverage inter-residue distance information or the latest technological breakthrough in deep learning that has recently revolutionized protein structure prediction.

RESULTS

We present a new distance-based single-model quality estimation method called QDeep by harnessing the power of stacked deep residual neural networks (ResNets). Our method first employs stacked deep ResNets to perform residue-level ensemble error classifications at multiple predefined error thresholds, and then combines the predictions from the individual error classifiers for estimating the quality of a protein structural model. Experimental results show that our method consistently outperforms existing state-of-the-art methods including ProQ2, ProQ3, ProQ3D, ProQ4, 3DCNN, MESHI, and VoroMQA in multiple independent test datasets across a wide-range of accuracy measures; and that predicted distance information significantly contributes to the improved performance of QDeep.

AVAILABILITY AND IMPLEMENTATION

https://github.com/Bhattacharya-Lab/QDeep.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

An Effective Hybrid Approach for Forecasting Currency Exchange Rates

Accurately forecasting the movement of exchange rates is of interest in a variety of fields, such as international business, financial management, and monetary policy, though this is not an easy task due to dramatic fluctuations caused by political and economic events. In this study, we develop a new forecasting approach referred to as FSPSOSVR, which is able to accurately predict exchange rates by combining particle swarm optimization (PSO), random forest feature selection, and support vector regression (SVR). PSO is used to obtain the optimal SVR parameters for predicting exchange rates. Our analysis involves the monthly exchange rates from January 1971 to December 2017 of seven countries including Australia, Canada, China, the European Union, Japan, Taiwan, and the United Kingdom. The out-of-sample forecast performance of the FSPSOSVR algorithm is compared with six competing forecasting models using the mean absolute percentage error (MAPE) and root mean square error (RMSE), including random walk, exponential smoothing, autoregressive integrated moving average (ARIMA), seasonal ARIMA, SVR, and PSOSVR. Our empirical results show that the FSPSOSVR algorithm consistently yields excellent predictive accuracy, which compares favorably with competing models for all currencies. These findings suggest that the proposed algorithm is a promising method for the empirical forecasting of exchange rates. Finally, we show the empirical relevance of exchange rate forecasts arising from FSPSOSVR by use of foreign exchange carry trades and find that the proposed trading strategies can deliver positive excess returns of more than 3% per annum for most currencies, except for AUD and NTD.

VoroCNN: Deep convolutional neural network built on 3D Voronoi tessellation of protein structures

MOTIVATION

Effective use of evolutionary information has recently led to tremendous progress in computational prediction of three-dimensional (3D) structures of proteins and their complexes. Despite the progress, the accuracy of predicted structures tends to vary considerably from case to case. Since the utility of computational models depends on their accuracy, reliable estimates of deviation between predicted and native structures are of utmost importance.

RESULTS

For the first time, we present a deep convolutional neural network (CNN) constructed on a Voronoi tessellation of 3D molecular structures. Despite the irregular data domain, our data representation allows us to efficiently introduce both convolution and pooling operations and train the network in an end-to-end fashion without precomputed descriptors. The resultant model, VoroCNN, predicts local qualities of 3D protein folds. The prediction results are competitive to state of the art and superior to the previous 3D CNN architectures built for the same task. We also discuss practical applications of VoroCNN, for example, in recognition of protein binding interfaces.

AVAILABILITY

The model, data, and evaluation tests are available at https://team.inria.fr/nano-d/software/vorocnn/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Unsupervised multi-instance learning for protein structure determination

Many regions of the protein universe remain inaccessible by wet-laboratory or computational structure determination methods. A significant challenge in elucidating these dark regions in silico relates to the ability to discriminate relevant structure(s) among many structures/decoys computed for a protein of interest, a problem known as decoy selection. Clustering decoys based on geometric similarity remains popular. However, it is unclear how exactly to exploit the groups of decoys revealed via clustering to select individual structures for prediction. In this paper, we provide an intuitive formulation of the decoy selection problem as an instance of unsupervised multi-instance learning. We address the problem in three stages, first organizing given decoys of a protein molecule into bags, then identifying relevant bags, and finally drawing individual instances from these bags to offer as prediction. We propose both non-parametric and parametric algorithms for drawing individual instances. Our evaluation utilizes two datasets, one benchmark dataset of ensembles of decoys for a varied list of protein molecules, and a dataset of decoy ensembles for targets drawn from recent CASP competitions. A comparative analysis with state-of-the-art methods reveals that the proposed approach outperforms existing methods, thus warranting further investigation of multi-instance learning to advance our treatment of decoy selection.

