Classification of toxicity effects of biotransformed hepatic drugs using whale optimized support vector machines

GeoDILI: A Robust and Interpretable Model for Drug-Induced Liver Injury Prediction Using Graph Neural Network-Based Molecular Geometric Representation

Drug-induced liver injury (DILI) is a significant cause of drug failure and withdrawal due to liver damage. Accurate prediction of hepatotoxic compounds is crucial for safe drug development. Several DILI prediction models have been published, but they are built on different data sets, making it difficult to compare model performance. Moreover, most existing models are based on molecular fingerprints or descriptors, neglecting molecular geometric properties and lacking interpretability. To address these limitations, we developed GeoDILI, an interpretable graph neural network that uses a molecular geometric representation. First, we utilized a geometry-based pretrained molecular representation and optimized it on the DILI data set to improve predictive performance. Second, we leveraged gradient information to obtain high-precision atomic-level weights and deduce the dominant substructure. We benchmarked GeoDILI against recently published DILI prediction models, as well as popular GNN models and fingerprint-based machine learning models using the same data set, showing superior predictive performance of our proposed model. We applied the interpretable method in the DILI data set and derived seven precise and mechanistically elucidated structural alerts. Overall, GeoDILI provides a promising approach for accurate and interpretable DILI prediction with potential applications in drug discovery and safety assessment. The data and source code are available at GitHub repository (https://github.com/CSU-QJY/GeoDILI).

Binarization of Metaheuristics: Is the Transfer Function Really Important?

In this work, an approach is proposed to solve binary combinatorial problems using continuous metaheuristics. It focuses on the importance of binarization in the optimization process, as it can have a significant impact on the performance of the algorithm. Different binarization schemes are presented and a set of actions, which combine different transfer functions and binarization rules, under a selector based on reinforcement learning is proposed. The experimental results show that the binarization rules have a greater impact than transfer functions on the performance of the algorithms and that some sets of actions are statistically better than others. In particular, it was found that sets that incorporate the elite or elite roulette binarization rule are the best. Furthermore, exploration and exploitation were analyzed through percentage graphs and a statistical test was performed to determine the best set of actions. Overall, this work provides a practical approach for the selection of binarization schemes in binary combinatorial problems and offers guidance for future research in this field.

Machine-learning technique, QSAR and molecular dynamics for hERG-drug interactions

One of the most well-known anti-targets defining medication cardiotoxicity is the voltage-dependent hERG K + channel, which is well-known for its crucial involvement in cardiac action potential repolarization. Torsades de Pointes, QT prolongation, and sudden death are all caused by hERG (the human Ether-à-go-go-Related Gene) inhibition. There is great interest in creating predictive computational (in silico) tools to identify and weed out potential hERG blockers early in the drug discovery process because testing for hERG liability and the traditional experimental screening are complicated, expensive and time-consuming. This study used 2D descriptors of a large curated dataset of 6766 compounds and machine learning approaches to build robust descriptor-based QSAR and predictive classification models for KCNH2 liability. Decision Tree, Random Forest, Logistic Regression, Ada Boosting, kNN, SVM, Naïve Bayes, neural network and stochastic gradient classification classifier algorithms were used to build classification models. If a compound's IC50 value was between 10 μM and less, it was classified as a blocker (hERG-positive), and if it was more, it was classified as a non-blocker (hERG-negative). Matthew's correlation coefficient formula and F1score were applied to compare and track the developed models' performance. Molecular docking and dynamics studies were performed to understand the cardiotoxicity relating to the hERG-gene. The hERG residues interacting after 100 ns are LEU:697, THR:708, PHE:656, HIS:674, HIS:703, TRP:705 and ASN:709 and the hERG-ligand-16 complex trajectory showed stable behaviour with lesser fluctuations in the entire simulation of 200 ns.Communicated by Ramaswamy H. Sarma.

A novel framework of credit risk feature selection for SMEs during industry 4.0

With the development of industry 4.0, the credit data of SMEs are characterized by a large volume, high speed, diversity and low-value density. How to select the key features that affect the credit risk from the high-dimensional data has become the critical point to accurately measure the credit risk of SMEs and alleviate their financing constraints. In doing so, this paper proposes a credit risk feature selection approach that integrates the binary opposite whale optimization algorithm (BOWOA) and the Kolmogorov-Smirnov (KS) statistic. Furthermore, we use seven machine learning classifiers and three discriminant methods to verify the robustness of the proposed model by using three actual bank data from SMEs. The empirical results show that although no one artificial intelligence credit evaluation method is universal for different SMEs' credit data, the performance of the BOWOA-KS model proposed in this paper is better than other methods if the number of indicators in the optimal subset of indicators and the prediction performance of the classifier are considered simultaneously. By providing a high-dimensional data feature selection method and improving the predictive performance of credit risk, it could help SMEs focus on the factors that will allow them to improve their creditworthiness and more easily access loans from financial institutions. Moreover, it will also help government agencies and policymakers develop policies to help SMEs reduce their credit risks.

