Article
Chemistry, Analytical
Ahmed M. Elshewey, Mahmoud Y. Shams, Nora El-Rashidy, Abdelghafar M. Elhady, Samaa M. Shohieb, Zahraa Tarek
Summary: This paper presents an advanced model called BO-SVM to classify individuals with Parkinson's disease. Bayesian Optimization is used to optimize the hyperparameters of six machine learning models, and the performance of these models is evaluated using various metrics. Experimental results show that the SVM model achieves the highest accuracy of 92.3% after hyperparameter tuning using BO.
Article
Computer Science, Artificial Intelligence
Shili Peng, Wenwu Wang, Yinli Chen, Xueling Zhong, Qinghua Hu
Summary: This article presents a new idea for addressing the challenge of unifying classification and regression in machine learning. It proposes converting the classification problem into a regression problem and using regression methods to solve key problems in classification. Experimental results demonstrate that the proposed method outperforms existing algorithms in terms of prediction accuracy and model uncertainty.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Biotechnology & Applied Microbiology
Yifeng Dou, Wentao Meng
Summary: This paper introduces the research, prediction, and diagnosis methods of breast cancer, using the improved optimization algorithm GSP_SVM, which shows excellent performance in breast cancer diagnosis and improves the diagnostic efficiency of medical institutions.
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
A. Ponmalar, V Dhanakoti
Summary: This paper presents a novel technique to enhance intrusion detection by addressing the complexities of heterogeneous security data in big data. The proposed methodology significantly improves accuracy and can identify different types of attacks. Comparisons with baseline models demonstrate the effectiveness of the approach.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Interdisciplinary Applications
Maliheh Abbaszadeh, Saeed Soltani-Mohammadi, Ali Najah Ahmed
Summary: This article introduces the application of the support vector classifier in geological modeling and proposes an improved method based on particle swarm optimization to select the best model parameters. Through the application in the modeling process of the Iju porphyry copper deposit, the effectiveness and superiority of this method are demonstrated.
COMPUTERS & GEOSCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Yanmeng Li, Huaijiang Sun
Summary: In this paper, a new method named Safe Sample Screening for robust TSVM (SSS-RTSVM) is proposed. SSS-RTSVM clips the hinge loss in the traditional soft margin twin support vector machine to the ramp loss, and provides a pair of nonparallel proximal hyperplanes to achieve good anti-noise ability. Additionally, safe sample screening rules based on CCCP are integrated to reduce the computational cost without sacrificing the optimal accuracy.
APPLIED INTELLIGENCE
(2023)
Article
Environmental Sciences
Guangxin Liu, Liguo Wang, Danfeng Liu, Lei Fei, Jinghui Yang
Summary: This article proposes a non-parallel SVM model, which improves the classification effect and generalization performance for hyperspectral images by adding an additional empirical risk minimization term and bias constraint.
Article
Geosciences, Multidisciplinary
Wei Xie, Wen Nie, Pooya Saffari, Luis F. Robledo, Pierre-Yves Descote, Wenbin Jian
Summary: The study proposed a novel approach for landslide hazard assessment using support vector machine (SVM) and Bayesian optimization (BO) algorithm and achieved better accuracy compared to the traditional SVM model. Through multicollinearity diagnosis and model validation, the optimized SVM model showed higher accuracy in landslide assessment.
Article
Computer Science, Interdisciplinary Applications
Hongyou Cao, Huiyang Li, Wen Sun, Yuxi Xie, Bin Huang
Summary: In order to improve the computational efficiency of structural optimization, this study proposes a boundary identification approach (BIA) to identify the feasible region boundary of search space by treating the feasibility evaluation as a two-class classification problem. The BIA includes a virtual sampling technique (VST), an improved Latin hypercube sampling (ILHS) method, and a support vector machine (SVM) classifier. Through numerical and truss examples, it is shown that the BIA can achieve high prediction accuracy and significantly reduce the number of structural analyses required.
