Protein subcellular localization prediction tools.

Protein subcellular localization prediction is of great significance in bioinformatics and biological research. Most of the proteins do not have experimentally determined localization information, computational prediction methods and tools have been acting as an active research area for more than two decades now. Knowledge of the subcellular location of a protein provides valuable information about its functionalities, the functioning of the cell, and other possible interactions with proteins. Fast, reliable, and accurate predictors provides platforms to harness the abundance of sequence data to predict subcellular locations accordingly. During the last decade, there has been a considerable amount of research effort aimed at developing subcellular localization predictors. This paper reviews recent subcellular localization prediction tools in the Eukaryotic, Prokaryotic, and Virus-based categories followed by a detailed analysis. Each predictor is discussed based on its main features, strengths, weaknesses, algorithms used, prediction techniques, and analysis. This review is supported by prediction tools taxonomies that highlight their rele- vant area and examples for uncomplicated categorization and ease of understandability. These taxonomies help users find suitable tools according to their needs. Furthermore, recent research gaps and challenges are discussed to cover areas that need the utmost attention. This survey provides an in-depth analysis of the most recent prediction tools to facilitate readers and can be considered a quick guide for researchers to identify and explore the recent literature advancements.

SCLpred-ECL: Subcellular Localization Prediction by Deep N-to-1 Convolutional Neural Networks.

The subcellular location of a protein provides valuable insights to bioinformaticians in terms of drug designs and discovery, genomics, and various other aspects of medical research. Experimental methods for protein subcellular localization determination are time-consuming and expensive, whereas computational methods, if accurate, would represent a much more efficient alternative. This article introduces an ab initio protein subcellular localization predictor based on an ensemble of Deep N-to-1 Convolutional Neural Networks. Our predictor is trained and tested on strict redundancy-reduced datasets and achieves 63% accuracy for the diverse number of classes. This predictor is a step towards bridging the gap between a protein sequence and the protein's function. It can potentially provide information about protein-protein interaction to facilitate drug design and processes like vaccine production that are essential to disease prevention.

Benefiting from the intrinsic role of epigenetics to predict patterns of CTCF binding.

Motivation: One of the most relevant mechanisms involved in the determination of chromatin structure is the formation of structural loops that are also related with the conservation of chromatin states. Many of these loops are stabilized by CCCTC-binding factor (CTCF) proteins at their base. Despite the relevance of chromatin structure and the key role of CTCF, the role of the epigenetic factors that are involved in the regulation of CTCF binding, and thus, in the formation of structural loops in the chromatin, is not thoroughly understood. Results: Here we describe a CTCF binding predictor based on Random Forest that employs different epigenetic data and genomic features. Importantly, given the ability of Random Forests to determine the relevance of features for the prediction, our approach also shows how the different types of descriptors impact the binding of CTCF, confirming previous knowledge on the relevance of chromatin accessibility and DNA methylation, but demonstrating the effect of epigenetic modifications on the activity of CTCF. We compared our approach against other predictors and found improved performance in terms of areas under PR and ROC curves (PRAUC-ROCAUC), outperforming current state-of-the-art methods.

SCLpred-MEM: Subcellular localization prediction of membrane proteins by deep N-to-1 convolutional neural networks.

The knowledge of the subcellular location of a protein is a valuable source of information in genomics, drug design, and various other theoretical and analytical perspectives of bioinformatics. Due to the expensive and time-consuming nature of experimental methods of protein subcellular location determination, various computational methods have been developed for subcellular localization prediction. We introduce "SCLpred-MEM," an ab initio protein subcellular localization predictor, powered by an ensemble of Deep N-to-1 Convolutional Neural Networks (N1-NN) trained and tested on strict redundancy reduced datasets. SCLpred-MEM is available as a web-server predicting query proteins into two classes, membrane and non-membrane proteins. SCLpred-MEM achieves a Matthews correlation coefficient of 0.52 on a strictly homology-reduced independent test set and 0.62 on a less strict homology reduced independent test set, surpassing or matching other state-of-the-art subcellular localization predictors.

Protein profiles: Biases and protocols.

