RESUMEN

Combining different drugs synergistically is an essential aspect of developing effective treatments. Although there is a plethora of research on computational prediction for new combination therapies, there is limited to no research on combination therapies in the treatment of viral diseases. This paper proposes AI-based models for predicting novel antiviral combinations to treat virus diseases synergistically. To do this, we assembled a comprehensive dataset comprising information on viral strains, drug compounds, and their known interactions. As far as we know, this is the first dataset and learning model on combination therapy for viruses. Our proposal includes using a random forest model, an SVM model, and a deep model to train viral combination therapy. The machine learning models showed the highest performance, and the predicted values were validated by a t-test, indicating the effectiveness of the proposed methods. One of the predicted combinations of acyclovir and ribavirin has been experimentally confirmed to have a synergistic antiviral effect against herpes simplex type-1 virus, as described in the literature.

Asunto(s)

RESUMEN

Monkeypox (MPXV) is one of the infectious viruses which caused morbidity and mortality problems in these years. Despite its danger to public health, there is no approved drug to stand and handle MPXV. On the other hand, drug repurposing is a promising screening method for the low-cost introduction of approved drugs for emerging diseases and viruses which utilizes computational methods. Therefore, drug repurposing is a promising approach to suggesting approved drugs for the MPXV. This paper proposes a computational framework for MPXV antiviral prediction. To do this, we have generated a new virus-antiviral dataset. Moreover, we applied several machine learning and one deep learning method for virus-antiviral prediction. The suggested drugs by the learning methods have been investigated using docking studies. The target protein structure is modeled using homology modeling and, then, refined and validated. To the best of our knowledge, this work is the first work to study deep learning methods for the prediction of MPXV antivirals. The screening results confirm that Tilorone, Valacyclovir, Ribavirin, Favipiravir, and Baloxavir marboxil are effective drugs for MPXV treatment.

Asunto(s)

RESUMEN

Efficient drug discovery relies on drug repurposing, an important and open research field. This work presents a novel factorization method and a practical comparison of different approaches for drug repurposing. First, we propose a novel tensor-matrix-tensor (TMT) formulation as a new data array method with a gradient-based factorization procedure. Additionally, this paper examines and contrasts four computational drug repurposing approaches-factorization-based methods, machine learning methods, deep learning methods, and graph neural networks-to fulfill the second purpose. We test the strategies on two datasets and assess each approach's performance, drawbacks, problems, and benefits based on results. The results demonstrate that deep learning techniques work better than other strategies and that their results might be more reliable. Ultimately, graph neural methods need to be in an inductive manner to have a reliable prediction.

RESUMEN

Drug repurposing is an active area of research that aims to decrease the cost and time of drug development. Most of those efforts are primarily concerned with the prediction of drug-target interactions. Many evaluation models, from matrix factorization to more cutting-edge deep neural networks, have come to the scene to identify such relations. Some predictive models are devoted to the prediction's quality, and others are devoted to the efficiency of the predictive models, e.g., embedding generation. In this work, we propose new representations of drugs and targets useful for more prediction and analysis. Using these representations, we propose two inductive, deep network models of IEDTI and DEDTI for drug-target interaction prediction. Both of them use the accumulation of new representations. The IEDTI takes advantage of triplet and maps the input accumulated similarity features into meaningful embedding corresponding vectors. Then, it applies a deep predictive model to each drug-target pair to evaluate their interaction. The DEDTI directly uses the accumulated similarity feature vectors of drugs and targets and applies a predictive model on each pair to identify their interactions. We have done a comprehensive simulation on the DTINet dataset as well as gold standard datasets, and the results show that DEDTI outperforms IEDTI and the state-of-the-art models. In addition, we conduct a docking study on new predicted interactions between two drug-target pairs, and the results confirm acceptable drug-target binding affinity between both predicted pairs.

Asunto(s)

RESUMEN

The Longest Common Subsequence (LCS) is the problem of finding a subsequence among a set of strings that has two properties of being common to all and the longest. The LCS has applications in computational biology and text editing, among many others. Due to the NP-hardness of the general longest common subsequence, numerous heuristic algorithms and solvers have been proposed to give the best possible solution for different sets of strings. None of them has the best performance for all types of sets. In addition, there is no method to specify the type of a given set of strings. Besides that, the available hyper-heuristic is not efficient and fast enough to solve this problem in real-world applications. This paper proposes a novel hyper-heuristic to solve the longest common subsequence problem using a new criterion to classify a set of strings based on their similarity. To do this, we offer a general stochastic framework to identify the type of a given set of strings. Following that, we introduce the set similarity dichotomizer (S2D) algorithm based on the framework that divides the type of sets into two. This algorithm is introduced for the first time in this paper and opens a new way to go beyond the current LCS solvers. Then, we present our proposed hyper-heuristic that exploits the S2D and one of the internal properties of the given strings to choose the best matching heuristic among a set of heuristics. We compare the results on benchmark datasets with the best heuristics and hyper-heuristics. The results show that our proposed dichotomizer (i.e., S2D) can classify datasets with 98% of accuracy. Also, our proposed hyper-heuristic obtains competitive performance in comparison with the best methods and outperforms best hyper-heuristics for uncorrelated datasets in terms of both quality of solutions and run time factors. All supplementary files, including the source codes and datasets, are publicly available on GitHub.1.

RESUMEN

BACKGROUND: Due to the high resource consumption of introducing a new drug, drug repurposing plays an essential role in drug discovery. To do this, researchers examine the current drug-target interaction (DTI) to predict new interactions for the approved drugs. Matrix factorization methods have much attention and utilization in DTIs. However, they suffer from some drawbacks. METHODS: We explain why matrix factorization is not the best for DTI prediction. Then, we propose a deep learning model (DRaW) to predict DTIs without having input data leakage. We compare our model with several matrix factorization methods and a deep model on three COVID-19 datasets. In addition, to ensure the validation of DRaW, we evaluate it on benchmark datasets. Furthermore, as an external validation, we conduct a docking study on the COVID-19 recommended drugs. RESULTS: In all cases, the results confirm that DRaW outperforms matrix factorization and deep models. The docking results approve the top-ranked recommended drugs for COVID-19. CONCLUSIONS: In this paper, we show that it may not be the best choice to use matrix factorization in the DTI prediction. Matrix factorization methods suffer from some intrinsic issues, e.g., sparsity in the domain of bioinformatics applications and fixed-unchanged size of the matrix-related paradigm. Therefore, we propose an alternative method (DRaW) that uses feature vectors rather than matrix factorization and demonstrates better performance than other famous methods on three COVID-19 and four benchmark datasets.

Asunto(s)

RESUMEN

The advent of portable cardiac monitoring devices has enabled real-time analysis of cardiac signals. These devices can be used to develop algorithms for real-time detection of dangerous heart rhythms such as ventricular arrhythmias. This paper presents a Markov model based algorithm for real-time detection of ventricular tachycardia, ventricular flutter, and ventricular fibrillation episodes. The algorithm does not rely on any noise removal pre-processing or peak annotation of the original signal. When evaluated using ECG signals from three publicly available databases, the model resulted in an AUC of 0.96 and F1-score of 0.91 for 5-second long signals and an AUC of 0.97 and F1-score of 0.93 for 2-second long signals.

Asunto(s)

RESUMEN

Fast and accurate midline shift (MLS) estimation has a significant impact on diagnosis and treatment of patients with Traumatic Brain Injury (TBI). In this paper, we propose an automated method to calculate the amount of shift in the midline structure of TBI patients. The MLS values were annotated by a neuroradiologist. We first select a number of slices among all the slices in a CT scan based on metadata as well as information extracted from the images. After the slice selection, we propose an efficient segmentation technique to detect the ventricles. We use the ventricular geometric patterns to calculate the actual midline and also anatomical information to detect the ideal midline. The distance between these two lines is used as an estimate of MLS. The proposed methods are applied on a TBI dataset where they show a significant improvement of the the proposed method upon existing approach.

Asunto(s)

RESUMEN

Detection of atrial fibrillation (AFib) using wearable ECG monitors has recently gained popularity. The signal quality of such recordings is often much lower than that of traditional monitoring systems such as Holter monitors. Larger noise contamination can lead to reduced accuracy of the QRS detection which is the basis of the heart rate variability (HRV) analysis. Hence, it is crucial to accurately classify short ECG recording segments for AFib monitoring. A comparative study was conducted to investigate the applicability and performance of a variety of HRV feature extraction methods applied to short single lead ECG recordings to detect AFib. The data employed in this study is the publicly available dataset of the 2017 PhysioNet challenge. In particular, detection of AFib against non-AFib instances, including normal sinus rhythm, other types of arrhythmias and noisy signals, is investigated in this study. The HRV features can be divided into the categories of statistical, geometrical, frequency, entropy, Poincare plotand Lorentz plot-based. For feature selection, stepwise forward selection approach was employed and support vector machines with linear and radial basis function kernels were used for classification. The results indicate that a combination of features from all the categories leads to the highest accuracy levels. The feasibility of using different HRV features for short signals is discussed as well. In conclusion, AFib can be detected with high accuracy using short single-lead ECG signals using HRV features.

Asunto(s)

RESUMEN

Wearable devices are becoming a natural and economic means to gather biometric data from end users. The massive amount of information that they will provide, unimaginable until a few years ago, owns an immense potential for applications such as continuous monitoring for personalized healthcare and use within fitness applications. Wearables are however heavily constrained in terms of amount of memory, transmission capability and energy reserve. This calls for dedicated, lightweight but still effective algorithms for data management. This paper is centered around lossy data compression techniques, whose aim is to minimize the amount of information that is to be stored on their onboard memory and subsequently transmitted over wireless interfaces. Specifically, we analyze selected compression techniques for biometric signals, quantifying their complexity (energy consumption) and compression performance. Hence, we propose a new class of codebook-based (CB) compression algorithms, designed to be energy efficient, online and amenable to any type of signal exhibiting recurrent patterns. Finally, the performance of the selected and the new algorithm is assessed, underlining the advantages offered by CB schemes in terms of memory savings and classification algorithms.

Asunto(s)