Modeling Choices for Virtual Screening Hit Identification

In the evolving field of cybersecurity, detecting malicious activity in high-dimensional network data remains a persistent challenge for traditional machine learning (ML) techniques. This study investigates the use of convolutional variational autoencoders (VAEs) to generate latent features that enhance the performance of various ML classifiers on the 2015 NSL-KDD dataset. Classifiers, including Gaussian Naïve Bayes (GNB), support vector machines (SVMs) with Radial Basis Function (RBF) kernel, decision trees, and dense neural networks, were evaluated using metrics such as accuracy, precision, recall, F1 score, and the Matthews Correlation Coefficient (MCC). To assess the effectiveness of VAEs, Principal Component Analysis (PCA) was used as a baseline dimensionality reduction method, and performance comparisons were made. The best-performing model was an SVM with an RBF kernel, a PCA (threshold = 0.92), and a VAE with six latent features, achieving an accuracy of 82.8%, an F1 score of 0.830, and an MCC of 0.682. The results indicate that VAEs can significantly enhance classifier performance, particularly in GNB and SVM models, suggesting their value in developing more effective intrusion detection systems. Received: 23 August 2024 | Revised: 3 June 2025 | Accepted: 15 July 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in NSL-KDD Dataset at https://github.com/t-taylor/cvaes-research/tree/main/results. Author Contribution Statement Thomas Taylor: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing – original draft, Writing – review & editing, Visualization. Amna Eleyan: Conceptualization, Methodology, Writing – original draft, Writing – review & editing, Supervision, Project administration. Mohammed Al-Khalidi: Validation, Resources, Writing – original draft, Writing – review & editing, Visualization, Supervision.

Structural optimization on a virtual screening hit of smoothened receptor

Near infrared spectroscopy was used in discrimination of intact bovine teeth in terms of animal sex, diet, tooth type and place of origin. Discriminant Analysis (DA) models were developed and tested using a stratified random 70:30 data split to calibration and test sets. Of the discriminant techniques of Soft Independent Modelling of Class Analogy (SIMCA), Partial Least Squares – DA, Artificial Neural Networks (ANN) and Support Vector Machine (SVM), SVM and PLS-DA models performed best in most instances, with pretreatment choice impacting technique success. For test set prediction of animal sex, an accuracy of 95% was achieved using a PLS-DA model, and similar performance achieved using a SVM model. SVM, ANN and SIMCA models predicted three categories of tooth type (deciduous, permanent unerupted and erupted) with similar accuracies (89, 79 and 82%, respectively), however, permanent unerupted teeth were conflated with permanent erupted teeth. Prediction accuracy for ANN, SVM and PLS-DA models were also similar for discrimination of teeth from animals on a grain versus grass diet (PLS-DA 82%). There was considerable variation between models in prediction of geographic origin. Of the seven locations, two were discriminated with true positive rate around 70% using SVM and ANN models. Potential applications of this technology are discussed.

Malware forensic investigation plays a critical role in cybersecurity, aiming to unveil malicious activities, decipher their tactics, and bolster defense mechanisms. This article introduces an innovative approach to malware forensic investigation, harnessing the capabilities of the Gray Wolf Optimization (GWO) algorithm in conjunction with a range of machine learning classifiers. These classifiers include naive Bayes, random forests (RF), decision trees, support vector machines, and K-nearest neighbors. The study leverages the CIC-MalMem-2022 dataset, which comprises memory-based data, and employs the Python programming language for model development. Research findings highlight the superiority of the RF classifier, achieving an impressive 75.6% accuracy in a multiclass classification scenario involving 16 classes. Notably, our proposed approach consistently exhibits higher accuracy when compared to existing models applied to different datasets, reaching 99.2% in binary classification. Furthermore, on the same dataset, our model outperforms the competition by achieving 86.34% and 75.64% accuracy in multiclass classification scenarios involving four classes and 16 classes, respectively. These results underscore the promising potential of our proposed model in the domain of malware forensic investigation, particularly when analyzing data extracted from memory. By combining the strength of the GWO algorithm with RF, this study aids in the progression of robust and accurate malware forensic investigation methods, thereby enhancing cybersecurity efforts in an ever-evolving threat landscape. Received: 20 December 2024 | Revised: 10 March 2025 | Accepted: 3 April 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement Data are available on request from the corresponding author upon reasonable request. Author Contribution Statement Mosleh Mohammd Abualhaj: Conceptualization, Methodology, Investigation, Writing – original draft, Writing – review & editing, Supervision. Sumaya Al-Khatib: Conceptualization, Software, Validation, Resources, Data curation, Writing – original draft, Visualization. Nida Al Shafi: Software, Validation, Resources, Data curation, Writing – review & editing. Iyas Qaddara: Methodology, Formal analysis, Writing – original draft, Visualization. Abdallah Hyassat: Methodology, Formal analysis.

기업의 부도를 예측하는 것은 회계나 재무 분야에서 중요한 연구주제이다. 지금까지 기업 부도예측을 위해 여러 가지 데이터마이닝 기법들이 적용되었으나 주로 단일 모형을 사용함으로서 복잡한 분류 문제에의 적용에 한계를 갖고 있었다. 본 논문에서는 최근에 각광받고 있는 SVM (support vector machine) 모형들을 결합한 앙상블 SVM 모형 (ensemble SVM model)을 부도예측에 사용하고자 한다. 제안된 앙상블 모형은 v-조각 교차 타당성 (v-fold cross-validation)에 의해 얻어진 여러 가지 모형 중에서 성능이 좋은 상위 k개의 단일 모형으로 구성하고 과반수 투표 방식 (majority voting)을 사용하여 미지의 클래스를 분류한다. 본 논문에서 제안된 앙상블 SVM 모형의 성능을 평가하기 위해 실제 기업의 재무비율 자료와 모의실험자료를 가지고 실험하였고, 실험결과 제안된 앙상블 모형이 여러 가지 평가척도 하에서 단일 SVM 모형들보다 좋은 성능을 보임을 알 수 있었다. Corporate bankruptcy prediction has been an important topic in the accounting and finance field for a long time. Several data mining techniques have been used for bankruptcy prediction. However, there are many limits for application to real classification problem with a single model. This study proposes ensemble SVM (support vector machine) model which assembles different SVM models with each different kernel functions. Our ensemble model is made and evaluated by v-fold cross-validation approach. The k top performing models are recruited into the ensemble. The classification is then carried out using the majority voting opinion of the ensemble. In this paper, we investigate the performance of ensemble SVM classifier in terms of accuracy, error rate, sensitivity, specificity, ROC curve, and AUC to compare with single SVM classifiers based on financial ratios dataset and simulation dataset. The results confirmed the advantages of our method: It is robust while providing good performance.

Prediction of the acute toxicity of chemical compounds to the fathead minnow by machine learning approaches

This work presents a novel concept known as Heart Disease Systematic Machine learning Analytical Risk prediction Technology (HD-SMART) that is considered a unique perspective in handling cardiac disease and the identification of sophisticated risk markers using superior computational technology. The work offers a rather peculiar approach to harnessing multiple machine learning algorithms in combination with feature selection methods that proved themselves highly accurate in cardiovascular risk estimation. The novelty is that these algorithms, namely, the Random Forest, Support Vector Machines (SVM), and Logistic Regression, are to be adopted in a systematic manner with supplementary feature engineering and with hyperparameter optimization, respectively. Based on the UCI Heart Disease dataset of 303 instances with 14 attributes, the new HD-SMART framework illustrated exceptional predictive capability, with the Random Forest at 97.57%, followed by SVM (95.23%) and Logistic Regression at 94.18%. The methodology achieved unique convergent optimization regarding feature selection with a minimum cost function of 0.0004 at iteration 50, while the Root Mean Square Error convergence was reached within the first four iterations with a value of 0.030. The innovative approach of data preprocessing and feature analysis in the framework pointed out critical patterns in cardiological parameters, such as in chest pain distribution (n ≈ 410 typical angina cases), bimodal blood pressure peaks (130–140 mmHg and 190–200 mmHg), as well as electrocardiogram variabilities (450 normal and 350 ST-T-wave abnormalities). The new proportion of 70–30 train-test split ratio was more optimal for model performance. This work introduces a completely new, computational diagnostic approach that not only outperforms but significantly surpasses conventional methods, and its robust statistical validity is maintained across a number of performance metrics. HD-SMART contributes to the advancement of cardiovascular diagnosis as a new, effective tool for early detection of heart disease for health practitioners based on big data analysis. Received: 30 May 2025 | Revised: 11 November 2025 | Accepted: 8 January 2026 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The Heart Disease data set that supports the findings of this study is openly available at https://doi.org/10.1007/s00521-021-06124-1 and at https://doi.org/10.1109/iciccs48265.2020.9121169, reference number [22, 24]. Author Contribution Statement Gitanjali Gupta: Conceptualization, Methodology, Writing – original draft. Meena Malik: Conceptualization, Software, Validation, Visualization. Ramandeep Sandhu: Formal analysis, Investigation. Chander Prabha: Methodology, Resources, Data curation, Writing – review & editing, Supervision. Aimin Li: Investigation, Resources, Project administration. Saurav Mallik: Writing – review & editing, Visualization, Supervision.

