Inherently interpretable position-aware convolutional motif kernel networks for biological sequencing data
Abstract Artificial neural networks show promising performance in detecting correlations within data that are associated with specific outcomes. However, the black-box nature of such models can hinder the knowledge advancement in research fields by obscuring the decision process and preventing scien...
Main Authors: | Jonas C. Ditz, Bernhard Reuter, Nico Pfeifer |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-10-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-44175-7 |
Similar Items
-
Computing distribution of scale independent motifs in biological sequences
by: Vinga Susana, et al.
Published: (2006-10-01) -
Dense Nested Network Based on Position-Aware Dynamic Parameter Convolution Kernel for Infrared Small Target Detection
by: Bing-Kun Nian, et al.
Published: (2023-01-01) -
Multinomial Convolutions for Joint Modeling of Regulatory Motifs and Sequence Activity Readouts
by: Minjun Park, et al.
Published: (2022-09-01) -
Kernel methods in computational biology /
by: Scholkopf, Bernhard, et al.
Published: (2004) -
Object-Aware Adaptive Convolution Kernel Attention Mechanism in Siamese Network for Visual Tracking
by: Dongliang Yuan, et al.
Published: (2022-01-01)