Article
Biochemistry & Molecular Biology
Arthur Cartel Foahom Gouabou, Jules Collenne, Jilliana Monnier, Rabah Iguernaissi, Jean-Luc Damoiseaux, Abdellatif Moudafi, Djamal Merad
Summary: This study presents a new framework for automated melanoma diagnosis, which aims to improve the performance of existing systems and provide more transparency in the decision-making process by introducing the concept of players and decision theory. The proposed framework achieves good results in the diagnosis of melanoma, nevus, and benign keratosis, outperforming existing methods in this task. This approach could aid dermatologists in diagnosing challenging pigmented lesions and serve as a teaching tool for less experienced doctors.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Shi Qiu, Yi Jin, Songhe Feng, Tao Zhou, Yidong Li
Summary: Dwarfism refers to the condition where children of the same gender and age are lower than two standard deviations of normal height in the same environment. A computer-aided diagnosis model based on brain image data and clinical features is established for the first time, along with a dwarfism prediction algorithm using multimodal pyradiomics.
INFORMATION FUSION
(2022)
Article
Computer Science, Information Systems
Ilhame Ait Lbachir, Imane Daoudi, Saadia Tallal
Summary: A complete CAD system for mass detection and diagnosis in breast cancer was proposed in this paper, achieving successful results with high accuracy rates in both the MIAS and CBIS-DDSM databases. The system includes preprocessing, segmentation, feature reduction, and classification steps, resulting in accurate detection and classification of abnormalities.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Automation & Control Systems
Jingwei Wang, Chuan Liu, Yukai Zhao, Zhirui Zhao, Yunlong Ma, Min Liu, Weiming Shen
Summary: This paper discusses the abstraction of the inverse graph partitioning (IGP) problem from real IIoT applications and proposes a novel optimization approach using graph convolutional networks and a node swap procedure to achieve remarkable performance.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Multidisciplinary Sciences
Wei-Chia Chen, Juannan Zhou, Jason M. Sheltzer, Justin B. Kinney, David M. McCandlish
Summary: Density estimation in sequence space is a fundamental problem in machine learning with applications in computational biology. Maximum entropy is a common strategy used for estimating probability distributions in sequence space, providing a balance between data richness and data scarcity. This approach allows for a more flexible and expressive estimation of probability distributions, resulting in better understanding of complex biological data.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2021)
Article
Computer Science, Artificial Intelligence
Xiaofeng Qi, Fasheng Yi, Lei Zhang, Yao Chen, Yong Pi, Yuanyuan Chen, Jixiang Guo, Jianyong Wang, Quan Guo, Jilan Li, Yi Chen, Qing Lv, Zhang Yi
Summary: Ultrasonography of the breast mass is an important imaging technology for diagnosing breast cancer, and ultrasound equipment is widely used in medical institutions in China. This study develops an automated breast cancer diagnosis system deployed on mobile phones, which improves diagnostic accuracy and aids in the early screening and diagnosis of breast cancer, reducing morbidity and mortality.
Article
Chemistry, Multidisciplinary
Jakub Kluk, Marek R. R. Ogiela
Summary: Advanced diagnosis systems can provide doctors with high-quality data for diagnosing diseases, like brain cancers, but humans may overlook tumor symptoms due to information overload. Therefore, the combination of diagnostic devices and software systems is becoming more common. This study focuses on designing a neural network system that can automatically diagnose brain tumors from MRI images and identify important areas. The research compared Convolutional Neural Networks and Vision Transformers, finding that both architectures achieved a high tumor recognition rate, but Vision Transformers were easier to train and provided more detailed decision reasoning. The results suggest that computer-aided diagnosis and Vision Transformers could play a significant role in the development of modern medicine in IoT and healthcare systems.
APPLIED SCIENCES-BASEL
(2022)
Article
Multidisciplinary Sciences
Zhongzhi Yu, Yemin Shi
Summary: In computer-aided diagnosis (CAD), accurately defining the decision boundary between known and unknown classes is a challenging task. This paper proposes a Centralized Space Learning (CSL) method that learns a centralized space to separate known and unknown classes, improving the robustness of CAD.
SCIENTIFIC REPORTS
(2023)
Article
Chemistry, Physical
Kanishka Singh, Jannes Munchmeyer, Leon Weber, Ulf Leser, Annika Bande
Summary: In this study, five different Graph Neural Networks (GNNs) were benchmarked and analyzed for the prediction of excitation spectra in organic molecules. The performance of GNNs was compared in terms of runtime measurements, prediction accuracy, and analysis of outliers in the test set. Through TMAP clustering and statistical analysis, clear hotspots of high prediction errors and optimal spectra prediction for molecules with specific functional groups were identified. This in-depth benchmarking and subsequent analysis protocol provides a recipe for comparing different machine learning methods and evaluating dataset quality.
JOURNAL OF CHEMICAL THEORY AND COMPUTATION
(2022)
Article
Computer Science, Interdisciplinary Applications
Richard J. Chen, Ming Y. Lu, Jingwen Wang, Drew F. K. Williamson, Scott J. Rodig, Neal Lindeman, Faisal Mahmood
Summary: This study proposes an interpretable strategy for multimodal fusion of histology image and genomic features for survival outcome prediction. The results on glioma and clear cell renal cell carcinoma datasets demonstrate that this approach improves the prognostic determinations.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Computer Science, Artificial Intelligence
Xue Liu, Dan Sun, Wei Wei
Summary: This paper introduces a novel graph entropy definition to evaluate the smoothness of a data manifold and proposes a strategy to generate randomly perturbed training data while preserving both graph topology and graph entropy. Experimental results demonstrate the effectiveness of the method in improving semi-supervised node classification accuracy and enhancing the robustness of the training process for GCN.
PATTERN RECOGNITION
(2022)
Article
Oncology
Zilong He, Yue Li, Weixiong Zeng, Weimin Xu, Jialing Liu, Xiangyuan Ma, Jun Wei, Hui Zeng, Zeyuan Xu, Sina Wang, Chanjuan Wen, Jiefang Wu, Chenya Feng, Mengwei Ma, Genggeng Qin, Yao Lu, Weiguo Chen
Summary: This study evaluated the impact of a CAD method based on perceptive features learned from quantitative BI-RADS descriptions on breast mass diagnosis performance. The results showed that the CAD model improved radiologists' diagnostic performance for breast masses, especially for junior radiologists.
FRONTIERS IN ONCOLOGY
(2021)
Article
Computer Science, Information Systems
Weidong Mei, Rui Zhang
Summary: Intelligent reflecting surface (IRS) is considered as a revolutionary technology for achieving smart and reconfigurable wireless communication environments. In this study, a new IRS-aided communication system is proposed, where multiple IRSs assist in establishing multi-hop signal reflection between a multi-antenna base station and a single-antenna user. By maximizing the received signal power at the user, the optimal active and cooperative passive beamforming solutions for a given beam route are provided, revealing a trade-off between passive beamforming gain and multi-reflection path loss in optimal beam routing design. The proposed algorithm shows significant performance gains over benchmark schemes in numerical results.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2021)
Article
Multidisciplinary Sciences
Jessie Liu, Blanca Gallego, Sebastiano Barbieri
Summary: This paper proposes a learning to defer with uncertainty algorithm for computer-aided diagnosis, which identifies patients with high diagnostic uncertainty and defers them for evaluation by human experts. The algorithm is evaluated on different diagnosis tasks and compared with other methods, showing a good balance between diagnostic accuracy and deferral rate.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Artificial Intelligence
Gang Chen, Zhengkuan Xu
Summary: A computer-aided diagnosis system based on CDCGAN model and MRI quantitative indicators was established for the diagnosis of lumbar disc herniation (LDH), achieving an accuracy rate of 94.15% in LDH diseases. Various MRI quantitative indicators were found to have significant correlations with the course of LDH.
APPLIED SOFT COMPUTING
(2021)
Article
Chemistry, Multidisciplinary
Francisco Salgado, Mauricio Moncada-Basualto, Josue Pozo-Martinez, Ana Liempi, Ulrike Kemmerling, Juan-Diego Maya, Pablo Jaque, Fernanda Borges, Eugenio Uriarte, Maria J. Matos, Claudio Olea-Azar
Summary: This study evaluated the trypanocidal activity and mechanism of action of a series of synthetic 4-acyloxy-3-nitrocoumarins, showing potential for treatment against Trypanosoma cruzi. Compound 1 decreased the number of infected Vero cells in an intracellular model, indicating promising application prospects.
