A comprehensive review and comparison of existing computational methods for intrinsically disordered protein and region prediction

flDPnn: Accurate intrinsic disorder prediction with putative propensities of disorder functions

Identification of intrinsic disorder in proteins relies in large part on computational predictors, which demands that their accuracy should be high. Since intrinsic disorder carries out a broad range of cellular functions, it is desirable to couple the disorder and disorder function predictions. We report a computational tool, flDPnn, that provides accurate, fast and comprehensive disorder and disorder function predictions from protein sequences. The recent Critical Assessment of protein Intrinsic Disorder prediction (CAID) experiment and results on other test datasets demonstrate that flDPnn offers accurate predictions of disorder, fully disordered proteins and four common disorder functions. These predictions are substantially better than the results of the existing disorder predictors and methods that predict functions of disorder. Ablation tests reveal that the high predictive performance stems from innovative ways used in flDPnn to derive sequence profiles and encode inputs. flDPnn's webserver is available at http://biomine.cs.vcu.edu/servers/flDPnn/.

IUPred3: prediction of protein disorder enhanced with unambiguous experimental annotation and visualization of evolutionary conservation

Intrinsically disordered proteins and protein regions (IDPs/IDRs) exist without a single well-defined conformation. They carry out important biological functions with multifaceted roles which is also reflected in their evolutionary behavior. Computational methods play important roles in the characterization of IDRs. One of the commonly used disorder prediction methods is IUPred, which relies on an energy estimation approach. The IUPred web server takes an amino acid sequence or a Uniprot ID/accession as an input and predicts the tendency for each amino acid to be in a disordered region with an option to also predict context-dependent disordered regions. In this new iteration of IUPred, we added multiple novel features to enhance the prediction capabilities of the server. First, learning from the latest evaluation of disorder prediction methods we introduced multiple new smoothing functions to the prediction that decreases noise and increases the performance of the predictions. We constructed a dataset consisting of experimentally verified ordered/disordered regions with unambiguous annotations which were added to the prediction. We also introduced a novel tool that enables the exploration of the evolutionary conservation of protein disorder coupled to sequence conservation in model organisms. The web server is freely available to users and accessible at https://iupred3.elte.hu.

The diversity of molecular interactions involving intrinsically disordered proteins: A molecular modeling perspective

Intrinsically Disordered Proteins and Regions (IDPs/IDRs) are key components of a multitude of biological processes. Conformational malleability enables IDPs/IDRs to perform very specialized functions that cannot be accomplished by globular proteins. The functional role for most of these proteins is related to the recognition of other biomolecules to regulate biological processes or as a part of signaling pathways. Depending on the extent of disorder, the number of interacting sites and the type of partner, very different architectures for the resulting assemblies are possible. More recently, molecular condensates with liquid-like properties composed of multiple copies of IDPs and nucleic acids have been proven to regulate key processes in eukaryotic cells. The structural and kinetic details of disordered biomolecular complexes are difficult to unveil experimentally due to their inherent conformational heterogeneity. Computational approaches, alone or in combination with experimental data, have emerged as unavoidable tools to understand the functional mechanisms of this elusive type of assemblies. The level of description used, all-atom or coarse-grained, strongly depends on the size of the molecular systems and on the timescale of the investigated mechanism. In this mini-review, we describe the most relevant architectures found for molecular interactions involving IDPs/IDRs and the computational strategies applied for their investigation.

Solubility Parameters of Amino Acids on Liquid-Liquid Phase Separation and Aggregation of Proteins

The solution properties of amino acids determine the folding, aggregation, and liquid–liquid phase separation (LLPS) behaviors of proteins. Various indices of amino acids, such as solubility, hydropathy, and conformational parameter, describe the behaviors of protein folding and solubility both in vitro and in vivo. However, understanding the propensity of LLPS and aggregation is difficult due to the multiple interactions among different amino acids. Here, the solubilities of aromatic amino acids (SAs) were investigated in solution containing 20 types of amino acids as amino acid solvents. The parameters of SAs in amino acid solvents (PSASs) were varied and dependent on the type of the solvent. Specifically, Tyr and Trp had the highest positive values while Glu and Asp had the lowest. The PSAS values represent soluble and insoluble interactions, which collectively are the driving force underlying the formation of droplets and aggregates. Interestingly, the PSAS of a soluble solvent reflected the affinity between amino acids and aromatic rings, while that of an insoluble solvent reflected the affinity between amino acids and water. These findings suggest that the PSAS can distinguish amino acids that contribute to droplet and aggregate formation, and provide a deeper understanding of LLPS and aggregation of proteins.

Current directions in combining simulation-based macromolecular modeling approaches with deep learning

Introduction: Structure-guided drug discovery relies on accurate computational methods for modeling macromolecules. Simulations provide means of predicting macromolecular folds, of discovering function from structure, and of designing macromolecules to serve as drugs. Success rates are limited for any of these tasks, however. Recently, deep neural network-based methods have greatly enhanced the accuracy of predictions of protein structure from sequence, generating excitement about the potential impact of deep learning.Areas covered: This review introduces biologists to deep neural network architecture, surveys recent successes of deep learning in structure prediction, and discusses emerging deep learning-based approaches for structure-function analysis and design. Particular focus is given to the interplay between simulation-based and neural network-based approaches.Expert opinion: As deep learning grows integral to macromolecular modeling, simulation- and neural network-based approaches must grow more tightly interconnected. Modular software architecture must emerge allowing both types of tools to be combined with maximal versatility. Open sharing of code under permissive licenses will be essential. Although experiments will remain the gold standard for reliable information to guide drug discovery, we may soon see successful drug development projects based on high-accuracy predictions from algorithms that combine simulation with deep learning - the ultimate validation of this combination's power.

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/.