Support vector machine modeling has become increasingly popular in chemoinformatics. Recently, several advanced support vector machine applications have been reported including, among others, multitask learning for ligand-target prediction. Here, we introduce another support vector machine approach to add compound potency information to similarity searching and enrich database selection sets with potent hits. For this purpose, we introduce a structure-activity kernel function and a potency-oriented support vector machine linear combination approach. Using fingerprint descriptors, potency-directed support vector machine searching has been successfully applied to four high-throughput screening data sets, and different support vector machine strategies have been compared. For potency-balanced compound reference sets, potency-directed support vector machine searching meets or exceeds recall rates of standard support vector machine calculations but detects many more potent hits.

The paper explores the hybrid of SVM and system of Artificial Neural Network as the finest binary classification system for calculating the diabetic nature of people in comparison to Support Vector Machine (SVM). In this research, the sets of all the parameters describing the diabetic nature of a person are taken from the laboratories. This approach is chosen so that a better learning method can be used for various problems. The testing results were found to be in accordance with the accepted results that resemble with the direct diagnosis of a physician. The results of this research shows that this hybrid SVM and Artificial Neural Network (ANN) model is more precise than the SVM model. These results of the hybrid SVM and ANN model suggest that it is very effective for the classification of Diabetic and Non Diabetic nature of a person. This paper highlights the concept of Support Vector Machines and its integration with Artificial Neural Network, the two key characteristics with one being the generalization theory of the SVM model that best describes how to select a hypothesis and functions given by Kernel that introduces the idea of non-linearity without the inclusion of the actual algorithm.

This study compares single and hybrid soft computing models for estimating daily solar radiation flux for two scenarios. Scenario I developed single soft computing models, including multilayer perceptron (MLP), support vector machines (SVM), adaptive neuro-fuzzy inference system (ANFIS), and multivariate adaptive regression splines (MARS), for estimating daily solar radiation flux at two stations from the USA and South Korea. The MLP model was used to evaluate the effect of factors controlling daily solar radiation flux. Using different combinations of controlling factors as input, the MLP and SVM models, based on evaluation measures, were found to be superior to the ANFIS and MARS models at Big Bend station, USA. In addition, the MLP, SVM, and MARS models performed better than did the ANFIS model at Incheon station, South Korea. Scenario II combined the discrete wavelet transform (DWT) and single soft computing models (e.g., MLP and SVM) for improved performance using 4-input combination. The wavelet-based MLP (WMLP) and SVM (WSVM) models were superior to other single soft computing models (MLP, SVM, ANFIS, and MARS) at two stations. Taylor diagrams, violin plots and point density plots were also utilized to examine the similarity between the observed and estimated solar radiation flux values. Results showed that scenarios I and II can be alternatives for estimating daily solar radiation flux based on different meteorological information, such as peninsular and continental conditions.

Astrocytoma is the most common neuroepithelial neoplasm, and its grading greatly affects treatment and prognosis. According to relevant factors of astrocytoma, this study developed a support vector machine (SVM) model to predict the astrocytoma grades and compared the SVM prediction with the clinician's diagnostic performance. Patients were recruited from a cohort of astrocytoma patients in our hospital between January 2008 and April 2009. Among all astrocytoma patients, nine had grade I, 25 had grade II, 12 had grade III, and 60 had grade IV astrocytoma. An SVM model was constructed using radial basis kernel. The SVM model was trained with nine magnetic resonance (MR) features and one clinical parameter by fivefold cross-validation and differentiated astrocytomas of grades I-IV at two levels, respectively. The clinician also predicted the grade of astrocytoma. According to the two prediction methods above, the areas under receiving operating characteristics (ROC) curves to discriminate low- and high-grade groups, accuracies of high-grade grouping, overall accuracy, and overall kappa values were compared. For SVM, the overall accuracy was 0.821 and the overall kappa value was 0.679; for clinicians, the overall accuracy was 0.651 and the overall kappa value was 0.466. The diagnostic performance of SVM is significantly better than clinician performance, with the exception of the low-grade group. The SVM model can provide useful information to help clinicians improve diagnostic performance when predicting astrocytoma grade based on MR images.

Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS

Purpose: Accurate lymph node (LN) status evaluation for intrahepatic cholangiocarcinoma (ICC) patients is essential for surgical planning. This study aimed to develop and validate a prediction model for preoperative LN status evaluation in ICC patients.Methods and Materials: A group of 106 ICC patients, who were diagnosed between April 2011 and February 2016, was used for prediction model training. Image features were extracted from T1-weighted contrast-enhanced MR images. A support vector machine (SVM) model was built by using the most LN status-related features, which were selected using the maximum relevance minimum redundancy (mRMR) algorithm. The mRMR method ranked each feature according to its relevance to the LN status and redundancy with other features. An SVM score was calculated for each patient to reflect the LN metastasis (LNM) probability from the SVM model. Finally, a combination nomogram was constructed by incorporating the SVM score and clinical features. An independent group of 42 patients who were diagnosed from March 2016 to November 2017 was used to validate the prediction models. The model performances were evaluated on discrimination, calibration, and clinical utility.Results: The SVM model was constructed based on five selected image features. Significant differences were found between patients with LNM and non-LNM in SVM scores in both groups (the training group: 0.5466 (interquartile range (IQR), 0.4059-0.6985) vs. 0.3226 (IQR, 0.0527-0.4659), P<0.0001; the validation group: 0.5831 (IQR, 0.3641-0.8162) vs. 0.3101 (IQR, 0.1029-0.4661), P=0.0015). The combination nomogram based on the SVM score, the CA 19-9 level, and the MR-reported LNM factor showed better discrimination in separating patients with LNM and non-LNM, comparing to the SVM model alone (AUC: the training group: 0.842 vs. 0.788; the validation group: 0.870 vs. 0.787). Favorable clinical utility was observed using the decision curve analysis for the nomogram.Conclusion: The nomogram, incorporating the SVM score, CA 19-9 level and the MR-reported LNM factor, provided an individualized LN status evaluation and helped clinicians guide the surgical decisions.

Support vector regression (SVR) is a premier approach for the prediction of compound potency. Given the conceptual link between support vector machine (SVM) and SVR modeling, SVR is capable of accounting for continuous and discontinuous structure-activity relationships (SARs) in potency prediction, which further extends the classical quantitative SAR (QSAR) paradigm. In the context of virtual compound screening, compound potency prediction can be applied to identify the most potent compounds that are available or enrich database selection sets with potent compounds. To these ends, we have evaluated new potency prediction strategies. Conventional (direct) potency prediction using SVR was compared to two-stage SVM-SVR modeling and potency prediction using SVR models trained in the presence of active and inactive compounds, a previously unconsidered approach. The latter models were found to maximize the recall of potent compounds but were least accurate in predicting high potency values. For this purpose, direct SVR predictions were preferred. However, the best balance between accurate potency predictions and enrichment of potent compounds in database selection sets was achieved by combined SVM-SVR modeling. Taken together, our findings further extend current approaches for compound potency prediction in virtual compound screening.

Comparative study of different machine learning models in landslide susceptibility assessment: A case study of Conghua District, Guangzhou, China