Article
Construction & Building Technology
Hongyan Wang, Wen Wen, Zihong Zhang, Ning Gao
Summary: This study uses the optimized Relevance Vector Machine (RVM) model with Sparrow Search Algorithm (SSA), Simulate Anneal Arithmetic (SAA), Particle Swarm Optimization (PSO), and Bayesian Optimization Algorithm (BOP) to construct an energy dissipation model for public buildings in Wuhan City. The study finds that building area, personnel density, and supply air temperature significantly impact energy dissipation in public buildings. By employing Principal Component Analysis (PCA) for dimensionality reduction, the study selects seven main influential factors to predict building energy consumption accurately. The BOP-RVM model performs well in terms of R-2 (0.9523), r (0.9761), RMSE (5.3894), and SI (0.056), providing practical value for energy management strategies.
Article
Multidisciplinary Sciences
Alexander S. Garruss, Katherine M. Collins, George M. Church
Summary: Recent advances in DNA synthesis and sequencing have allowed for systematic studies of protein function at a large scale. A deep learning approach was used to predict the impact of protein variants on transcriptional repression, with promising results suggesting the potential for improving predictions of other important protein properties.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2021)
Article
Biochemistry & Molecular Biology
Farman Ali, Wajdi Alghamdi, Alaa Omran Almagrabi, Omar Alghushairy, Ameen Banjar, Majdi Khalid
Summary: Angiogenic proteins (AGPs) have various applications in cancer and are important in understanding cardiovascular and neurodegenerative diseases. In this research, a computational model using deep learning was established to identify AGPs. By constructing a sequence-based dataset and designing a novel feature encoder, the highest success rate was achieved with a proposed new feature descriptor in a 2D-CNN model. The proposed method (Deep-AGP) has potential for use in cancer research and the development of therapeutic methods for cardiovascular and neurodegenerative diseases.
INTERNATIONAL JOURNAL OF BIOLOGICAL MACROMOLECULES
(2023)
Article
Biochemistry & Molecular Biology
Yeeun Lee, Seungyoon Nam
Summary: This study compared two CNN models, GoogLeNet and AlexNet, along with a LASSO model for multi-class drug responsiveness prediction. The results showed that AlexNet and GoogLeNet outperformed LASSO, indicating that DL models are useful tools for drug responsiveness prediction in precision oncology.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2021)
Review
Biochemical Research Methods
Siqi Chen, Tiancheng Li, Luna Yang, Fei Zhai, Xiwei Jiang, Rongwu Xiang, Guixia Ling
Summary: Predicting drug interactions is crucial for drug development and safety monitoring, and AI technology has shown great advantages in this field. This article systematically reviews the application of AI in drug-drug, drug-food, and drug-microbiome interactions, identifying potential areas for future research.
BRIEFINGS IN BIOINFORMATICS
(2022)
Review
Biochemical Research Methods
Meng Zhang, Cangzhi Jia, Fuyi Li, Chen Li, Yan Zhu, Tatsuya Akutsu, Geoffrey Webb, Quan Zou, Lachlan J. M. Coin, Jiangning Song
Summary: This study provides benchmark datasets for promoter prediction in 58 different species, and finds that deep learning and traditional machine learning-based approaches generally outperform scoring function-based approaches.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Automation & Control Systems
Blake VanBerlo, Matthew A. S. Ross, Jonathan Rivard, Ryan Booker
Summary: This study introduces a machine learning approach to predict chronic homelessness using de-identified client shelter records from a Canadian homelessness management information system. The training method was fine-tuned to achieve a high level of performance, balancing recall and precision.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Geosciences, Multidisciplinary
Spyros Kondylatos, Ioannis Prapas, Michele Ronco, Ioannis Papoutsis, Gustau Camps-Valls, Maria Piles, Miguel-Angel Fernandez-Torres, Nuno Carvalhais
Summary: Climate change worsens the occurrence of large wildfires by increasing extreme droughts and heatwaves. This study uses Deep Learning to predict wildfire danger and explainable Artificial Intelligence to analyze model attributions. The presented methodology improves the accuracy of wildfire anticipation and reveals the contribution of different variables.