Identification of Intrinsically Disordered Protein Regions Based on Deep Neural Network-VGG16

The accurate of i identificationntrinsically disordered proteins or protein regions is of great importance, as they are involved in critical biological process and related to various human diseases. In this paper, we develop a deep neural network that is based on the well-known VGG16. Our deep neural network is then trained through using 1450 proteins from the dataset DIS1616 and the trained neural network is tested on the remaining 166 proteins. Our trained neural network is also tested on the blind test set R80 and MXD494 to further demonstrate the performance of our model. The MCC value of our trained deep neural network is 0.5132 on the test set DIS166, 0.5270 on the blind test set R80 and 0.4577 on the blind test set MXD494. All of these MCC values of our trained deep neural network exceed the corresponding values of existing prediction methods.

APOD: accurate sequence-based predictor of disordered flexible linkers

Motivation

Disordered flexible linkers (DFLs) are abundant and functionally important intrinsically disordered regions that connect protein domains and structural elements within domains and which facilitate disorder-based allosteric regulation. Although computational estimates suggest that thousands of proteins have DFLs, they were annotated experimentally in <200 proteins. This substantial annotation gap can be reduced with the help of accurate computational predictors. The sole predictor of DFLs, DFLpred, trade-off accuracy for shorter runtime by excluding relevant but computationally costly predictive inputs. Moreover, it relies on the local/window-based information while lacking to consider useful protein-level characteristics.

Results

We conceptualize, design and test APOD (Accurate Predictor Of DFLs), the first highly accurate predictor that utilizes both local- and protein-level inputs that quantify propensity for disorder, sequence composition, sequence conservation and selected putative structural properties. Consequently, APOD offers significantly more accurate predictions when compared with its faster predecessor, DFLpred, and several other alternative ways to predict DFLs. These improvements stem from the use of a more comprehensive set of inputs that cover the protein-level information and the application of a more sophisticated predictive model, a well-parametrized support vector machine. APOD achieves area under the curve = 0.82 (28% improvement over DFLpred) and Matthews correlation coefficient = 0.42 (180% increase over DFLpred) when tested on an independent/low-similarity test dataset. Consequently, APOD is a suitable choice for accurate and small-scale prediction of DFLs.

Availability and implementation

https://yanglab.nankai.edu.cn/APOD/.

IDPology of the living cell: intrinsic disorder in the subcellular compartments of the human cell

Intrinsic disorder can be found in all proteomes of all kingdoms of life and in viruses, being particularly prevalent in the eukaryotes. We conduct a comprehensive analysis of the intrinsic disorder in the human proteins while mapping them into 24 compartments of the human cell. In agreement with previous studies, we show that human proteins are significantly enriched in disorder relative to a generic protein set that represents the protein universe. In fact, the fraction of proteins with long disordered regions and the average protein-level disorder content in the human proteome are about 3 times higher than in the protein universe. Furthermore, levels of intrinsic disorder in the majority of human subcellular compartments significantly exceed the average disorder content in the protein universe. Relative to the overall amount of disorder in the human proteome, proteins localized in the nucleus and cytoskeleton have significantly increased amounts of disorder, measured by both high disorder content and presence of multiple long intrinsically disordered regions. We empirically demonstrate that, on average, human proteins are assigned to 2.3 subcellular compartments, with proteins localized to few subcellular compartments being more disordered than the proteins that are localized to many compartments. Functionally, the disordered proteins localized in the most disorder-enriched subcellular compartments are primarily responsible for interactions with nucleic acids and protein partners. This is the first-time disorder is comprehensively mapped into the human cell. Our observations add a missing piece to the puzzle of functional disorder and its organization inside the cell.

Tuning intrinsic disorder predictors for virus proteins

Many virus-encoded proteins have intrinsically disordered regions that lack a stable, folded three-dimensional structure. These disordered proteins often play important functional roles in virus replication, such as down-regulating host defense mechanisms. With the widespread availability of next-generation sequencing, the number of new virus genomes with predicted open reading frames is rapidly outpacing our capacity for directly characterizing protein structures through crystallography. Hence, computational methods for structural prediction play an important role. A large number of predictors focus on the problem of classifying residues into ordered and disordered regions, and these methods tend to be validated on a diverse training set of proteins from eukaryotes, prokaryotes, and viruses. In this study, we investigate whether some predictors outperform others in the context of virus proteins and compared our findings with data from non-viral proteins. We evaluate the prediction accuracy of 21 methods, many of which are only available as web applications, on a curated set of 126 proteins encoded by viruses. Furthermore, we apply a random forest classifier to these predictor outputs. Based on cross-validation experiments, this ensemble approach confers a substantial improvement in accuracy, e.g., a mean 36 per cent gain in Matthews correlation coefficient. Lastly, we apply the random forest predictor to severe acute respiratory syndrome coronavirus 2 ORF6, an accessory gene that encodes a short (61 AA) and moderately disordered protein that inhibits the host innate immune response. We show that disorder prediction methods perform differently for viral and non-viral proteins, and that an ensemble approach can yield more robust and accurate predictions.

NCBRPred: predicting nucleic acid binding residues in proteins based on multilabel learning

The interactions between proteins and nucleic acid sequences play many important roles in gene expression and some cellular activities. Accurate prediction of the nucleic acid binding residues in proteins will facilitate the research of the protein functions, gene expression, drug design, etc. In this regard, several computational methods have been proposed to predict the nucleic acid binding residues in proteins. However, these methods cannot satisfactorily measure the global interactions among the residues along protein. Furthermore, these methods are suffering cross-prediction problem, new strategies should be explored to solve this problem. In this study, a new computational method called NCBRPred was proposed to predict the nucleic acid binding residues based on the multilabel sequence labeling model. NCBRPred used the bidirectional Gated Recurrent Units (BiGRUs) to capture the global interactions among the residues, and treats this task as a multilabel learning task. Experimental results on three widely used benchmark datasets and an independent dataset showed that NCBRPred achieved higher predictive results with lower cross-prediction, outperforming 10 existing state-of-the-art predictors. The web-server and a stand-alone package of NCBRPred are freely available at http://bliulab.net/NCBRPred. It is anticipated that NCBRPred will become a very useful tool for identifying nucleic acid binding residues.

Critical assessment of protein intrinsic disorder prediction

Intrinsically disordered proteins, defying the traditional protein structure-function paradigm, are a challenge to study experimentally. Because a large part of our knowledge rests on computational predictions, it is crucial that their accuracy is high. The Critical Assessment of protein Intrinsic Disorder prediction (CAID) experiment was established as a community-based blind test to determine the state of the art in prediction of intrinsically disordered regions and the subset of residues involved in binding. A total of 43 methods were evaluated on a dataset of 646 proteins from DisProt. The best methods use deep learning techniques and notably outperform physicochemical methods. The top disorder predictor has F_max = 0.483 on the full dataset and F_max = 0.792 following filtering out of bona fide structured regions. Disordered binding regions remain hard to predict, with F_max = 0.231. Interestingly, computing times among methods can vary by up to four orders of magnitude.

Comparative Assessment of Intrinsic Disorder Predictions with a Focus on Protein and Nucleic Acid-Binding Proteins

With over 60 disorder predictors, users need help navigating the predictor selection task. We review 28 surveys of disorder predictors, showing that only 11 include assessment of predictive performance. We identify and address a few drawbacks of these past surveys. To this end, we release a novel benchmark dataset with reduced similarity to the training sets of the considered predictors. We use this dataset to perform a first-of-its-kind comparative analysis that targets two large functional families of disordered proteins that interact with proteins and with nucleic acids. We show that limiting sequence similarity between the benchmark and the training datasets has a substantial impact on predictive performance. We also demonstrate that predictive quality is sensitive to the use of the well-annotated order and inclusion of the fully structured proteins in the benchmark datasets, both of which should be considered in future assessments. We identify three predictors that provide favorable results using the new benchmark set. While we find that VSL2B offers the most accurate and robust results overall, ESpritz-DisProt and SPOT-Disorder perform particularly well for disordered proteins. Moreover, we find that predictions for the disordered protein-binding proteins suffer low predictive quality compared to generic disordered proteins and the disordered nucleic acids-binding proteins. This can be explained by the high disorder content of the disordered protein-binding proteins, which makes it difficult for the current methods to accurately identify ordered regions in these proteins. This finding motivates the development of a new generation of methods that would target these difficult-to-predict disordered proteins. We also discuss resources that support users in collecting and identifying high-quality disorder predictions.

Roles, Characteristics, and Analysis of Intrinsically Disordered Proteins: A Minireview

In recent years, there has been a growing understanding that a significant fraction of the eukaryotic proteome is intrinsically disordered, and that these conformationally dynamic proteins play a myriad of vital biological roles in both normal and pathological states. In this review, selected examples of intrinsically disordered proteins are highlighted, with particular attention for a few which are relevant in neurological disorders and in viral infection. Next, the underlying causes for the intrinsic disorder are discussed, along with computational methods used to predict whether a given amino acid sequence is likely to adopt a folded or unfolded state in the solution. Finally, biophysical methods for the analysis of intrinsically disordered proteins will be discussed, as well as the unique challenges they pose in this context due to their highly dynamic nature.

Towards Decoding the Sequence-Based Grammar Governing the Functions of Intrinsically Disordered Protein Regions

A substantial portion of the proteome consists of intrinsically disordered regions (IDRs) that do not fold into well-defined 3D structures yet perform numerous biological functions and are associated with a broad range of diseases. It has been a long-standing enigma how different IDRs successfully execute their specific functions. Further putting a spotlight on IDRs are recent discoveries of functionally relevant biomolecular assemblies, which in some cases form through liquid-liquid phase separation. At the molecular level, the formation of biomolecular assemblies is largely driven by weak, multivalent, but selective IDR-IDR interactions. Emerging experimental and computational studies suggest that the primary amino acid sequences of IDRs encode a variety of their interaction behaviors. In this review, we focus on findings and insights that connect sequence-derived features of IDRs to their conformations, propensities to form biomolecular assemblies, selectivity of interaction partners, functions in the context of physiology and disease, and regulation of function. We also discuss directions of future research to facilitate establishing a comprehensive sequence-function paradigm that will eventually allow prediction of selective interactions and specificity of function mediated by IDRs.

Homology modeling in the time of collective and artificial intelligence

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

Identification of protein complexes and functional modules in E. coli PPI networks

Background

Escherichia coli always plays an important role in microbial research, and it has been a benchmark model for the study of molecular mechanisms of microorganisms. Molecular complexes, operons, and functional modules are valuable molecular functional domains of E. coli. The identification of protein complexes and functional modules of E. coli is essential to reveal the principles of cell organization, process, and function. At present, many studies focus on the detection of E. coli protein complexes based on experimental methods. However, based on the large-scale proteomics data set of E. coli, the simultaneous prediction of protein complexes and functional modules, especially the comparative analysis of them is relatively less.

Results

In this study, the Edge Label Propagate Algorithm (ELPA) of the complex biological network was used to predict the protein complexes and functional modules of two high-quality PPI networks of E. coli, respectively. According to the gold standard protein complexes and function annotations provided by EcoCyc dataset, most protein modules predicted in the two datasets matched highly with real protein complexes, cellular processes, and biological functions. Some novel and significant protein complexes and functional modules were revealed based on ELPA. Moreover, through a comparative analysis of predicted complexes with corresponding functional modules, we found the protein complexes were significantly overlapped with corresponding functional modules, and almost all predicted protein complexes were completely covered by one or more functional modules. Finally, on the same PPI network of E. coli, ELPA was compared with a well-known protein module detection method (MCL) and we found that the performance of ELPA and MCL is comparable in predicting protein complexes.

Conclusions

In this paper, a link clustering method was used to predict protein complexes and functional modules in PPI networks of E. coli, and the correlation between them was compared, which could help us to understand the molecular functional units of E. coli better.

BioSeq-Analysis2.0: an updated platform for analyzing DNA, RNA and protein sequences at sequence level and residue level based on machine learning approaches

As the first web server to analyze various biological sequences at sequence level based on machine learning approaches, many powerful predictors in the field of computational biology have been developed with the assistance of the BioSeq-Analysis. However, the BioSeq-Analysis can be only applied to the sequence-level analysis tasks, preventing its applications to the residue-level analysis tasks, and an intelligent tool that is able to automatically generate various predictors for biological sequence analysis at both residue level and sequence level is highly desired. In this regard, we decided to publish an important updated server covering a total of 26 features at the residue level and 90 features at the sequence level called BioSeq-Analysis2.0 (http://bliulab.net/BioSeq-Analysis2.0/), by which the users only need to upload the benchmark dataset, and the BioSeq-Analysis2.0 can generate the predictors for both residue-level analysis and sequence-level analysis tasks. Furthermore, the corresponding stand-alone tool was also provided, which can be downloaded from http://bliulab.net/BioSeq-Analysis2.0/download/. To the best of our knowledge, the BioSeq-Analysis2.0 is the first tool for generating predictors for biological sequence analysis tasks at residue level. Specifically, the experimental results indicated that the predictors developed by BioSeq-Analysis2.0 can achieve comparable or even better performance than the existing state-of-the-art predictors.

A Method for Prediction of Thermophilic Protein Based on Reduced Amino Acids and Mixed Features

The thermostability of proteins is a key factor considered during enzyme engineering, and finding a method that can identify thermophilic and non-thermophilic proteins will be helpful for enzyme design. In this study, we established a novel method combining mixed features and machine learning to achieve this recognition task. In this method, an amino acid reduction scheme was adopted to recode the amino acid sequence. Then, the physicochemical characteristics, auto-cross covariance (ACC), and reduced dipeptides were calculated and integrated to form a mixed feature set, which was processed using correlation analysis, feature selection, and principal component analysis (PCA) to remove redundant information. Finally, four machine learning methods and a dataset containing 500 random observations out of 915 thermophilic proteins and 500 random samples out of 793 non-thermophilic proteins were used to train and predict the data. The experimental results showed that 98.2% of thermophilic and non-thermophilic proteins were correctly identified using 10-fold cross-validation. Moreover, our analysis of the final reserved features and removed features yielded information about the crucial, unimportant and insensitive elements, it also provided essential information for enzyme design.

Dancing while self-eating: Protein intrinsic disorder in autophagy

Autophagy is a major catabolic pathway that must be tightly regulated to maintain cellular homeostasis. Protein intrinsic disorder provides a very suitable conformation for regulation; accordingly, the molecular machinery of autophagy is significantly enriched in intrinsically disordered proteins and protein regions (IDPs/IDPRs). Despite experimental challenges that the characterization of IDPRs encounters, remarkable progress has been made in recent years in revealing various roles of IDPs/IDPRs in autophagy. This chapter describes the autophagy pathway from a specific point of view, that of IDPRs. It focuses in detail on structural and mechanistic functions in autophagy that are executed by disordered regions. Via a description of autophagosome biogenesis, linking the cargo to the autophagy machinery, as well as a discussion of certain post-translational regulations, this review reveals many indispensable roles of IDPRs in the functional autophagy pathway. Devastating pathologies such as neurodegeneration, cancer, or diabetes have been linked to a malfunction in IDPs/IDPRs. The same pathologies are associated with dysfunctional autophagy, indicating that autophagic IDPRs may be a paramount causative factor. Several disease-related mechanisms of the autophagy pathway involving protein intrinsic disorder are reported in this chapter, to illustrate a wide-ranging potential of IDPRs in the therapeutic modulation of autophagy.

Simple Selection Procedure to Distinguish between Static and Flexible Loops

Loops are the most variable and unorganized elements of the secondary structure of proteins. Their ability to shift their shape can play a role in the binding of small ligands, enzymatic catalysis, or protein–protein interactions. Due to the loop flexibility, the positions of their residues in solved structures show the largest B-factors, or in a worst-case scenario can be unknown. Based on the loops’ movements’ timeline, they can be divided into slow (static) and fast (flexible). Although most of the loops that are missing in experimental structures belong to the flexible loops group, the computational tools for loop reconstruction use a set of static loop conformations to predict the missing part of the structure and evaluate the model. We believe that these two loop types can adopt different conformations and that using scoring functions appropriate for static loops is not sufficient for flexible loops. We showed that common model evaluation methods, are insufficient in the case of flexible solvent-exposed loops. Instead, we recommend using the potential energy to evaluate such loop models. We provide a novel model selection method based on a set of geometrical parameters to distinguish between flexible and static loops without the use of molecular dynamics simulations. We have also pointed out the importance of water network and interactions with the solvent for the flexible loop modeling.

SPOT-Disorder2: Improved Protein Intrinsic Disorder Prediction by Ensembled Deep Learning

Intrinsically disordered or unstructured proteins (or regions in proteins) have been found to be important in a wide range of biological functions and implicated in many diseases. Due to the high cost and low efficiency of experimental determination of intrinsic disorder and the exponential increase of unannotated protein sequences, developing complementary computational prediction methods has been an active area of research for several decades. Here, we employed an ensemble of deep Squeeze-and-Excitation residual inception and long short-term memory (LSTM) networks for predicting protein intrinsic disorder with input from evolutionary information and predicted one-dimensional structural properties. The method, called SPOT-Disorder2, offers substantial and consistent improvement not only over our previous technique based on LSTM networks alone, but also over other state-of-the-art techniques in three independent tests with different ratios of disordered to ordered amino acid residues, and for sequences with either rich or limited evolutionary information. More importantly, semi-disordered regions predicted in SPOT-Disorder2 are more accurate in identifying molecular recognition features (MoRFs) than methods directly designed for MoRFs prediction. SPOT-Disorder2 is available as a web server and as a standalone program at https://sparks-lab.org/server/spot-disorder2/.

RFPR-IDP: reduce the false positive rates for intrinsically disordered protein and region prediction by incorporating both fully ordered proteins and disordered proteins

As an important type of proteins, intrinsically disordered proteins/regions (IDPs/IDRs) are related to many crucial biological functions. Accurate prediction of IDPs/IDRs is beneficial to the prediction of protein structures and functions. Most of the existing methods ignore the fully ordered proteins without IDRs during training and test processes. As a result, the corresponding predictors prefer to predict the fully ordered proteins as disordered proteins. Unfortunately, these methods were only evaluated on datasets consisting of disordered proteins without or with only a few fully ordered proteins, and therefore, this problem escapes the attention of the researchers. However, most of the newly sequenced proteins are fully ordered proteins in nature. These predictors fail to accurately predict the ordered and disordered proteins in real-world applications. In this regard, we propose a new method called RFPR-IDP trained with both fully ordered proteins and disordered proteins, which is constructed based on the combination of convolution neural network (CNN) and bidirectional long short-term memory (BiLSTM). The experimental results show that although the existing predictors perform well for predicting the disordered proteins, they tend to predict the fully ordered proteins as disordered proteins. In contrast, the RFPR-IDP predictor can correctly predict the fully ordered proteins and outperform the other 10 state-of-the-art methods when evaluated on a test dataset with both fully ordered proteins and disordered proteins. The web server and datasets of RFPR-IDP are freely available at http://bliulab.net/RFPR-IDP/server.

Progress in the development of antimicrobial peptide prediction tools

Antimicrobial peptides (AMPs) are natural polypeptides with antimicrobial activities and are found in most organisms. AMPs are evolutionarily conservative components that belong to the innate immune system and show potent activity against bacteria, fungi, viruses and in some cases display antitumor activity. Thus, AMPs are major candidates in the development of new antibacterial reagents. In the last few decades, AMPs have attracted significant attention from the research community. During the early stages of the development of this research field, AMPs were experimentally identified, which is an expensive and time-consuming procedure. Therefore, research and development (R&D) of fast, highly efficient computational tools for predicting AMPs has enabled the rapid identification and analysis of new AMPs from a wide range of organisms. Moreover, these computational tools have allowed researchers to better understand the activities of AMPs, which has promoted R&D of antibacterial drugs. In this review, we systematically summarize AMP prediction tools and their corresponding algorithms used.

DISOselect: Disorder predictor selection at the protein level

The intense interest in the intrinsically disordered proteins in the life science community, together with the remarkable advancements in predictive technologies, have given rise to the development of a large number of computational predictors of intrinsic disorder from protein sequence. While the growing number of predictors is a positive trend, we have observed a considerable difference in predictive quality among predictors for individual proteins. Furthermore, variable predictor performance is often inconsistent between predictors for different proteins, and the predictor that shows the best predictive performance depends on the unique properties of each protein sequence. We propose a computational approach, DISOselect, to estimate the predictive performance of 12 selected predictors for individual proteins based on their unique sequence-derived properties. This estimation informs the users about the expected predictive quality for a selected disorder predictor and can be used to recommend methods that are likely to provide the best quality predictions. Our solution does not depend on the results of any disorder predictor; the estimations are made based solely on the protein sequence. Our solution significantly improves predictive performance, as judged with a test set of 1,000 proteins, when compared to other alternatives. We have empirically shown that by using the recommended methods the overall predictive performance for a given set of proteins can be improved by a statistically significant margin. DISOselect is freely available for non-commercial users through the webserver at http://biomine.cs.vcu.edu/servers/DISOselect/.

Selecting Essential MicroRNAs Using a Novel Voting Method

Among the large number of known microRNAs (miRNAs), some miRNAs play negligible roles in cell regulation. Therefore, selecting essential miRNAs is an important initial step for a deeper understanding of miRNAs and their functions. In this study, we generated 60 classification models by combining 12 representative feature extraction methods and 5 commonly used classification algorithms. The optimal model for essential miRNA classification that we obtained is based on the Mismatch feature extraction method combined with the random forest algorithm. The F-Measure, area under the curve, and accuracy values of this model were 93.2%, 96.7%, and 93.0%, respectively. We also found that the distribution of the positive and negative examples of the first few features greatly influenced the classification results. The feature extraction methods performed best when the differences between the positive and negative examples were obvious, and this led to better classification of essential miRNAs. Because each classifier's predictions for the same sample may be different, we employed a novel voting method to improve the accuracy of the classification of essential miRNAs. The performance results showed that the best classification results were obtained when five classification models were used in the voting. The five classification models were constructed based on the Mismatch, pseudo-distance structure status pair composition, Subsequence, Kmer, and Triplet feature extraction methods. The voting result was 95.3%. Our results suggest that the voting method can be an important tool for selecting essential miRNAs.

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

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

A comprehensive review and evaluation of computational methods for identifying protein complexes from protein–protein interaction networks

Protein complexes are the fundamental units for many cellular processes. Identifying protein complexes accurately is critical for understanding the functions and organizations of cells. With the increment of genome-scale protein–protein interaction (PPI) data for different species, various computational methods focus on identifying protein complexes from PPI networks. In this article, we give a comprehensive and updated review on the state-of-the-art computational methods in the field of protein complex identification, especially focusing on the newly developed approaches. The computational methods are organized into three categories, including cluster-quality-based methods, node-affinity-based methods and ensemble clustering methods. Furthermore, the advantages and disadvantages of different methods are discussed, and then, the performance of 17 state-of-the-art methods is evaluated on two widely used benchmark data sets. Finally, the bottleneck problems and their potential solutions in this important field are discussed.