The use of evolutionary profiles to predict protein secondary structure, as well as other protein structural features, has been standard practice since the 1990s. Using profiles in the input of such predictors, in place or in addition to the sequence itself, leads to significantly more accurate predictions. While profiles can enhance structural signals, their role remains somewhat surprising as proteins do not use profiles when folding in vivo. Furthermore, the same sequence-based redundancy reduction protocols initially derived to train and evaluate sequence-based predictors, have been applied to train and evaluate profile-based predictors. This can lead to unfair comparisons since profiles may facilitate the bleeding of information between training and test sets. Here we use the extensively studied problem of secondary structure prediction to better evaluate the role of profiles and show that: (1) high levels of profile similarity between training and test proteins are observed when using standard sequence-based redundancy protocols; (2) the gain in accuracy for profile-based predictors, over sequence-based predictors, strongly relies on these high levels of profile similarity between training and test proteins; and (3) the overall accuracy of a profile-based predictor on a given protein dataset provides a biased measure when trying to estimate the actual accuracy of the predictor, or when comparing it to other predictors. We show, however, that this bias can be mitigated by implementing a new protocol (EVALpro) which evaluates the accuracy of profile-based predictors as a function of the profile similarity between training and test proteins. Such a protocol not only allows for a fair comparison of the predictors on equally hard or easy examples, but also reduces the impact of choosing a given similarity cutoff when selecting test proteins. The EVALpro program is available in the SCRATCH suite ( www.scratch.proteomics.ics.uci.edu) and can be downloaded at: www.download.igb.uci.edu/#evalpro.

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.

Prediction of polyproline II secondary structure propensity in proteins.

Background: The polyproline II helix (PPIIH) is an extended protein left-handed secondary structure that usually but not necessarily involves prolines. Short PPIIHs are frequently, but not exclusively, found in disordered protein regions, where they may interact with peptide-binding domains. However, no readily usable software is available to predict this state. Results: We developed PPIIPRED to predict polyproline II helix secondary structure from protein sequences, using bidirectional recurrent neural networks trained on known three-dimensional structures with dihedral angle filtering. The performance of the method was evaluated in an external validation set. In addition to proline, PPIIPRED favours amino acids whose side chains extend from the backbone (Leu, Met, Lys, Arg, Glu, Gln), as well as Ala and Val. Utility for individual residue predictions is restricted by the rarity of the PPIIH feature compared to structurally common features. Conclusion: The software, available at http://bioware.ucd.ie/PPIIPRED, is useful in large-scale studies, such as evolutionary analyses of PPIIH, or computationally reducing large datasets of candidate binding peptides for further experimental validation.

Brewery: deep learning and deeper profiles for the prediction of 1D protein structure annotations.

MOTIVATION: Protein structural annotations (PSAs) are essential abstractions to deal with the prediction of protein structures. Many increasingly sophisticated PSAs have been devised in the last few decades. However, the need for annotations that are easy to compute, process and predict has not diminished. This is especially true for protein structures that are hardest to predict, such as novel folds. RESULTS: We propose Brewery, a suite of ab initio predictors of 1D PSAs. Brewery uses multiple sources of evolutionary information to achieve state-of-the-art predictions of secondary structure, structural motifs, relative solvent accessibility and contact density. AVAILABILITY AND IMPLEMENTATION: The web server, standalone program, Docker image and training sets of Brewery are available at http://distilldeep.ucd.ie/brewery/. CONTACT: gianluca.pollastri@ucd.ie.

SCLpred-EMS: subcellular localization prediction of endomembrane system and secretory pathway proteins by Deep N-to-1 Convolutional Neural Networks.

MOTIVATION: The subcellular location of a protein can provide useful information for protein function prediction and drug design. Experimentally determining the subcellular location of a protein is an expensive and time-consuming task. Therefore, various computer-based tools have been developed, mostly using machine learning algorithms, to predict the subcellular location of proteins. RESULTS: Here, we present a neural network-based algorithm for protein subcellular location prediction. We introduce SCLpred-EMS a subcellular localization predictor powered by an ensemble of Deep N-to-1 Convolutional Neural Networks. SCLpred-EMS predicts the subcellular location of a protein into two classes, the endomembrane system and secretory pathway versus all others, with a Matthews correlation coefficient of 0.75-0.86 outperforming the other state-of-the-art web servers we tested. AVAILABILITY AND IMPLEMENTATION: SCLpred-EMS is freely available for academic users at http://distilldeep.ucd.ie/SCLpred2/. CONTACT: catherine.mooney@ucd.ie.

Deeper Profiles and Cascaded Recurrent and Convolutional Neural Networks for state-of-the-art Protein Secondary Structure Prediction.

Protein Secondary Structure prediction has been a central topic of research in Bioinformatics for decades. In spite of this, even the most sophisticated ab initio SS predictors are not able to reach the theoretical limit of three-state prediction accuracy (88-90%), while only a few predict more than the 3 traditional Helix, Strand and Coil classes. In this study we present tests on different models trained both on single sequence and evolutionary profile-based inputs and develop a new state-of-the-art system with Porter 5. Porter 5 is composed of ensembles of cascaded Bidirectional Recurrent Neural Networks and Convolutional Neural Networks, incorporates new input encoding techniques and is trained on a large set of protein structures. Porter 5 achieves 84% accuracy (81% SOV) when tested on 3 classes and 73% accuracy (70% SOV) on 8 classes on a large independent set. In our tests Porter 5 is 2% more accurate than its previous version and outperforms or matches the most recent predictors of secondary structure we tested. When Porter 5 is retrained on SCOPe based sets that eliminate homology between training/testing samples we obtain similar results. Porter is available as a web server and standalone program at http://distilldeep.ucd.ie/porter/ alongside all the datasets and alignments.

PaleAle 5.0: prediction of protein relative solvent accessibility by deep learning.

Predicting the three-dimensional structure of proteins is a long-standing challenge of computational biology, as the structure (or lack of a rigid structure) is well known to determine a protein's function. Predicting relative solvent accessibility (RSA) of amino acids within a protein is a significant step towards resolving the protein structure prediction challenge especially in cases in which structural information about a protein is not available by homology transfer. Today, arguably the core of the most powerful prediction methods for predicting RSA and other structural features of proteins is some form of deep learning, and all the state-of-the-art protein structure prediction tools rely on some machine learning algorithm. In this article we present a deep neural network architecture composed of stacks of bidirectional recurrent neural networks and convolutional layers which is capable of mining information from long-range interactions within a protein sequence and apply it to the prediction of protein RSA using a novel encoding method that we shall call "clipped". The final system we present, PaleAle 5.0, which is available as a public server, predicts RSA into two, three and four classes at an accuracy exceeding 80% in two classes, surpassing the performances of all the other predictors we have benchmarked.

Correct machine learning on protein sequences: a peer-reviewing perspective.

Machine learning methods are becoming increasingly popular to predict protein features from sequences. Machine learning in bioinformatics can be powerful but carries also the risk of introducing unexpected biases, which may lead to an overestimation of the performance. This article espouses a set of guidelines to allow both peer reviewers and authors to avoid common machine learning pitfalls. Understanding biology is necessary to produce useful data sets, which have to be large and diverse. Separating the training and test process is imperative to avoid over-selling method performance, which is also dependent on several hidden parameters. A novel predictor has always to be compared with several existing methods, including simple baseline strategies. Using the presented guidelines will help nonspecialists to appreciate the critical issues in machine learning.

Accurate Ab Initio and Template-Based Prediction of Short Intrinsically-Disordered Regions by Bidirectional Recurrent Neural Networks Trained on Large-Scale Datasets.

Intrinsically-disordered regions lack a well-defined 3D structure, but play key roles in determining the function of many proteins. Although predictors of disorder have been shown to achieve relatively high rates of correct classification of these segments, improvements over the the years have been slow, and accurate methods are needed that are capable of accommodating the ever-increasing amount of structurally-determined protein sequences to try to boost predictive performances. In this paper, we propose a predictor for short disordered regions based on bidirectional recurrent neural networks and tested by rigorous five-fold cross-validation on a large, non-redundant dataset collected from MobiDB, a new comprehensive source of protein disorder annotations. The system exploits sequence and structural information in the forms of frequency profiles, predicted secondary structure and solvent accessibility and direct disorder annotations from homologous protein structures (templates) deposited in the Protein Data Bank. The contributions of sequence, structure and homology information result in large improvements in predictive accuracy. Additionally, the large scale of the training set leads to low false positive rates, making our systems a robust and efficient way to address high-throughput disorder prediction.

Reconstructing protein structures by neural network pairwise interaction fields and iterative decoy set construction.

Predicting the fold of a protein from its amino acid sequence is one of the grand problems in computational biology. While there has been progress towards a solution, especially when a protein can be modelled based on one or more known structures (templates), in the absence of templates, even the best predictions are generally much less reliable. In this paper, we present an approach for predicting the three-dimensional structure of a protein from the sequence alone, when templates of known structure are not available. This approach relies on a simple reconstruction procedure guided by a novel knowledge-based evaluation function implemented as a class of artificial neural networks that we have designed: Neural Network Pairwise Interaction Fields (NNPIF). This evaluation function takes into account the contextual information for each residue and is trained to identify native-like conformations from non-native-like ones by using large sets of decoys as a training set. The training set is generated and then iteratively expanded during successive folding simulations. As NNPIF are fast at evaluating conformations, thousands of models can be processed in a short amount of time, and clustering techniques can be adopted for model selection. Although the results we present here are very preliminary, we consider them to be promising, with predictions being generated at state-of-the-art levels in some of the cases.

Toward an accurate prediction of inter-residue distances in proteins using 2D recursive neural networks.