ARABIAN JOURNAL OF CHEMISTRY
(2021)
Article
Chemistry, Multidisciplinary
Osvaldo Yanez, Manuel Isaias Osorio, Eugenio Uriarte, Carlos Areche, William Tiznado, Jose M. Perez-Donoso, Olimpo Garcia-Beltran, Fernando Gonzalez-Nilo
Summary: This study utilized computational models to evaluate potential inhibitors of the SARS-CoV-2 enzyme M-pro, identifying compounds with high affinity that could serve as promising candidates for therapeutic development.
FRONTIERS IN CHEMISTRY
(2021)
Article
Energy & Fuels
Harbil Bediaga, Maria Isabel Moreno, Sonia Arrasate, Jose Luis Vilas, Lucia Orbe, Elias Unzueta, Juan Perez Mercader, Humberto Gonzalez-Diaz
Summary: This study developed an IFPTML model for classifying gasoline samples using Information Fusion, Perturbation Theory, and Machine Learning algorithms, with over 230,000 outcomes from a petroleum refinery plant. The model showed high sensitivity and specificity on training and validation sets, as well as robustness to changes in experimental techniques.
Article
Biochemistry & Molecular Biology
Cristian R. Munteanu, Pablo Gutierrez-Asorey, Manuel Blanes-Rodriguez, Ismael Hidalgo-Delgado, Maria de Jesus Blanco Liverio, Brais Castineiras Galdo, Ana B. Porto-Pazos, Marcos Gestal, Sonia Arrasate, Humbert Gonzalez-Diaz
Summary: The study develops PTML models to predict DDNP complexes, utilizing perturbations of molecular descriptors as inputs. Out of 10 tested machine learning methods, the Bagging classifier was found to be the best model with high accuracy for drug-nanoparticle complexes.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2021)
Article
Biochemistry & Molecular Biology
Marco Mellado, Cesar Gonzalez, Jaime Mella, Luis F. Aguilar, Ismail Celik, Fernanda Borges, Eugenio Uriarte, Giovanna Delogu, Dolores Vina, Maria J. Matos
Summary: Monoamine oxidases (MAOs) have been identified as attractive targets in drug design due to their role in modulating neurotransmitter levels and reactive oxygen species production. In this study, a comparative analysis was conducted to evaluate the inhibitory activity of two coumarin-based compounds (3-phenylcoumarin and trans-6-styrylcoumarin) on both MAO isoforms. Crystallographic structures, 3D-QSAR models, docking simulations, and molecular dynamics simulations were utilized to investigate the interaction mechanisms between these compounds and MAOs. Trans-6-styrylcoumarin exhibited significantly higher inhibitory activity on MAO-B compared to 3-phenylcoumarin and trans-resveratrol.
Article
Chemistry, Multidisciplinary
Karel Dieguez-Santana, Bakhtiyor Rasulev, Humberto Gonzalez-Diaz
Summary: This paper introduces an application of information fusion perturbation-theory machine learning method in antibacterial drug-nanoparticle systems. The method accelerates the testing of bacterial sensitivity to different strains and shows good predictive performance. Additionally, the concept of MDR computational surveillance for detecting multidrug-resistant strains is introduced.
ENVIRONMENTAL SCIENCE-NANO
(2022)
Article
Chemistry, Multidisciplinary
Josue Pozo-Martinez, Francisco Salgado, Ana Liempi, Ulrike Kemmerling, Raul Mera-Adasme, Claudio Olea-Azar, Mauricio Moncada-Basualto, Fernanda Borges, Eugenio Uriarte, Maria Joao Matos
Summary: The study demonstrated that a series of catechol-containing 3-arylcoumarins have moderate trypanocidal activity on the trypomastigote form of the parasite, with 3-(4'-bromophenyl)-6,7-dihydroxycoumarin (8) showing the highest activity but also the highest cytotoxicity in Vero cells. The inclusion in beta-cyclodextrins reduced the trypanocidal activity and cytotoxicity, but increased solubility. Compound 8 was found to act through the generation of oxidative stress, and the combination with BZN showed a synergistic effect, reducing the necessary dose of BZN and proving to be a promising alternative strategy for treating the disease.
ARABIAN JOURNAL OF CHEMISTRY
(2022)
Article
Environmental Sciences
Karel Dieguez-Santana, Manuel Mesias Nachimba-Mayanchi, Amilkar Puris, Roldan Torres Gutierrez, Humberto Gonzalez-Diaz
Summary: This study developed Quantitative Structure-Toxicity Relationship (QSTR) models using multiple statistical models and machine learning algorithms, and found that the Random Forest regression model was the most superior. The results suggest that the developed QSTR models can reliably predict pesticide toxicity in Americamysis bahia, and can be applied in pesticide screening and prioritization.