ApoPred: Identification of Apolipoproteins and Their Subfamilies With Multifarious Features

Apolipoprotein is a group of plasma proteins that are associated with a variety of diseases, such as hyperlipidemia, atherosclerosis, Alzheimer’s disease, and diabetes. In order to investigate the function of apolipoproteins and to develop effective targets for related diseases, it is necessary to accurately identify and classify apolipoproteins. Although it is possible to identify apolipoproteins accurately through biochemical experiments, they are expensive and time-consuming. This work aims to establish a high-efficiency and high-accuracy prediction model for recognition of apolipoproteins and their subfamilies. We firstly constructed a high-quality benchmark dataset including 270 apolipoproteins and 535 non-apolipoproteins. Based on the dataset, pseudo-amino acid composition (PseAAC) and composition of k-spaced amino acid pairs (CKSAAP) were used as input vectors. To improve the prediction accuracy and eliminate redundant information, analysis of variance (ANOVA) was used to rank the features. And the incremental feature selection was utilized to obtain the best feature subset. Support vector machine (SVM) was proposed to construct the classification model, which could produce the accuracy of 97.27%, sensitivity of 96.30%, and specificity of 97.76% for discriminating apolipoprotein from non-apolipoprotein in 10-fold cross-validation. In addition, the same process was repeated to generate a new model for predicting apolipoprotein subfamilies. The new model could achieve an overall accuracy of 95.93% in 10-fold cross-validation. According to our proposed model, a convenient webserver called ApoPred was established, which can be freely accessed at http://tang-biolab.com/server/ApoPred/service.html. We expect that this work will contribute to apolipoprotein function research and drug development in relevant diseases.

Approaches for the discovery of new cell-penetrating peptides

Introduction: The capability of cell-penetrating peptides (CPP), also known as protein transduction domains (PTD), to enter into cells possibly with an attached cargo, makes their application as delivery vectors or as direct therapeutics compelling. They are generally biocompatible, nontoxic, and easy to synthesize and modify. Three decades after the discovery of the first CPPs, ~2,000 CPP sequences have been identified, and many more predicted. Nevertheless, the field has a strong commitment to authenticate new, more efficient, and specific CPPs.Areas covered: Although a scattering of CPPs have been found by chance, various systematic approaches have been developed and refined over the years to directly aid the identification and depiction of new peptide-based delivery vectors or therapeutics. Here, the authors give an overview of CPPs, and review various approaches of discovering new ones. An emphasis is placed on in silico methods, as these have advanced rapidly in recent years.Expert opinion: Although there are many known CPPs, there is a need to find more efficient and specific CPPs. Several approaches are used to identify such sequences. The success of these approaches depends on the advancement of others and the successful prediction of CPP sequences relies on experimental data.

An information gain-based approach for evaluating protein structure models

For three decades now, knowledge-based scoring functions that operate through the "potential of mean force" (PMF) approach have continuously proven useful for studying protein structures. Although these statistical potentials are not to be confused with their physics-based counterparts of the same name-i.e. PMFs obtained by molecular dynamics simulations-their particular success in assessing the native-like character of protein structure predictions has lead authors to consider the computed scores as approximations of the free energy. However, this physical justification is a matter of controversy since the beginning. Alternative interpretations based on Bayes' theorem have been proposed, but the misleading formalism that invokes the inverse Boltzmann law remains recurrent in the literature. In this article, we present a conceptually new method for ranking protein structure models by quality, which is (i) independent of any physics-based explanation and (ii) relevant to statistics and to a general definition of information gain. The theoretical development described in this study provides new insights into how statistical PMFs work, in comparison with our approach. To prove the concept, we have built interatomic distance-dependent scoring functions, based on the former and new equations, and compared their performance on an independent benchmark of 60,000 protein structures. The results demonstrate that our new formalism outperforms statistical PMFs in evaluating the quality of protein structural decoys. Therefore, this original type of score offers a possibility to improve the success of statistical PMFs in the various fields of structural biology where they are applied. The open-source code is available for download at https://gitlab.rpbs.univ-paris-diderot.fr/src/ig-score.

