A Convolutional Neural Network System to Discriminate Drug-Target Interactions

Deep-WET: a deep learning-based approach for predicting DNA-binding proteins using word embedding techniques with weighted features

DNA-binding proteins (DBPs) play a significant role in all phases of genetic processes, including DNA recombination, repair, and modification. They are often utilized in drug discovery as fundamental elements of steroids, antibiotics, and anticancer drugs. Predicting them poses the most challenging task in proteomics research. Conventional experimental methods for DBP identification are costly and sometimes biased toward prediction. Therefore, developing powerful computational methods that can accurately and rapidly identify DBPs from sequence information is an urgent need. In this study, we propose a novel deep learning-based method called Deep-WET to accurately identify DBPs from primary sequence information. In Deep-WET, we employed three powerful feature encoding schemes containing Global Vectors, Word2Vec, and fastText to encode the protein sequence. Subsequently, these three features were sequentially combined and weighted using the weights obtained from the elements learned through the differential evolution (DE) algorithm. To enhance the predictive performance of Deep-WET, we applied the SHapley Additive exPlanations approach to remove irrelevant features. Finally, the optimal feature subset was input into convolutional neural networks to construct the Deep-WET predictor. Both cross-validation and independent tests indicated that Deep-WET achieved superior predictive performance compared to conventional machine learning classifiers. In addition, in extensive independent test, Deep-WET was effective and outperformed than several state-of-the-art methods for DBP prediction, with accuracy of 78.08%, MCC of 0.559, and AUC of 0.805. This superior performance shows that Deep-WET has a tremendous predictive capacity to predict DBPs. The web server of Deep-WET and curated datasets in this study are available at https://deepwet-dna.monarcatechnical.com/ . The proposed Deep-WET is anticipated to serve the community-wide effort for large-scale identification of potential DBPs.

Drug-Target Interaction Prediction via Graph Auto-Encoder and Multi-Subspace Deep Neural Networks

Computational prediction of drug-target interaction (DTI) is important for the new drug discovery. Currently, the deep neural network (DNN) has been widely used in DTI prediction. However, parameters of the DNN could be insufficiently trained and features of the data could be insufficiently utilized, because the DTI data is limited and its dimension is very high. To deal with the above problems, in this paper, a graph auto-encoder and multi-subspace deep neural network (GAEMSDNN) is designed. GAEMSDNN enhances its learning ability with a graph auto-encoder, a subspace layer and an ensemble layer. The graph auto-encoder can preserve the reconstruction information. The subspace layer can obtain different strong feature subsets. The ensemble layer in the GAEMSDNN can comprehensively utilize these strong feature subsets in a unified optimization framework. As a result, more features can be extracted from the network input and the DNN network can be better trained. In experiments, the results of GAEMSDNN are significantly improved compared to the previous methods, which validates the effectiveness of our strategies.

Transformer-based multitask learning for reaction prediction under low-resource circumstances

Recently, effective and rapid deep-learning methods for predicting chemical reactions have significantly aided the research and development of organic chemistry and drug discovery. Owing to the insufficiency of related chemical reaction data, computer-assisted predictions based on low-resource chemical datasets generally have low accuracy despite the exceptional ability of deep learning in retrosynthesis and synthesis. To address this issue, we introduce two types of multitask models: retro-forward reaction prediction transformer (RFRPT) and multiforward reaction prediction transformer (MFRPT). These models integrate multitask learning with the transformer model to predict low-resource reactions in forward reaction prediction and retrosynthesis. Our results demonstrate that introducing multitask learning significantly improves the average top-1 accuracy, and the RFRPT (76.9%) and MFRPT (79.8%) outperform the transformer baseline model (69.9%). These results also demonstrate that a multitask framework can capture sufficient chemical knowledge and effectively mitigate the impact of the deficiency of low-resource data in processing reaction prediction tasks. Both RFRPT and MFRPT methods significantly improve the predictive performance of transformer models, which are powerful methods for eliminating the restriction of limited training data.

Protein-Protein Interaction Sites Prediction Based on an Under-Sampling Strategy and Random Forest Algorithm

The computational methods of protein-protein interaction sites prediction can effectively avoid the shortcomings of high cost and time in traditional experimental approaches. However, the serious class imbalance between interface and non-interface residues on the protein sequences limits the prediction performance of these methods. This work therefore proposed a new strategy, NearMiss-based under-sampling for unbalancing datasets and Random Forest classification (NM-RF), to predict protein interaction sites. Herein, the residues on protein sequences were represented by the PSSM-derived features, hydropathy index (HI) and relative solvent accessibility (RSA). In order to resolve the class imbalance problem, an under-sampling method based on NearMiss algorithm is adopted to remove some non-interface residues, and then the random forest algorithm is used to perform binary classification on the balanced feature datasets. Experiments show that the accuracy of NM-RF model reaches 87.6% and 84.3% on Dtestset72 and PDBtestset164 respectively, which demonstrate the effectiveness of the proposed NM-RF method in differentiating the interface or non-interface residues.

