Evaluating the informativeness of deep learning annotations for human complex diseases
Deep learning models have shown great promise in predicting regulatory effects from DNA sequence. Here the authors evaluate sequence-based epigenomic deep learning models and conclude that these models are not yet ready to inform our knowledge of human disease.
Saved in:
Main Authors: | Kushal K. Dey, Bryce van de Geijn, Samuel Sungil Kim, Farhad Hormozdiari, David R. Kelley, Alkes L. Price |
---|---|
Format: | article |
Language: | EN |
Published: |
Nature Portfolio
2020
|
Subjects: | |
Online Access: | https://doaj.org/article/e966c41c45b24c86a35cad7f34f42b80 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Functional disease architectures reveal unique biological role of transposable elements
by: Farhad Hormozdiari, et al.
Published: (2019) -
Improving the informativeness of Mendelian disease-derived pathogenicity scores for common disease
by: Samuel S. Kim, et al.
Published: (2020) -
Annotation-efficient deep learning for automatic medical image segmentation
by: Shanshan Wang, et al.
Published: (2021) -
Harnessing clinical annotations to improve deep learning performance in prostate segmentation.
by: Karthik V Sarma, et al.
Published: (2021) -
Embeddings from deep learning transfer GO annotations beyond homology
by: Maria Littmann, et al.
Published: (2021)