BACKGROUND: Protein inter-residue contact maps provide a translation and rotation invariant topological representation of a protein. They can be used as an intermediary step in protein structure predictions. However, the prediction of contact maps represents an unbalanced problem as far fewer examples of contacts than non-contacts exist in a protein structure.In this study we explore the possibility of completely eliminating the unbalanced nature of the contact map prediction problem by predicting real-value distances between residues. Predicting full inter-residue distance maps and applying them in protein structure predictions has been relatively unexplored in the past. RESULTS: We initially demonstrate that the use of native-like distance maps is able to reproduce 3D structures almost identical to the targets, giving an average RMSD of 0.5Å. In addition, the corrupted physical maps with an introduced random error of ±6Å are able to reconstruct the targets within an average RMSD of 2Å.After demonstrating the reconstruction potential of distance maps, we develop two classes of predictors using two-dimensional recursive neural networks: an ab initio predictor that relies only on the protein sequence and evolutionary information, and a template-based predictor in which additional structural homology information is provided. We find that the ab initio predictor is able to reproduce distances with an RMSD of 6Å, regardless of the evolutionary content provided. Furthermore, we show that the template-based predictor exploits both sequence and structure information even in cases of dubious homology and outperforms the best template hit with a clear margin of up to 3.7Å.Lastly, we demonstrate the ability of the two predictors to reconstruct the CASP9 targets shorter than 200 residues producing the results similar to the state of the machine learning art approach implemented in the Distill server. CONCLUSIONS: The methodology presented here, if complemented by more complex reconstruction protocols, can represent a possible path to improve machine learning algorithms for 3D protein structure prediction. Moreover, it can be used as an intermediary step in protein structure predictions either on its own or complemented by NMR restraints.

SCLpredT: Ab initio and homology-based prediction of subcellular localization by N-to-1 neural networks.

The prediction of protein subcellular localization is a important step towards the prediction of protein function, and considerable effort has gone over the last decade into the development of computational predictors of protein localization. In this article we design a new predictor of protein subcellular localization, based on a Machine Learning model (N-to-1 Neural Networks) which we have recently developed. This system, in three versions specialised, respectively, on Plants, Fungi and Animals, has a rich output which incorporates the class "organelle" alongside cytoplasm, nucleus, mitochondria and extracellular, and, additionally, chloroplast in the case of Plants. We investigate the information gain of introducing additional inputs, including predicted secondary structure, and localization information from homologous sequences. To accommodate the latter we design a new algorithm which we present here for the first time. While we do not observe any improvement when including predicted secondary structure, we measure significant overall gains when adding homology information. The final predictor including homology information correctly predicts 74%, 79% and 60% of all proteins in the case of Fungi, Animals and Plants, respectively, and outperforms our previous, state-of-the-art predictor SCLpred, and the popular predictor BaCelLo. We also observe that the contribution of homology information becomes dominant over sequence information for sequence identity values exceeding 50% for Animals and Fungi, and 60% for Plants, confirming that subcellular localization is less conserved than structure. SCLpredT is publicly available at http://distillf.ucd.ie/sclpredt/. Sequence- or template-based predictions can be obtained, and up to 32kbytes of input can be processed in a single submission.

CPPpred: prediction of cell penetrating peptides.

Cell penetrating peptides (CPPs) are attracting much attention as a means of overcoming the inherently poor cellular uptake of various bioactive molecules. Here, we introduce CPPpred, a web server for the prediction of CPPs using a N-to-1 neural network. The server takes one or more peptide sequences, between 5 and 30 amino acids in length, as input and returns a prediction of how likely each peptide is to be cell penetrating. CPPpred was developed with redundancy reduced training and test sets, offering an advantage over the only other currently available CPP prediction method.

Predicting binding within disordered protein regions to structurally characterised peptide-binding domains.

Disordered regions of proteins often bind to structured domains, mediating interactions within and between proteins. However, it is difficult to identify a priori the short disordered regions involved in binding. We set out to determine if docking such peptide regions to peptide binding domains would assist in these predictions.We assembled a redundancy reduced dataset of SLiM (Short Linear Motif) containing proteins from the ELM database. We selected 84 sequences which had an associated PDB structures showing the SLiM bound to a protein receptor, where the SLiM was found within a 50 residue region of the protein sequence which was predicted to be disordered. First, we investigated the Vina docking scores of overlapping tripeptides from the 50 residue SLiM containing disordered regions of the protein sequence to the corresponding PDB domain. We found only weak discrimination of docking scores between peptides involved in binding and adjacent non-binding peptides in this context (AUC 0.58).Next, we trained a bidirectional recurrent neural network (BRNN) using as input the protein sequence, predicted secondary structure, Vina docking score and predicted disorder score. The results were very promising (AUC 0.72) showing that multiple sources of information can be combined to produce results which are clearly superior to any single source.We conclude that the Vina docking score alone has only modest power to define the location of a peptide within a larger protein region known to contain it. However, combining this information with other knowledge (using machine learning methods) clearly improves the identification of peptide binding regions within a protein sequence. This approach combining docking with machine learning is primarily a predictor of binding to peptide-binding sites, and is not intended as a predictor of specificity of binding to particular receptors.