This project includes:

1 DNA/protein 'word' detection and segment system.

2 a DNA/protein search engine based on text information retrieval technology like Google.

3 Protein sequence to Gene ontology terms translation system.

related paper：

(2010-06)how to build a dna search engine like google，http://www.omicsonline.org/0974-7230/JCSB-04-081.php?aid=2901, http://arxiv.org/abs/1006.4114

(2012-02)Segmenting DNA sequence into `words',http://arxiv.org/abs/1202.2518

(2013-06)A new DNA alignment method based on inverted index，http://arxiv.org/abs/1307.0194

(2013-11)Translate gene sequence into gene ontology terms based on statistical machine translation，http://f1000research.com/articles/2-231/v1

(2104-04)Protein secondary structure detection based on unsupervised word segmentation，http://arxiv.org/abs/1404.6866?context=q-bio

a news，http://www.technologyreview.com/view/419624/how-to-build-a-better-dna-search-engine/

The downloads files is mainly the first version.latest version should download from svn

Demo: http://www.dnasearchengine.com/

service： http://www.proteinsearch.com/

new codes will come to github: https://github.com/maris205/