Segmenting DNA sequence into `words'
This work addresses DNA sequence segmentation for bioinformatics researchers, but it appears incremental as it builds on n-gram statistical language models.
The paper tackles the problem of segmenting DNA sequences into 'words' by determining that most DNA words are 12-15 bps long through analysis of 12 model species, and it presents an unsupervised probability-based method for segmentation along with a proposed benchmark.
This paper presents a novel method to segment/decode DNA sequences based on n-grams statistical language model. Firstly, we find the length of most DNA 'words' is 12 to 15 bps by analyzing the genomes of 12 model species. Then we design an unsupervised probability based approach to segment the DNA sequences. The benchmark of segmenting method is also proposed.