Search

The study presented in this paper evaluated gene expression profiles from The Cancer Genome Atlas (TCGA). To reduce complexity, we focused on genes in the cGAS–STING pathway, crucial for cytosolic DNA detection and immune response. The study analyzes three clinical variables: disease-specific survival (DSS), overall survival (OS), and tumor stage. To effectively utilize the high-dimensional gene expression data, we needed to find a way to project these data meaningfully. Since gene pathways can be represented as graphs, a novel method of presenting genomics data using graph data structure was employed, rather than the conventional tabular format. To leverage the gene expression data represented as graphs, we utilized a graph convolutional network (GCN) machine learning model in conjunction with the genetic algorithm optimization technique. This allowed for obtaining an optimal graph representation topology and capturing important activations within the pathway for each use case, enabling a more insightful analysis of the cGAS–STING pathway and its activations across different cancer types and clinical variables. To tackle the problem of unexplainable AI, graph visualization alongside the integrated gradients method was employed to explain the GCN model's decision-making process, identifying key nodes (genes) in the cGAS–STING pathway. This approach revealed distinct molecular mechanisms, enhancing interpretability. This study demonstrates the potential of GCNs combined with explainable AI to analyze gene expression, providing insights into cancer progression. Further research with more data is needed to validate these findings. [ABSTRACT FROM AUTHOR]

Collaboration across the agriculture supply chain is essential to address the high-yield demand and sustainable practices amid global overpopulation. Limited resources, such as soil and water, are compromised by excessive chemical agents and nutrient use. The Internet of Things (IoT) and smart farming offer solutions by optimizing agent applications, data analysis, and farm monitoring. Evidence from numerous studies indicates that collaboration in the supply chain, including farmers, can improve efficiency and productivity, reduce costs, and enhance crop quality. This paper investigates the transformation of traditional agriculture into smart farming through the integration of IoT technology and community partnerships. It presents a case study focused on educating farm owners about advanced technologies to enhance decision-making, improve crop yields, and promote sustainability. Additionally, the paper highlights the role of data analytics in agriculture. Farmers in the southern region of Zagreb, Croatia, were trained on the use of sensors and yield monitoring. Small farms in that region face challenges in improving yields due to limited capacity and lack of entrepreneurial experience. The DMAIC methodology was employed to address these issues and measure relevant parameters. The paper also discusses consistent patterns between electrical conductivity (EC) measurements and potassium levels in soil. It explains the potential of estimating potassium concentrations based on EC readings, or vice versa. Leveraging EC as a proxy for potassium levels could offer a cost-effective means of assessing soil fertility and nutrient dynamics. Additionally, Principal Component Analysis (PCA) biplot analysis is presented, showing that pH values behaved independently. Understanding these dynamics enhances knowledge of soil variability and informs sustainable soil management practices. [ABSTRACT FROM AUTHOR]

Recent advancements in cognitive neuroscience, particularly in electroencephalogram (EEG) signal processing, image generation, and brain–computer interfaces (BCIs), have opened up new avenues for research. This study introduces a novel framework, Bridging Artificial Intelligence and Neurological Signals (BRAINS), which leverages the power of artificial intelligence (AI) to extract meaningful information from EEG signals and generate images. The BRAINS framework addresses the limitations of traditional EEG analysis techniques, which struggle with nonstationary signals, spectral estimation, and noise sensitivity. Instead, BRAINS employs Long Short-Term Memory (LSTM) networks and contrastive learning, which effectively handle time-series EEG data and recognize intrinsic connections and patterns. The study utilizes the MNIST dataset of handwritten digits as stimuli in EEG experiments, allowing for diverse yet controlled stimuli. The data collected are then processed through an LSTM-based network, employing contrastive learning and extracting complex features from EEG data. These features are fed into an image generator model, producing images as close to the original stimuli as possible. This study demonstrates the potential of integrating AI and EEG technology, offering promising implications for the future of brain–computer interfaces. [ABSTRACT FROM AUTHOR]