Pair Potentials as Machine Learning Features

Atom pairwise potential functions make up an essential part of many scoring functions for protein decoy detection. With the development of machine learning (ML) tools, there are multiple ways to combine potential functions to create novel ML models and methods. Potential function parameters can be easily extracted; however, it is usually hard to directly obtain the calculated atom pairwise energies from scoring functions. Amber, as one of the most popular suites of modeling programs, has an extensive history and library of force field potential functions. In this work, we directly used the force field parameters in ff94 and ff14SB from Amber and encoded them to calculate atom pairwise energies for different interactions. Two sets of structures (single amino acid set and a dipeptide set) were used to evaluate the performance of our encoded Amber potentials. From the comparison results between energy terms obtained from our encoding and Amber, we find energy difference within ±0.06 kcal/mol for all tested structures. Previously we have shown that the Random Forest (RF) model can help to emphasize more important atom pairwise interactions and ignore insignificant ones [Pei, J.; Zheng, Z.; Merz, K. M. J. Chem. Inf. Model. 2019, 59, 1919-1929]. Here, as an example of combining ML methods with traditional potential functions, we followed the same work flow to combine the RF models with force field potential functions from Amber. To determine the performance of our RF models with force field potential functions, 224 different protein native-decoy systems were used as our training and testing sets We find that the RF models with ff94 and ff14SB force field parameters outperformed all other scoring functions (RF models with KECSA2, RWplus, DFIRE, dDFIRE, and GOAP) considered in this work for native structure detection, and they performed similarly in detecting the best decoy. Through inclusion of best decoy to decoy comparisons in building our RF models, we were able to generate models that outperformed the score functions tested herein both on accuracy and best decoy detection, again showing the performance and flexibility of our RF models to tackle this problem. Finally, the importance of the RF algorithm and force field parameters were also tested and the comparison results suggest that both the RF algorithm and force field potentials are important with the ML scoring function achieving its best performance only by combining them together. All code and data used in this work are available at https://github.com/JunPei000/FFENCODER_for_Protein_Folding_Pose_Selection.

Predicting Gram-Positive Bacterial Protein Subcellular Location by Using Combined Features

There are a lot of bacteria in the environment, and Gram-positive bacteria are the most common ones. Some Gram-positive bacteria are very harmful to the human body, so it is significant to predict Gram-positive bacterial protein subcellular location. And identification of Gram-positive bacterial protein subcellular location is important for developing effective drugs. In this paper, a new Gram-positive bacterial protein subcellular location dataset was established. The amino acid composition, the gene ontology annotation information, the hydropathy dipeptide composition information, the amino acid dipeptide composition information, and the autocovariance average chemical shift information were selected as characteristic parameters, then these parameters were combined. The locations of Gram-positive bacterial proteins were predicted by the Support Vector Machine (SVM) algorithm, and the overall accuracy (OA) reached 86.1% under the Jackknife test. The overall accuracy (OA) in our predictive model was higher than those in existing methods. This improved method may be helpful for protein function prediction.

Prediction of N7-methylguanosine sites in human RNA based on optimal sequence features

N-7 methylguanosine (m7G) modification is a ubiquitous post-transcriptional RNA modification which is vital for maintaining RNA function and protein translation. Developing computational tools will help us to easily predict the m7G sites in RNA sequence. In this work, we designed a sequence-based method to identify the modification site in human RNA sequences. At first, several kinds of sequence features were extracted to code m7G and non-m7G samples. Subsequently, we used mRMR, F-score, and Relief to obtain the optimal subset of features which could produce the maximum prediction accuracy. In 10-fold cross-validation, results showed that the highest accuracy is 94.67% achieved by support vector machine (SVM) for identifying m7G sites in human genome. In addition, we examined the performances of other algorithms and found that the SVM-based model outperformed others. The results indicated that the predictor could be a useful tool for studying m7G. A prediction model is available at https://github.com/MapFM/m7g_model.git.

iRNAD: a computational tool for identifying D modification sites in RNA sequence

MOTIVATION

Dihydrouridine (D) is a common RNA post-transcriptional modification found in eukaryotes, bacteria and a few archaea. The modification can promote the conformational flexibility of individual nucleotide bases. And its levels are increased in cancerous tissues. Therefore, it is necessary to detect D in RNA for further understanding its functional roles. Since wet-experimental techniques for the aim are time-consuming and laborious, it is urgent to develop computational models to identify D modification sites in RNA.