GEOPHYSICAL RESEARCH LETTERS
(2022)
Article
Meteorology & Atmospheric Sciences
Jonathan A. Weyn, Dale R. Durran, Rich Caruana, Nathaniel Cresswell-Clay
Summary: The study presents an ensemble prediction system using a computationally efficient Deep Learning Weather Prediction (DLWP) model to recursively predict key atmospheric variables with good skill globally. The model performs well in simulating mid-latitude weather systems and generating tropical cyclones, showing decent predictive capabilities.
JOURNAL OF ADVANCES IN MODELING EARTH SYSTEMS
(2021)
Review
Biochemical Research Methods
Jing Wang, Qinglong Zhang, Junshan Han, Yanpeng Zhao, Caiyun Zhao, Bowei Yan, Chong Dai, Lianlian Wu, Yuqi Wen, Yixin Zhang, Dongjin Leng, Zhongming Wang, Xiaoxi Yang, Song He, Xiaochen Bo
Summary: This review article discusses the recent applications of computational methods in synthetic lethality (SL) prediction. It introduces the concept and screening methods of SL, summarizes various SL-related data resources, and provides an overview of computational methods including statistical-based methods, network-based methods, classical machine learning methods, and deep learning methods for SL prediction. The article also highlights the use of negative sampling methods in these models. Representative tools for SL prediction are introduced, and the challenges and future work for SL prediction are discussed.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Nora El-Rashidy, Nesma E. ElSayed, Amir El-Ghamry, Fatma M. Talaat
Summary: This paper proposes a data replacement and prediction framework for monitoring pregnant women's vital signs, involving the use of IoT layer, fog layer, and cloud layer for data transmission and storage. In the fog layer, the unused data is replaced using DFM and GDM incidence is predicted using EPM. Through evaluation on data of 16,354 pregnant women, the prediction model performs better than existing techniques. Overall, this framework provides a cost-effective solution for early prediction of GDM.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Environmental Sciences
Rajnish Kumar, Farhat Ullah Khan, Anju Sharma, Mohammed Haris Siddiqui, Izzatdin B. A. Aziz, Mohammad Amjad Kamal, Ghulam Md Ashraf, Badrah S. Alghamdi, Md Sahab Uddin
Summary: Identifying and screening mutagenic chemicals are crucial for ensuring the safety of chemical compounds, and prediction models developed using machine learning techniques such as DNN have shown higher accuracy and performance.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2021)
Review
Pharmacology & Pharmacy
Yaojia Chen, Liran Juan, Xiao Lv, Lei Shi
Summary: This article reviews the current research status of modeling-based anti-cancer drug sensitivity prediction, emphasizing the importance of genomics data in the prediction task, while also pointing out that existing prediction models neglect the significant impacts of gene mutations, methylation, and copy number variations on drug sensitivity.
FRONTIERS IN PHARMACOLOGY
(2021)
Article
Chemistry, Analytical
H. Sabireen, Neelanarayanan Venkataraman
Summary: This paper proposes a method based on Long Short-Term Memory (LSTM) and Computation Memory and Power (CRP) rule for predicting faults in fog devices due to insufficient resources. The results show that the proposed method outperforms existing machine learning and deep learning techniques with a prediction accuracy of 95.16% on the training data and 98.69% on the testing data.
Article
Environmental Sciences
Eunjeong Lee, Jung-Hoon Kim, Ki-Young Heo, Yang-Ki Cho
Summary: The study reproduced a sea fog event observed over the Eastern Yellow Sea on 15-16 April 2012 using a high-resolution Weather Research and Forecasting (WRF) simulation. It investigated the roles of physical processes and synoptic-scale flows on advection fog with phase transition, highlighting the impact of longwave radiative cooling and warm-moist air advection on cloud formation and transition from cold-sea fog to warm-sea fog during nighttime.