Experimental Study of Potential CD8+ Trivalent Synthetic Peptides for Liver Cancer Vaccine Development Using Sprague Dawley Rat Models

Background. Liver cancer (LC) is the most devastating disease affecting a large set of populations in the world. The mortality due to LC is escalating, indicating the lack of effective therapeutic options. Immunotherapeutic agents may play an important role against cancer cells. As immune cells, especially T lymphocytes, which are part of cancer immunology, the design of vaccine candidates for cytotoxic T lymphocytes may be an effective strategy for curing liver cancer. Results. In our study, based on an immunoinformatics approach, we predicted potential T cell epitopes of MHC class I molecules using integrated steps of data retrieval, screening of antigenic proteins, functional analysis, peptide synthesis, and experimental in vivo investigations. We predicted the binding affinity of epitopes LLECADDRADLAKY, VSEHRIQDKDGLFY, and EYILSLEELVNGMY of LC membrane-bounded extracellular proteins including butyrophilin-like protein-2 (BTNL2), glypican-3 (GPC3), and serum albumin (ALB), respectively, with MHC class I molecules (allele: HLA-A $\ast$ 01:01). These T cell epitopes rely on the level of their binding energy and antigenic properties. We designed and constructed a trivalent immunogenic model by conjugating these epitopes with linkers to activate cytotoxic T cells. For validation, the nonspecific hematological assays showed a significant rise in the count of white blood cells ( $5\times {10}^9/\text{l}$ ), lymphocytes ( $13\times {10}^9/\text{l}$ ), and granulocytes ( $5\times {10}^9/\text{l}$ ) compared to the control after administration of trivalent peptides. Specific immunoassays including granzyme B and IgG ELISA exhibited the significant concentration of these effector molecules in blood serum, indicating the activity of cytotoxic T cells. Granzyme concentration increased to 1050 pg/ml at the second booster dose compared to the control (95 pg/ml), while the concentration of IgG raised to 6 g/l compared to the control (2 g/l). Conclusion. We concluded that a potential therapeutic trivalent vaccine can activate and modulate the immune system to cure liver cancer on the basis of significant outcomes of specific and nonspecific assays.

Application of non-equidistant GM(1,1) model based on the fractional-order accumulation in building settlement monitoring

Non-equidistant GM(1,1) (abbreviated as NEGM) model is widely used in building settlement prediction because of its high accuracy and outstanding adaptability. To improve the building settlement prediction accuracy of the NEGM model, the fractional-order non-equidistant GM(1,1) model (abbreviated as FNEGM) is established in this study. In the modeling process of the FNEGM model, the fractional-order accumulated generating sequence is extended based on the first-order accumulated generating sequence, and the optimal parameters that increase the prediction precision of the model are obtained by using the whale optimization algorithm. The FNEGM model and the other two grey prediction models are applied to three cases, and five prediction performance indexes are used to evaluate the prediction precision of the three models. The results show that the FNEGM model is more suitable for predicting the settlement of buildings than the other two grey prediction models.

In silico and in vivo neuropharmacological evaluation of two γ-amino acid isomers derived from 2,3-disubstituted benzofurans, as ligands of GluN1-GluN2A NMDA receptor

The GABAergic and glutamatergic neurotransmission systems are involved in seizures and other disorders of the central nervous system (CNS). Benzofuran derivatives often serve as the core in drugs used to treat such neurological disorders. The aim of this study was to synthesize new γ-amino acids structurally related to GABA and derived from 2,3-disubstituted benzofurans, analyze in silico their potential toxicity, ADME properties, and affinity for the GluN1-GluN2A NMDA receptor, and evaluate their potential activity and neuronal mechanisms in a murine model of pentylenetetrazol (PTZ)- and 4-aminopyridine (4-AP)-induced seizures. The in silico analysis evidenced a low risk of toxicity for the test compounds as well as the probability that they can cross the blood-brain barrier (BBB) to reach their targets in the CNS. According to docking simulations, these compounds bind at the active site of the NMDA glutamate receptor with high affinity. The in vivo assays demonstrated that 4 protects against 4-AP-induced seizure episodes, suggesting negative allosteric modulation (NAMs) at the glutamatergic NMDA receptor. Contrarily, 3 (the regioisomer of 4) and its racemic derivatives (cis-2,3-dihydrobenzofurans) were previously described to exacerbate such episodes, pointing to their positive allosteric modulation (PAMs) of the same receptor.

