Article
Environmental Sciences
Andrey A. Toropov, Devon A. Barnes, Alla P. Toropova, Alessandra Roncaglioni, Alasdair R. Irvine, Rosalinde Masereeuw, Emilio Benfenati
Summary: Drug-induced nephrotoxicity can have fatal consequences and the poor predictability of clinical responses based on preclinical research hinders pharmaceutical development. Computational predictions using SMILES-based descriptors offer a promising solution for early and accurate diagnosis, potentially replacing animal testing. Implementing this tool in the drug development process could lead to safer drugs in the future.
Article
Chemistry, Multidisciplinary
S. Ahmadi, S. Lotfi, S. Afshari, P. Kumar, E. Ghasemi
Summary: Global QSAR modelling was performed to predict the plC(50) values of 233 diverse heterocyclic compounds as BTK inhibitors. Eight reliable and robust QSAR models were constructed using the Monte Carlo algorithm of CORAL software. The reliability and predictability of the designed models were assessed through internal and external validation techniques, and the structural attributes responsible for the activity of BTK inhibitors were identified.
SAR AND QSAR IN ENVIRONMENTAL RESEARCH
(2021)
Article
Biochemistry & Molecular Biology
Shahin Ahmadi, Hosein Ghanbari, Shahram Lotfi, Neda Azimi
Summary: QSAR modeling was conducted using SMILES of compounds and the Monte Carlo method to predict the antioxidant activity of various compounds against different radiation sources. The models were designed using CORAL software and an optimizing method known as the index of ideality correlation, resulting in reliable and predictive models for antioxidant activity.
MOLECULAR DIVERSITY
(2021)
Article
Chemistry, Multidisciplinary
Andrey A. Toropov, Alla P. Toropova, Danuta Leszczynska, Jerzy Leszczynski
Summary: An algorithm for the simulation of nanoparticles' anticancer activity toward different cell lines has been developed using the quasi-SMILES approach. This study focuses on the quantitative structure-property-activity relationships analysis of the nanoparticles through the vector of ideality of correlation. The proposed approach differs from traditional models as it considers experimental situations rather than molecules and allows the user to control experimental conditions to achieve desired endpoint values.
Article
Pharmacology & Pharmacy
Natalia Czub, Adam Paclawski, Jakub Szlek, Aleksander Mendyk
Summary: The study presents the best-in-class predictive model for the serotonin 1A receptor affinity and validates it according to OECD guidelines. This can help simplify the drug discovery and development process, improving efficiency.
Article
Chemistry, Medicinal
Jiachen Wen, Dan Liu, Linxiang Zhao
Summary: Gamma-secretase is a large transmembrane protein complex consisting of four distinct units, which has garnered attention for its role in intramembrane proteolysis. The recent discovery of its atomic structure through cryo-EM has enhanced our understanding of its physiological functions and facilitated the development of novel molecules targeting gamma-secretase. This review focuses on the latest progress of gamma-secretase inhibitors and modulators in clinical and preclinical stages, as well as their potential applications in various biological indications.
EUROPEAN JOURNAL OF MEDICINAL CHEMISTRY
(2022)
Review
Biochemistry & Molecular Biology
Joanna E. Luo, Yue-Ming Li
Summary: Alzheimer's disease is a common neurodegenerative disorder associated with the accumulation of A beta peptides. γ-secretase, the enzyme responsible for generating A beta peptides, has been a challenging drug target due to its complex structure and function. However, the development of γ-secretase modulators has opened up new possibilities for Alzheimer's disease treatment.
CELL AND BIOSCIENCE
(2022)
Article
Engineering, Environmental
Giovanna J. Lavado, Diego Baderna, Edoardo Carnesecchi, Alla P. Toropova, Andrey A. Toropov, Jean Lou C. M. Dorne, Emilio Benfenati
Summary: Soil pollution is a critical environmental challenge that can have adverse effects on both humans and the ecosystem. Various bioassays have been developed to investigate the soil ecotoxicity of chemicals, including a 28-day collembolan reproduction test with the springtail Folsomia candida. Despite limited toxicity data for Collembola, QSAR models have been developed for predicting reproductive toxicity induced by organic compounds in Folsomia candida, showing good predictive performance for ecological risk assessment of chemicals.
JOURNAL OF HAZARDOUS MATERIALS
(2022)
Article
Biochemistry & Molecular Biology
Karel Nesmerak, Andrey Toropov, Ilkay Yildiz
Summary: This study demonstrates the potential of using quantitative structure-activity relationship (QSAR) methods to evaluate the antibacterial activity of compounds against Staphylococcus aureus infections. The developed models show satisfactory predictive capabilities for both endpoints examined.
FRONTIERS IN BIOSCIENCE-LANDMARK
(2022)
Article
Materials Science, Multidisciplinary
R. Martinho Vieira, O. Eriksson, T. Bjorkman, A. Bergman, H. C. Herper
Summary: The study presents an efficient computational approach for evaluating the entropy change of magnetocaloric materials, with a focus on hcp Gd. It demonstrates the importance of the mixed-scheme for magnetic Monte Carlo simulations and highlights the dominant contribution of magnetism to the entropy change. The calculated total entropy change is in agreement with experimental measurements at room temperature.
MATERIALS RESEARCH LETTERS
(2022)
Article
Chemistry, Physical
Kamal Tabti, Oumayma Abdessadak, Abdelouahid Sbai, Hamid Maghat, Mohammed Bouachrine, Tahar Lakhlifi
Summary: In this study, the Monte Carlo method was used to investigate the quantitative structure-activity relationship of novel steroidal spiro-oxindoles as potent antiproliferative inhibitors against human breast cancer. The models derived from this study provide valuable information on the molecular fragments responsible for the modulation of activity. Furthermore, the prediction of absorption, distribution, metabolism, excretion, and toxicity assists in drug development. The docking of the designed ligands and determination of the most selective receptor provide insights into the behavior and target specificity of the inhibitors, which is important for the development of new and more potent inhibitors against breast cancer.
JOURNAL OF MOLECULAR STRUCTURE
(2023)
Article
Biochemistry & Molecular Biology
Kumar Sambhav Chopdar, Ganesh Chandra Dash, Pranab Kishor Mohapatra, Binata Nayak, Mukesh Kumar Raval
Summary: Urease inhibitors play a vital role in medicine and agriculture, but their stability and toxicity are major concerns. This study developed a Monte-Carlo method-based QSAR model to predict the urease inhibiting potency of molecules, improving prediction accuracy.
JOURNAL OF BIOMOLECULAR STRUCTURE & DYNAMICS
(2022)
Article
Multidisciplinary Sciences
Hamideh Hamzehali, Shahram Lotfi, Shahin Ahmadi, Parvin Kumar
Summary: The aim of this study is to construct QSAR models for predicting the inhibition potencies of imatinib derivatives against BCR-ABL TK. QSAR models were developed using the Monte Carlo algorithm and SMILES notations to compute correlation weights. Three stable QSAR models were established to predict the inhibition effects, and they performed well on the validation set. The Y-randomization test confirmed the reliability of the models. Mechanistic interpretations of structural attributes were made by identifying the factors influencing the inhibition potency.
SCIENTIFIC REPORTS
(2022)
Article
Chemistry, Multidisciplinary
Ziwan Xu, Kaiyuan Ni, Jianming Mao, Taokun Luo, Wenbin Lin
Summary: The study conducted Monte Carlo simulations to compare radiosensitization effects of nanoscale metal-organic frameworks (nMOFs) with solid nanoparticles (NPs) under X-ray excitation. The results showed that lattices formed by nanoscale secondary building units (SBUs) outperformed solid NPs in enhancing scatterings of photons and electrons within the lattices, regardless of radiation sources or particle sizes. Optimum dose enhancement was achieved by tuning SBU size and inter-SBU distance.
ADVANCED MATERIALS
(2021)
Article
Biology
Alla P. Toropova, Andrey A. Toropov, Alessandra Roncaglioni, Emilio Benfenati
Summary: This study demonstrates that models for the antioxidant activity of tripeptides from frog skin can be built without the need for complex calculations involving 3D architecture and quantum mechanics descriptors. The structure of tripeptides represented by sequences of symbol abbreviations of amino acids can be used for building quantitative structure-activity relationships. The best model for the validation set shows good statistical quality with n = 27, r(2) = 0.93, RMSE = 0.15.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Environmental Sciences
A. A. Toropov, M. R. Di Nicola, A. P. Toropova, A. Roncaglioni, J. L. C. M. Dorne, E. Benfenati
Summary: Simplified molecular input-line entry systems (SMILES) are used to establish quantitative models for molecular structure and property/activity relationships. Quasi-SMILES extends SMILES by incorporating symbols reflecting experimental conditions. Quasi-SMILES models were used to predict toxicity to tadpoles, taking into account exposure time. Good results were obtained with these models, with an average determination coefficient of about 0.97 for the validation sets. New models were developed for this poorly studied amphibian endpoint.
Article
Biochemistry & Molecular Biology
Alla P. Toropova, Andrey A. Toropov, Natalja Fjodorova
Summary: This paper proposes a simulation method to investigate the effect of metal nano-oxides at different concentrations on cell viability in THP-1 cells. The molecular structure was represented using a simplified molecular input-line entry system (SMILES). The approach based on building models using quasi-SMILES was proven to be stable and self-consistent.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Environmental Sciences
Alla P. Toropova, Andrey A. Toropov, Alessandra Roncaglioni, Emilio Benfenati, Danuta Leszczynska, Jerzy Leszczynski
Summary: The traditional application of QSPRs/QSARs predicts the impact of molecular features using measurable characteristics of substances, but it is necessary to evaluate the influence of exposure conditions and environmental factors. This study proposes a novel approach for modeling the absorption of heavy metals by worms, based on quasi-SMILES descriptors that incorporate experimental conditions. The impact on protein, hydrocarbon, and lipid levels in worms caused by different combinations of heavy metal concentrations and exposure time is modeled.
ARCHIVES OF ENVIRONMENTAL CONTAMINATION AND TOXICOLOGY
(2023)
Article
Chemistry, Multidisciplinary
Alla P. P. Toropova, Joao Meneses, Ernesto Alfaro-Moreno, Andrey A. A. Toropov
Summary: The study defined quasi-SMILES as a line of symbols that encoded the physicochemical features of the impact of nanoparticles, such as core structure, doping, surface quality, diameter, and dose. The correlation weight for each code in the quasi-SMILES was calculated using the Monte Carlo method. The computational experiments confirmed the potential of this approach as a tool to predict the impact of nanomaterials under different experimental conditions.
DRUG AND CHEMICAL TOXICOLOGY
(2023)
Article
Biochemistry & Molecular Biology
Nilima Rani Das, Tripti Sharma, Andrey A. Toropov, Alla P. Toropova, Manish Kumar Tripathi, P. Ganga Raju Achary
Summary: One of the most well-known anti-targets defining medication cardiotoxicity is the voltage-dependent hERG K+ channel, which is known for causing cardiac disorders. This study aimed to create predictive computational tools to identify potential hERG blockers early in the drug discovery process. Machine learning approaches were used to build robust predictive models, and molecular docking and dynamics studies were conducted to understand the cardiotoxicity related to the hERG gene.
JOURNAL OF BIOMOLECULAR STRUCTURE & DYNAMICS
(2023)
Article
Toxicology
Joao Meneses, Michael Gonzalez-Durruthy, Eli Fernandez-de-Gortari, Alla P. Toropova, Andrey A. Toropov, Ernesto Alfaro-Moreno
Summary: This study developed a machine learning model to predict the potential lung toxicity of engineered nanomaterials. The tree-based learning algorithms were able to efficiently predict the cytotoxic risk of nanomaterials. The model also suggested that smaller nanomaterials could have stronger cytotoxicity and that polyethylene glycol surface coating could protect the lungs from cytotoxic metal ions.
