QAcon: single model quality assessment using protein structural and contact information with machine learning techniques

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.

G-ACP: a machine learning approach to the prediction of therapeutic peptides for gastric cancer

Conventional Gastrointestinal (GI) cancer treatments are quite expensive and have major hazards. Nowadays, a different strategy places more emphasis on creating tiny biologically active peptides that do not cause severe poisoning. Anticancer peptides (ACPs) are found through experimental screening, which is time-dependent and frequently fraught with difficulties. Gastric ACPs are emerging as a promising GI cancer treatment in the current day. It is crucial to identify novel gastric ACPs to have an improved knowledge of their functioning processes and treatment of gastric cancer. As a result of the post-genomic era's massive production of peptide sequences, rapid and effective ACPs using a computational method are essential. Several adaptive statistical techniques for distinguishing ACPs and non-ACPs have recently been developed. A variety of adapted statistically significant methods have been developed to differentiate between ACPs and non-ACPs. Despite significant progress, there is no specific model for the prediction of gastric ACPs because the specific model will predict a particular type of peptide more accurately and quickly. To overcome this, an initiative is taken for the creation of a reliable framework for the accurate identification of gastric ACPs. The current technique in particular contains four possible features along with one hybrid feature encoding mechanisms which are the target-class motif previously indicated by Amino Acid Composition, Dipeptide Composition, Tripeptide Composition (TPC), Pseudo Amino Acid Composition (PAAC), and their Hybrid. Machine Learning algorithms make high-performance and accurate prediction tools. Moreover, highly variable and ideal deep feature selection is done using an ANOVA-based F score for feature pruning. Experiments on a range of algorithms are carried out to identify the optimal operating strategy due to the diverse nature of learning. Following analysis of the empirical results, Naïve Bayes with TPC and Hybrid feature space outperforms other methods with 0.99 accuracy score on the testing dataset. To find the model generalization an external validation is carried out. In external datasets, the Extra Trees with PAAC features outperforms with the accuracy of 0.94. The comparison study shows that our suggested model will predict gastric ACPs more accurately and will be useful in drug development and gastric cancer. The predictive model can be freely accessed at https://github.com/humeraazad10/G-ACP.git.Communicated by Ramaswamy H. Sarma.

Estimating protein complex model accuracy based on ultrafast shape recognition and deep learning in CASP15

This article reports and analyzes the results of protein complex model accuracy estimation by our methods (DeepUMQA3 and GraphGPSM) in the 15th Critical Assessment of techniques for protein Structure Prediction (CASP15). The new deep learning-based multimeric complex model accuracy estimation methods are proposed based on the ensemble of three-level features coupling with deep residual/graph neural networks. For the input multimeric complex model, we describe it from three levels: overall complex features, intra-monomer features, and inter-monomer features. We designed an overall ultrafast shape recognition (USR) to characterize the relationship between local residues and the overall complex topology, and an inter-monomer USR to characterize the relationship between the residues of one monomer and the topology of other monomers. DeepUMQA3 (Group name: GuijunLab-RocketX) ranked first in the interface residue accuracy estimation of CASP15. The Pearson correlation between the interface residue Local Distance Difference Test (lDDT) predicted by DeepUMQA3 and the real lDDT is 0.570, the only method that exceeds 0.5. Among the top 5 methods, DeepUMQA3 achieved the highest Pearson correlation of lDDT on 25 out of 39 targets. GraphGPSM (Group name: GuijunLab-PAthreader) has TM-score Pearson correlations greater than 0.9 on 14 targets, showing a good ability to estimate the overall fold accuracy. The DeepUMQA3 server is available at http://zhanglab-bioinf.com/DeepUMQA/ and the GraphGPSM server is available at http://zhanglab-bioinf.com/GraphGPSM/.

DeepUMQA3: a web server for accurate assessment of interface residue accuracy in protein complexes

MOTIVATION

Model quality assessment is a crucial part of protein structure prediction and a gateway to proper usage of models in biomedical applications. Many methods have been proposed for assessing the quality of structural models of protein monomers, but few methods for evaluating protein complex models. As protein complex structure prediction becomes a new challenge, there is an urgent need for model quality assessment methods that can accurately assess the accuracy of interface residues of complex structures.

RESULTS

Here, we present DeepUMQA3, a web server for evaluating the accuracy of interface residues of protein complex structures using deep neural networks. For an input complex structure, features are extracted from three levels of overall complex, intra-monomer, and inter-monomer, and an improved deep residual neural network is used to predict per-residue lDDT and interface residue accuracy. DeepUMQA3 ranks first in the blind test of interface residue accuracy estimation in CASP15, with Pearson, Spearman, and AUC of 0.564, 0.535, and 0.755 under the lDDT measurement, which are 17.6%, 23.6%, and 10.9% higher than the second best method, respectively. DeepUMQA3 can also assess the accuracy of all residues in the entire complex and distinguish high- and low-precision residues.

AVAILABILITY AND IMPLEMENTATION

The web sever of DeepUMQA3 are freely available at http://zhanglab-bioinf.com/DeepUMQA_server/.

Predicting mechanical properties of silk from its amino acid sequences via machine learning

The silk fiber is increasingly being sought for its superior mechanical properties, biocompatibility, and eco-friendliness, making it promising as a base material for various applications. One of the characteristics of protein fibers, such as silk, is that their mechanical properties are significantly dependent on the amino acid sequence. Numerous studies have been conducted to determine the specific relationship between the amino acid sequence of silk and its mechanical properties. Still, the relationship between the amino acid sequence of silk and its mechanical properties is yet to be clarified. Other fields have adopted machine learning (ML) to establish a relationship between the inputs, such as the ratio of different input material compositions and the resulting mechanical properties. We have proposed a method to convert the amino acid sequence into numerical values for input and succeeded in predicting the mechanical properties of silk from its amino acid sequences. Our study sheds light on predicting mechanical properties of silk fiber from respective amino acid sequences.

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.

Deep neural learning based protein function prediction

It is vital for the annotation of uncharacterized proteins by protein function prediction. At present, Deep Neural Network based protein function prediction is mainly carried out for dataset of small scale proteins or Gene Ontology, and usually explore the relationships between single protein feature and function tags. The practical methods for large-scale multi-features protein prediction still need to be studied in depth. This paper proposes a DNN based protein function prediction approach IGP-DNN. This method uses Grasshopper Optimization Algorithm (GOA) and Intuitionistic Fuzzy c-Means clustering (IFCM) based protein function modules extracting algorithm to extract the features of protein modules, utilizing Kernel Principal Component Analysis (KPCA) method to reduce the dimensionality of the protein attribute information, and integrating module features and attribute features. Inputting integrated data into DNN through multiple hidden layers to classify proteins and predict protein functions. In the experiments, the F-measure value of IGP-DNN on the DIP dataset reaches 0.4436, which shows better performance.

MUfoldQA_G: High-accuracy protein model QA via retraining and transformation

Protein tertiary structure prediction is an active research area and has attracted significant attention recently due to the success of AlphaFold from DeepMind. Methods capable of accurately evaluating the quality of predicted models are of great importance. In the past, although many model quality assessment (QA) methods have been developed, their accuracies are not consistently high across different QA performance metrics for diverse target proteins. In this paper, we propose MUfoldQA_G, a new multi-model QA method that aims at simultaneously optimizing Pearson correlation and average GDT-TS difference, two commonly used QA performance metrics. This method is based on two new algorithms MUfoldQA_Gp and MUfoldQA_Gr. MUfoldQA_Gp uses a new technique to combine information from protein templates and reference protein models to maximize the Pearson correlation QA metric. MUfoldQA_Gr employs a new machine learning technique that resamples training data and retrains adaptively to learn a consensus model that is better than naïve consensus while minimizing average GDT-TS difference. MUfoldQA_G uses a new method to combine the results of MUfoldQA_Gr and MUfoldQA_Gp so that the final QA prediction results achieve low average GDT-TS difference that is close to the results from MUfoldQA_Gr, while maintaining high Pearson correlation that is the same as the results from MUfoldQA_Gp. In CASP14 QA categories, MUfoldQA_G ranked No. 1 in Pearson correlation and No. 2 in average GDT-TS difference.

Protein model accuracy estimation empowered by deep learning and inter-residue distance prediction in CASP14

The inter-residue contact prediction and deep learning showed the promise to improve the estimation of protein model accuracy (EMA) in the 13th Critical Assessment of Protein Structure Prediction (CASP13). To further leverage the improved inter-residue distance predictions to enhance EMA, during the 2020 CASP14 experiment, we integrated several new inter-residue distance features with the existing model quality assessment features in several deep learning methods to predict the quality of protein structural models. According to the evaluation of performance in selecting the best model from the models of CASP14 targets, our three multi-model predictors of estimating model accuracy (MULTICOM-CONSTRUCT, MULTICOM-AI, and MULTICOM-CLUSTER) achieve the averaged loss of 0.073, 0.079, and 0.081, respectively, in terms of the global distance test score (GDT-TS). The three methods are ranked first, second, and third out of all 68 CASP14 predictors. MULTICOM-DEEP, the single-model predictor of estimating model accuracy (EMA), is ranked within top 10 among all the single-model EMA methods according to GDT-TS score loss. The results demonstrate that inter-residue distance features are valuable inputs for deep learning to predict the quality of protein structural models. However, larger training datasets and better ways of leveraging inter-residue distance information are needed to fully explore its potentials.

QUARTERplus: Accurate disorder predictions integrated with interpretable residue-level quality assessment scores

A recent advance in the disorder prediction field is the development of the quality assessment (QA) scores. QA scores complement the propensities produced by the disorder predictors by identifying regions where these predictions are more likely to be correct. We develop, empirically test and release a new QA tool, QUARTERplus, that addresses several key drawbacks of the current QA method, QUARTER. QUARTERplus is the first solution that utilizes QA scores and the associated input disorder predictions to produce very accurate disorder predictions with the help of a modern deep learning meta-model. The deep neural network utilizes the QA scores to identify and fix the regions where the original/input disorder predictions are poor. More importantly, the accurate QUATERplus's predictions are accompanied by easy to interpret residue-level QA scores that reliably quantify their residue-level predictive quality. We provide these interpretable QA scores for QUARTERplus and 10 other popular disorder predictors. Empirical tests on a large and independent (low similarity) test dataset show that QUARTERplus predictions secure AUC = 0.93 and are statistically more accurate than the results of twelve state-of-the-art disorder predictors. We also demonstrate that the new QA scores produced by QUARTERplus are highly correlated with the actual predictive quality and that they can be effectively used to identify regions of correct disorder predictions. This feature empowers the users to easily identify which parts of the predictions generated by the modern disorder predictors are more trustworthy. QUARTERplus is available as a convenient webserver at http://biomine.cs.vcu.edu/servers/QUARTERplus/.

Improved Protein Model Quality Assessment By Integrating Sequential And Pairwise Features Using Deep Learning

MOTIVATION

Accurately estimating protein model quality in the absence of experimental structure is not only important for model evaluation and selection, but also useful for model refinement. Progress has been steadily made by introducing new features and algorithms (especially deep neural networks), but the accuracy of quality assessment (QA) is still not very satisfactory, especially local QA on hard protein targets.

RESULTS

We propose a new single-model-based QA method ResNetQA for both local and global quality assessment. Our method predicts model quality by integrating sequential and pairwise features using a deep neural network composed of both 1 D and 2 D convolutional residual neural networks (ResNet). The 2 D ResNet module extracts useful information from pairwise features such as model-derived distance maps, co-evolution information, and predicted distance potential from sequences. The 1 D ResNet is used to predict local (global) model quality from sequential features and pooled pairwise information generated by 2 D ResNet. Tested on the CASP12 and CASP13 datasets, our experimental results show that our method greatly outperforms existing state-of-the-art methods. Our ablation studies indicate that the 2 D ResNet module and pairwise features play an important role in improving model quality assessment.

AVAILABILITY

https://github.com/AndersJing/ResNetQA.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Empirical Comparison and Analysis of Web-Based DNA N 4-Methylcytosine Site Prediction Tools

DNA N⁴-methylcytosine (4mC) is a crucial epigenetic modification involved in various biological processes. Accurate genome-wide identification of these sites is critical for improving our understanding of their biological functions and mechanisms. As experimental methods for 4mC identification are tedious, expensive, and labor-intensive, several machine learning-based approaches have been developed for genome-wide detection of such sites in multiple species. However, the predictions projected by these tools are difficult to quantify and compare. To date, no systematic performance comparison of 4mC tools has been reported. The aim of this study was to compare and critically evaluate 12 publicly available 4mC site prediction tools according to species specificity, based on a huge independent validation dataset. The tools 4mCCNN (Escherichia coli), DNA4mC-LIP (Arabidopsis thaliana), iDNA-MS (Fragaria vesca), DNA4mC-LIP and 4mCCNN (Drosophila melanogaster), and four tools for Caenorhabditis elegans achieved excellent overall performance compared with their counterparts. However, none of the existing methods was suitable for Geoalkalibacter subterraneus, Geobacter pickeringii, and Mus musculus, thereby limiting their practical applicability. Model transferability to five species and non-transferability to three species are also discussed. The presented evaluation will assist researchers in selecting appropriate prediction tools that best suit their purpose and provide useful guidelines for the development of improved 4mC predictors in the future.

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/ .

Two New Heuristic Methods for Protein Model Quality Assessment

Protein tertiary structure prediction is an important open challenge in bioinformatics and requires effective methods to accurately evaluate the quality of protein 3-D models generated computationally. Many quality assessment (QA) methods have been proposed over the past three decades. However, the accuracy or robustness is unsatisfactory for practical applications. In this paper, two new heuristic QA methods are proposed: MUfoldQA_S and MUfoldQA_C. The MUfoldQA_S is a quasi-single-model QA method that assesses the model quality based on the known protein structures with similar sequences. This algorithm can be directly applied to protein fragments without the necessity of building a full structural model. A BLOSUM-based heuristic is also introduced to help differentiate accurate templates from poor ones. In MUfoldQA_C, the ideas from MUfoldQA_S were combined with the consensus approach to create a multi-model QA method that could also utilize information from existing reference models and have demonstrated improved performance. Extensive experimental results of these two methods have shown significant improvement over existing methods. In addition, both methods have been blindly tested in the CASP12 world-wide competition in the protein structure prediction field and ranked as top performers in their respective categories.

PSICA: a fast and accurate web service for protein model quality analysis

This paper presents a new fast and accurate web service for protein model quality analysis, called PSICA (Protein Structural Information Conformity Analysis). It is designed to evaluate how much a tertiary model of a given protein primary sequence conforms to the known protein structures of similar protein sequences, and to evaluate the quality of predicted protein models. PSICA implements the MUfoldQA_S method, an efficient state-of-the-art protein model quality assessment (QA) method. In CASP12, MUfoldQA_S ranked No. 1 in the protein model QA select-20 category in terms of the difference between the predicted and true GDT-TS value of each model. For a given predicted 3D model, PSICA generates (i) predicted global GDT-TS value; (ii) interactive comparison between the model and other known protein structures; (iii) visualization of the predicted local quality of the model; and (iv) JSmol rendering of the model. Additionally, PSICA implements MUfoldQA_C, a new consensus method based on MUfoldQA_S. In CASP12, MUfoldQA_C ranked No. 1 in top 1 model GDT-TS loss on the select-20 QA category and No. 2 in the average difference between the predicted and true GDT-TS value of each model for both select-20 and best-150 QA categories. The PSICA server is freely available at http://qas.wangwb.com/∼wwr34/mufoldqa/index.html.

