CHASHNIt for enhancing skin disease classification using GAN augmented hybrid model with LIME and SHAP based XAI heatmaps.

Correct categorization of skin diseases is vital for prompt diagnosis. However, obstacles such as imbalance of data and interpretability of deep learning models limit their use in medical settings. To overcome these setbacks, Combined Hybrid Architecture for Scalable High-performance in Neural Iterations or CHASHNIt is proposed, which is an integration of EfficientNetB7, DenseNet201, and InceptionResNetV2 to outperform current models on every ground.

Alterations of the skin microbiome in multiple system atrophy: a pilot study.

Multiple system atrophy (MSA) alters skin physiology, potentially impacting skin microbiota. This pilot study investigated whether skin microbiota differs in MSA and whether these differences relate to disease severity. Using 16S rRNA sequencing of cervical and axillary sites in MSA, Parkinson's disease, and controls, we identified distinct microbial patterns among groups.

A review on multi-omics integration for aiding study design of large scale TCGA cancer datasets.

Background: Rapid advancements in high-throughput sequencing technologies allow for detailed and accurate measurement of omics features within their biological context. The integration of different omics types creates heterogeneous datasets, presenting challenges in analysis due to variations in measurement units, sample numbers, and features. Currently, there is a lack of generalized guidelines for making decisions in multi-omics study design (MOSD), such as selecting an appropriate number of samples and features, type of preprocessing and integration for robust analysis results.

Key frame extraction based abnormal vehicle identification technique using statistical distribution analysis.

In recent days, due to potential growth of vehicle usage, the researchers have to concentrate on abnormal vehicle identification areas to provide solutions to avoid accidents. Though many vehicle identification works have been done by applying machine and deep learning approaches, still there is some problem with handling repetition frames and identifying the abnormal vehicles among vehicles in a camera. To overcome these challenges, this paper introduces KFEAVI (Key Frame Extraction based Abnormal Vehicle Identification) technique that uses statistical feature extraction technique and constrained angular second moment technique.

Automated detection of Parkinson's disease using improved linknet-ghostnet model based on handwriting images.

Parkinson's disease (PD), is a neural disorder that damages movement control, which is reflected by different non-motor and motor symptoms. PD is caused by the weakening of neurons that produce dopamine in the brain, and it includes symptoms like bradykinesia (delay in movements), stiffness, and tremors. People frequently suffer from loss of motor skills when the illness worsens, which has a big influence on everyday tasks like writing.

Optimization and predictive performance of fly ash-based sustainable concrete using integrated multitask deep learning framework with interpretable machine learning techniques.

Concrete strength prediction is of great relevance for construction safety and quality assurance; however, these methods often trade-off their accuracy or interpretability, especially when it comes to the use of supplementary cementitious materials like fly ash in process. This study aims to build an interpretable, highly accurate model for predicting the compressive and tensile strength of concrete with a hybrid approach based on gradient boosting (XGBoost), deep neural networks (DNNs), and optimization via AutoGluon Process. The model is put into a multitask learning (MTL) framework that includes mix design variables, environmental factors, and non-destructive testing (NDT) data samples.

Miconazole attenuates LPS-induced lung inflammation by modulating alveolar macrophage polarization via promoting lipid metabolic reprogramming.

Objective: Pulmonary inflammation is closely associated with macrophage polarization and lipid metabolic reprogramming. Miconazole (MCZ), traditionally used as an antifungal agent, exhibits emerging anti-inflammatory potential, yet its underlying mechanisms remain unclear.

Methods: A mouse model of lipopolysaccharide (LPS)-induced lung inflammation was employed to evaluate MCZ's anti-inflammatory efficacy.

Robust cortical thickness estimation in the presence of partial volumes using adaptive diffusion equation.

Background: Automated estimation of cortical thickness in brain MRI is a critical step when investigating neuroanatomical population differences and changes associated with normal development and aging, as well as in neurodegenerative diseases such as Alzheimer's and Parkinson's. The limited spatial resolution of the scanner leads to partial volume effects, where each voxel in the scanned image may represent a mixture of more than one type of tissue. Due to the highly convoluted structure of the cortex, this can have a significant impact on the accuracy of thickness estimates, particularly if a hard intensity threshold is used to delineate cortical boundaries.

AlzFormer: Multi-modal framework for Alzheimer's classification using MRI and graph-embedded demographics guided by adaptive attention gating.

Alzheimer's disease (AD) is the most common neurodegenerative progressive disorder and the fifth-leading cause of death in older people. The detection of AD is a very challenging task for clinicians and radiologists due to the complex nature of this disease, thus requiring automatic data-driven machine-learning models to enhance diagnostic accuracy and support expert decision-making. However, machine learning models are hindered by three key limitations, in AD classification:(i) diffuse and subtle structural changes in the brain that make it difficult to capture global pathology (ii) non-uniform alterations across MRI planes, which limit single-view learning and (iii) the lack of deep integration of demographic context, which is often ignored despite its clinical importance.

Short-Term Prediction Model for Breast Cancer Risk Based on One Million Medical Records.

Background: Despite progress in breast cancer screening many women are diagnosed with advanced stage. We sought to develop a short-term (one year) prediction model for breast cancer risk, based on readily available data from electronic medical records (EMRs), to support decision-making.

Methods: A retrospective cohort study using data of 1,039,212 members of a large healthcare organization between the years 1985 and 2021.

Leveraging Retrieval-Augmented Large Language Models for Dietary Recommendations With Traditional Chinese Medicine's Medicine Food Homology: Algorithm Development and Validation.

Background: Traditional Chinese Medicine (TCM) emphasizes the concept of medicine food homology (MFH), which integrates dietary therapy into health care. However, the practical application of MFH principles relies heavily on expert knowledge and manual interpretation, posing challenges for automating MFH-based dietary recommendations. Although large language models (LLMs) have shown potential in health care decision support, their performance in specialized domains such as TCM is often hindered by hallucinations and a lack of domain knowledge.

A Bottom-Up Approach Integrating Computer Vision with Material Flow Analysis to Estimate the Recycling Potential of Distributed Solar Panels Using Satellite Imagery.

The rapid deployment of solar photovoltaic (PV) systems has created a growing challenge in managing end-of-life panels. While many studies project future recycling potential, they are often limited by the lack of data on existing distributed PV installations. To address this need, we developed SolarScope, an open-source model that integrates computer vision (CV) with dynamic material flow analysis (dMFA) to automatically identify distributed PV panel areas and evaluate the urban mining potential.

An interdisciplinary approach in teaching RNA secondary structure prediction to first-year undergraduate students using an automated deep learning RNA 3D model prediction tool.

The use of artificial intelligence (AI) in biologics drug design is interlaced into the fabric of the drug discovery pipeline for many in the biotechnology industry. The use of AI tools in RNA therapeutic drug design has gained traction in recent years to develop more effective therapeutics in a short period of time, revolutionizing rapid-response therapeutics. Indeed, machine learning (ML) and deep learning (DL) are streamlining RNA therapeutic design in ways we never thought were possible just a decade ago.

Lessons from complex systems science for AI governance.

The study of complex adaptive systems, pioneered in physics, biology, and the social sciences, offers important lessons for artificial intelligence (AI) governance. Contemporary AI systems and the environments in which they operate exhibit many of the properties characteristic of complex systems, including nonlinear growth patterns, emergent phenomena, and cascading effects that can lead to catastrophic failures. Complex systems science can help illuminate the features of AI that pose central challenges for policymakers, such as feedback loops induced by training AI models on synthetic data and the interconnectedness between AI systems and critical infrastructure.

Enhancing leaf disease classification using GAT-GCN hybrid model.

Agriculture plays a critical role in the global economy, providing livelihoods and ensuring food security for billions. Progress in agricultural techniques has helped boost crop yield, along with a growing need for precise disease monitoring solutions. This requires accurate, efficient, and timely disease detection methods.

Adaptive spatial feature extraction and graphical feature awareness for robust point cloud registration.

In recent years Transformers have achieved significant success in the field of 3D vision due to their inherent advantages in capturing global correlations between features. However, this can be a drawback in point cloud registration, especially in scenes with low overlap rates, where a large number of non-overlapping points can lead to ineffective or even negative attention allocation. Moreover, existing RANSAC-based registration estimators usually require a large number of iterations to obtain acceptable results, resulting in significant computational overhead.

Evaluation of large language model-driven AutoML in data and model management from human-centered perspective.

As organizations increasingly seek to leverage machine learning (ML) capabilities, the technical complexity of implementing ML solutions creates significant barriers to adoption and impacts operational efficiency. This research examines how Large Language Models (LLMs) can transform the accessibility of ML technologies within organizations through a human-centered Automated Machine Learning (AutoML) approach. Through a comprehensive user study involving 15 professionals across various roles and technical backgrounds, we evaluate the organizational impact of an LLM-based AutoML framework compared to traditional implementation methods.

Learning-based parallel acceleration for HaplotypeCaller.

In the genome analysis workflow, Genome Analysis Toolkit (GATK) HaplotypeCaller is a widely used variant calling tool designed to accurately identify single nucleotide polymorphisms (SNPs) and insertions/deletions (Indels) in samples. However, when processing large-scale datasets, HaplotypeCaller often faces the challenge of excessively long runtime. Parallelizing GATK HaplotypeCaller with data segmentation is an effective solution, but existing methods struggle to accurately estimate the computational complexity of each data block, leading to severe computational skew.

Enhancing signed graph neural networks through curriculum-based training.

Signed graphs are powerful models for representing complex relations with both positive and negative connections. Recently, Signed Graph Neural Networks (SGNNs) have emerged as potent tools for analyzing such graphs. To our knowledge, no prior research has been conducted on devising a training plan specifically for SGNNs.

MGDMCL: A multi-omics integration framework based on masked graph dynamic learning and multi-granularity feature contrastive learning for biomedical classification.

Background And Objective: Integrating multi-omics data facilitates a comprehensive understanding of the etiology of complex diseases, which is critical for achieving precision medicine. Recently, graph-based approaches have been increasingly leveraged in the integrative multi-omics data analysis due to their robust expressive capability. However, these methods still face two limitations: 1) relying predominantly on a fixed sample similarity graph (SSG) to obtain omics-specific feature representation, and 2) insufficiently exploring the interrelations between different features from various omics.

Design and Reprogrammability of Zero Modes in 2D Materials from a Single Element.

Mechanical extremal materials, a class of metamaterials that exist at the bounds of elastic theory, possess the extraordinary capability to engineer any desired elastic behavior by harnessing mechanical zero modes - deformation modes that demand minimal or, ideally, no elastic energy. However, the potential for arbitrary construction and reprogramming of metamaterials remains largely unrealized, primarily due to significant challenges in qualitatively transforming zero modes within the confines of existing metamaterial design frameworks. This work presents a method for explicitly defining and in situ reprogramming zero modes of 2D extremal materials by employing straight-line mechanisms (SLMs) and planar symmetry, which prescribe and coordinate the zero modes, respectively.

Accelerating Biomolecular Modeling with AtomWorks and RF3.

Deep learning methods trained on protein structure databases have revolutionized biomolecular structure prediction, but developing and training new models remains a considerable challenge. To facilitate the development of new models, we present AtomWorks: a broadly applicable data framework for developing state-of-the-art biomolecular foundation models spanning diverse tasks, including structure prediction, generative protein design, and fixed backbone sequence design. We use AtomWorks to train RosettaFold-3 (RF3), a structure prediction network capable of predicting arbitrary biomolecular complexes with an improved treatment of chirality that narrows the performance gap between closed-source AlphaFold3 (AF3) and existing open-source implementations.

consHLA: a next generation sequencing consensus-based HLA typing workflow.

Background: Human Leukocyte Antigens (HLA) play central roles in histocompatibility and immune system functions, including antigen presentation. Accurate typing of Class I and II HLA genes is crucial for transplant tissue matching, characterising autoimmune diseases and informing cancer immunotherapy. Clinical serology and PCR-based testing are the gold standards for HLA typing, but offer only single-field resolution (e.