RESULTS

We constructed a predictor, called iRNAD, for identifying D modification sites in RNA sequence. In this predictor, the RNA samples derived from five species were encoded by nucleotide chemical property and nucleotide density. Support vector machine was utilized to perform the classification. The final model could produce the overall accuracy of 96.18% with the area under the receiver operating characteristic curve of 0.9839 in jackknife cross-validation test. Furthermore, we performed a series of validations from several aspects and demonstrated the robustness and reliability of the proposed model.

AVAILABILITY AND IMPLEMENTATION

A user-friendly web-server called iRNAD can be freely accessible at http://lin-group.cn/server/iRNAD, which will provide convenience and guide to users for further studying D modification.

MASS: predict the global qualities of individual protein models using random forests and novel statistical potentials

BACKGROUND

Protein model quality assessment (QA) is an essential procedure in protein structure prediction. QA methods can predict the qualities of protein models and identify good models from decoys. Clustering-based methods need a certain number of models as input. However, if a pool of models are not available, methods that only need a single model as input are indispensable.

RESULTS

We developed MASS, a QA method to predict the global qualities of individual protein models using random forests and various novel energy functions. We designed six novel energy functions or statistical potentials that can capture the structural characteristics of a protein model, which can also be used in other protein-related bioinformatics research. MASS potentials demonstrated higher importance than the energy functions of RWplus, GOAP, DFIRE and Rosetta when the scores they generated are used as machine learning features. MASS outperforms almost all of the four CASP11 top-performing single-model methods for global quality assessment in terms of all of the four evaluation criteria officially used by CASP, which measure the abilities to assign relative and absolute scores, identify the best model from decoys, and distinguish between good and bad models. MASS has also achieved comparable performances with the leading QA methods in CASP12 and CASP13.

CONCLUSIONS

MASS and the source code for all MASS potentials are publicly available at http://dna.cs.miami.edu/MASS/ .

mAHTPred: a sequence-based meta-predictor for improving the prediction of anti-hypertensive peptides using effective feature representation

MOTIVATION

Cardiovascular disease is the primary cause of death globally accounting for approximately 17.7 million deaths per year. One of the stakes linked with cardiovascular diseases and other complications is hypertension. Naturally derived bioactive peptides with antihypertensive activities serve as promising alternatives to pharmaceutical drugs. So far, there is no comprehensive analysis, assessment of diverse features and implementation of various machine-learning (ML) algorithms applied for antihypertensive peptide (AHTP) model construction.

RESULTS

In this study, we utilized six different ML algorithms, namely, Adaboost, extremely randomized tree (ERT), gradient boosting (GB), k-nearest neighbor, random forest (RF) and support vector machine (SVM) using 51 feature descriptors derived from eight different feature encodings for the prediction of AHTPs. While ERT-based trained models performed consistently better than other algorithms regardless of various feature descriptors, we treated them as baseline predictors, whose predicted probability of AHTPs was further used as input features separately for four different ML-algorithms (ERT, GB, RF and SVM) and developed their corresponding meta-predictors using a two-step feature selection protocol. Subsequently, the integration of four meta-predictors through an ensemble learning approach improved the balanced prediction performance and model robustness on the independent dataset. Upon comparison with existing methods, mAHTPred showed superior performance with an overall improvement of approximately 6-7% in both benchmarking and independent datasets.

AVAILABILITY AND IMPLEMENTATION

The user-friendly online prediction tool, mAHTPred is freely accessible at http://thegleelab.org/mAHTPred.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Recent Advances in Computational Methods for Identifying Anticancer Peptides

Anticancer peptide (ACP) is a kind of small peptides that can kill cancer cells without damaging normal cells. In recent years, ACP has been pre-clinically used for cancer treatment. Therefore, accurate identification of ACPs will promote their clinical applications. In contrast to labor-intensive experimental techniques, a series of computational methods have been proposed for identifying ACPs. In this review, we briefly summarized the current progress in computational identification of ACPs. The challenges and future perspectives in developing reliable methods for identification of ACPs were also discussed. We anticipate that this review could provide novel insights into future researches on anticancer peptides.