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.

Deep learning methods in protein structure prediction

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

iDNA6mA-Rice: A Computational Tool for Detecting N6-Methyladenine Sites in Rice

DNA N6-methyladenine (6mA) is a dominant DNA modification form and involved in many biological functions. The accurate genome-wide identification of 6mA sites may increase understanding of its biological functions. Experimental methods for 6mA detection in eukaryotes genome are laborious and expensive. Therefore, it is necessary to develop computational methods to identify 6mA sites on a genomic scale, especially for plant genomes. Based on this consideration, the study aims to develop a machine learning-based method of predicting 6mA sites in the rice genome. We initially used mono-nucleotide binary encoding to formulate positive and negative samples. Subsequently, the machine learning algorithm named Random Forest was utilized to perform the classification for identifying 6mA sites. Our proposed method could produce an area under the receiver operating characteristic curve of 0.964 with an overall accuracy of 0.917, as indicated by the fivefold cross-validation test. Furthermore, an independent dataset was established to assess the generalization ability of our method. Finally, an area under the receiver operating characteristic curve of 0.981 was obtained, suggesting that the proposed method had good performance of predicting 6mA sites in the rice genome. For the convenience of retrieving 6mA sites, on the basis of the computational method, we built a freely accessible web server named iDNA6mA-Rice at http://lin-group.cn/server/iDNA6mA-Rice.

rawMSA: End-to-end Deep Learning using raw Multiple Sequence Alignments

In the last decades, huge efforts have been made in the bioinformatics community to develop machine learning-based methods for the prediction of structural features of proteins in the hope of answering fundamental questions about the way proteins function and their involvement in several illnesses. The recent advent of Deep Learning has renewed the interest in neural networks, with dozens of methods being developed taking advantage of these new architectures. However, most methods are still heavily based pre-processing of the input data, as well as extraction and integration of multiple hand-picked, and manually designed features. Multiple Sequence Alignments (MSA) are the most common source of information in de novo prediction methods. Deep Networks that automatically refine the MSA and extract useful features from it would be immensely powerful. In this work, we propose a new paradigm for the prediction of protein structural features called rawMSA. The core idea behind rawMSA is borrowed from the field of natural language processing to map amino acid sequences into an adaptively learned continuous space. This allows the whole MSA to be input into a Deep Network, thus rendering pre-calculated features such as sequence profiles and other features calculated from MSA obsolete. We showcased the rawMSA methodology on three different prediction problems: secondary structure, relative solvent accessibility and inter-residue contact maps. We have rigorously trained and benchmarked rawMSA on a large set of proteins and have determined that it outperforms classical methods based on position-specific scoring matrices (PSSM) when predicting secondary structure and solvent accessibility, while performing on par with methods using more pre-calculated features in the inter-residue contact map prediction category in CASP12 and CASP13. Clearly demonstrating that rawMSA represents a promising development that can pave the way for improved methods using rawMSA instead of sequence profiles to represent evolutionary information in the coming years. Availability: datasets, dataset generation code, evaluation code and models are available at: https://bitbucket.org/clami66/rawmsa.

AtbPpred: A Robust Sequence-Based Prediction of Anti-Tubercular Peptides Using Extremely Randomized Trees

Mycobacterium tuberculosis is one of the most dangerous pathogens in humans. It acts as an etiological agent of tuberculosis (TB), infecting almost one-third of the world's population. Owing to the high incidence of multidrug-resistant TB and extensively drug-resistant TB, there is an urgent need for novel and effective alternative therapies. Peptide-based therapy has several advantages, such as diverse mechanisms of action, low immunogenicity, and selective affinity to bacterial cell envelopes. However, the identification of anti-tubercular peptides (AtbPs) via experimentation is laborious and expensive; hence, the development of an efficient computational method is necessary for the prediction of AtbPs prior to both in vitro and in vivo experiments. To this end, we developed a two-layer machine learning (ML)-based predictor called AtbPpred for the identification of AtbPs. In the first layer, we applied a two-step feature selection procedure and identified the optimal feature set individually for nine different feature encodings, whose corresponding models were developed using extremely randomized tree (ERT). In the second-layer, the predicted probability of AtbPs from the above nine models were considered as input features to ERT and developed the final predictor. AtbPpred respectively achieved average accuracies of 88.3% and 87.3% during cross-validation and an independent evaluation, which were ~8.7% and 10.0% higher than the state-of-the-art method. Furthermore, we established a user-friendly webserver which is currently available at http://thegleelab.org/AtbPpred. We anticipate that this predictor could be useful in the high-throughput prediction of AtbPs and also provide mechanistic insights into its functions.

•

We developed a novel computational framework for the identification of anti-tubercular peptides using Extremely randomized tree.

•

AtbPpred displayed superior performance compared to the existing method on both benchmark and independent datasets.

•

We constructed a user-friendly web server that implements the proposed AtbPpred method.

