Can I read Protein Sequence Segmentation and Motif Discovery on EtoBox?
Protein Sequence Segmentation and Motif Discovery by yannikegido is a document available to read on EtoBox.
What is Protein Sequence Segmentation and Motif Discovery about?
The document introduces peptide-pair encoding (PPE), a probabilistic method for segmenting protein sequences into variable-length sub-sequences to enhance motif discovery and sequence embedding. It presents two main applications: DiMotif, a discriminative motif discovery method that shows high recall in identifying experimentally verified motifs, and ProtVecX, an extension of protein vector embedding that improves classification tasks. The study emphasizes the importance of variable-length segmentation in b
- Author
- yannikegido
- Language
- EN