A Survey for Predicting Enzyme Family Classes Using Machine Learning Methods

Enzymes are proteins that act as biological catalysts to speed up cellular biochemical processes. According to their main Enzyme Commission (EC) numbers, enzymes are divided into six categories: EC-1: oxidoreductase; EC-2: transferase; EC-3: hydrolase; EC-4: lyase; EC-5: isomerase and EC-6: synthetase. Different enzymes have different biological functions and acting objects. Therefore, knowing which family an enzyme belongs to can help infer its catalytic mechanism and provide information about the relevant biological function. With the large amount of protein sequences influxing into databanks in the post-genomics age, the annotation of the family for an enzyme is very important. Since the experimental methods are cost ineffective, bioinformatics tool will be a great help for accurately classifying the family of the enzymes. In this review, we summarized the application of machine learning methods in the prediction of enzyme family from different aspects. We hope that this review will provide insights and inspirations for the researches on enzyme family classification.

Redundancy-weighting the PDB for detailed secondary structure prediction using deep-learning models

MOTIVATION

The Protein Data Bank (PDB), the ultimate source for data in structural biology, is inherently imbalanced. To alleviate biases, virtually all structural biology studies use nonredundant (NR) subsets of the PDB, which include only a fraction of the available data. An alternative approach, dubbed redundancy-weighting (RW), down-weights redundant entries rather than discarding them. This approach may be particularly helpful for machine-learning (ML) methods that use the PDB as their source for data. Methods for secondary structure prediction (SSP) have greatly improved over the years with recent studies achieving above 70% accuracy for eight-class (DSSP) prediction. As these methods typically incorporate ML techniques, training on RW datasets might improve accuracy, as well as pave the way toward larger and more informative secondary structure classes.

RESULTS

This study compares the SSP performances of deep-learning models trained on either RW or NR datasets. We show that training on RW sets consistently results in better prediction of 3- (HCE), 8- (DSSP) and 13-class (STR2) secondary structures.

AVAILABILITY AND IMPLEMENTATION

The ML models, the datasets used for their derivation and testing, and a stand-alone SSP program for DSSP and STR2 predictions, are freely available under LGPL license in http://meshi1.cs.bgu.ac.il/rw.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Sequence Alignment Using Machine Learning for Accurate Template-based Protein Structure Prediction

Template-based modeling, the process of predicting the tertiary structure of a protein by using homologous protein structures, is useful when good templates can be available. Indeed, modern homology detection methods can find remote homologs with high sensitivity. However, the accuracy of template-based models generated from the homology-detection-based alignments is often lower than that from ideal alignments. In this study, we propose a new method that generates pairwise sequence alignments for more accurate template-based modeling. Our method trains a machine learning model using the structural alignment of known homologs. When calculating sequence alignments, instead of a fixed substitution matrix, this method dynamically predicts a substitution score from the trained model.

Anomaly Detection-Based Recognition of Near-Native Protein Structures

The three-dimensional structures populated by a protein molecule determine to a great extent its biological activities. The rich information encoded by protein structure on protein function continues to motivate the development of computational approaches for determining functionally-relevant structures. The majority of structures generated in silico are not relevant. Discriminating relevant/native protein structures from non-native ones is an outstanding challenge in computational structural biology. Inherently, this is a recognition problem that can be addressed under the umbrella of machine learning. In this paper, based on the premise that near-native structures are effectively anomalies, we build on the concept of anomaly detection in machine learning. We propose methods that automatically select relevant subsets, as well as methods that select a single structure to offer as prediction. Evaluations are carried out on benchmark datasets and demonstrate that the proposed methods advance the state of the art. The presented results motivate further building on and adapting concepts and techniques from machine learning to improve recognition of near-native structures in protein structure prediction.

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.

