Exploring variable-length features (motifs) for predicting binding sites through interpretable deep neural networks.
Chandra Mohan DasariSanthosh AmilpurRaju BhukyaPublished in: Eng. Appl. Artif. Intell. (2021)
Keyphrases
- variable length
- binding sites
- neural network
- dna sequences
- fixed length
- motif discovery
- biological sequences
- sequence data
- transcription factors
- gene expression
- transcription factor binding sites
- protein families
- feature extraction
- n gram
- co occurrence
- feature vectors
- bayesian networks
- bitstream
- information extraction
- pairwise
- feature space
- similarity measure
- web pages
- data mining