PARTICLE AND FIBRE TOXICOLOGY
(2023)
Article
Toxicology
Andrey A. A. Toropov, Alla P. P. Toropova, Alessandra Roncaglioni, Emilio Benfenati
Summary: Quantitative structure-property/activity relationships (QSPRs/QSARs) are important tools in modern theoretical and computational chemistry. The self-consistent model system is used to build and assess the reliability of a group of QSPR/QSAR models. In this study, models predicting pesticide toxicity towards Daphnia magna were compared for different training and test subsets. The results were used to formulate a self-consistent model system, which improved the predictive potential of the models. The suggested models showed high predictive potential, with an average determination coefficient of 0.841 and dispersion of 0.033 for the validation sets. The best model achieved an average determination coefficient of 0.89 for the external validation sets.
TOXICOLOGY MECHANISMS AND METHODS
(2023)
Article
Environmental Sciences
Alla P. Toropova, Andrey A. Toropov, Alessandra Roncaglioni, Emilio Benfenati
Summary: Binding to AChE k1 may have toxic effects in humans. Organophosphates can be both dangerous and useful, being employed in chemical warfare and as pesticides. Models for organophosphates binding to AChE k1 were developed using simplified molecular input-line entry system and optimal descriptors calculated with the Monte Carlo technique using the CORAL free software.
TOXICOLOGICAL AND ENVIRONMENTAL CHEMISTRY
(2023)
Article
Biochemistry & Molecular Biology
Alla P. Toropova, Andrey A. Toropov, Alessandra Roncaglioni, Emilio Benfenati, Danuta Leszczynska, Jerzy Leszczynski
Summary: In order to ensure the reliability of predictions, this study uses a random partition of data and construction of random models to achieve a reliable forecast. The experiments conducted on blood-brain barrier permeation models showed that this approach is effective and better than previous methods. The suggested approach to validate models is different from traditional methods and can be applied to any model.
JOURNAL OF MOLECULAR MODELING
(2023)
Article
Chemistry, Physical
Nilima R. Das, Tripti Sharma, Nainee Goyal, Nagendra Singh, Andrey A. Toropov, Alla P. Toropova, P. Ganga Raju Achary
Summary: A QSAR investigation was conducted to correlate the structures of 273 compounds to their actions against ICMT protein. Three QSAR models were identified with good performance. An ANN model was used to assess the contribution of descriptors to the structure-activity association. The results of QSAR, molecular docking, and dynamics study can be further analyzed for the development of ICMT inhibitors.
JOURNAL OF MOLECULAR STRUCTURE
(2023)
Article
Biochemistry & Molecular Biology
Andrey A. Toropov, Alla P. Toropova, Alessandra Roncaglioni, Emilio Benfenati, Danuta Leszczynska, Jerzy Leszczynski
Summary: Studying the Henry's law constants is crucial for understanding the dispersion and impact of atmospheric pollutants, as well as predicting the behavior of organic molecules in the atmosphere.
Article
Chemistry, Multidisciplinary
Andrey A. A. Toropov, Alla P. P. Toropova, P. Ganga Raju Achary
Summary: The octanol-water partition coefficient (logP) is an important indicator for assessing the biological activity of platinum (IV) complexes in drug design. Incorporating fragments of local symmetry (FLS) in the Simplified Molecular Input-Line Entry System (SMILES) significantly improves the predictive potential of logP-models for platinum (IV) coordination compounds.
STRUCTURAL CHEMISTRY
(2023)
Article
Toxicology
Alla P. Toropova, Andrey A. Toropov, Alessandra Roncaglioni, Emilio Benfenati
Summary: Mutagenicity is a dangerous property, and it is costly to experimentally determine. In this study, a system for constructing random models and comparing molecular features was proposed. The Morgan connectivity values were found to be more informative for mutagenicity models compared to the quality of different rings in molecules. The resulting models showed a high average determination coefficient of 0.8737 ± 0.0312 for the validation set.