COMPUTERS & STRUCTURES
(2023)
Article
Computer Science, Artificial Intelligence
Duong Tran Anh, Manish Pandey, Varun Narayan Mishra, Kiran Kumari Singh, Kourosh Ahmadi, Saeid Janizadeh, Thanh Thai Tran, Nguyen Thi Thuy Linh, Nguyen Mai Dang
Summary: Water supply is one of the most important concerns and challenges for achieving sustainable development goals in most countries. Accurate identification of areas with groundwater potential is therefore crucial for the protection, management, and exploitation of water resources. This study used Multivariate adaptive regression spline (MARS) and Support vector machine (SVM) machine learning models, along with two random search (RS) and Bayesian optimization hyperparameter algorithms, to model and predict groundwater potential in Markazi province, Iran. The results showed that using hyperparameters random search and Bayesian optimization improved the accuracy of the SVM model in both training and validation stages. The evaluation of accuracy in the validation stage revealed AUC values of 87.40%, 88.25%, 90.73%, and 91.73% for the MARS, SVM, RS-SVM, and B-SVM models, respectively. The assessment of variable importance indicated that elevation, precipitation in the coldest month, soil, and slope variables were the most important in modeling groundwater potential, while aspect, profile curvature, and TWI variables had the least importance in predicting groundwater potential in Markazi province.
APPLIED SOFT COMPUTING
(2023)
Article
Biochemistry & Molecular Biology
Maninder Singh, Jyotika Rajawat, Jitendra Kuldeep, Nidhi Shukla, Durga Prasad Mishra, Mohammad Imran Siddiqi
Summary: PARP1 inhibition strategy is increasingly used for cancer treatment, especially in patients with BRCA1/BRCA2 gene mutations. Through virtual screening, three potential PARP1 inhibitors were identified, one of which could be a new chemotype of PARP1 inhibitors.
JOURNAL OF BIOMOLECULAR STRUCTURE & DYNAMICS
(2022)
Article
Automation & Control Systems
Zhenchao Ma, Laurence Tianruo Yang, Qingchen Zhang
Summary: This study proposes a Support Multimode Tensor Machine (SMTM) algorithm that generalizes the formulation of traditional Support Tensor Machine (STM) by applying multimode product. Experiments conducted on various datasets validate the superior performance of SMTM in multiple classification tasks and suggest the potential of the proposed model for multiple classification in industrial big data.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Artificial Intelligence
Bagesh Kumar, Ayush Sinha, Sourin Chakrabarti, O. P. Vyas
Summary: In this paper, a fast training method for OCSSVM is proposed, which enhances its scalability without compromising precision significantly. Experimental results show that the proposed method achieves the best tradeoff between training time and accuracy, providing similar accuracies to regular OCSSVM and better scalability compared to existing state-of-the-art one-class classifiers.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Instruments & Instrumentation
Mahsa Mohammadi, Mohammadreza Khanmohammadi Khorrami, Hossein Ghasemzadeh
Summary: This paper investigates the classification of nanofluid solutions based on viscosity values using different predictive modeling algorithms. The results show that the Logistic Model Tree algorithm performs well in this classification task.
INFRARED PHYSICS & TECHNOLOGY
(2022)
Article
Management
Asuncion Jimenez-Cordero, Juan Miguel Morales, Salvador Pineda
Summary: Feature selection has become a challenging issue in machine learning, particularly in classification problems. Support Vector Machine is a widely used technique in classification tasks, with various methodologies proposed for selecting the most relevant features in SVM. The authors introduce an embedded feature selection method based on a min-max optimization problem to balance model complexity and classification accuracy, showcasing efficiency and usefulness in benchmark datasets.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2021)
Article
Chemistry, Organic
Sergey Grintsevich, Alexander Sapegin, Beata Duszynska, Andrzej J. Bojarski, Mikhail Krasavin
Summary: Attempts to extend the hydrated imidazoline ring expansion strategy to a series of diarene-fused [1,4]diazepinones did not lead to ring expansion but resulted in expulsion of the 2-aminoethyl side chain. This setback led to the discovery of selective dopamine D-2 ligands with elements of structure-activity relationships.