ENVIRONMENTAL RESEARCH
(2022)
Article
Chemistry, Medicinal
Carlos Santiago, Bernabe Ortega-Tenezaca, Iratxe Barbolla, Brenda Fundora-Ortiz, Sonia Arrasate, Maria Auxiliadora Dea-Ayuela, Humberto Gonzalez-Diaz, Nuria Sotomayor, Esther Lete
Summary: In this study, the authors used the SOFT.PTML tool to pre-process a ChEMBL dataset of pre-clinical assays of anti-leishmanial compound candidates. They compared different ML algorithms and found that the IFPTML-LOGR model had excellent specificity and sensitivity values. They illustrated the use of the software with a practical case study and identified compounds with potential activity. They also performed a computational high-throughput screening and validated the accuracy of the model.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2022)
Article
Medicine, Research & Experimental
Karel Dieguez-Santana, Gerardo M. Casanola-Martin, Roldan Torres, Bakhtiyor Rasulev, James R. Green, Humbert Gonzalez-Diaz
Summary: This study utilized the IFPTML algorithm to analyze a large dataset from the ChEMBL database, investigating the interaction between antibacterial drugs and bacterial metabolic networks. The results showed that both linear and nonlinear models had good statistical parameters and were able to predict antibacterial compounds, potentially leading to the discovery of new metabolic mutations in antibiotic resistance.
MOLECULAR PHARMACEUTICS
(2022)
Article
Chemistry, Medicinal
Maria Joao Matos, Eugenio Uriarte, Nuria Seoane, Aitor Picos, Jose Gil-Longo, Manuel Campos-Toimil
Summary: The newly synthesized nitrate-coumarins have been found to possess vasorelaxant activity on rat aorta rings, making them potential alternatives for the development of vasodilator drugs.
Article
Chemistry, Medicinal
Karel Dieguez-Santana, Amilkar Puris, Oscar M. Rivera-Borroto, Gerardo M. Casanola-Martin, Bakhtiyor Rasulev, Humberto Gonzalez-Diaz
Summary: This study proposes a new machine learning algorithm called FURIA-C for classifying drug-like compounds with antidiabetic inhibitory ability. The algorithm achieved satisfactory accuracy scores and derived fuzzy rules with high Certainty Factor values. Comparison tests showed that FURIA-C outperforms other methods, making it a cutting-edge technique for predicting the inhibitory activity of new compounds and speeding up the discovery of multi-target antidiabetic agents.
CURRENT COMPUTER-AIDED DRUG DESIGN
(2022)
Article
Biochemistry & Molecular Biology
Lucia Bada, Renato B. Pereira, David M. Pereira, Marta Lores, Maria Celeiro, Elias Quezada, Eugenio Uriarte, Jose Gil-Longo, Dolores Vina
Summary: The genus Ulex consists of thirteen accepted species of perennial shrubs in the Fabaceae family. In Galicia, Spain, many of these species are considered spontaneous colonizers that are easy to establish and maintain. Among them, Ulex gallii Planch. is used in traditional medicine for its anti-infective, hypotensive, and diuretic properties. Limited scientific studies have been conducted on Ulex gallii Planch., and its composition has not been reported. In this study, different metabolites, mainly flavonoids, were tentatively identified in the sub-fractions of Ulex gallii Planch., which exhibited antiproliferative activity against lung and stomach cancer cell lines.
Article
Biology
Karel Dieguez-Santana, Humberto Gonzalez-Diaz
Summary: This article utilizes machine learning methods to predict the activity of unknown drugs and discover potential antibacterial drugs. Through a bibliometric study of 1596 Scopus documents from 2006 to 2022, the contributions of leading authors, universities/organizations, and countries are analyzed in terms of productivity, citations, and bibliographic linkage. Essential topics related to the application of machine learning in antibacterial development are identified, and emerging topics are proposed. The applied methodology contributes to a broader and more specific understanding of machine learning research in antibacterial studies for future projects.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Review
Chemistry, Medicinal
Aitor Carneiro, Eugenio Uriarte, Fernanda Borges, Maria Joao Matos
Summary: Propargylamine is widely used in medicinal chemistry and chemical biology due to its unique reactivity. This review discusses the applications and potential of propargylamine-based compounds in drug discovery, highlighting their impact in various therapeutic fields.
FUTURE MEDICINAL CHEMISTRY
(2023)