Àá½Ã¸¸ ±â´Ù·Á ÁÖ¼¼¿ä. ·ÎµùÁßÀÔ´Ï´Ù.
KMID : 0578320090270050547
Molecules and Cells
2009 Volume.27 No. 5 p.547 ~ p.556
Prediction of parathyroid hormone signalling potency using SVMs
Yoo Ah-Rim

Ko Sung-Geon
Lim Sung-Kil
Lee Weon-Tae
Yang Dae-Ryook
Abstract
Parathyroid hormone is the most important endocrine regulator of calcium concentration. Its N-terminal fragment (1?34) has sufficient activity for biological function. Recently, site-directed mutagenesis studies demonstrated that substitutions at several positions within shorter analogues (1?14) can enhance the bioactivity to greater than that of PTH (1?34). However, designing the optimal sequence combination is not simple due to complex combinatorial problems. In this study, support vector machines were introduced to predict the biological activity of modified PTH (1?14) analogues using mono-substituted experimental data and to analyze the key physicochemical properties at each position that correlated with bioactivity. This systematic approach can reduce the time and effort needed to obtain desirable molecules by bench experiments and provide useful information in the design of simpler activating molecules.
KEYWORD
function, parathyroid hormone, peptide analogue, SVM
FullTexts / Linksout information
Listed journal information
SCI(E) MEDLINE ÇмúÁøÈïÀç´Ü(KCI)