Yang Ding

The paper introduces Markonv, a convolutional layer that models inter-positional correlations using Markov transition matrices, showing effectiveness in analyzing omics data and decoding electrical signals.

The paper introduces a variable-convolutional layer for motif identification in omics data, showing improved performance over standard convolutional layers.

This study uses multi-omics data from evolving E. coli strains to identify convergent and divergent adaptation principles at metabolic, transcriptomic, and genetic levels.

This paper introduces expectation pooling, an interpretable CNN pooling method that improves DNA-protein binding prediction by combining probabilistic ideas with deep learning.

This paper introduces an exact transformation to convert CNN kernels to PWMs, enabling accurate motif identification and preserving CNN performance.