Detecting Drug–Target Interactions with Feature Similarity Fusion and Molecular Graphs

Simple Summary

Accurate identification of potential targets for drugs to interact with can accelerate drug development. The identification of drug–target interactions can provide insights into hidden drug efficacy. This paper presents a prediction model based on feature similarity fusion that can identify crucial features of drugs and targets to help predict drug–target interactions.

Abstract

The key to drug discovery is the identification of a target and a corresponding drug compound. Effective identification of drug–target interactions facilitates the development of drug discovery. In this paper, drug similarity and target similarity are considered, and graphical representations are used to extract internal structural information and intermolecular interaction information about drugs and targets. First, drug similarity and target similarity are fused using the similarity network fusion (SNF) method. Then, the graph isomorphic network (GIN) is used to extract the features with information about the internal structure of drug molecules. For target proteins, feature extraction is carried out using TextCNN to efficiently capture the features of target protein sequences. Three different divisions (CVD, CVP, CVT) are used on the standard dataset, and experiments are carried out separately to validate the performance of the model for drug–target interaction prediction. The experimental results show that our method achieves better results on AUC and AUPR. The docking results also show the superiority of the proposed model in predicting drug–target interactions.

Predicting Drug-Target Interactions Based on the Ensemble Models of Multiple Feature Pairs

Backgroud: The prediction of drug–target interactions (DTIs) is of great significance in drug development. It is time-consuming and expensive in traditional experimental methods. Machine learning can reduce the cost of prediction and is limited by the characteristics of imbalanced datasets and problems of essential feature selection. Methods: The prediction method based on the Ensemble model of Multiple Feature Pairs (Ensemble-MFP) is introduced. Firstly, three negative sets are generated according to the Euclidean distance of three feature pairs. Then, the negative samples of the validation set/test set are randomly selected from the union set of the three negative sets in the validation set/test set. At the same time, the ensemble model with weight is optimized and applied to the test set. Results: The area under the receiver operating characteristic curve (area under ROC, AUC) in three out of four sub-datasets in gold standard datasets was more than 94.0% in the prediction of new drugs. The effectiveness of the proposed method is also shown with the comparison of state-of-the-art methods and demonstration of predicted drug–target pairs. Conclusion: The Ensemble-MFP can weigh the existing feature pairs and has a good prediction effect for general prediction on new drugs.

Intelligent Health Care: Applications of Deep Learning in Computational Medicine

With the progress of medical technology, biomedical field ushered in the era of big data, based on which and driven by artificial intelligence technology, computational medicine has emerged. People need to extract the effective information contained in these big biomedical data to promote the development of precision medicine. Traditionally, the machine learning methods are used to dig out biomedical data to find the features from data, which generally rely on feature engineering and domain knowledge of experts, requiring tremendous time and human resources. Different from traditional approaches, deep learning, as a cutting-edge machine learning branch, can automatically learn complex and robust feature from raw data without the need for feature engineering. The applications of deep learning in medical image, electronic health record, genomics, and drug development are studied, where the suggestion is that deep learning has obvious advantage in making full use of biomedical data and improving medical health level. Deep learning plays an increasingly important role in the field of medical health and has a broad prospect of application. However, the problems and challenges of deep learning in computational medical health still exist, including insufficient data, interpretability, data privacy, and heterogeneity. Analysis and discussion on these problems provide a reference to improve the application of deep learning in medical health.

PreDTIs: prediction of drug-target interactions based on multiple feature information using gradient boosting framework with data balancing and feature selection techniques

Discovering drug–target (protein) interactions (DTIs) is of great significance for researching and developing novel drugs, having a tremendous advantage to pharmaceutical industries and patients. However, the prediction of DTIs using wet-lab experimental methods is generally expensive and time-consuming. Therefore, different machine learning-based methods have been developed for this purpose, but there are still substantial unknown interactions needed to discover. Furthermore, data imbalance and feature dimensionality problems are a critical challenge in drug-target datasets, which can decrease the classifier performances that have not been significantly addressed yet. This paper proposed a novel drug–target interaction prediction method called PreDTIs. First, the feature vectors of the protein sequence are extracted by the pseudo-position-specific scoring matrix (PsePSSM), dipeptide composition (DC) and pseudo amino acid composition (PseAAC); and the drug is encoded with MACCS substructure fingerings. Besides, we propose a FastUS algorithm to handle the class imbalance problem and also develop a MoIFS algorithm to remove the irrelevant and redundant features for getting the best optimal features. Finally, balanced and optimal features are provided to the LightGBM Classifier to identify DTIs, and the 5-fold CV validation test method was applied to evaluate the prediction ability of the proposed method. Prediction results indicate that the proposed model PreDTIs is significantly superior to other existing methods in predicting DTIs, and our model could be used to discover new drugs for unknown disorders or infections, such as for the coronavirus disease 2019 using existing drugs compounds and severe acute respiratory syndrome coronavirus 2 protein sequences.

