Prediction of viral oncoproteins through the combination of generative adversarial networks and machine learning techniques DOI Creative Commons
Jorge F. Beltrán,

Lisandra Herrera-Belén,

Alejandro J. Yáñez

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Ноя. 7, 2024

Viral oncoproteins play crucial roles in transforming normal cells into cancer cells, representing a significant factor the etiology of various cancers. Traditionally, identifying these is both time-consuming and costly. With advancements computational biology, bioinformatics tools based on machine learning have emerged as effective methods for predicting biological activities. Here, first time, we propose an innovative approach that combines Generative Adversarial Networks (GANs) with supervised to enhance accuracy generalizability viral oncoprotein prediction. Our methodology evaluated multiple models, including Random Forest, Multilayer Perceptron, Light Gradient Boosting Machine, eXtreme Boosting, Support Vector Machine. In ten-fold cross-validation our training dataset, GAN-enhanced Forest model demonstrated superior performance metrics: 0.976 accuracy, F1 score, 0.977 precision, sensitivity, 1.0 AUC. During independent testing, this achieved 0.982 These results establish new tool, VirOncoTarget, accessible via web application. We anticipate VirOncoTarget will be valuable resource researchers, enabling rapid reliable prediction advancing understanding their role biology.

Язык: Английский

The identification of biomarkers for Alzheimer's disease using a systems biology approach based on lncRNA-circRNA-miRNA-mRNA ceRNA networks DOI
Babak Sokouti

Computers in Biology and Medicine, Год журнала: 2024, Номер 179, С. 108860 - 108860

Опубликована: Июль 11, 2024

Язык: Английский

Процитировано

0
Advanced Active Player Tracking System in Handball Videos Using Multi-Deep Sort Algorithm with GAN Approach DOI Open Access
R. J. Poovaraghan,

P. Prabhavathy

International Journal of Advanced Computer Science and Applications, Год журнала: 2024, Номер 15(7)

Опубликована: Янв. 1, 2024

Active player tracking in sports analytics is crucial for understanding team dynamics, performance, and game strategies. This paper introduces an innovative approach to active players handball videos using a fusion of the Multi-Deep SORT algorithm Generative Adversarial Network (GAN) model. The novel integration aims enhance appearance robust precise dynamic gameplay. system starts with GAN model trained on annotated video data, generating synthetic frames improve visual quality realism appearances, thereby refining input data tracking. algorithm, enhanced GAN-generated features, improves object association continuous framework addresses key challenges tracking, handling occlusions, variations complex interactions. Additionally, GAN-based enhancements accuracy distinguishing from inactive players, facilitating localization recognition. Performance evaluation demonstrates system's efficacy achieving high accuracy, robustness, differentiation between activity levels. Metrics such as Average Precision (AP), Recall (AR), F1-score affirm advancement pioneering enhancement sets new standard precise, robust, context-aware videos. It offers comprehensive insights coaches, analysts, optimize strategies performance. highlights integration's advancements benefits domain analytics. Notably, proposed method achieved efficiency average precision 94.99%, recall 93.67%, 93.89%, F-score 94.33%.

Язык: Английский

Процитировано

0
Advancing plant biology through deep learning-powered natural language processing DOI
Shuang Peng, Loïc Rajjou

Plant Cell Reports, Год журнала: 2024, Номер 43(8)

Опубликована: Авг. 1, 2024

Язык: Английский

Процитировано

0
GenAI for Scientific Discovery in Electrochemical Energy Storage: State‐of‐the‐Art and Perspectives from Nano‐ and Micro‐Scale DOI
Shuangqi Li, Fengqi You

Small, Год журнала: 2024, Номер unknown

Опубликована: Окт. 9, 2024

Abstract The transition to electric vehicles (EVs) and the increased reliance on renewable energy sources necessitate significant advancements in electrochemical storage systems. Fuel cells, lithium‐ion batteries, flow batteries play a key role enhancing efficiency sustainability of usage transportation storage. Despite their potential, these technologies face limitations such as high costs, material scarcity, challenges. This research introduces novel integration Generative AI (GenAI) within systems address issues. By leveraging advanced GenAI techniques like Adversarial Networks, autoencoders, diffusion flow‐based models, multimodal large language this paper demonstrates improvements discovery, battery design, performance prediction, lifecycle management across different types further emphasizes importance nano‐ micro‐scale interactions, providing detailed insights into optimizing interactions for improved longevity. Additionally, discusses challenges future directions integrating research, highlighting data quality, model transparency, workflow integration, scalability, ethical considerations. addressing aspects, sets new benchmark use development, promoting sustainable, efficient, safer solutions.

Язык: Английский

Процитировано

0
Prediction of viral oncoproteins through the combination of generative adversarial networks and machine learning techniques DOI Creative Commons
Jorge F. Beltrán,

Lisandra Herrera-Belén,

Alejandro J. Yáñez

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Ноя. 7, 2024

Viral oncoproteins play crucial roles in transforming normal cells into cancer cells, representing a significant factor the etiology of various cancers. Traditionally, identifying these is both time-consuming and costly. With advancements computational biology, bioinformatics tools based on machine learning have emerged as effective methods for predicting biological activities. Here, first time, we propose an innovative approach that combines Generative Adversarial Networks (GANs) with supervised to enhance accuracy generalizability viral oncoprotein prediction. Our methodology evaluated multiple models, including Random Forest, Multilayer Perceptron, Light Gradient Boosting Machine, eXtreme Boosting, Support Vector Machine. In ten-fold cross-validation our training dataset, GAN-enhanced Forest model demonstrated superior performance metrics: 0.976 accuracy, F1 score, 0.977 precision, sensitivity, 1.0 AUC. During independent testing, this achieved 0.982 These results establish new tool, VirOncoTarget, accessible via web application. We anticipate VirOncoTarget will be valuable resource researchers, enabling rapid reliable prediction advancing understanding their role biology.

Язык: Английский

Процитировано

0