Accuracy of protein-level disorder predictions

Experimental annotations of intrinsic disorder are available for 0.1% of 147 000 000 of currently sequenced proteins. Over 60 sequence-based disorder predictors were developed to help bridge this gap. Current benchmarks of these methods assess predictive performance on datasets of proteins; however, predictions are often interpreted for individual proteins. We demonstrate that the protein-level predictive performance varies substantially from the dataset-level benchmarks. Thus, we perform first-of-its-kind protein-level assessment for 13 popular disorder predictors using 6200 disorder-annotated proteins. We show that the protein-level distributions are substantially skewed toward high predictive quality while having long tails of poor predictions. Consequently, between 57% and 75% proteins secure higher predictive performance than the currently used dataset-level assessment suggests, but as many as 30% of proteins that are located in the long tails suffer low predictive performance. These proteins typically have relatively high amounts of disorder, in contrast to the mostly structured proteins that are predicted accurately by all 13 methods. Interestingly, each predictor provides the most accurate results for some number of proteins, while the best-performing at the dataset-level method is in fact the best for only about 30% of proteins. Moreover, the majority of proteins are predicted more accurately than the dataset-level performance of the most accurate tool by at least four disorder predictors. While these results suggests that disorder predictors outperform their current benchmark performance for the majority of proteins and that they complement each other, novel tools that accurately identify the hard-to-predict proteins and that make accurate predictions for these proteins are needed.

A Random Forest Sub-Golgi Protein Classifier Optimized via Dipeptide and Amino Acid Composition Features

To gain insight into the malfunction of the Golgi apparatus and its relationship to various genetic and neurodegenerative diseases, the identification of sub-Golgi proteins, both cis-Golgi and trans-Golgi proteins, is of great significance. In this study, a state-of-art random forests sub-Golgi protein classifier, rfGPT, was developed. The rfGPT used 2-gap dipeptide and split amino acid composition for the feature vectors and was combined with the synthetic minority over-sampling technique (SMOTE) and an analysis of variance (ANOVA) feature selection method. The rfGPT was trained on a sub-Golgi protein sequence data set (137 sequences), with sequence identity less than 25%. For the optimal rfGPT classifier with 93 features, the accuracy (ACC) was 90.5%; the Matthews correlation coefficient (MCC) was 0.811; the sensitivity (Sn) was 92.6%; and the specificity (Sp) was 88.4%. The independent testing scores for the rfGPT were ACC = 90.6%; MCC = 0.696; Sn = 96.1%; and Sp = 69.2%. Although the independent testing accuracy was 4.4% lower than that for the best reported sub-Golgi classifier trained on a data set with 40% sequence identity (304 sequences), the rfGPT is currently the top sub-Golgi protein predictor utilizing feature vectors without any position-specific scoring matrix and its derivative features. Therefore, the rfGPT is a more practical tool, because no sequence alignment is required with tens of millions of protein sequences. To date, the rfGPT is the Golgi classifier with the best independent testing scores, optimized by training on smaller benchmark data sets. Feature importance analysis proves that the non-polar and aliphatic residues composition, the (aromatic residues) + (non-polar, aliphatic residues) dipeptide and aromatic residues composition between NH2-termial and COOH-terminal of protein sequences are the three top biological features for distinguishing the sub-Golgi proteins.

Orchestration of algal metabolism by protein disorder

Intrinsically disordered proteins (IDPs) are proteins that provide many functional advantages in a large number of metabolic and signalling pathways. Because of their high flexibility that endows them with pressure-, heat- and acid-resistance, IDPs are valuable metabolic regulators that help algae to cope with extreme conditions of pH, temperature, pressure and light. They have, however, been overlooked in these organisms. In this review, we present some well-known algal IDPs, including the conditionally disordered CP12, a protein involved in the regulation of CO₂ assimilation, as probably the best known example, whose disorder content is strongly dependent on the redox conditions, and the essential pyrenoid component 1 that serves as a scaffold for ribulose-1, 5-bisphosphate carboxylase/oxygenase. We also describe how some enzymes are regulated by protein regions, called intrinsically disordered regions (IDRs), such as ribulose-1, 5-bisphosphate carboxylase/oxygenase activase, the A₂B₂ form of glyceraldehyde-3-phosphate dehydrogenase and the adenylate kinase. Several molecular chaperones, which are crucial for cell proteostasis, also display significant disorder propensities such as the algal heat shock proteins HSP33, HSP70 and HSP90. This review confirms the wide distribution of IDPs in algae but highlights that further studies are needed to uncover their full role in orchestrating algal metabolism.

Identification of Intrinsically Disordered Proteins and Regions by Length-Dependent Predictors Based on Conditional Random Fields

Accurate identification of intrinsically disordered proteins/regions (IDPs/IDRs) is critical for predicting protein structure and function. Previous studies have shown that IDRs of different lengths have different characteristics, and several classification-based predictors have been proposed for predicting different types of IDRs. Compared with these classification-based predictors, the previously proposed predictor IDP-CRF exhibits state-of-the-art performance for predicting IDPs/IDRs, which is a sequence labeling model based on conditional random fields (CRFs). Motivated by these methods, we propose a predictor called IDP-FSP, which is an ensemble of three CRF-based predictors called IDP-FSP-L, IDP-FSP-S, and IDP-FSP-G. These three predictors are specially designed to predict long, short, and generic disordered regions, respectively, and they are constructed based on different features. To the best of our knowledge, IDP-FSP is the first predictor that combines a sequence labeling algorithm with IDRs of different lengths. Experimental results using two independent test datasets show that IDP-FSP achieves better or at least comparable predictive performance with 26 existing state-of-the-art methods in this field, proving the effectiveness of IDP-FSP.

iCircDA-MF: identification of circRNA-disease associations based on matrix factorization

Circular RNAs (circRNAs) are a group of novel discovered non-coding RNAs with closed-loop structure, which play critical roles in various biological processes. Identifying associations between circRNAs and diseases is critical for exploring the complex disease mechanism and facilitating disease-targeted therapy. Although several computational predictors have been proposed, their performance is still limited. In this study, a novel computational method called iCircDA-MF is proposed. Because the circRNA-disease associations with experimental validation are very limited, the potential circRNA-disease associations are calculated based on the circRNA similarity and disease similarity extracted from the disease semantic information and the known associations of circRNA-gene, gene-disease and circRNA-disease. The circRNA-disease interaction profiles are then updated by the neighbour interaction profiles so as to correct the false negative associations. Finally, the matrix factorization is performed on the updated circRNA-disease interaction profiles to predict the circRNA-disease associations. The experimental results on a widely used benchmark dataset showed that iCircDA-MF outperforms other state-of-the-art predictors and can identify new circRNA-disease associations effectively.

