• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ¾Ï ¿¹Èĸ¦ È¿°úÀûÀ¸·Î ¿¹ÃøÇϱâ À§ÇÑ Node2Vec ±â¹ÝÀÇ À¯ÀüÀÚ ¹ßÇö·® À̹ÌÁö Ç¥Çö±â¹ý
¿µ¹®Á¦¸ñ(English Title) A Node2Vec-Based Gene Expression Image Representation Method for Effectively Predicting Cancer Prognosis
ÀúÀÚ(Author) ÃÖÁ¾È¯   ¹Ú»óÇö   Jonghwan Choi   Sanghyun Park  
¿ø¹®¼ö·Ïó(Citation) VOL 08 NO. 10 PP. 0397 ~ 0402 (2019. 10)
Çѱ۳»¿ë
(Korean Abstract)
¾Ï ȯÀÚ¿¡°Ô ÀûÀýÇÑ Ä¡·á°èȹÀ» Á¦°øÇϱâ À§ÇØ ¾ÏÀÇ ÁøÇà¾ç»ó ¶Ç´Â ȯÀÚÀÇ »ýÁ¸ ±â°£ µî¿¡ ÇØ´çÇϴ ȯÀÚÀÇ ¿¹Èĸ¦ Á¤È®È÷ ¿¹ÃøÇÏ´Â °ÍÀº »ý¹°Á¤º¸ÇÐ ºÐ¾ß¿¡¼­ ´Ù·ç´Â Áß¿äÇÑ µµÀü °úÁ¦ Áß ÇϳªÀÌ´Ù. ¸¹Àº ¿¬±¸¿¡¼­ ¾Ï ȯÀÚÀÇ À¯ÀüÀÚ ¹ßÇö·® µ¥ÀÌÅ͸¦ ÀÌ¿ëÇÏ¿© ȯÀÚÀÇ ¿¹Èĸ¦ ¿¹ÃøÇÏ´Â ±â°èÇÐ ½À ¸ðµ¨µéÀÌ ¸¹ÀÌ Á¦¾ÈµÇ¾î ¿À°í ÀÖ´Ù. À¯ÀüÀÚ ¹ßÇö·® µ¥ÀÌÅÍ´Â ¾à 17,000°³ÀÇ À¯ÀüÀÚ¿¡ ´ëÇÑ ¼öÄ¡°ªÀ» °®´Â °íÂ÷¿øÀÇ ¼öÄ¡Çü ÀÚ·áÀ̱⿡, ±âÁ¸ÀÇ ¿¬±¸µéÀº Ư¡ ¼±Åà ¶Ç´Â Â÷¿ø Ãà¼Ò Àü·«À» ÀÌ¿ëÇÏ¿© ¿¹Ãø ¸ðµ¨ÀÇ ¼º´É Çâ»óÀ» µµ¸ðÇÏ¿´´Ù. ±×·¯³ª ÀÌ·¯ÇÑ Á¢±Ù¹ýÀº Ư¡ ¼±Åðú ¿¹Ãø ¸ðµ¨ÀÇ ÈÆ·Ã ÀÌ ºÐ¸®µÇ¾î À־, ±â°èÇнÀ ¸ðµ¨Àº ¼±º°µÈ À¯ÀüÀÚµéÀÌ »ý¹°ÇÐÀûÀ¸·Î ¾î¶² °ü°è°¡ ÀÖ´ÂÁö ¾Ë±â°¡ ¾î·Æ´Ù. º» ¿¬±¸¿¡¼­´Â À¯ÀüÀÚ ¹ßÇö·® µ¥ÀÌÅ͸¦ À̹ÌÁö ÇüÅ·Πº¯È¯ÇÏ¿© ¿¹ÈÄ ¿¹ÃøÀÌ È¿°úÀûÀ¸·Î Ư¡ ¼±Åà ¹× ¿¹ÈÄ ¿¹ÃøÀ» ¼öÇàÇÒ ¼ö ÀÖ´Â ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. À¯ÀüÀÚµé »çÀÌÀÇ »ý¹°ÇÐÀû »óÈ£ÀÛ¿ë °ü°è¸¦ À¯ÀüÀÚ ¹ßÇö·® µ¥ÀÌÅÍ¿¡ ÅëÇÕÇϱâ À§ÇØ Node2VecÀ» È°¿ëÇÏ¿´À¸¸ç, 2Â÷¿ø À̹ÌÁö·Î Ç¥ÇöµÈ ¹ßÇö·® µ¥ÀÌÅ͸¦ È¿°úÀûÀ¸·Î ÇнÀÇÒ ¼ö ÀÖµµ·Ï ÇÕ¼º°ö ½Å°æ¸Á ¸ðµ¨À» »ç¿ëÇÏ¿´´Ù. Á¦¾ÈÇÏ´Â ¸ðµ¨ÀÇ ¼º´ÉÀº ÀÌÁß ±³Â÷°ËÁõÀ» ÅëÇØ Æò°¡µÇ¾ú°í, À¯ÀüÀÚ ¹ßÇö·® µ¥ÀÌÅ͸¦ ±×´ë·Î ÀÌ¿ëÇÏ´Â ±â°èÇнÀ ¸ðµ¨º¸´Ù ¿ì¿ùÇÑ ¿¹ÈÄ ¿¹Ãø Á¤È®µµ¸¦ °¡Áö´Â °ÍÀÌ È®ÀεǾú´Ù. Node2VecÀ» ÀÌ¿ëÇÑ À¯ÀüÀÚ ¹ßÇö·®ÀÇ »õ·Î¿î À̹ÌÁö Ç¥Çö¹ýÀº Ư¡ ¼±ÅÃÀ¸·Î ÀÎÇÑ Á¤º¸ÀÇ ¼Õ½ÇÀÌ ¾ø¾î ¿¹Ãø ¸ðµ¨ÀÇ ¼º´ÉÀ» ³ôÀÏ ¼ö ÀÖÀ¸¸ç, ÀÌ·¯ÇÑ Á¢±Ù¹ýÀÌ °³ÀÎ ¸ÂÃãÇü ÀÇÇÐÀÇ ¹ßÀü¿¡ À̹ÙÁöÇÒ °ÍÀ¸·Î ±â´ëÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Accurately predicting cancer prognosis to provide appropriate treatment strategies for patients is one of the critical challenges in bioinformatics. Many researches have suggested machine learning models to predict patients¡¯ outcomes based on their gene expression data. Gene expression data is high-dimensional numerical data containing about 17,000 genes, so traditional researches used feature selection or dimensionality reduction approaches to elevate the performance of prognostic prediction models. These approaches, however, have an issue of making it difficult for the predictive models to grasp any biological interaction between the selected genes because feature selection and model training stages are performed independently. In this paper, we propose a novel two-dimensional image formatting approach for gene expression data to achieve feature selection and prognostic prediction effectively. Node2Vec is exploited to integrate biological interaction network and gene expression data and a convolutional neural network learns the integrated two-dimensional gene expression image data and predicts cancer prognosis. We evaluated our proposed model through double cross-validation and confirmed superior prognostic prediction accuracy to traditional machine learning models based on raw gene expression data. As our proposed approach is able to improve prediction models without loss of information caused by feature selection steps, we expect this will contribute to development of personalized medicine.
Å°¿öµå(Keyword) »ý¹°Á¤º¸ÇР  À¯ÀüÀÚ ¹ßÇö·®   Node2Vec   ¾Ï ¿¹ÈÄ ¿¹Ãø   ¸ÂÃãÇü ÀÇÇР  Bioinformatics   Gene Expression   Node2Vec   Cancer Prognostic Prediction   Personalized Medicine  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå