Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
ÇѱÛÁ¦¸ñ(Korean Title) |
À¯ÀüÀÚ ÀÓº£µùÀ» ÀÌ¿ëÇÑ ¾Ï ¿¹ÈÄ ¿¹Ãø ¹æ¹ý |
¿µ¹®Á¦¸ñ(English Title) |
A Method for Cancer Prognosis Prediction Using Gene Embedding |
ÀúÀÚ(Author) |
±èÇöÁö
¾ÈÀç±Õ
Hyunji Kim
Jaegyoon Ahn
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 48 NO. 07 PP. 0842 ~ 0849 (2021. 07) |
Çѱ۳»¿ë (Korean Abstract) |
¾ÏÀÇ ¿¹ÈÄ¿Í °ü·ÃÀÌ ÀÖ´Â À¯ÀüÀÚ¸¦ ½Äº°ÇÏ°í À̸¦ ÀÌ¿ëÇÏ¿© ¾ÏȯÀÚÀÇ ¿¹Èĸ¦ ¿¹ÃøÇÏ´Â °ÍÀº ȯÀÚ¿¡°Ô È¿°úÀûÀÎ Ä¡·á¹æ¹ýÀ» Á¦°øÇϴµ¥ ±â¿©ÇÏ´Â ¹Ù°¡ Å©´Ù. À¯ÀüÀÚ ¹ßÇö µ¥ÀÌÅ͸¦ ÀÌ¿ëÇÏ¿© ¿¹ÈÄ °ü·Ã À¯ÀüÀÚ¸¦ Ž»öÇϰųª ¾ÏÀÇ ¿¹Èĸ¦ ¿¹ÃøÇϱâ À§ÇÑ ´Ù¾çÇÑ ¿¬±¸¹æ¹ýµéÀÌ Á¦½ÃµÇ¾úÀ¸¸ç, ÃÖ±Ù¿¡´Â µö·¯´×À» ºñ·ÔÇÑ ¸Ó½Å·¯´× ±â¹ýµéÀÌ ÁýÁßÀûÀ¸·Î ¿¬±¸µÇ°í ÀÖ´Ù. ÇÏÁö¸¸ À¯ÀüÀÚ ¹ßÇö·® µ¥ÀÌÅÍ¿¡ ±â°èÇнÀ ¹æ¹ýÀ» Àû¿ëÇÏ´Â °ÍÀº »ç¿ë °¡´ÉÇÑ »ùÇÃÀÇ ¼ö°¡ Àû°í À¯ÀüÀÚÀÇ ¼ö°¡ ¸¹´Ù´Â ±Ùº»ÀûÀÎ ¹®Á¦°¡ ÀÖ´Ù. º» ¿¬±¸¿¡¼´Â À¯ÀüÀÚ ³×Æ®¿öÅ© µ¥ÀÌÅ͸¦ Ãß°¡ÀûÀ¸·Î »ç¿ëÇÏ¿©, ¸¹Àº ¼öÀÇ ¹«ÀÛÀ§ À¯ÀüÀÚ °æ·Î¸¦ ÇнÀ µ¥ÀÌÅÍ »ç¿ëÇÔÀ¸·Î½á ÀûÀº ¼öÀÇ »ùÇÃÀ̶ó´Â ¹®Á¦¸¦ º¸¿ÏÇÏ°íÀÚ ÇÑ´Ù. º» ¿¬±¸¿¡¼ Á¦½ÃÇÏ´Â ¹æ¹ýÀ» ÀÌ¿ëÇÏ¿© 5°¡Áö ¾Ï¿¡ ´ëÇÑ À¯ÀüÀÚ ¹ßÇö µ¥ÀÌÅÍ¿Í À¯ÀüÀÚ ³×Æ®¿öÅ©¸¦ ÀÌ¿ëÇÏ¿© ¿¹ÈÄ Æ¯ÀÌÀû À¯ÀüÀÚ¸¦ ½Äº°ÇÏ°í ȯÀÚÀÇ ¿¹Èĸ¦ ¿¹ÃøÇÑ °á°ú, ´Ù¸¥ ±âÁ¸ ¹æ¹ýµé°ú ºñ±³ÇÏ¿© ³ôÀº Á¤È®µµ·Î ¿¹ÃøÀ» ÇÏ´Â °ÍÀ» È®ÀÎÇÒ ¼ö ÀÖ¾úÀ¸¸ç, ÀûÀº »ùÇÃÀ» »ç¿ëÇÑ ¿¹Ãø¿¡¼ ³ôÀº ¼º´ÉÀ» È®ÀÎÇÒ ¼ö ÀÖ¾ú´Ù. |
¿µ¹®³»¿ë (English Abstract) |
Identifying prognostic genes and using them to predict the prognosis of cancer patients can help provide them with more effective treatments. Many methods have been proposed to identify prognostic genes and predict cancer prognosis, and recent studies have focused on machine learning methods including deep learning. However, applying gene expression data to machine learning methods has the limitations of a small number of samples and a large number of genes. In this study, we additionally use a gene network to generate many random gene paths, which we used for training the model, thereby compensating for the small sample problem. We identified the prognostic genes and predicted the prognosis of patients using the gene expression data and gene networks for five cancer types and confirmed that the proposed method showed better predictive accuracy compared to other existing methods, and good performance on small sample data. |
Å°¿öµå(Keyword) |
±â°è ÇнÀ
¾Ï ¿¹ÈÄ ¿¹Ãø
¹ÙÀÌ¿À¸¶Ä¿
µö·¯´×
machine learning
cancer prognosis prediction
biomarker
deep learning
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|