• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Current Result Document : 10 / 44 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ¾ÈÁ¤Àû À¯ÀüÀÚ Æ¯Â¡ ¼±ÅÃÀ» À§ÇÑ À¯ÀüÀÚ ¹ßÇö·® µ¥ÀÌÅÍÀÇ ºÎÆ®½ºÆ®·¦ ±â¹Ý Lasso ȸ±Í ºÐ¼®
¿µ¹®Á¦¸ñ(English Title) Lasso Regression of RNA-Seq Data based on Bootstrapping for Robust Feature Selection
ÀúÀÚ(Author) Á¶Á¤Èñ   À±¼º·Î   Jeonghee Jo   Sungroh Yoon  
¿ø¹®¼ö·Ïó(Citation) VOL 23 NO. 09 PP. 0557 ~ 0563 (2017. 09)
Çѱ۳»¿ë
(Korean Abstract)
¸¹Àº ¼öÀÇ À¯ÀüÀÚ µ¥ÀÌÅ͸¦ ÀÌ¿ëÇؼ­ Lasso ȸ±Í ºÐ¼®À» ÇÒ ¶§, À¯ÀüÀÚ ¹ßÇö·® °ªµé »çÀÌÀÇ ³ôÀº »ó°ü¼ºÀ¸·Î ÀÎÇÏ¿© ȸ±Í °è¼öÀÇ ÃßÁ¤°ªÀÌ È¸±Í ºÐ¼®ÀÇ ¹Ýº¹ ½ÃÇึ´Ù ´Þ¶óÁú ¼ö ÀÖ´Ù. L1 Á¤±ÔÈ­¿¡ ÀÇÇØ Ãà¼ÒµÇ´Â ȸ±Í °è¼öÀÇ ºÒ¾ÈÁ¤¼ºÀº º¯¼ö ¼±ÅÃÀ» ¾î·Æ°Ô ÇÏ´Â ¿äÀÎÀÌ µÈ´Ù. º» ¿¬±¸¿¡¼­´Â ÀÌ·¯ÇÑ ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇÏ¿© ºÎÆ®½ºÆ®·¦ ´Ü°è¸¦ ¹Ýº¹ ½ÃÇàÇÏ¿© ³ôÀº ºóµµ·Î ¼±ÅÃµÈ À¯ÀüÀÚµéÀ» ÀÌ¿ëÇÑ È¸±Í ¸ðÇüµéÀ» ¸¸µé°í, °¢ ¸ðÇüµé¿¡¼­ ¾ÈÁ¤ÀûÀ¸·Î ¼±ÅõǴ Ư¡ À¯ÀüÀÚµéÀ» ã°í, ±× À¯ÀüÀÚµéÀÌ À§¾ç¼º °á°ú°¡ ¾Æ´ÔÀ» ÀÔÁõÇÏ¿´´Ù. ¶ÇÇÑ, ȸ±Í¸ðÇü º° ¿¹ÃøÁö¼öÀÇ Á¤È®µµ¸¦ ½ÇÁ¦Áö¼ö¿ÍÀÇ »ó°ü°ü°è¸¦ ÀÌ¿ëÇØ ÃøÁ¤ÇÏ¿´´Âµ¥, ¼±ÅÃµÈ Æ¯Â¡ À¯ÀüÀÚµéÀÇ È¸±Í°è¼ö ºÎÈ£ÀÇ ºÐÆ÷°¡ Á¤È®µµ¿Í °ü·Ã¼ºÀ» º¸ÀÓÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
When large-scale gene expression data are analyzed using lasso regression, the estimation of regression coefficients may be unstable due to the highly correlated expression values between associated genes. This irregularity, in which the coefficients are reduced by L1 regularization, causes difficulty in variable selection. To address this problem, we propose a regression model which exploits the repetitive bootstrapping of gene expression values prior to lasso regression. The genes selected with high frequency were used to build each regression model. Our experimental results show that several genes were consistently selected in all regression models and we verified that these genes were not false positives. We also identified that the sign distribution of the regression coefficients of the selected genes from each model was correlated to the real dependent variables.
Å°¿öµå(Keyword) ȸ±ÍºÐ¼®   º¯¼ö¼±Åà  ¶ó½î   ºÎÆ®½ºÆ®·¦   regression   feature selection   lasso   bootstrapping  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå