Background: The Knight Alzheimer Research Imaging (KARI) dataset, a compilation of data from projects conducted at Washington University in St. Louis, represents a comprehensive effort to advance our understanding of Alzheimer disease (AD) through multimodal data collection. The overarching goal is to characterize normal aging and disease progression to contribute insights into the biological changes preceding AD symptom onset.
Methods: The dataset comprises cross-sectional and longitudinal measures of magnetic resonance imaging (MRI), including T1 and T2-weighted structural, diffusion, and resting-state acquisitions, from over 1,600 participants aged 42 to 103 years. Additionally, a subset of participants underwent amyloid (1,100+) and tau (500+) tracer positron emission tomography (PET) acquisitions, along with cognitive, genetic, and cerebrospinal fluid (CSF) biofluid measures.
Results: In addition to raw MRI and PET acquisitions, this dataset also includes processed output that has undergone rigorous quality assessment, anatomical segmentation, and quantification procedures using FreeSurfer, as well as post-processing quantification of amyloid and tau burden. All data are publicly available in an online repository and can be accessed upon request.
Conclusions: The KARI dataset offers a valuable resource for investigating biomarkers, genetic factors, and imaging data in normal aging, preclinical, and symptomatic Alzheimer's disease. Expanded use could contribute to the development of early diagnostic tools, treatment strategies, and a deeper understanding of the complexities associated with neurodegenerative diseases.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1002/alz.086955 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Background: The Knight Alzheimer Research Imaging (KARI) dataset, a compilation of data from projects conducted at Washington University in St. Louis, represents a comprehensive effort to advance our understanding of Alzheimer disease (AD) through multimodal data collection. The overarching goal is to characterize normal aging and disease progression to contribute insights into the biological changes preceding AD symptom onset.
View Article and Find Full Text PDFAI-DPAPT: a machine learning framework for predicting PROTAC activity.
Mol Divers
October 2024
Pharmaceutical Chemistry Department, Faculty of Pharmacy, Damanhour University, Damanhour, 22516, El-Buhaira, Egypt.
Article Synopsis
- Proteolysis Targeting Chimeras (PROTACs) are innovative tools in targeted protein degradation (TPD) that hold promise for drug development, but predicting their effectiveness is challenging.
- This study introduces an AI-powered PROTAC Activity Prediction Tool (AI-DPAPT) that leverages machine learning and molecular fingerprinting techniques to accurately predict PROTAC activity based on chemical structures.
- The research demonstrated strong performance across various machine learning classifiers, with the Random Forest model yielding an impressive area under the curve score of 0.97, enhancing the understanding of structure-activity relationships in TPD and potentially accelerating drug development processes.
The opportunity to lead facilitates PA professional well-being.
JAAPA
June 2024
Kari Sue Bernard is associate director of research and capstone in the Doctor of Medical Science program at A.T. Still University's Arizona School of Health Sciences in Mesa, Ariz., and practices in psychiatry at Orion Behavioral Health Network in Eagle River, Alaska. Nancy Bostain is an adjunct faculty member at Walden University in Minneapolis, Minn. Dr. Bernard discloses that she owns and operates Bernard Wellness Initiative, LLC, a professional well-being business that provides continuing medical education, coaching, and workplace assessments to healthcare providers and organizations. The authors have disclosed no other potential conflicts of interest, financial or otherwise.
Objective: Physician associates/assistants (PAs) with mature careers represent an important leadership resource for healthcare employers. This study sought to determine whether PA leadership task responsibility interacted with experience level to predict professional well-being.
Methods: This quantitative study used an archival dataset from a national sample of PAs.
Environment and taxonomy shape the genomic signature of prokaryotic extremophiles.
Sci Rep
September 2023
School of Computer Science, University of Waterloo, Waterloo, ON, Canada.
This study provides comprehensive quantitative evidence suggesting that adaptations to extreme temperatures and pH imprint a discernible environmental component in the genomic signature of microbial extremophiles. Both supervised and unsupervised machine learning algorithms were used to analyze genomic signatures, each computed as the k-mer frequency vector of a 500 kbp DNA fragment arbitrarily selected to represent a genome. Computational experiments classified/clustered genomic signatures extracted from a curated dataset of [Formula: see text] extremophile (temperature, pH) bacteria and archaea genomes, at multiple scales of analysis, [Formula: see text].
View Article and Find Full Text PDFiDeLUCS: a deep learning interactive tool for alignment-free clustering of DNA sequences.
Bioinformatics
September 2023
Cheriton School of Computer Science, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
Summary: We present an interactive Deep Learning-based software tool for Unsupervised Clustering of DNA Sequences (iDeLUCS), that detects genomic signatures and uses them to cluster DNA sequences, without the need for sequence alignment or taxonomic identifiers. iDeLUCS is scalable and user-friendly: its graphical user interface, with support for hardware acceleration, allows the practitioner to fine-tune the different hyper-parameters involved in the training process without requiring extensive knowledge of deep learning. The performance of iDeLUCS was evaluated on a diverse set of datasets: several real genomic datasets from organisms in kingdoms Animalia, Protista, Fungi, Bacteria, and Archaea, three datasets of viral genomes, a dataset of simulated metagenomic reads from microbial genomes, and multiple datasets of synthetic DNA sequences.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!