Meta-4mCpred: A Sequence-Based Meta-Predictor for Accurate DNA 4mC Site Prediction Using Effective Feature Representation

DNA N4-methylcytosine (4mC) is an important genetic modification and plays crucial roles in differentiation between self and non-self DNA and in controlling DNA replication, cell cycle, and gene-expression levels. Accurate 4mC site identification is fundamental to improve the understanding of 4mC biological functions and mechanisms. Hence, it is necessary to develop in silico approaches for efficient and high-throughput 4mC site identification. Although some bioinformatic tools have been developed in this regard, their prediction accuracy and generalizability require improvement to optimize their usability in practical applications. For this purpose, we here proposed Meta-4mCpred, a meta-predictor for 4mC site prediction. In Meta-4mCpred, we employed a feature representation learning scheme and generated 56 probabilistic features based on four different machine-learning algorithms and seven feature encodings covering diverse sequence information, including compositional, physicochemical, and position-specific information. Subsequently, the probabilistic features were used as an input to support vector machine and developed a final meta-predictor. To the best of our knowledge, this is the first meta-predictor for 4mC site prediction. Cross-validation results show that Meta-4mCpred achieved an overall average accuracy of 84.2% from six different species, which is ∼2%–4% higher than those attainable using the state-of-the-art predictors. Furthermore, Meta-4mCpred achieved an overall average accuracy of 86% on independent datasets evaluation, which is over 4% higher than those yielded by the state-of-the-art predictors. The user-friendly webserver employed to implement the proposed Meta-4mCpred is freely accessible at http://thegleelab.org/Meta-4mCpred.

Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13

Predicting residue‐residue distance relationships (eg, contacts) has become the key direction to advance protein structure prediction since 2014 CASP11 experiment, while deep learning has revolutionized the technology for contact and distance distribution prediction since its debut in 2012 CASP10 experiment. During 2018 CASP13 experiment, we enhanced our MULTICOM protein structure prediction system with three major components: contact distance prediction based on deep convolutional neural networks, distance‐driven template‐free (ab initio) modeling, and protein model ranking empowered by deep learning and contact prediction. Our experiment demonstrates that contact distance prediction and deep learning methods are the key reasons that MULTICOM was ranked 3rd out of all 98 predictors in both template‐free and template‐based structure modeling in CASP13. Deep convolutional neural network can utilize global information in pairwise residue‐residue features such as coevolution scores to substantially improve contact distance prediction, which played a decisive role in correctly folding some free modeling and hard template‐based modeling targets. Deep learning also successfully integrated one‐dimensional structural features, two‐dimensional contact information, and three‐dimensional structural quality scores to improve protein model quality assessment, where the contact prediction was demonstrated to consistently enhance ranking of protein models for the first time. The success of MULTICOM system clearly shows that protein contact distance prediction and model selection driven by deep learning holds the key of solving protein structure prediction problem. However, there are still challenges in accurately predicting protein contact distance when there are few homologous sequences, folding proteins from noisy contact distances, and ranking models of hard targets.

mACPpred: A Support Vector Machine-Based Meta-Predictor for Identification of Anticancer Peptides

Anticancer peptides (ACPs) are promising therapeutic agents for targeting and killing cancer cells. The accurate prediction of ACPs from given peptide sequences remains as an open problem in the field of immunoinformatics. Recently, machine learning algorithms have emerged as a promising tool for helping experimental scientists predict ACPs. However, the performance of existing methods still needs to be improved. In this study, we present a novel approach for the accurate prediction of ACPs, which involves the following two steps: (i) We applied a two-step feature selection protocol on seven feature encodings that cover various aspects of sequence information (composition-based, physicochemical properties and profiles) and obtained their corresponding optimal feature-based models. The resultant predicted probabilities of ACPs were further utilized as feature vectors. (ii) The predicted probability feature vectors were in turn used as an input to support vector machine to develop the final prediction model called mACPpred. Cross-validation analysis showed that the proposed predictor performs significantly better than individual feature encodings. Furthermore, mACPpred significantly outperformed the existing methods compared in this study when objectively evaluated on an independent dataset.

Validation and quality assessment of macromolecular structures using complex network analysis

Validation of three-dimensional structures is at the core of structural determination methods. The local validation criteria, such as deviations from ideal bond length and bonding angles, Ramachandran plot outliers and clashing contacts, are a standard part of structure analysis before structure deposition, whereas the global and regional packing may not yet have been addressed. In the last two decades, three-dimensional models of macromolecules such as proteins have been successfully described by a network of nodes and edges. Amino acid residues as nodes and close contact between the residues as edges have been used to explore basic network properties, to study protein folding and stability and to predict catalytic sites. Using complex network analysis, we introduced common network parameters to distinguish between correct and incorrect three-dimensional protein structures. The analysis showed that correct structures have a higher average node degree, higher graph energy, and lower shortest path length than their incorrect counterparts. Thus, correct protein models are more densely intra-connected, and in turn, the transfer of information between nodes/amino acids is more efficient. Moreover, protein graph spectra were used to investigate model bias in protein structure.

iGHBP: Computational identification of growth hormone binding proteins from sequences using extremely randomised tree

A soluble carrier growth hormone binding protein (GHBP) that can selectively and non-covalently interact with growth hormone, thereby acting as a modulator or inhibitor of growth hormone signalling. Accurate identification of the GHBP from a given protein sequence also provides important clues for understanding cell growth and cellular mechanisms. In the postgenomic era, there has been an abundance of protein sequence data garnered, hence it is crucial to develop an automated computational method which enables fast and accurate identification of putative GHBPs within a vast number of candidate proteins. In this study, we describe a novel machine-learning-based predictor called iGHBP for the identification of GHBP. In order to predict GHBP from a given protein sequence, we trained an extremely randomised tree with an optimal feature set that was obtained from a combination of dipeptide composition and amino acid index values by applying a two-step feature selection protocol. During cross-validation analysis, iGHBP achieved an accuracy of 84.9%, which was ~7% higher than the control extremely randomised tree predictor trained with all features, thus demonstrating the effectiveness of our feature selection protocol. Furthermore, when objectively evaluated on an independent data set, our proposed iGHBP method displayed superior performance compared to the existing method. Additionally, a user-friendly web server that implements the proposed iGHBP has been established and is available at http://thegleelab.org/iGHBP.