Early Diagnosis of Hepatocellular Carcinoma Using Machine Learning Method

Hepatocellular carcinoma (HCC) is a serious cancer which ranked the fourth in cancer-related death worldwide. Hence, more accurate diagnostic models are urgently needed to aid the early HCC diagnosis under clinical scenarios and thus improve HCC treatment and survival. Several conventional methods have been used for discriminating HCC from cirrhosis tissues in patients without HCC (CwoHCC). However, the recognition successful rates are still far from satisfactory. In this study, we applied a computational approach that based on machine learning method to a set of microarray data generated from 1091 HCC samples and 242 CwoHCC samples. The within-sample relative expression orderings (REOs) method was used to extract numerical descriptors from gene expression profiles datasets. After removing the unrelated features by using maximum redundancy minimum relevance (mRMR) with incremental feature selection, we achieved “11-gene-pair” which could produce outstanding results. We further investigated the discriminate capability of the “11-gene-pair” for HCC recognition on several independent datasets. The wonderful results were obtained, demonstrating that the selected gene pairs can be signature for HCC. The proposed computational model can discriminate HCC and adjacent non-cancerous tissues from CwoHCC even for minimum biopsy specimens and inaccurately sampled specimens, which can be practical and effective for aiding the early HCC diagnosis at individual level.

Extremely-randomized-tree-based Prediction of N6-Methyladenosine Sites in Saccharomyces cerevisiae

Introduction

N⁶-methyladenosine (m6A) is one of the most common post-transcriptional modifications in RNA, which has been related to several biological processes. The accurate prediction of m6A sites from RNA sequences is one of the challenging tasks in computational biology. Several computational methods utilizing machine-learning algorithms have been proposed that accelerate in silico screening of m6A sites, thereby drastically reducing the experimental time and labor costs involved.

Methodology

In this study, we proposed a novel computational predictor termed ERT-m6Apred, for the accurate prediction of m6A sites. To identify the feature encodings with more discriminative capability, we applied a two-step feature selection technique on seven different feature encodings and identified the corresponding optimal feature set.

Results

Subsequently, performance comparison of the corresponding optimal feature set-based extremely randomized tree model revealed that Pseudo k-tuple composition encoding, which includes 14 physicochemical properties significantly outperformed other encodings. Moreover, ERT-m6Apred achieved an accuracy of 78.84% during cross-validation analysis, which is comparatively better than recently reported predictors.

Conclusion

In summary, ERT-m6Apred predicts Saccharomyces cerevisiae m6A sites with higher accuracy, thus facilitating biological hypothesis generation and experimental validations.

A Brief Survey of Machine Learning Methods in Identification of Mitochondria Proteins in Malaria Parasite

The number of human deaths caused by malaria is increasing day-by-day. In fact, the mitochondrial proteins of the malaria parasite play vital roles in the organism. For developing effective drugs and vaccines against infection, it is necessary to accurately identify mitochondrial proteins of the malaria parasite. Although precise details for the mitochondrial proteins can be provided by biochemical experiments, they are expensive and time-consuming. In this review, we summarized the machine learning-based methods for mitochondrial proteins identification in the malaria parasite and compared the construction strategies of these computational methods. Finally, we also discussed the future development of mitochondrial proteins recognition with algorithms.

A Bioinformatics Tool for the Prediction of DNA N6-Methyladenine Modifications Based on Feature Fusion and Optimization Protocol

DNA N⁶-methyladenine (6mA) is closely involved with various biological processes. Identifying the distributions of 6mA modifications in genome-scale is of great significance to in-depth understand the functions. In recent years, various experimental and computational methods have been proposed for this purpose. Unfortunately, existing methods cannot provide accurate and fast 6mA prediction. In this study, we present 6mAPred-FO, a bioinformatics tool that enables researchers to make predictions based on sequences only. To sufficiently capture the characteristics of 6mA sites, we integrate the sequence-order information with nucleotide positional specificity information for feature encoding, and further improve the feature representation capacity by analysis of variance-based feature optimization protocol. The experimental results show that using this feature protocol, we can significantly improve the predictive performance. Via further feature analysis, we found that the sequence-order information and positional specificity information are complementary to each other, contributing to the performance improvement. On the other hand, the improvement is also due to the use of the feature optimization protocol, which is capable of effectively capturing the most informative features from the original feature space. Moreover, benchmarking comparison results demonstrate that our 6mAPred-FO outperforms several existing predictors. Finally, we establish a web-server that implements the proposed method for convenience of researchers' use, which is currently available at http://server.malab.cn/6mAPred-FO.