Loading...
Loading...
Go to the dataset
https://figshare.com/articles/dataset/KANG2P_data/29622509Contributors:
Dataset URI:
10.6084/m9.figshare.29622509.v2Genomic prediction has emerged as a powerful tool with applications spanning human disease risk assessment and plant/animal breeding. Kolmogorov–Arnold networks (KANs) have risen as a potential substitute for multilayer perceptrons within dense fully connected networks. Substantial efforts have been dedicated to incorporating KANs into diverse deep learning frameworks in computer vision and natural language processing. However, the integration of KANs into deep learning models for genomic prediction remains unexplored. Here, we present KANG2P, a novel method designed to enhance genomic prediction accuracy. We extensively evaluated KANG2P on diverse datasets, including ALS and Parkinson's disease, as well as maize and rice datasets. In classification and regression tasks, KANG2P demonstrated superior performance compared to existing methods. By integrating both genotype and predicted expression data, KANG2P leverages a unique architecture to better capture complex genetic patterns. We also propose an explainable approach for spline functions to identify disease-related functional genes. Our results highlight KANG2P's potential to advance research and applications in both biomedical and agricultural fields.
Keyword(s):
Bioinformatic methods development; Genomics; Processed datasets.
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
No Associated Publication Data Available
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)
Go to the dataset
https://figshare.com/articles/dataset/KANG2P_data/29622509