Evaluation of different computational methods on 5-methylcytosine sites identification

5-Methylcytosine (m5C) plays an extremely important role in the basic biochemical process. With the great increase of identified m5C sites in a wide variety of organisms, their epigenetic roles become largely unknown. Hence, accurate identification of m5C site is a key step in understanding its biological functions. Over the past several years, more attentions have been paid on the identification of m5C sites in multiple species. In this work, we firstly summarized the current progresses in computational prediction of m5C sites and then constructed a more powerful and reliable model for identifying m5C sites. To train the model, we collected experimentally confirmed m5C data from Homo sapiens, Mus musculus, Saccharomyces cerevisiae and Arabidopsis thaliana, and compared the performances of different feature extraction methods and classification algorithms for optimizing prediction model. Based on the optimal model, a novel predictor called iRNA-m5C was developed for the recognition of m5C sites. Finally, we critically evaluated the performance of iRNA-m5C and compared it with existing methods. The result showed that iRNA-m5C could produce the best prediction performance. We hope that this paper could provide a guide on the computational identification of m5C site and also anticipate that the proposed iRNA-m5C will become a powerful tool for large scale identification of m5C sites.

Predicting Ion Channels Genes and Their Types With Machine Learning Techniques

Motivation: The number of ion channels is increasing rapidly. As many of them are associated with diseases, they are the targets of more than 700 drugs. The discovery of new ion channels is facilitated by computational methods that predict ion channels and their types from protein sequences. Methods: We used the SVMProt and the k-skip-n-gram methods to extract the feature vectors of ion channels, and obtained 188- and 400-dimensional features, respectively. The 188- and 400-dimensional features were combined to obtain 588-dimensional features. We then employed the maximum-relevance-maximum-distance method to reduce the dimensions of the 588-dimensional features. Finally, the support vector machine and random forest methods were used to build the prediction models to evaluate the classification effect. Results: Different methods were employed to extract various feature vectors, and after effective dimensionality reduction, different classifiers were used to classify the ion channels. We extracted the ion channel data from the Universal Protein Resource (UniProt, http://www.uniprot.org/) and Ligand-Gated Ion Channel databases (http://www.ebi.ac.uk/compneur-srv/LGICdb/LGICdb.php), and then verified the performance of the classifiers after screening. The findings of this study could inform the research and development of drugs.

Sequence Effects on Size, Shape, and Structural Heterogeneity in Intrinsically Disordered Proteins

Intrinsically disordered proteins (IDPs) lack well-defined three-dimensional structures, thus challenging the archetypal notion of structure-function relationships. Determining the ensemble of conformations that IDPs explore under physiological conditions is the first step toward understanding their diverse cellular functions. Here, we quantitatively characterize the structural features of IDPs as a function of sequence and length using coarse-grained simulations. For diverse IDP sequences, with the number of residues ( NT) ranging from 20 to 441, our simulations not only reproduce the radii of gyration ( Rg) obtained from experiments, but also predict the full scattering intensity profiles in excellent agreement with small-angle X-ray scattering experiments. The Rg values are well-described by the standard Flory scaling law, Rg = Rg0 NTν, with ν ≈ 0.588, making it tempting to assert that IDPs behave as polymers in a good solvent. However, clustering analysis reveals that the menagerie of structures explored by IDPs is diverse, with the extent of heterogeneity being highly sequence-dependent, even though ensemble-averaged properties, such as the dependence of Rg on chain length, may suggest synthetic polymer-like behavior in a good solvent. For example, we show that for the highly charged Prothymosin-α, a substantial fraction of conformations is highly compact. Even if the sequence compositions are similar, as is the case for α-Synuclein and a truncated construct from the Tau protein, there are substantial differences in the conformational heterogeneity. Taken together, these observations imply that metrics based on net charge or related quantities alone cannot be used to anticipate the phases of IDPs, either in isolation or in complex with partner IDPs or RNA. Our work sets the stage for probing the interactions of IDPs with each other, with folded protein domains, or with partner RNAs, which are critical for describing the structures of stress granules and biomolecular condensates with important cellular functions.

Identification of Phage Viral Proteins With Hybrid Sequence Features

The uniqueness of bacteriophages plays an important role in bioinformatics research. In real applications, the function of the bacteriophage virion proteins is the main area of interest. Therefore, it is very important to classify bacteriophage virion proteins and non-phage virion proteins accurately. Extracting comprehensive and effective sequence features from proteins plays a vital role in protein classification. In order to more fully represent protein information, this paper is more comprehensive and effective by combining the features extracted by the feature information representation algorithm based on sequence information (CCPA) and the feature representation algorithm based on sequence and structure information. After extracting features, the Max-Relevance-Max-Distance (MRMD) algorithm is used to select the optimal feature set with the strongest correlation between class labels and low redundancy between features. Given the randomness of the samples selected by the random forest classification algorithm and the randomness features for producing each node variable, a random forest method is employed to perform 10-fold cross-validation on the bacteriophage protein classification. The accuracy of this model is as high as 93.5% in the classification of phage proteins in this study. This study also found that, among the eight physicochemical properties considered, the charge property has the greatest impact on the classification of bacteriophage proteins These results indicate that the model discussed in this paper is an important tool in bacteriophage protein research.

MinE-RFE: determine the optimal subset from RFE by minimizing the subset-accuracy–defined energy

Recursive feature elimination (RFE), as one of the most popular feature selection algorithms, has been extensively applied to bioinformatics. During the training, a group of candidate subsets are generated by iteratively eliminating the least important features from the original features. However, how to determine the optimal subset from them still remains ambiguous. Among most current studies, either overall accuracy or subset size (SS) is used to select the most predictive features. Using which one or both and how they affect the prediction performance are still open questions. In this study, we proposed MinE-RFE, a novel RFE-based feature selection approach by sufficiently considering the effect of both factors. Subset decision problem was reflected into subset-accuracy space and became an energy-minimization problem. We also provided a mathematical description of the relationship between the overall accuracy and SS using Gaussian Mixture Models together with spline fitting. Besides, we comprehensively reviewed a variety of state-of-the-art applications in bioinformatics using RFE. We compared their approaches of deciding the final subset from all the candidate subsets with MinE-RFE on diverse bioinformatics data sets. Additionally, we also compared MinE-RFE with some well-used feature selection algorithms. The comparative results demonstrate that the proposed approach exhibits the best performance among all the approaches. To facilitate the use of MinE-RFE, we further established a user-friendly web server with the implementation of the proposed approach, which is accessible at http://qgking.wicp.net/MinE/. We expect this web server will be a useful tool for research community.

A Review of DNA-binding Proteins Prediction Methods

Background:

DNA-binding proteins, binding to DNA, widely exist in living cells, participating in many cell activities. They can participate some DNA-related cell activities, for instance DNA replication, transcription, recombination, and DNA repair.

Objective:

Given the importance of DNA-binding proteins, studies for predicting the DNA-binding proteins have been a popular issue over the past decades. In this article, we review current machine-learning methods which research on the prediction of DNA-binding proteins through feature representation methods, classifiers, measurements, dataset and existing web server.

Method:

The prediction methods of DNA-binding protein can be divided into two types, based on amino acid composition and based on protein structure. In this article, we accord to the two types methods to introduce the application of machine learning in DNA-binding proteins prediction.

Results:

Machine learning plays an important role in the classification of DNA-binding proteins, and the result is better. The best ACC is above 80%.

Conclusion:

Machine learning can be widely used in many aspects of biological information, especially in protein classification. Some issues should be considered in future work. First, the relationship between the number of features and performance must be explored. Second, many features are used to predict DNA-binding proteins and propose solutions for high-dimensional spaces.

k-Skip-n-Gram-RF: A Random Forest Based Method for Alzheimer's Disease Protein Identification

In this paper, a computational method based on machine learning technique for identifying Alzheimer's disease genes is proposed. Compared with most existing machine learning based methods, existing methods predict Alzheimer's disease genes by using structural magnetic resonance imaging (MRI) technique. Most methods have attained acceptable results, but the cost is expensive and time consuming. Thus, we proposed a computational method for identifying Alzheimer disease genes by use of the sequence information of proteins, and classify the feature vectors by random forest. In the proposed method, the gene protein information is extracted by adaptive k-skip-n-gram features. The proposed method can attain the accuracy to 85.5% on the selected UniProt dataset, which has been demonstrated by the experimental results.

Protein fold recognition based on multi-view modeling

Motivation

Protein fold recognition has attracted increasing attention because it is critical for studies of the 3D structures of proteins and drug design. Researchers have been extensively studying this important task, and several features with high discriminative power have been proposed. However, the development of methods that efficiently combine these features to improve the predictive performance remains a challenging problem.

Results

In this study, we proposed two algorithms: MV-fold and MT-fold. MV-fold is a new computational predictor based on the multi-view learning model for fold recognition. Different features of proteins were treated as different views of proteins, including the evolutionary information, secondary structure information and physicochemical properties. These different views constituted the latent space. The ε-dragging technique was employed to enlarge the margins between different protein folds, improving the predictive performance of MV-fold. Then, MV-fold was combined with two template-based methods: HHblits and HMMER. The ensemble method is called MT-fold incorporating the advantages of both discriminative methods and template-based methods. Experimental results on five widely used benchmark datasets (DD, RDD, EDD, TG and LE) showed that the proposed methods outperformed some state-of-the-art methods in this field, indicating that MV-fold and MT-fold are useful computational tools for protein fold recognition and protein homology detection and would be efficient tools for protein sequence analysis. Finally, we constructed an update and rigorous benchmark dataset based on SCOPe (version 2.07) to fairly evaluate the performance of the proposed method, and our method achieved stable performance on this new dataset. This new benchmark dataset will become a widely used benchmark dataset to fairly evaluate the performance of different methods for fold recognition.

Supplementary information

Supplementary data are available at Bioinformatics online.

IDP⁻CRF: Intrinsically Disordered Protein/Region Identification Based on Conditional Random Fields

Accurate prediction of intrinsically disordered proteins/regions is one of the most important tasks in bioinformatics, and some computational predictors have been proposed to solve this problem. How to efficiently incorporate the sequence-order effect is critical for constructing an accurate predictor because disordered region distributions show global sequence patterns. In order to capture these sequence patterns, several sequence labelling models have been applied to this field, such as conditional random fields (CRFs). However, these methods suffer from certain disadvantages. In this study, we proposed a new computational predictor called IDP⁻CRF, which is trained on an updated benchmark dataset based on the MobiDB database and the DisProt database, and incorporates more comprehensive sequence-based features, including PSSMs (position-specific scoring matrices), kmer, predicted secondary structures, and relative solvent accessibilities. Experimental results on the benchmark dataset and two independent datasets show that IDP⁻CRF outperforms 25 existing state-of-the-art methods in this field, demonstrating that IDP⁻CRF is a very useful tool for identifying IDPs/IDRs (intrinsically disordered proteins/regions). We anticipate that IDP⁻CRF will facilitate the development of protein sequence analysis.