Motivation Annotation of enzyme function has a broad range of applications, such as metagenomics, industrial biotechnology, and diagnosis of enzyme deficiency-caused diseases. However, the time and resource required make it prohibitively expensive to experimentally determine the function of every enzyme. Therefore, computational enzyme function prediction has become increasingly important. In this paper, we develop such an approach, determining the enzyme function by predicting the Enzyme Commission number. Results We propose an end-to-end feature selection and classification model training approach, as well as an automatic and robust feature dimensionality uniformization method, DEEPre, in the field of enzyme function prediction. Instead of extracting manually crafted features from enzyme sequences, our model takes the raw sequence encoding as inputs, extracting convolutional and sequential features from the raw encoding based on the classification result to directly improve the prediction performance. The thorough cross-fold validation experiments conducted on two large-scale datasets show that DEEPre improves the prediction performance over the previous state-of-the-art methods. In addition, our server outperforms five other servers in determining the main class of enzymes on a separate low-homology dataset. Two case studies demonstrate DEEPre's ability to capture the functional difference of enzyme isoforms. Availability and implementation The server could be accessed freely at http://www.cbrc.kaust.edu.sa/DEEPre. Contact xin.gao@kaust.edu.sa. Supplementary information Supplementary data are available at Bioinformatics online.

DEEPre: sequence-based enzyme EC number prediction by deep learning

Drug repositioning is the process of identifying novel therapeutic potentials for existing drugs and discovering therapies for untreated diseases. Drug repositioning, therefore, plays an important role in optimizing the pre-clinical process of developing novel drugs by saving time and cost compared to the traditional de novo drug discovery processes. Since drug repositioning relies on data for existing drugs and diseases the enormous growth of publicly available large-scale biological, biomedical, and electronic health-related data along with the high-performance computing capabilities have accelerated the development of computational drug repositioning approaches. Multidisciplinary researchers and scientists have carried out numerous attempts, with different degrees of efficiency and success, to computationally study the potential of repositioning drugs to identify alternative drug indications. This study reviews recent advancements in the field of computational drug repositioning. First, we highlight different drug repositioning strategies and provide an overview of frequently used resources. Second, we summarize computational approaches that are extensively used in drug repositioning studies. Third, we present different computing and experimental models to validate computational methods. Fourth, we address prospective opportunities, including a few target areas. Finally, we discuss challenges and limitations encountered in computational drug repositioning and conclude with an outline of further research directions.

/pdf/a-review-of-computational-drug-repositioning-strategies-1v2n78gmrc.pdf

A review of computational drug repositioning: strategies, approaches, opportunities, challenges, and directions

The remarkable flexibility and adaptability of ensemble methods and deep learning models have led to the proliferation of their application in bioinformatics research. Traditionally, these two machine learning techniques have largely been treated as independent methodologies in bioinformatics applications. However, the recent emergence of ensemble deep learning—wherein the two machine learning techniques are combined to achieve synergistic improvements in model accuracy, stability and reproducibility—has prompted a new wave of research and application. Here, we share recent key developments in ensemble deep learning and look at how their contribution has benefited a wide range of bioinformatics research from basic sequence analysis to systems biology. While the application of ensemble deep learning in bioinformatics is diverse and multifaceted, we identify and discuss the common challenges and opportunities in the context of bioinformatics research. We hope this Review Article will bring together the broader community of machine learning researchers, bioinformaticians and biologists to foster future research and development in ensemble deep learning, and inspire novel bioinformatics applications that are unattainable by traditional methods. Recent developments in machine learning have seen the merging of ensemble and deep learning techniques. The authors review advances in ensemble deep learning methods and their applications in bioinformatics, and discuss the challenges and opportunities going forward.

