A New Representation on Protein Sequences
碩士 === 國立陽明大學 === 生物醫學資訊研究所 === 96 === Under the situation of high accuracy of protein secondary structure prediction, we uti-lized the information offered by existing protein secondary structure prediction tools and derived certain segments from each protein sequence to represent its original one....
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2008
|
Online Access: | http://ndltd.ncl.edu.tw/handle/07901372293321136589 |
Summary: | 碩士 === 國立陽明大學 === 生物醫學資訊研究所 === 96 === Under the situation of high accuracy of protein secondary structure prediction, we uti-lized the information offered by existing protein secondary structure prediction tools and derived certain segments from each protein sequence to represent its original one. To evaluate the power of our encoded sequence, we performed protein clustering on both protein sequences and their encoded form. The results of clustering are evaluated by sensitivity and specificity. We found that the encoded sequence whose original se-quence is over 100 amino acids could receive better sensitivity than its original one; the improvement is up to 16%. Our future work is to apply more proteomic applica-tions on encoded protein sequence, and hopefully their encoded form would improve the performance of these applications.
|
---|