Identifying Phage Virion Proteins by Using Two-Step Feature Selection Methods

Accurate identification of phage virion protein is not only a key step for understanding the function of the phage virion protein but also helpful for further understanding the lysis mechanism of the bacterial cell. Since traditional experimental methods are time-consuming and costly for identifying phage virion proteins, it is extremely urgent to apply machine learning methods to accurately and efficiently identify phage virion proteins. In this work, a support vector machine (SVM) based method was proposed by mixing multiple sets of optimal g-gap dipeptide compositions. The analysis of variance (ANOVA) and the minimal-redundancy-maximal-relevance (mRMR) with an increment feature selection (IFS) were applied to single out the optimal feature set. In the five-fold cross-validation test, the proposed method achieved an overall accuracy of 87.95%. We believe that the proposed method will become an efficient and powerful method for scientists concerning phage virion proteins.

PIP-EL: A New Ensemble Learning Method for Improved Proinflammatory Peptide Predictions

Proinflammatory cytokines have the capacity to increase inflammatory reaction and play a central role in first line of defence against invading pathogens. Proinflammatory inducing peptides (PIPs) have been used as an antineoplastic agent, an antibacterial agent and a vaccine in immunization therapies. Due to the advancement in sequence technologies that resulted an avalanche of protein sequence data. Therefore, it is necessary to develop an automated computational method to enable fast and accurate identification of novel PIPs within the vast number of candidate proteins and peptides. To address this, we proposed a new predictor, PIP-EL, for predicting PIPs using the strategy of ensemble learning (EL). Our benchmarking dataset is imbalanced. Thus, we applied a random under-sampling technique to generate 10 balanced models for each composition. Technically, PIP-EL is the fusion of 50 independent random forest (RF) models, where each of the five different compositions, including amino acid, dipeptide, composition-transition-distribution, physicochemical properties, and amino acid index contains 10 RF models. PIP-EL achieves the Matthews' correlation coefficient (MCC) of 0.435 in a 5-fold cross-validation test, which is ~2-5% higher than that of the individual classifiers and hybrid feature-based classifier. Furthermore, we evaluate the performance of PIP-EL on the independent dataset, showing that our method outperforms the existing method and two different machine learning methods developed in this study, with an MCC of 0.454. These results indicate that PIP-EL will be a useful tool for predicting PIPs and for researchers working in the field of peptide therapeutics and immunotherapy. The user-friendly web server, PIP-EL, is freely accessible.

Identification of Bacteriophage Virion Proteins Using Multinomial Naïve Bayes with g-Gap Feature Tree

Bacteriophages, which are tremendously important to the ecology and evolution of bacteria, play a key role in the development of genetic engineering. Bacteriophage virion proteins are essential materials of the infectious viral particles and in charge of several of biological functions. The correct identification of bacteriophage virion proteins is of great importance for understanding both life at the molecular level and genetic evolution. However, few computational methods are available for identifying bacteriophage virion proteins. In this paper, we proposed a new method to predict bacteriophage virion proteins using a Multinomial Naïve Bayes classification model based on discrete feature generated from the g-gap feature tree. The accuracy of the proposed model reaches 98.37% with MCC of 96.27% in 10-fold cross-validation. This result suggests that the proposed method can be a useful approach in identifying bacteriophage virion proteins from sequence information. For the convenience of experimental scientists, a web server (PhagePred) that implements the proposed predictor is available, which can be freely accessed on the Internet.

PrESOgenesis: A two-layer multi-label predictor for identifying fertility-related proteins using support vector machine and pseudo amino acid composition approach

Successful spermatogenesis and oogenesis are the two genetically independent processes preceding embryo development. To date, several fertility-related proteins have been described in mammalian species. Nevertheless, further studies are required to discover more proteins associated with the development of germ cells and embryogenesis in order to shed more light on the processes. This work builds on our previous software (OOgenesis_Pred), mainly focusing on algorithms beyond what was previously done, in particular new fertility-related proteins and their classes (embryogenesis, spermatogenesis and oogenesis) based on the support vector machine according to the concept of Chou's pseudo-amino acid composition features. The results of five-fold cross validation, as well as the independent test demonstrated that this method is capable of predicting the fertility-related proteins and their classes with accuracy of more than 80%. Moreover, by using feature selection methods, important properties of fertility-related proteins were identified that allowed for their accurate classification. Based on the proposed method, a two-layer classifier software, named as "PrESOgenesis" ( https://github.com/mrb20045/PrESOgenesis ) was developed. The tool identified a query sequence (protein or transcript) as fertility or non-fertility-related protein at the first layer and then classified the predicted fertility-related protein into different classes of embryogenesis, spermatogenesis or oogenesis at the second layer.