Ensemble deep learning in bioinformatics

Background: Alanine scanning mutagenesis is a powerful experimental methodology for investigating the structural and energetic characteristics of protein complexes. Individual aminoacids are systematically mutated to alanine and changes in free energy of binding (Delta Delta G) measured. Several experiments have shown that protein-protein interactions are critically dependent on just a few residues ("hot spots") at the interface. Hot spots make a dominant contribution to the free energy of binding and if mutated they can disrupt the interaction. As mutagenesis studies require significant experimental efforts, there is a need for accurate and reliable computational methods. Such methods would also add to our understanding of the determinants of affinity and specificity in protein-protein recognition.Results: We present a novel computational strategy to identify hot spot residues, given the structure of a complex. We consider the basic energetic terms that contribute to hot spot interactions, i.e. van der Waals potentials, solvation energy, hydrogen bonds and Coulomb electrostatics. We treat them as input features and use machine learning algorithms such as Support Vector Machines and Gaussian Processes to optimally combine and integrate them, based on a set of training examples of alanine mutations. We show that our approach is effective in predicting hot spots and it compares favourably to other available methods. In particular we find the best performances using Transductive Support Vector Machines, a semi-supervised learning scheme. When hot spots are defined as those residues for which Delta Delta G >= 2 kcal/mol, our method achieves a precision and a recall respectively of 56% and 65%.Conclusion: We have developed an hybrid scheme in which energy terms are used as input features of machine learning models. This strategy combines the strengths of machine learning and energy-based methods. Although so far these two types of approaches have mainly been applied separately to biomolecular problems, the results of our investigation indicate that there are substantial benefits to be gained by their integration.

Prediction of hot spot residues at protein-protein interfaces by combining machine learning and energy-based methods

Proteins participate in various essential processes in vivo via interactions with other molecules. Identifying the residues participating in these interactions not only provides biological insights for protein function studies but also has great significance for drug discoveries. Therefore, predicting protein-ligand binding sites has long been under intense research in the fields of bioinformatics and computer aided drug discovery. In this review, we first introduce the research background of predicting protein-ligand binding sites and then classify the methods into four categories, namely, 3D structure-based, template similarity-based, traditional machine learning-based and deep learning-based methods. We describe representative algorithms in each category and elaborate on machine learning and deep learning-based prediction methods in more detail. Finally, we discuss the trends and challenges of the current research such as molecular dynamics simulation based cryptic binding sites prediction, and highlight prospective directions for the near future.

Exploring the computational methods for protein-ligand binding site prediction

Research on quantitative structure-activity relationships (QSAR) provides an effective approach to determine new hits and promising lead compounds during drug discovery. In the past decades, various works have gained good performance for QSAR with the development of machine learning. The rise of deep learning, along with massive accessible chemical databases, made improvement on the QSAR performance. This article proposes a novel deep-learning-based method to implement QSAR prediction by the concatenation of end-to-end encoder-decoder model and convolutional neural network (CNN) architecture. The encoder-decoder model is mainly used to generate fixed-size latent features to represent chemical molecules; while these features are then input into CNN framework to train a robust and stable model and finally to predict active chemicals. Two models with different schemes are investigated to evaluate the validity of our proposed model on the same data sets. Experimental results showed that our proposed method outperforms other state-of-the-art methods in successful identification of chemical molecule whether it is active.

A Deep Learning-Based Chemical System for QSAR Prediction

Accurate identification of potential interactions between drugs and protein targets is a critical step to accelerate drug discovery. Despite many relative experimental researches have been done in the past decades, detecting drug-target interactions (DTIs) remains to be extremely resource-intensive and time-consuming. Therefore, many computational approaches have been developed for predicting drug-target associations on a large scale. In this paper, we proposed an deep learning-based method to predict DTIs only using the information of drug structures and protein sequences. The final results showed that our method can achieve good performance with the accuracies up to 92.0%, 90.0%, 92.0% and 90.7% for the target families of enzymes, ion channels, GPCRs and nuclear receptors of our created dataset, respectively. Another dataset derived from DrugBank was used to further assess the generalization of the model, which yielded an accuracy of 0.9015 and an AUC value of 0.9557. It was elucidated that our model shows improved performance in comparison with other state-of-the-art computational methods on the common benchmark datasets. Experimental results demonstrated that our model successfully extracted more nuanced yet useful features, and therefore can be used as a practical tool to discover new drugs. http://deeplearner.ahu.edu.cn/web/CnnDTI.htm.