SYNTHESIS-STUTTGART
(2022)
Article
Biochemistry & Molecular Biology
Katarzyna Szczepanska, Sabina Podlewska, Maria Dichiara, Davide Gentile, Vincenzo Patamia, Niklas Rosier, Denise Moennich, Ma Carmen Ruiz Cantero, Tadeusz Karcz, Dorota Lazewska, Agata Siwek, Steffen Pockes, Enrique J. Cobos, Agostino Marrazzo, Holger Stark, Antonio Rescifina, Andrzej J. Bojarski, Emanuele Amata, Katarzyna Kiec-Kononowicz
Summary: Recent studies have shown that some clinically evaluated histamine H-3 receptor antagonists have nanomolar affinity at sigma-1 receptors. Among 20 representative structures of H3R ligands tested, six showed higher affinity towards sigma R-1 than sigma R-2, with the piperidine moiety being a critical structural element for dual H-3/sigma(1) receptor activity. Molecular modeling techniques identified high-affinity lead structures for further evaluation, showing promising antinociceptive activity in vivo and potential as dual-acting compounds for improving pain therapies.
ACS CHEMICAL NEUROSCIENCE
(2022)
Article
Biochemistry & Molecular Biology
Eduardo Penna, Mauro Niso, Sabina Podlewska, Floriana Volpicelli, Marianna Crispino, Carla Perrone-Capano, Andrzej J. Bojarski, Enza Lacivita, Marcello Leopoldo
Summary: The kinetics of drug-target interaction has been a topic of increasing interest in the field of pharmacology. Previous studies have shown the importance of the lipophilicity of a molecule in this process, but there has been limited research on the 5-HT7 receptor (5-HT7R), a GPCR involved in neurodevelopmental and neuropsychiatric disorders. In this study, the researchers explored the structure-kinetics relationships of a specific class of ligands for the 5-HT7R and found that the position of polar groups within the molecule, rather than overall lipophilicity, influenced the interaction kinetics. Additionally, molecular docking and dynamics simulations were used to gain further insights into the relationship between structure and kinetics.
ACS CHEMICAL NEUROSCIENCE
(2022)
Article
Biochemistry & Molecular Biology
Anna Stankiewicz, Katarzyna Kaczorowska, Ryszard Bugno, Aneta Koziol, Maria H. Paluchowska, Grzegorz Burnat, Barbara Chruscicka, Paulina Chorobik, Piotr Branski, Joanna M. Wieronska, Beata Duszynska, Andrzej Pilc, Andrzej J. Bojarski
Summary: This study developed a group of 1,2,4-oxadiazole derivatives that exhibited positive allosteric modulatory activity on mGlu(4) receptors. These derivatives were selectively active on mGlu(7) and mGlu(8) receptors and showed anxiolytic- and antipsychotic-like properties.
JOURNAL OF ENZYME INHIBITION AND MEDICINAL CHEMISTRY
(2022)
Article
Pharmacology & Pharmacy
Lucja Kudla, Ryszard Bugno, Sabina Podlewska, Lukasz Szumiec, Lucja Wiktorowska, Andrzej J. Bojarski, Ryszard Przewlocki
Summary: This study evaluated the effects of G protein-biased opioid agonists SR-14968 and SR-17018 on antinociception, motor activity, and addiction-like behaviors in mice. The results showed that these compounds have strong antinociceptive effects, induce locomotor activity and addictive behaviors, and develop antinociceptive tolerance. Furthermore, SR agonists can slow down the development of antinociceptive tolerance to morphine and inhibit morphine withdrawal symptoms.
Review
Biochemistry & Molecular Biology
Kinga Czarnota-Lydka, Katarzyna Kucwaj-Brysz, Patryk Pyka, Wawrzyniec Haberek, Sabina Podlewska, Jadwiga Handzlik
Summary: This review analyzes the current state of the art in the treatment of cognitive disorders, focusing on Alzheimer's disease (AD). The potential therapeutic benefits of serotonin 5-HT6 receptor (5-HT6R) and certain kinases in AD treatment are explored, and the possibility of developing dual agents that target both 5-HT6R and kinases is investigated.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Biochemistry & Molecular Biology
Katarzyna Kaczorowska, Anna Stankiewicz, Ryszard Bugno, Maria H. H. Paluchowska, Grzegorz Burnat, Piotr Branski, Paulina Cieslik, Joanna M. Wieronska, Mariusz Milik, Mateusz Nowak, Agnieszka Przybylowicz, Aneta Koziol, Agata Hogendorf, Adam S. S. Hogendorf, Justyna Kalinowska-Tluscik, Beata Duszynska, Andrzej Pilc, Andrzej J. J. Bojarski
Summary: Based on the glutamatergic theory of schizophrenia, a new compound library containing 103 members was synthesized and examined for NAM mGlu(7) activity. Active compounds were found only within the quinazolinone chemotype. The compound 2-(2-Chlorophenyl)-6-(2,3-dimethoxyphenyl)-3-methylquinazolin-4(3H)-one (A9-7, ALX-171) exhibited selective activity against other group III mGlu receptors, satisfactory drug-like properties, and showed antipsychotic-like activity in animal models.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Biochemistry & Molecular Biology
Jaroslaw Duda, Sabina Podlewska
Summary: Various in silico approaches play a crucial role in predicting the activity and properties of chemical compounds in computer-aided drug design. This study introduces the Hierarchical Correlation Reconstruction approach, which predicts the probability distribution of compound properties and detects structural features important for property optimization.
MOLECULAR DIVERSITY
(2022)
Article
Biochemistry & Molecular Biology
Katarzyna Grychowska, Wojciech Pietrus, Ludmila Kulawik, Ophelie Bento, Grzegorz Satala, Xavier Bantreil, Frederic Lamaty, Andrzej J. Bojarski, Joanna Golebiowska, Agnieszka Nikiforuk, Philippe Marin, Severine Chaumont-Dubel, Rafal Kurczab, Pawel Zajdel
Summary: Salt bridge formation is a strong molecular non-covalent interaction in biological systems. This study investigated the influence of substitution pattern and geometry modifications on the quality of salt bridge formation in 5-HT6 receptor and D-3 receptor. The results showed that the modifications significantly improved the affinity and antagonist properties of the compounds at 5-HT6 receptor, but had no effect on D3 receptor. In silico experiments demonstrated that the applied modifications were beneficial for salt bridge formation at the 5-HT6 receptor, but unfavorable for D3 receptor.
Article
Biochemistry & Molecular Biology
Wojciech Pietrus, Rafal Kurczab, Dawid Warszycki, Andrzej J. J. Bojarski, Jurgen Bajorath
Summary: In this study, a total of 898 F-containing isomeric analog sets were identified and analyzed for structure-activity relationship (SAR) in the ChEMBL database. The results showed significant differences in affinity for some isomeric compounds against different aminergic GPCRs, and the change of fluorine position could lead to a significant change in potency. Additionally, a computational workflow was proposed to score the fluorine positions in the molecule.
Article
Biochemistry & Molecular Biology
Vittorio Canale, Wojciech Trybala, Severine Chaumont-Dubel, Paulina Koczurkiewicz-Adamczyk, Grzegorz Satala, Ophelie Bento, Klaudia Blicharz-Futera, Xavier Bantreil, Elzbieta Pekala, Andrzej J. Bojarski, Frederic Lamaty, Philippe Marin, Pawel Zajdel
Summary: In addition to the canonical Gs adenylyl cyclase pathway, the serotonin type 6 receptor (5-HT6R) recruits additional signaling pathways that control cognitive function, brain development, and synaptic plasticity in an agonist-dependent and independent manner. The development of biased ligands with different functional profiles at specific 5-HT6R-elicited signaling pathways may provide a novel therapeutic perspective in neurodegenerative and psychiatric diseases. A newly synthesized compound 3g exhibits neutral antagonist activity at the 5-HT6R-operated Gs signaling and inverse agonist activity at the Cdk5 pathway, making it a promising biased ligand to investigate the role of these signaling pathways in neurodegenerative diseases.
Article
Chemistry, Medicinal
Tobiasz Cieplinski, Tomasz Danel, Sabina Podlewska, Stanislaw Jastrzebski
Summary: Designing compounds with desired properties is essential in drug discovery, but measuring progress has been challenging due to lack of benchmarks and validation cost. To address this, a docking-based benchmark was proposed, using the widely used SMINA software. Graph-based generative models fail to produce high-scoring molecules, suggesting limitations in current models for de novo drug design. The benchmark also includes simpler tasks and is available at https://github.com/cieplinski-tobiasz/smina-docking-benchmark.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Chemistry, Medicinal
Katarzyna Szczepanska, Tadeusz Karcz, Maria Dichiara, Szczepan Mogilski, Justyna Kalinowska-Tluscik, Boguslaw Pilarski, Arkadiusz Leniak, Wojciech Pietrus, Sabina Podlewska, Katarzyna Popiolek-Barczyk, Laura J. Humphrys, M. Carmen Ruiz-Cantero, David Reiner-Link, Luisa Leitzbach, Dorota Lazewska, Steffen Pockes, Michal Gorka, Adam Zmyslowski, Thierry Calmels, Enrique J. Cobos, Agostino Marrazzo, Holger Stark, Andrzej J. Bojarski, Emanuele Amata, Katarzyna Kiec-Kononowicz
Summary: In search of new dual-acting histamine H-3/sigma-1 receptor ligands, a series of compounds were designed based on previously studied highly active in vivo ligands. An in-depth analysis was conducted on the protonation states of piperazine and piperidine derivatives in the compounds, due to the significant difference in affinity at sigma-1 receptors observed in closely related compounds. Three lead structures (3, 7, and 12) were selected for further biological evaluation, and compound 12 showed a broad spectrum of analgesic activity based on a novel molecular mechanism in both nociceptive and neuropathic pain models.
JOURNAL OF MEDICINAL CHEMISTRY
(2023)
Article
Infectious Diseases
Karolina Witek, Aneta Kaczor, Ewa Zeslawska, Sabina Podlewska, Malgorzata Anna Marc, Kinga Czarnota-Lydka, Wojciech Nitek, Gniewomir Latacz, Waldemar Tejchman, Markus Bischoff, Claus Jacob, Jadwiga Handzlik
Summary: This study explores new derivatives that can improve the antibacterial activity of conventional antibiotics and help overcome MRSA infections. The results show that the 1-benzhydrylpiperazine 5-spirofluorenehydantoin derivative (13) is the most effective in enhancing the activity of oxacillin, even at low concentrations. In addition, thiazole derivatives have shown complex mode of action in S. aureus isolates, acting as both oxacillin and erythromycin conjugators, potentially affecting the Msr(A) efflux pump. These findings suggest that imidazolones have a high potential to become commercially available antibiotic adjuvants.
Article
Chemistry, Multidisciplinary
Emilia Kuzniak-Glanowska, Michal Glanowski, Rafal Kurczab, Andrzej J. Bojarski, Robert Podgajny
Summary: Mutual positioning and non-covalent interactions between anions and aromatic motifs play a crucial role in the functional performance of biological systems. A comprehensive screening of the Protein Data Bank (PDB) led to the identification of numerous unique anion-aromatic motifs, highlighting the importance of ion-π interactions in these motifs.