Applications of Machine Learning in Drug Target Discovery

Drug target discovery is a critical step in drug development. It is the basis of modern drug development because it determines the target molecules related to specific diseases in advance. Predicting drug targets by computational methods saves a great deal of financial and material resources compared to in vitro experiments. Therefore, several computational methods for drug target discovery have been designed. Recently, machine learning (ML) methods in biomedicine have developed rapidly. In this paper, we present an overview of drug target discovery methods based on machine learning. Considering that some machine learning methods integrate network analysis to predict drug targets, network-based methods are also introduced in this article. Finally, the challenges and future outlook of drug target discovery are discussed.

Supervised machine learning tools: a tutorial for clinicians

In an increasingly data-driven world, artificial intelligence is expected to be a key tool for converting big data into tangible benefits and the healthcare domain is no exception to this. Machine learning aims to identify complex patterns in multi-dimensional data and use these uncovered patterns to classify new unseen cases or make data-driven predictions. In recent years, deep neural networks have shown to be capable of producing results that considerably exceed those of conventional machine learning methods for various classification and regression tasks. In this paper, we provide an accessible tutorial of the most important supervised machine learning concepts and methods, including deep learning, which are potentially the most relevant for the medical domain. We aim to take some of the mystery out of machine learning and depict how machine learning models can be useful for medical applications. Finally, this tutorial provides a few practical suggestions for how to properly design a machine learning model for a generic medical problem.

DeepACTION: A deep learning-based method for predicting novel drug-target interactions

Drug-target interactions (DTIs) play a key role in drug development and discovery processes. Wet lab prediction of DTIs is time-consuming, expensive, and tedious. Fortunately, computational approaches can identify new interactions (drug-target pairs) and accelerate the process of drug repurposing. However, a vast number of interactions remain undiscovered; therefore, we proposed a deep learning-based method (deepACTION) for predicting potential or unknown DTIs. Here, each drug chemical structure and protein sequence are transformed according to structural and sequence information using different descriptors to represent their features correctly. There have been some challenges, such as the high dimensionality and class imbalance of data during the prediction process. To address these problems, we developed the MMIB technique to balance the majority and minority instances in the dataset and utilized a LASSO model to handle the high dimensionality of the data. In addition, we trained the convolutional neural network algorithm with balanced and reduced features for accurate prediction of DTIs. In this study, the AUC is considered a primary evaluation metric for comparing the performance of the deep ACTION model with that of existing methods by a 5-fold cross-validation test. Our experiential dataset obtained from the DrugBank database and our deepACTION model achieved an AUC of 0.9836 for this dataset. The experimental results ensured that the model can predict significant numbers of new DTIs and provide complete information to motivate scientists to develop drugs.

Predicting Drug-Target Interactions with Electrotopological State Fingerprints and Amphiphilic Pseudo Amino Acid Composition

The task of drug-target interaction (DTI) prediction plays important roles in drug development. The experimental methods in DTIs are time-consuming, expensive and challenging. To solve these problems, machine learning-based methods are introduced, which are restricted by effective feature extraction and negative sampling. In this work, features with electrotopological state (E-state) fingerprints for drugs and amphiphilic pseudo amino acid composition (APAAC) for target proteins are tested. E-state fingerprints are extracted based on both molecular electronic and topological features with the same metric. APAAC is an extension of amino acid composition (AAC), which is calculated based on hydrophilic and hydrophobic characters to construct sequence order information. Using the combination of these feature pairs, the prediction model is established by support vector machines. In order to enhance the effectiveness of features, a distance-based negative sampling is proposed to obtain reliable negative samples. It is shown that the prediction results of area under curve for Receiver Operating Characteristic (AUC) are above 98.5% for all the three datasets in this work. The comparison of state-of-the-art methods demonstrates the effectiveness and efficiency of proposed method, which will be helpful for further drug development.

Developing Computational Model to Predict Protein-Protein Interaction Sites Based on the XGBoost Algorithm

The study of protein-protein interaction is of great biological significance, and the prediction of protein-protein interaction sites can promote the understanding of cell biological activity and will be helpful for drug development. However, uneven distribution between interaction and non-interaction sites is common because only a small number of protein interactions have been confirmed by experimental techniques, which greatly affects the predictive capability of computational methods. In this work, two imbalanced data processing strategies based on XGBoost algorithm were proposed to re-balance the original dataset from inherent relationship between positive and negative samples for the prediction of protein-protein interaction sites. Herein, a feature extraction method was applied to represent the protein interaction sites based on evolutionary conservatism of proteins, and the influence of overlapping regions of positive and negative samples was considered in prediction performance. Our method showed good prediction performance, such as prediction accuracy of 0.807 and MCC of 0.614, on an original dataset with 10,455 surface residues but only 2297 interface residues. Experimental results demonstrated the effectiveness of our XGBoost-based method.