/pdf/predicting-drug-target-interactions-from-drug-structure-and-34askwxpgj.pdf

Predicting drug-target interactions from drug structure and protein sequence using novel convolutional neural networks

Background: Proteins have the fundamental ability to selectively bind to other molecules and perform specific functions through such interactions, such as protein-ligand binding. Accurate prediction of protein residues that physically bind to ligands is important for drug design and protein docking studies. Most of the successful protein-ligand binding predictions were based on known structures. However, structural information is not largely available in practice due to the huge gap between the number of known protein sequences and that of experimentally solved structures. Results: This paper proposes a dynamic ensemble approach to identify protein-ligand binding residues by using sequence information only. To avoid problems resulting from highly imbalanced samples between the ligand-binding sites and non ligand-binding sites, we constructed several balanced data sets and we trained a random forest classifier for each of them. We dynamically selected a subset of classifiers according to the similarity between the target protein and the proteins in the training data set. The combination of the predictions of the classifier subset to each query protein target yielded the final predictions. The ensemble of these classifiers formed a sequence-based predictor to identify protein-ligand binding sites. Conclusions: Experimental results on two Critical Assessment of protein Structure Prediction datasets and the ccPDB dataset demonstrated that of our proposed method compared favorably with the state-of-the-art. Availability: http://www2.ahu.edu.cn/pchen/web/LigandDSES.htm

/pdf/a-sequence-based-dynamic-ensemble-learning-system-for-4dko5s18w7.pdf

A Sequence-Based Dynamic Ensemble Learning System for Protein Ligand-Binding Site Prediction

Hot spots are interfacial core areas of binding proteins, which have been applied as targets in drug design. Experimental methods are costly in both time and expense to locate hot spot areas. Recently, in-silicon computational methods have been widely used for hot spot prediction through sequence or structure characterization. As the structural information of proteins is not always solved, and thus hot spot identification from amino acid sequences only is more useful for real-life applications. This work proposes a new sequence-based model that combines physicochemical features with the relative accessible surface area of amino acid sequences for hot spot prediction. The model consists of 83 classifiers involving the IBk (Instance-based k means) algorithm, where instances are encoded by important properties extracted from a total of 544 properties in the AAindex1 (Amino Acid Index) database. Then top-performance classifiers are selected to form an ensemble by a majority voting technique. The ensemble classifier outperforms the state-of-the-art computational methods, yielding an F1 score of 0.80 on the benchmark binding interface database (BID) test set.Availability: http://www2.ahu.edu.cn/pchen/web/HotspotEC.htm
 .

Protein binding hot spots prediction from sequence only by a new ensemble learning method

Biological targets are most commonly proteins such as enzymes, ion channels, and receptors. They are anything within a living organism to bind with some other entities (like an endogenous ligand or a drug), resulting in change in their behaviors or functions. Exploring potential drug-target interactions (DTIs) are crucial for drug discovery and effective drug development. Computational methods were widely applied in drug-target interactions, since experimental methods are extremely time-consuming and resource-intensive. In this paper, we proposed a novel deep learning-based prediction system, with a new negative instance generation, to identify DTIs. As a result, our method achieved an accuracy of 0.9800 on our created dataset. Another dataset derived from DrugBank was used to further assess the generalization of the model, which yielded a good performance with accuracy of 0.8814 and AUC value of 0.9527 on the dataset. The outcome of our experimental results indicated that the proposed method, involving the credible negative generation, can be employed to discriminate the interactions between drugs and targets. Website: http://www.dlearningapp.com/web/DrugCNN.htm .

ShanShan Hu

Papers

A Deep Learning-Based Chemical System for QSAR Prediction

Predicting drug-target interactions from drug structure and protein sequence using novel convolutional neural networks

A Sequence-Based Dynamic Ensemble Learning System for Protein Ligand-Binding Site Prediction

Protein binding hot spots prediction from sequence only by a new ensemble learning method

A Convolutional Neural Network System to Discriminate Drug-Target Interactions