iRSpot-Pse6NC: Identifying recombination spots in Saccharomyces cerevisiae by incorporating hexamer composition into general PseKNC

Meiotic recombination caused by meiotic double-strand DNA breaks. In some regions the frequency of DNA recombination is relatively higher, while in other regions the frequency is lower: the former is usually called "recombination hotspot", while the latter the "recombination coldspot". Information of the hot and cold spots may provide important clues for understanding the mechanism of genome revolution. Therefore, it is important to accurately predict these spots. In this study, we rebuilt the benchmark dataset by unifying its samples with a same length (131 bp). Based on such a foundation and using SVM (Support Vector Machine) classifier, a new predictor called "iRSpot-Pse6NC" was developed by incorporating the key hexamer features into the general PseKNC (Pseudo K-tuple Nucleotide Composition) via the binomial distribution approach. It has been observed via rigorous cross-validations that the proposed predictor is superior to its counterparts in overall accuracy, stability, sensitivity and specificity. For the convenience of most experimental scientists, the web-server for iRSpot-Pse6NC has been established at http://lin-group.cn/server/iRSpot-Pse6NC, by which users can easily obtain their desired result without the need to go through the detailed mathematical equations involved.

HBPred: a tool to identify growth hormone-binding proteins

Hormone-binding protein (HBP) is a kind of soluble carrier protein and can selectively and non-covalently interact with hormone. HBP plays an important role in life growth, but its function is still unclear. Correct recognition of HBPs is the first step to further study their function and understand their biological process. However, it is difficult to correctly recognize HBPs from more and more proteins through traditional biochemical experiments because of high experimental cost and long experimental period. To overcome these disadvantages, we designed a computational method for identifying HBPs accurately in the study. At first, we collected HBP data from UniProt to establish a high-quality benchmark dataset. Based on the dataset, the dipeptide composition was extracted from HBP residue sequences. In order to find out the optimal features to provide key clues for HBP identification, the analysis of various (ANOVA) was performed for feature ranking. The optimal features were selected through the incremental feature selection strategy. Subsequently, the features were inputted into support vector machine (SVM) for prediction model construction. Jackknife cross-validation results showed that 88.6% HBPs and 81.3% non-HBPs were correctly recognized, suggesting that our proposed model was powerful. This study provides a new strategy to identify HBPs. Moreover, based on the proposed model, we established a webserver called HBPred, which could be freely accessed at http://lin-group.cn/server/HBPred.

Identifying RNA N6-Methyladenosine Sites in Escherichia coli Genome

N⁶-methyladenosine (m⁶A) plays important roles in a branch of biological and physiological processes. Accurate identification of m⁶A sites is especially helpful for understanding their biological functions. Since the wet-lab techniques are still expensive and time-consuming, it's urgent to develop computational methods to identify m⁶A sites from primary RNA sequences. Although there are some computational methods for identifying m⁶A sites, no methods whatsoever are available for detecting m⁶A sites in microbial genomes. In this study, we developed a computational method for identifying m⁶A sites in Escherichia coli genome. The accuracies obtained by the proposed method are >90% in both 10-fold cross-validation test and independent dataset test, indicating that the proposed method holds the high potential to become a useful tool for the identification of m⁶A sites in microbial genomes.

AIPpred: Sequence-Based Prediction of Anti-inflammatory Peptides Using Random Forest

The use of therapeutic peptides in various inflammatory diseases and autoimmune disorders has received considerable attention; however, the identification of anti-inflammatory peptides (AIPs) through wet-lab experimentation is expensive and often time consuming. Therefore, the development of novel computational methods is needed to identify potential AIP candidates prior to in vitro experimentation. In this study, we proposed a random forest (RF)-based method for predicting AIPs, called AIPpred (AIP predictor in primary amino acid sequences), which was trained with 354 optimal features. First, we systematically studied the contribution of individual composition [amino acid-, dipeptide composition (DPC), amino acid index, chain-transition-distribution, and physicochemical properties] in AIP prediction. Since the performance of the DPC-based model is significantly better than that of other composition-based models, we applied a feature selection protocol on this model and identified the optimal features. AIPpred achieved an area under the curve (AUC) value of 0.801 in a 5-fold cross-validation test, which was ∼2% higher than that of the control RF predictor trained with all DPC composition features, indicating the efficiency of the feature selection protocol. Furthermore, we evaluated the performance of AIPpred on an independent dataset, with results showing that our method outperformed an existing method, as well as 3 different machine learning methods developed in this study, with an AUC value of 0.814. These results indicated that AIPpred will be a useful tool for predicting AIPs and might efficiently assist the development of AIP therapeutics and biomedical research. AIPpred is freely accessible at www.thegleelab.org/AIPpred.

