A5021737508- Ovarian cancer diagnosis and treatment
- Genetic and phenotypic traits in livestock
- Cancer Genomics and Diagnostics
- Insect symbiosis and bacterial influences
- PARP inhibition in cancer therapy
- AI in cancer detection
- Effects of Environmental Stressors on Livestock
- Viral Infections and Vectors
- Vector-borne infectious diseases
- Cell Image Analysis Techniques
- Genetics, Bioinformatics, and Biomedical Research
- Animal Behavior and Welfare Studies
- RNA and protein synthesis mechanisms
- Radiomics and Machine Learning in Medical Imaging
- Molecular Biology Techniques and Applications
- Reproductive Physiology in Livestock
- Protein Structure and Dynamics
- Colorectal Cancer Screening and Detection
- SARS-CoV-2 and COVID-19 Research
Eötvös Loránd University
2022-2025
Semmelweis University
2024-2025
Abstract Leveraging recent advances in computational modeling of proteins with AlphaFold2 (AF2) we provide a complete curated data set all single mutations from each the 7 main SARS-CoV-2 lineages spike protein receptor binding domain (RBD) resulting 3819 X = 26733 PDB structures. We visualize generated structures and show that AF2 pLDDT values are correlated state-of-the-art disorder approximations, implying some internal dynamics also captured by model. Joint increasing mutational coverage...
Patients with High-Grade Serous Ovarian Cancer (HGSOC) exhibit varied responses to treatment, 20–30% showing de novo resistance platinum-based chemotherapy. While hematoxylin-eosin (H&E)-stained pathological slides are used for routine diagnosis of cancer type, they may also contain diagnostically useful information about treatment response. Our study demonstrates that combining H&E-stained whole slide images (WSIs) proteomic signatures using a multimodal deep learning framework...
Body condition scoring is a simple method to estimate the energy supply of dairy cattle. Our study aims investigate accuracy with which supervised machine learning, specifically deep convolutional neural network (CNN), can be used retrieve body score (BCS) classes estimated by an expert. We recorded images animals' rumps in three large-scale farms using action camera. The were annotated and different-sized bounding boxes A CNN pretrained model was fine-tuned on 12 3 BCS classes. Training 0...
Statistical learning algorithms strongly rely on an oversimplified assumption for optimal performance, that is, source (training) and target (testing) data are independent identically distributed. Variation in human tissue, physician labeling physical imaging parameters (PIPs) the generative process, yield medical image datasets with statistics render this central false. When deploying models, new examples often out of distribution respect to training data, thus, robust dependable predictive...
Climate-sensitive disease vectors, such as ticks, respond to the environment with changes in their microbiome. These can affect emergence or re-emergence of various vector-borne pathogens, causative agent Lyme borreliosis (LB) tick-borne encephalitis. This aspect is particularly emphasized light climate change. The climatically representative assessment microbiome differences developmental stages most common Central European tick species, Ixodes ricinus, deepens our understanding potential...
Abstract Patients with High-Grade Serous Ovarian Cancer (HGSOC) exhibit varied responses to treatment, 20-30% showing de novo resistance platinum-based chemotherapy. While hematoxylin-eosin (H&E) pathological slides are used for routine diagnosis of cancer type, they may also contain diagnostically useful information about treatment response. Our study demonstrates that combining H&E-stained Whole Slide Images (WSIs) proteomic signatures using a multimodal deep learning framework...
<title>Abstract</title> Patients with High-Grade Serous Ovarian Cancer (HGSOC) exhibit varied responses to treatment, 20–30% showing <italic>de novo</italic> resistance platinum-based chemotherapy. While hematoxylin-eosin (H&E) pathological slides are used for routine diagnosis of cancer type, they may also contain diagnostically useful information about treatment response. Our study demonstrates that combining H&E-stained Whole Slide Images (WSIs) proteomic signatures using a...
Pigeons' unexpected competence in learning to categorize unseen histopathological images has remained an unexplained discovery for almost a decade (Levenson
Abstract Body condition scoring is a simple method to estimate the energy supply of dairy cattle. Our study aimed investigate accuracy with which supervised machine learning, deep convolutional neural network, can be used retrieve body score (BCS) classes estimated by an expert. Using action camera, we recorded images animals’ rumps in three large-scale farms. The were annotated different-sized boxes A Faster-RCNN pre-trained model was trained on 12 and 3 BCS classes. Training classes, 0...
ABSTRACT Background The microbial communities of disease vectors may represent a key feature in several biological functions and thus deserve special attention light climate change the consequent need to develop novel control strategies. Nevertheless, vector-borne networks are still poorly understood. Assessing vectors’ interactions climatic dependencies contribute better-estimating pathogen transmission characteristics, public health risks urgency for steps be taken. Methods In climatically...