µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
À¯ÀüÀÚ ¹ßÇö·® Â÷À̸¦ ÀÌ¿ëÇÑ ³×Æ®¿öÅ© ±â¹Ý Áúº´ °ü·Ã À¯ÀüÀÚ Å½»ö ±â¹ý |
¿µ¹®Á¦¸ñ(English Title) |
A Network-based Approach to Detect Disease-related Genes using Differentially Expressed Gene Analysis |
ÀúÀÚ(Author) |
±èÇöÁø
¾ÈÀç±Õ
¹Ú»óÇö
Hyunjin Kim
Jaegyoon Ahn
Sanghyun Park
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 28 NO. 03 PP. 0089 ~ 0101 (2012. 12) |
Çѱ۳»¿ë (Korean Abstract) |
¸¶ÀÌÅ©·Î¾î·¹ÀÌ µ¥ÀÌÅ͸¦ ºÐ¼®ÇÏ´Â ´ëÇ¥ÀûÀÎ ¹æ¹ý Áß ÇÑ°¡Áö´Â Â÷µî ¹ßÇö À¯ÀüÀÚ(Differentially Expressed Gene)µéÀ» ã´Â °ÍÀÌ´Ù. Â÷µî ¹ßÇö À¯ÀüÀÚ¶õ µÎ ½ÇÇè Á¶°Ç ÇÏ¿¡¼ »ùÇà ÁýÇÕÀÇ À¯ÀüÀÚ ¹ßÇö·®ÀÌ ¸¹ÀÌ Â÷À̳ª´Â À¯ÀüÀÚ¸¦ ÀǹÌÇÑ´Ù. ÇÏÁö¸¸ ±âÁ¸ÀÇ Â÷µî ¹ßÇö À¯ÀüÀÚ¸¦ ã´Â ¹æ¹ýµéÀº À¯ÀüÀÚ³¢¸® ÁÖ°í ¹Þ´Â ¿µÇâÀ» °í·ÁÇÏÁö ¾Ê¾Æ ±Ùº»ÀûÀÎ ÇѰ踦 Áö´Ï°í ÀÖ´Ù. ½ÇÁ¦·Î ±âÁ¸ ¹æ¹ýµé·Î, Áúº´°ú °ü·ÃµÇ¾î ÀÖ´Ù°í »ý¹°ÇÐÀû ½ÇÇèÀ¸·Î Áõ¸íµÈ À¯ÀüÀÚµéÀ» ¸¹ÀÌ Ã£¾Æ³»Áö ¸øÇÏ°í ÀÖ´Ù. ÀÌ·¯ÇÑ ÇѰ踦 ±Øº¹Çϱâ À§ÇØ º» ¿¬±¸¿¡¼´Â À¯ÀüÀÚ »çÀÌÀÇ »ó°ü°ü°è¸¦ °í·ÁÇÑ ´Ü¹éÁú-´Ü¹éÁú »óÈ£ÀÛ¿ë(Protein-Protein Interaction) ³×Æ®¿öÅ©¸¦ Àû¿ëÇÏ¿© À¯ÀüÀÚ °£¿¡ ¹ÌÄ¡´Â ¿µÇâÀ» ±âÁ¸ ¹æ¹ý¿¡ Ãß°¡ÇÔÀ¸·Î½á Â÷µî ¹ßÇö À¯ÀüÀÚ¸¦ °Ë»öÇÏ´Â »õ·Î¿î ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ÀÌ·¸°Ô ã¾Æ³½ À¯ÀüÀÚµé·Î Áúº´°ú °ü·ÃµÈ Ŭ·¡½º ºÐ·ù¸¦ ½ÃµµÇÑ °á°ú, ±âÁ¸ÀÇ ³×Æ®¿öÅ©Àû Á¢±Ù ¹æ¹ýÀ» Àû¿ëÇÏÁö ¾ÊÀº Â÷µî¹ßÇö À¯ÀüÀÚ¸¦ ã´Â ¹æ¹ýº¸´Ù ´õ ³ôÀº Á¤È®µµ¿Í AUC(Area Under Curve)¸¦ º¸¿´´Ù. ¶ÇÇÑ Á¡¼ö °ªÀÇ »óÀ§¿¡ À§Ä¡ÇØÀÖ´Â À¯ÀüÀÚµéÀÌ ÇØ´ç Áúº´°ú ¾ó¸¶³ª °ü·ÃµÇ¾î ÀÖ´ÂÁö¿¡ ´ëÇؼ ´Ù¸¥ Ư¼º ¼±ÅÃ(Feature Selection) ¹æ¹ýµé°ú ºñ±³Çغ¸¾ÒÀ» ¶§ ´õ ³·Àº p-value¸¦ ³ªÅ¸³¿À¸·Î½á º» ¿¬±¸ÀÇ ¹æ¹ýÀÌ Áúº´ °ü·Ã À¯ÀüÀÚ¸¦ Àß °Ë»öÇÑ´Ù´Â »ç½ÇÀ» º¸¿©ÁÖ¾ú´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
One of general method for microarray analysis is discovering differentially expressed genes. The differentially expressed gene is a gene which shows different expression levels between two conditions. However, existing methods for finding differentially expressed genes have a limitation. They cannot consider influences among genes. Specifically, they can hardly discover the biologically proved genes which are related to specific diseases. To get over the limitation, we propose a novel approach to discover disease-related genes using differentially expressed genes and protein-protein interaction network. The proposed approach uses protein-protein interaction to reflect the influences among genes. The approach showed better accuracy and AUC(Area Under Curve) value than a method which does not consider the influences among genes and showed lower p-value than other feature selection methods.
|
Å°¿öµå(Keyword) |
Ư¼º ¼±ÅÃ
Â÷µî ¹ßÇö À¯ÀüÀÚ
¸¶ÀÌÅ©·Î¾î·¹ÀÌ µ¥ÀÌÅÍ ºÐ¼®
Áúº´
»ý¹°Á¤º¸ÇÐ
Feature selection
Differentially expressed gene
Microarray analysis
Disease
Bioinformatics
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|