Supervised Methods for Biomarker Detection from Microarray Experiments

Biomarkers are valuable indicators of the state of a biological system. Microarray technology has been extensively used to identify biomarkers and build computational predictive models for disease prognosis, drug sensitivity and toxicity evaluations. Activation biomarkers can be used to understand the underlying signaling cascades, mechanisms of action and biological cross talk. Biomarker detection from microarray data requires several considerations both from the biological and computational points of view. In this chapter, we describe the main methodology used in biomarkers discovery and predictive modeling and we address some of the related challenges. Moreover, we discuss biomarker validation and give some insights into multiomics strategies for biomarker detection.

In silico and in vivo neuropharmacological evaluation of two γ-amino acid isomers derived from 2,3-disubstituted benzofurans, as ligands of GluN1-GluN2A NMDA receptor

The GABAergic and glutamatergic neurotransmission systems are involved in seizures and other disorders of the central nervous system (CNS). Benzofuran derivatives often serve as the core in drugs used to treat such neurological disorders. The aim of this study was to synthesize new γ-amino acids structurally related to GABA and derived from 2,3-disubstituted benzofurans, analyze in silico their potential toxicity, ADME properties, and affinity for the GluN1-GluN2A NMDA receptor, and evaluate their potential activity and neuronal mechanisms in a murine model of pentylenetetrazol (PTZ)- and 4-aminopyridine (4-AP)-induced seizures. The in silico analysis evidenced a low risk of toxicity for the test compounds as well as the probability that they can cross the blood-brain barrier (BBB) to reach their targets in the CNS. According to docking simulations, these compounds bind at the active site of the NMDA glutamate receptor with high affinity. The in vivo assays demonstrated that 4 protects against 4-AP-induced seizure episodes, suggesting negative allosteric modulation (NAMs) at the glutamatergic NMDA receptor. Contrarily, 3 (the regioisomer of 4) and its racemic derivatives (cis-2,3-dihydrobenzofurans) were previously described to exacerbate such episodes, pointing to their positive allosteric modulation (PAMs) of the same receptor.

EWOA-OPF: Effective Whale Optimization Algorithm to Solve Optimal Power Flow Problem

The optimal power flow (OPF) is a vital tool for optimizing the control parameters of a power system by considering the desired objective functions subject to system constraints. Metaheuristic algorithms have been proven to be well-suited for solving complex optimization problems. The whale optimization algorithm (WOA) is one of the well-regarded metaheuristics that is widely used to solve different optimization problems. Despite the use of WOA in different fields of application as OPF, its effectiveness is decreased as the dimension size of the test system is increased. Therefore, in this paper, an effective whale optimization algorithm for solving optimal power flow problems (EWOA-OPF) is proposed. The main goal of this enhancement is to improve the exploration ability and maintain a proper balance between the exploration and exploitation of the canonical WOA. In the proposed algorithm, the movement strategy of whales is enhanced by introducing two new movement strategies: (1) encircling the prey using Levy motion and (2) searching for prey using Brownian motion that cooperate with canonical bubble-net attacking. To validate the proposed EWOA-OPF algorithm, a comparison among six well-known optimization algorithms is established to solve the OPF problem. All algorithms are used to optimize single- and multi-objective functions of the OPF under the system constraints. Standard IEEE 6-bus, IEEE 14-bus, IEEE 30-bus, and IEEE 118-bus test systems are used to evaluate the proposed EWOA-OPF and comparative algorithms for solving the OPF problem in diverse power system scale sizes. The comparison of results proves that the EWOA-OPF is able to solve single- and multi-objective OPF problems with better solutions than other comparative algorithms.

Review of Metaheuristics Inspired from the Animal Kingdom

The search for powerful optimizers has led to the development of a multitude of metaheuristic algorithms inspired from all areas. This work focuses on the animal kingdom as a source of inspiration and performs an extensive, yet not exhaustive, review of the animal inspired metaheuristics proposed in the 2006–2021 period. The review is organized considering the biological classification of living things, with a breakdown of the simulated behavior mechanisms. The centralized data indicated that 61.6% of the animal-based algorithms are inspired from vertebrates and 38.4% from invertebrates. In addition, an analysis of the mechanisms used to ensure diversity was performed. The results obtained showed that the most frequently used mechanisms belong to the niching category.

Risk prediction for delayed clearance of high-dose methotrexate in pediatric hematological malignancies by machine learning

This study aimed to establish a predictive model to identify children with hematologic malignancy at high risk for delayed clearance of high-dose methotrexate (HD-MTX) based on machine learning. A total of 205 patients were recruited. Five variables (hematocrit, risk classification, dose, SLC19A1 rs2838958, sex) and three variables (SLC19A1 rs2838958, sex, dose) were statistically significant in univariable analysis and, separately, multivariate logistic regression. The data was randomly split into a "training cohort" and a "validation cohort". A nomogram for prediction of delayed HD-MTX clearance was constructed using the three variables in the training dataset and validated in the validation dataset. Five machine learning algorithms (cart classification and regression trees, naïve Bayes, support vector machine, random forest, C5.0 decision tree) combined with different resampling methods were used for model building with five or three variables. When developed machine learning models were evaluated in the validation dataset, the C5.0 decision tree combined with the synthetic minority oversampling technique (SMOTE) using five variables had the highest area under the receiver operating characteristic curve (AUC 0.807 [95% CI 0.724-0.889]), a better performance than the nomogram (AUC 0.69 [95% CI 0.594-0.787]). The results support potential clinical application of machine learning for patient risk classification.

Non-equidistant non-homogenous grey prediction model with fractional accumulation and its application

Non-equidistant non-homogenous grey model (abbreviated as NENGM (1,1, k) model) is a grey prediction model suitable for predicting time series with non-equal intervals. It is widely used in various fields of society due to its high prediction accuracy and strong adaptability. In order to further improve the prediction accuracy of the NENGM (1,1, k) model, the NENGM (1,1, k) model is optimized in terms of the cumulative order and background value of the NENGM (1,1, k) model, and a NENGM (1,1, k) model based on double optimization is established (abbreviated as FBNENGM (1,1, k) model), and the whale optimization algorithm is used to solve the best parameters of the model. In order to verify the feasibility and validity of the FBNENGM (1,1, k) model, the FBNENGM (1,1, k) model and other four prediction models are applied to three cases respectively, and three indexes commonly used to evaluate the performance of prediction models are used to distinguish. The results show that the prediction accuracy of the FBNENGM (1,1, k) model based on double optimization is better than other prediction models.

Classification assessment methods

Classification techniques have been applied to many applications in various fields of sciences. There are several ways of evaluating classification algorithms. The analysis of such metrics and its significance must be interpreted correctly for evaluating different learning algorithms. Most of these measures are scalar metrics and some of them are graphical methods. This paper introduces a detailed overview of the classification assessment measures with the aim of providing the basics of these measures and to show how it works to serve as a comprehensive source for researchers who are interested in this field. This overview starts by highlighting the definition of the confusion matrix in binary and multi-class classification problems. Many classification measures are also explained in details, and the influence of balanced and imbalanced data on each metric is presented. An illustrative example is introduced to show (1) how to calculate these measures in binary and multi-class classification problems, and (2) the robustness of some measures against balanced and imbalanced data. Moreover, some graphical measures such as Receiver operating characteristics (ROC), Precision-Recall, and Detection error trade-off (DET) curves are presented with details. Additionally, in a step-by-step approach, different numerical examples are demonstrated to explain the preprocessing steps of plotting ROC, PR, and DET curves.

Predicting Drug-Induced Liver Injury Using Convolutional Neural Network and Molecular Fingerprint-Embedded Features

As a critical issue in drug development and postmarketing safety surveillance, drug-induced liver injury (DILI) leads to failures in clinical trials as well as retractions of on-market approved drugs. Therefore, it is important to identify DILI compounds in the early-stages through in silico and in vivo studies. It is difficult using conventional safety testing methods, since the predictive power of most of the existing frameworks is insufficiently effective to address this pharmacological issue. In our study, we employ a natural language processing (NLP) inspired computational framework using convolutional neural networks and molecular fingerprint-embedded features. Our development set and independent test set have 1597 and 322 compounds, respectively. These samples were collected from previous studies and matched with established chemical databases for structural validity. Our study comes up with an average accuracy of 0.89, Matthews's correlation coefficient (MCC) of 0.80, and an AUC of 0.96. Our results show a significant improvement in the AUC values compared to the recent best model with a boost of 6.67%, from 0.90 to 0.96. Also, based on our findings, molecular fingerprint-embedded featurizer is an effective molecular representation for future biological and biochemical studies besides the application of classic molecular fingerprints.

