A5013088352- Radiomics and Machine Learning in Medical Imaging
- Genomics and Rare Diseases
- Computational Drug Discovery Methods
- Hereditary Neurological Disorders
- Machine Learning in Healthcare
- Genetic Neurodegenerative Diseases
- RNA Research and Splicing
- Biomedical Text Mining and Ontologies
- Genetics, Bioinformatics, and Biomedical Research
- Bioinformatics and Genomic Networks
- Cancer Genomics and Diagnostics
- RNA regulation and disease
University of Utah
2023-2025
Abstract Precision oncology centers on the selection of targeted anticancer agents in tumors harboring actionable molecular alterations. However, most lack alterations, and individual biomarkers are often poor predictors response. These challenges particularly acute metastatic with their vast inter-tumoral heterogeneity diverse resistance mechanisms. As a result, cytotoxic chemotherapy remains mainstay treatment, yet few data-driven tools exist to inform selection. limitations need for...
Abstract Precision oncology hinges on accurate prediction of patient-specific treatment response from tumor molecular inputs. While deep learning (DL) models achieve state-of-the-art in cell lines, existing methods do not readily translate to the clinic where training data is limited. Here, we have developed and validated ScreenDL, a novel DL framework designed explicitly for use clinical precision applications. The underlying architecture ScreenDL consists two fully connected branches...
Precision oncology matches tumors to targeted therapies based on the presence of actionable molecular alterations. However, most lack alterations, restricting treatment options cytotoxic chemotherapies for which few data-driven prioritization strategies currently exist. Here, we report an integrated computational/experimental selection approach applicable both and agents irrespective We generated functional drug response data a large collection patient-derived tumor models used it train...
Background: An early genetic diagnosis can guide the time-sensitive treatment of individuals with epilepsies. However, identification a cause often occurs long after disease onset. Here, we aimed to identify clinical features suggestive diagnoses in epilepsy by systematic large-scale analysis information from full-text electronic medical records (EMR).Methods: We employed customized natural language processing (NLP) pipeline, extracting 89 million time-stamped standardized annotations...