Sequence-based predictive modeling to identify cancerlectins

Lectins are a diverse type of glycoproteins or carbohydrate-binding proteins that have a wide distribution to various species. They can specially identify and exclusively bind to a certain kind of saccharide groups. Cancerlectins are a group of lectins that are closely related to cancer and play a major role in the initiation, survival, growth, metastasis and spread of tumor. Several computational methods have emerged to discriminate cancerlectins from non-cancerlectins, which promote the study on pathogenic mechanisms and clinical treatment of cancer. However, the predictive accuracies of most of these techniques are very limited. In this work, by constructing a benchmark dataset based on the CancerLectinDB database, a new amino acid sequence-based strategy for feature description was developed, and then the binomial distribution was applied to screen the optimal feature set. Ultimately, an SVM-based predictor was performed to distinguish cancerlectins from non-cancerlectins, and achieved an accuracy of 77.48% with AUC of 85.52% in jackknife cross-validation. The results revealed that our prediction model could perform better comparing with published predictive tools.

PClass: Protein Quaternary Structure Classification by Using Bootstrapping Strategy as Model Selection

Protein quaternary structure complex is also known as a multimer, which plays an important role in a cell. The dimer structure of transcription factors is involved in gene regulation, but the trimer structure of virus-infection-associated glycoproteins is related to the human immunodeficiency virus. The classification of the protein quaternary structure complex for the post-genome era of proteomics research will be of great help. Classification systems among protein quaternary structures have not been widely developed. Therefore, we designed the architecture of a two-layer machine learning technique in this study, and developed the classification system PClass. The protein quaternary structure of the complex is divided into five categories, namely, monomer, dimer, trimer, tetramer, and other subunit classes. In the framework of the bootstrap method with a support vector machine, we propose a new model selection method. Each type of complex is classified based on sequences, entropy, and accessible surface area, thereby generating a plurality of feature modules. Subsequently, the optimal model of effectiveness is selected as each kind of complex feature module. In this stage, the optimal performance can reach as high as 70% of Matthews correlation coefficient (MCC). The second layer of construction combines the first-layer module to integrate mechanisms and the use of six machine learning methods to improve the prediction performance. This system can be improved over 10% in MCC. Finally, we analyzed the performance of our classification system using transcription factors in dimer structure and virus-infection-associated glycoprotein in trimer structure. PClass is available via a web interface at http://predictor.nchu.edu.tw/PClass/.

DHSpred: support-vector-machine-based human DNase I hypersensitive sites prediction using the optimal features selected by random forest

DNase I hypersensitive sites (DHSs) are genomic regions that provide important information regarding the presence of transcriptional regulatory elements and the state of chromatin. Therefore, identifying DHSs in uncharacterized DNA sequences is crucial for understanding their biological functions and mechanisms. Although many experimental methods have been proposed to identify DHSs, they have proven to be expensive for genome-wide application. Therefore, it is necessary to develop computational methods for DHS prediction. In this study, we proposed a support vector machine (SVM)-based method for predicting DHSs, called DHSpred (DNase I Hypersensitive Site predictor in human DNA sequences), which was trained with 174 optimal features. The optimal combination of features was identified from a large set that included nucleotide composition and di- and trinucleotide physicochemical properties, using a random forest algorithm. DHSpred achieved a Matthews correlation coefficient and accuracy of 0.660 and 0.871, respectively, which were 3% higher than those of control SVM predictors trained with non-optimized features, indicating the efficiency of the feature selection method. Furthermore, the performance of DHSpred was superior to that of state-of-the-art predictors. An online prediction server has been developed to assist the scientific community, and is freely available at: http://www.thegleelab.org/DHSpred.html.

ProLanGO: Protein Function Prediction Using Neural Machine Translation Based on a Recurrent Neural Network

With the development of next generation sequencing techniques, it is fast and cheap to determine protein sequences but relatively slow and expensive to extract useful information from protein sequences because of limitations of traditional biological experimental techniques. Protein function prediction has been a long standing challenge to fill the gap between the huge amount of protein sequences and the known function. In this paper, we propose a novel method to convert the protein function problem into a language translation problem by the new proposed protein sequence language “ProLan” to the protein function language “GOLan”, and build a neural machine translation model based on recurrent neural networks to translate “ProLan” language to “GOLan” language. We blindly tested our method by attending the latest third Critical Assessment of Function Annotation (CAFA 3) in 2016, and also evaluate the performance of our methods on selected proteins whose function was released after CAFA competition. The good performance on the training and testing datasets demonstrates that our new proposed method is a promising direction for protein function prediction. In summary, we first time propose a method which converts the protein function prediction problem to a language translation problem and applies a neural machine translation model for protein function prediction.

MLACP: machine-learning-based prediction of anticancer peptides

Cancer is the second leading cause of death globally, and use of therapeutic peptides to target and kill cancer cells has received considerable attention in recent years. Identification of anticancer peptides (ACPs) through wet-lab experimentation is expensive and often time consuming; therefore, development of an efficient computational method is essential to identify potential ACP candidates prior to in vitro experimentation. In this study, we developed support vector machine- and random forest-based machine-learning methods for the prediction of ACPs using the features calculated from the amino acid sequence, including amino acid composition, dipeptide composition, atomic composition, and physicochemical properties. We trained our methods using the Tyagi-B dataset and determined the machine parameters by 10-fold cross-validation. Furthermore, we evaluated the performance of our methods on two benchmarking datasets, with our results showing that the random forest-based method outperformed the existing methods with an average accuracy and Matthews correlation coefficient value of 88.7% and 0.78, respectively. To assist the scientific community, we also developed a publicly accessible web server at www.thegleelab.org/MLACP.html.