TOXICOLOGY IN VITRO
(2023)
Article
Chemistry, Inorganic & Nuclear
Alla P. Toropova, Andrey A. Toropov, Natalja Fjodorova
Summary: The system of self-consistent models is a tool to evaluate the predictive potential of different approaches by randomly dividing available data into training and validation sets. Considering multiple splits is more informative than considering a single model.
Proceedings Paper
Computer Science, Artificial Intelligence
Nilima R. Das, Tripti Sharma, Ayeshkant Mallick, Alla P. Toropova, Andrey A. Toropov, P. Ganga Raju Achary
Summary: Aldo-keto reductase family 1 member C1, also known as dihydrodiol dehydrogenase 1/2, is an enzyme encoded by the AKR1C1 gene in humans. Its increased expression in oncogenesis confers resistance to several anticancer agents, leading to extensive research on this enzyme to develop new and effective anticancer drugs. This study used a dataset of 60 AKR1C1 inhibitors to create models for the pIC50(M) endpoint based on quantitative structure-activity relationship. Molecular docking was also performed to identify the specific residues responsible for inhibition in the AKR1C1 gene.
AMBIENT INTELLIGENCE IN HEALTH CARE, ICAIHC 2022
(2023)
Article
Biology
Seyyed Bahram Borgheai, Alyssa Hillary Zisk, John McLinden, James Mcintyre, Reza Sadjadi, Yalda Shahriari
Summary: This study proposed a novel personalized scheme using fNIRS and EEG as the main tools to predict and compensate for the variability in BCI systems, especially for individuals with severe motor deficits. By establishing predictive models, it was found that there were significant associations between the predicted performances and the actual performances.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Hongliang Guo, Hanbo Liu, Ahong Zhu, Mingyang Li, Helong Yu, Yun Zhu, Xiaoxiao Chen, Yujia Xu, Lianxing Gao, Qiongying Zhang, Yangping Shentu
Summary: In this paper, a BDSMA-based image segmentation method is proposed, which improves the limitations of the original algorithm by combining SMA with DE and introducing a cooperative mixing model. The experimental results demonstrate the superiority of this method in terms of convergence speed and precision compared to other methods, and its successful application to brain tumor medical images.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Jingfei Hu, Linwei Qiu, Hua Wang, Jicong Zhang
Summary: This study proposes a novel semi-supervised point consistency network (SPC-Net) for retinal artery/vein (A/V) classification, addressing the challenges of specific tubular structures and limited well-labeled data in CNN-based approaches. The SPC-Net combines an AVC module and an MPC module, and introduces point set representations and consistency regularization to improve the accuracy of A/V classification.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Omair Ali, Muhammad Saif-ur-Rehman, Tobias Glasmachers, Ioannis Iossifidis, Christian Klaes
Summary: This study introduces a novel hybrid model called ConTraNet, which combines the strengths of CNN and Transformer neural networks, and achieves significant improvement in classification performance with limited training data.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Juan Antonio Valera-Calero, Dario Lopez-Zanoni, Sandra Sanchez-Jorge, Cesar Fernandez-de-las-Penas, Marcos Jose Navarro-Santana, Sofia Olivia Calvo-Moreno, Gustavo Plaza-Manzano
Summary: This study developed an easy-to-use application for assessing the diagnostic accuracy of digital pain drawings (PDs) compared to the classic paper-and-pencil method. The results demonstrated that digital PDs have higher reliability and accuracy compared to paper-and-pencil PDs, and there were no significant differences in assessing pain extent between the two methods. The PAIN EXTENT app showed good convergent validity.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Biao Qu, Jialue Zhang, Taishan Kang, Jianzhong Lin, Meijin Lin, Huajun She, Qingxia Wu, Meiyun Wang, Gaofeng Zheng
Summary: This study proposes a deep unrolled neural network, pFISTA-DR, for radial MRI image reconstruction, which successfully preserves image details using a preprocessing module, learnable convolution filters, and adaptive threshold.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Alireza Rafiei, Milad Ghiasi Rad, Andrea Sikora, Rishikesan Kamaleswaran
Summary: This study aimed to improve machine learning model prediction of fluid overload by integrating synthetic data, which could be translated to other clinical outcomes.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Jinlian Ma, Dexing Kong, Fa Wu, Lingyun Bao, Jing Yuan, Yusheng Liu
Summary: In this study, a new method based on MDenseNet is proposed for automatic segmentation of nodular lesions from ultrasound images. Experimental results demonstrate that the proposed method can accurately extract multiple nodules from thyroid and breast ultrasound images, with good accuracy and reproducibility, and it shows great potential in other clinical segmentation tasks.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Jiabao Sheng, SaiKit Lam, Jiang Zhang, Yuanpeng Zhang, Jing Cai
Summary: Omics fusion is an important preprocessing approach in medical image processing that assists in various studies. This study aims to develop a fusion methodology for predicting distant metastasis in nasopharyngeal carcinoma by mitigating the disparities in omics data and utilizing a label-softening technique and a multi-kernel-based neural network.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Zhenxiang Xiao, Liang He, Boyu Zhao, Mingxin Jiang, Wei Mao, Yuzhong Chen, Tuo Zhang, Xintao Hu, Tianming Liu, Xi Jiang
Summary: This study systematically investigates the functional connectivity characteristics between gyri and sulci in the human brain under naturalistic stimulus, and identifies unique features in these connections. This research provides novel insights into the functional brain mechanism under naturalistic stimulus and lays a solid foundation for accurately mapping the brain anatomy-function relationship.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Qianqian Wang, Mingyu Zhang, Aohan Li, Xiaojun Yao, Yingqing Chen
Summary: The development of PARP-1 inhibitors is crucial for the treatment of various cancers. This study investigates the structural regulation of PARP-1 by different allosteric inhibitors, revealing the basis of allosteric inhibition and providing guidance for the discovery of more innovative PARP-1 inhibitors.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Qing Xu, Wenting Duan
Summary: In this paper, a dual attention supervised module, named DualAttNet, is proposed for multi-label lesion detection in chest radiographs. By efficiently fusing global and local lesion classification information, the module is able to recognize targets with different sizes. Experimental results show that DualAttNet outperforms baselines in terms of mAP and AP50 with different detection architectures.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Kaja Gutowska, Piotr Formanowicz
Summary: The primary aim of this research is to propose algorithms for identifying significant reactions and subprocesses within biological system models constructed using classical Petri nets. These solutions enable two analysis methods: importance analysis for identifying critical individual reactions to the model's functionality and occurrence analysis for finding essential subprocesses. The utility of these methods has been demonstrated through analyses of an example model related to the DNA damage response mechanism. It should be noted that these proposed analyses can be applied to any biological phenomenon represented using the Petri net formalism. The presented analysis methods extend classical Petri net-based analyses, enhancing our comprehension of the investigated biological phenomena and aiding in the identification of potential molecular targets for drugs.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Hansle Gwon, Imjin Ahn, Yunha Kim, Hee Jun Kang, Hyeram Seo, Heejung Choi, Ha Na Cho, Minkyoung Kim, Jiye Han, Gaeun Kee, Seohyun Park, Kye Hwa Lee, Tae Joon Jun, Young-Hak Kim
Summary: Electronic medical records have potential in advancing healthcare technologies, but privacy issues hinder their full utilization. Deep learning-based generative models can mitigate this problem by creating synthetic data similar to real patient data. However, the risk of data leakage due to malicious attacks poses a challenge to traditional generative models. To address this, we propose a method that employs local differential privacy (LDP) to protect the model from attacks and preserve the privacy of training data, while generating medical data with reasonable performance.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Siwei Tao, Zonghan Tian, Ling Bai, Yueshu Xu, Cuifang Kuang, Xu Liu
Summary: This study proposes a transfer learning-based method to address the phase retrieval problem in grating-based X-ray phase contrast imaging. By generating a training dataset and using deep learning techniques, this method improves image quality and can be applied to X-ray 2D and 3D imaging.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)