Search

The prediction of novel drug-target interactions (DTIs) has intrinsic significance in drug discovery research. Wet-lab experiments of DTIs are laborious and expensive; computational methods can help minimize the complexity of identifying unknown DTIs and accelerate the drug repositioning process. Nowadays, the number of drug-target features and their interactions regularly increases, disabling traditional computational methods' prediction and analyzing ability. Therefore, developing a new robust model to derive the reduced features for effective prediction is important. Further, accurate interactions also depend on the negative drug-target pairs, and it is worthwhile to build a technique to generate perfect negative pairs. To this end, we propose a new multi-label approach, called idti-MLKdr, by introducing multi-kernel learning (MKL) based SVM for DTIs prediction with various dimensionality reduction techniques. First, we have extracted the drug-target features from chemical structures and protein sequences, applying different feature extraction methods. A new technique has been developed to construct the negative drug-target pairs based on drug-drug (or protein-protein) similarity scores. Then, three-dimensionality reduction techniques have been applied to the extracted drug-target features. Finally, we trained a multi kernel-based learner together with the reduced features and combined their prediction scores to show the final results. In this experiment, we considered auROC as an evaluation metric. The proposed method has been compared with the various existing methods under five-fold cross-validation, and the experimental results indicated that idti-MLKdr attains the best auROC for predicting DTIs. We believe that improved prediction performance will motivate the researchers for further drug development. [Display omitted] • Computational model idti-MLKdr is proposed for predicting Drug-Target Interactions. • FP2, AAC, DC and TC descriptors are used for extracting Drug-target features. • CluMS technique is proposed for resolving class imbalance problem, and three DR techniques are utilized to manage the high dimensionality. • Multi-kernel Learning (MKL) based SVM algorithm is used as a classifier. • Achieves the best prediction performance and can effectively predict the potential DTIs. [ABSTRACT FROM AUTHOR]

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. Image 1 • Computational model deepACTION is proposed for predicting Drug-Target Interactions (DTIs). • Different types of drug-protein features are generated by using Rcpi (package) and PROFEAT server. • MMIB technique is developed for resolving class imbalance, and LASSO is utilized to manage the high dimensionality. • Convolutional Neural Networks (CNNs) algorithm is used as a classifier. • Achieves the best prediction performance and can effectively predict the potential DTIs. [ABSTRACT FROM AUTHOR]

Accurate identification of drug-target interaction (DTI) is a crucial and challenging task in the drug discovery process, having enormous benefit to the patients and pharmaceutical company. The traditional wet-lab experiments of DTI is expensive, time-consuming, and labor-intensive. Therefore, many computational techniques have been established for this purpose; although a huge number of interactions are still undiscovered. Here, we present pdti-EssB, a new computational model for identification of DTI using protein sequence and drug molecular structure. More specifically, each drug molecule is transformed as the molecular substructure fingerprint. For a protein sequence, different descriptors are utilized to represent its evolutionary, sequence, and structural information. Besides, our proposed method uses data balancing techniques to handle the imbalance problem and applies a novel feature eliminator to extract the best optimal features for accurate prediction. In this paper, four classes of DTI benchmark datasets are used to construct a predictive model with XGBoost. Here, the auROC is utilized as an evaluation metric to compare the performance of pdti-EssB method with recent methods, applying five-fold cross-validation. Finally, the experimental results indicate that our proposed method is able to outperform other approaches in predicting DTI, and introduces new drug-target interaction samples based on prediction probability scores. pdti-EssB webserver is available online at http://pdtiessb-uestc.com/ Image 1 • Computational model pdti-EssB is proposed for predicting Drug-Target Interactions (DTIs). • MSF, PSSM-Bigram, PseAAC and SPIDER2 are used for extracting Drug-target features. • CUS and EnsRFS techniques are proposed for resolving class imbalance problem and high dimensionality of data. • Boosting algorithm is utilized as a classifier. • Achieves the best prediction performance and can effectively predict the potential DTIs. [ABSTRACT FROM AUTHOR]

Accurate determination of time-of-flight (TOF) is crucially important for precise ultrasonic flow measurement. Detection of ultrasonic signal onset (USO) is considered as an effective approach to determine the actual value of TOF. The USO can be estimated by signal fitting methods. However, the estimation accuracy and reliability of existing methods still need to be improved. This paper proposes a signal fitting method based on artificial fish swarm algorithm and particle swarm optimization combined algorithm (AFSA-PSO). In the method, AFSA is introduced to search all possible solution spaces firstly, considering the multi-modal characteristic of the objective function in signal fitting which is easily being amplified by the strong noise. Then, a feasible solution extraction strategy is proposed to extract the local optimal solution in every space. Finally, PSO is employed to further process the local solutions to obtain the accurate USO. The method is validated by both numerical and experiment tests, using simulated signals with different strength noise and measured signal in actual ultrasonic flowmeter respectively. Comparisons with the methods proposed by other researchers are also given in the paper. The proposed AFSA-PSO is found to be more accurate, more robust, having better anti-noise ability and less time-consuming under a given accuracy requirement. [ABSTRACT FROM AUTHOR]