Classification assessment methods

Classification techniques have been applied to many applications in various fields of sciences. There are several ways of evaluating classification algorithms. The analysis of such metrics and its significance must be interpreted correctly for evaluating different learning algorithms. Most of these measures are scalar metrics and some of them are graphical methods. This paper introduces a detailed overview of the classification assessment measures with the aim of providing the basics of these measures and to show how it works to serve as a comprehensive source for researchers who are interested in this field. This overview starts by highlighting the definition of the confusion matrix in binary and multi-class classification problems. Many classification measures are also explained in details, and the influence of balanced and imbalanced data on each metric is presented. An illustrative example is introduced to show (1) how to calculate these measures in binary and multi-class classification problems, and (2) the robustness of some measures against balanced and imbalanced data. Moreover, some graphical measures such as Receiver operating characteristics (ROC), Precision-Recall, and Detection error trade-off (DET) curves are presented with details. Additionally, in a step-by-step approach, different numerical examples are demonstrated to explain the preprocessing steps of plotting ROC, PR, and DET curves.

Feature Selection of Grey Wolf Optimizer Based on Quantum Computing and Uncertain Symmetry Rough Set

Considering the crucial influence of feature selection on data classification accuracy, a grey wolf optimizer based on quantum computing and uncertain symmetry rough set (QCGWORS) was proposed. QCGWORS was to apply a parallel of three theories to feature selection, and each of them owned the unique advantages of optimizing feature selection algorithm. Quantum computing had a good balance ability when exploring feature sets between global and local searches. Grey wolf optimizer could effectively explore all possible feature subsets, and uncertain symmetry rough set theory could accurately evaluate the correlation of potential feature subsets. QCGWORS intelligent algorithm could minimize the number of features while maximizing classification performance. In the experimental stage, k nearest neighbors (KNN) classifier and random forest (RF) classifier guided the machine learning process of the proposed algorithm, and 13 datasets were compared for testing experiments. Experimental results showed that compared with other feature selection methods, QCGWORS improved the classification accuracy on 12 datasets, among which the best accuracy was increased by 20.91%. In attribute reduction, each dataset had a benefit of the reduction effect of the minimum feature number.

Whale optimized mixed kernel function of support vector machine for colorectal cancer diagnosis

Microarray technique is a prevalent method for the classification and prediction of colorectal cancer (CRC). Nevertheless, microarray data suffers from the curse of dimensionality when selecting feature genes of the disease based on imbalance samples, thus causing low prediction accuracy. Hence, it is of vital significance to build proper models that can avoid the above problems and predict the CRC more accurately. In this paper, we use an ensemble model to classify samples into healthy and CRC groups and improve prediction performance. The proposed model is composed of three functional modules. The first module mainly performs the function of removing redundant genes. The main feature genes are selected using minimum redundancy maximum relevance (mRMR) method to reduce the dimensionality of features thereby increasing the prediction results. The second module aims to solve the problem caused by imbalanced data using hybrid sampling algorithm RUSBoost. The third module focuses on the classification algorithm optimization. We use mixed kernel function (MKF) based support vector machine (SVM) model to classify an unknown sample into healthy individuals and CRC patients, and then, the Whale Optimization Algorithm (WOA) is applied to find most optimal parameters of the proposed MKF-SVM. The final results show that the proposed model achieves higher G-means than other comparable models. The conclusion comes to show that RUSBoost wrapping WOA + MKF-SVM model can be applied to improve the predictive performance of colorectal cancer based on the imbalanced data.

Prediction of Drug-Likeness Using Deep Autoencoder Neural Networks

Due to diverse reasons, most drug candidates cannot eventually become marketed drugs. Developing reliable computational methods for prediction of drug-likeness of candidate compounds is of vital importance to improve the success rate of drug discovery and development. In this study, we used a fully connected neural networks (FNN) to construct drug-likeness classification models with deep autoencoder to initialize model parameters. We collected datasets of drugs (represented by ZINC World Drug), bioactive molecules (represented by MDDR and WDI), and common molecules (represented by ZINC All Purchasable and ACD). Compounds were encoded with MOLD2 two-dimensional structure descriptors. The classification accuracies of drug-like/non-drug-like model are 91.04% on WDI/ACD databases, and 91.20% on MDDR/ZINC, respectively. The performance of the models outperforms previously reported models. In addition, we develop a drug/non-drug-like model (ZINC World Drug vs. ZINC All Purchasable), which distinguishes drugs and common compounds, with a classification accuracy of 96.99%. Our work shows that by using high-latitude molecular descriptors, we can apply deep learning technology to establish state-of-the-art drug-likeness prediction models.