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

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ÇÐȸÁö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ÇÐȸÁö > µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) Æ®·£½ºÆ÷¸Ó ±â¹Ý ¾ÐŸ¸Ó-´Ü¹éÁú »óÈ£ÀÛ¿ë ¿¹Ãø ºÐ·ù±â¿Í À¯Àü¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇÑ ¾ÐŸ¸Ó Èĺ¸ ¼­¿­ »ý¼º ½Ã½ºÅÛ
¿µ¹®Á¦¸ñ(English Title) Aptamer candidate sequence generation system using transformer-based aptamer-protein interaction prediction classifier and genetic algorithm
ÀúÀÚ(Author) ½ÅÀÎö   ÃÖÁ¤ÈÆ   ÇÑ¿¬¼ö   ±ÇÁØÈ£   ¼Û±æÅ   Incheol Shin   Jeonghoon Choi   Yeonsu Han   Joonho Kwon   Giltae Song  
¿ø¹®¼ö·Ïó(Citation) VOL 39 NO. 01 PP. 0059 ~ 0071 (2023. 04)
Çѱ۳»¿ë
(Korean Abstract)
Äڷγª19ÀÇ À¯ÇàÀ¸·Î ¹é½Å, Ä¡·áÁ¦, Áø´ÜÅ°Æ®¿Í °°Àº ½Å¾à °³¹ßÀÇ Á߿伺ÀÌ °­Á¶µÇ°í ÀÖ°í, ½Å¼ÓÇÏ°í È¿°ú°¡ ¶Ù¾î³­ ½Å¾àÀ» °³¹ßÇϱâ À§ÇÑ ÀΰøÁö´É ±â¼ú Àû¿ëµµ È®´ëµÇ°í ÀÖ´Ù. ÀÌ·¯ÇÑ ½Å¾à °³¹ßÀÇ ÇÑ °¡Áö ¹æ¹ýÀ¸·Î Â÷¼¼´ë ¹ÙÀÌ¿À ¹°ÁúÀÎ ¡®¾ÐŸ¸Ó¡¯¸¦ ÀÌ¿ëÇÏ´Â ¹æ¹ýÀÌ °ü½ÉÀ» ¹Þ°í ÀÖ´Ù. ¾ÐŸ¸Ó´Â 3Â÷¿ø ±¸Á¶¸¦ °¡Áö´Â ´ÜÀÏ °¡ ´Ú ¿Ã¸®°í ´ºÅ¬·¹¿ÀŸÀ̵å·Î Ç¥Àû ´Ü¹éÁú¿¡ ƯÀÌÀûÀ¸·Î °áÇÕÇϴ Ư¡ÀÌ ÀÖ´Ù. ±×¸®°í ¾ÐŸ¸Ó´Â ±âÁ¸ ½Å¾à °³¹ß¿¡ È°¿ëµÇ´Â ¹ÙÀÌ¿À ¹°Áúº¸´Ù ¾ÈÁ¤¼º°ú »ý»ê¼ºÀÌ ³ôÀ¸¹Ç·Î °¨¿°º´ ½ÇÇè½Ç °Ë»ç, ¾Ï Ä¡·áÁ¦ µî ´Ù¾çÇÑ ½Å¾à °³¹ß ºÐ¾ß¿¡¼­ È°¿ëµÇ°í ÀÖ´Ù. ±×·¯³ª ¾ÐŸ¸Ó Èĺ¸ ¼­¿­À» ¹ß±¼Çϱâ À§ÇÑ ´ëÇ¥ÀûÀÎ ½ÇÇèÀÎ SELEX´Â Ç¥Àû ´Ü ¹éÁú¿¡ °áÇÕÇÏ´Â ¾ÐŸ¸Ó Èĺ¸ ¹°ÁúÀ» ã´Â µ¥ ¸¹Àº ½Ã°£ÀÌ °É¸°´Ù´Â ´ÜÁ¡ÀÌ ÀÖ´Ù. º» ³í¹®¿¡¼­´Â ¾ÐŸ¸Ó Èĺ¸ ¼­¿­ ¹ß±¼¿¡ ¸¹Àº ½Ã°£ÀÌ °É¸®´Â SELEX ½ÇÇèÀÇ ´ÜÁ¡À» º¸¿ÏÇϱâ À§ÇÑ ÄÄÇ»ÅÍ ½Ã¹Ä·¹ÀÌ¼Ç ±â¹Ý ¿¬±¸¸¦ ÁøÇàÇÏ ¿´´Ù. ³í¹®¿¡¼­´Â ¾ÐŸ¸Ó Èĺ¸ ¼­¿­ ¹ß±¼À» À§ÇÑ Æ®·£½ºÆ÷¸Ó(Transformer) ±â¹Ý ¾ÐŸ¸Ó-´Ü¹éÁú »óÈ£ÀÛ¿ë ¿¹ Ãø ºÐ·ù ¸ðµ¨À» °³¹ßÇÏ¿´°í, ÀÌ¿Í À¯Àü¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇÑ ¾ÐŸ¸Ó Èĺ¸ ¼­¿­ »ý¼º ½Ã½ºÅÛÀ» Á¦¾ÈÇÑ´Ù. ¼³°èÇÑ ½Ã½ºÅÛÀ» ÀÌ¿ëÇÏ¿© ´ºÅ¬·¹¿ÀŸÀÌµå ¼­¿­À» »ý¼ºÇÒ ¼ö ÀÖ¾ú°í, »ý¼ºµÈ Èĺ¸ ¼­¿­µéÀÇ Ç°Áú ÃøÁ¤À» À§ÇØ ZDOCK ºÐÀÚ ±¸Á¶ µµÅ· ½Ã¹Ä·¹À̼ÇÀ» ÀÌ¿ëÇÏ¿´´Ù. ±× °á°ú, »ý¼ºµÈ Èĺ¸ ¼­¿­µéÀÌ ½ÇÁ¦ ¾ÐŸ¸Óµéº¸´Ù µµÅ· Á¡¼ö°¡ ºñ½ÁÇϰųª ³ôÀº °ÍÀ» È®ÀÎÇÒ ¼ö ÀÖ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
Due to the COVID-19 Pandemic, the discovery of drugs, vaccines, and diagnosis kits has been one of major research topics. To improve the efficiency of the drug discovery, artificial intelligence has been actively applied in the field. Aptamers, one of next-generation biomaterials in the drug discovery, attracts a lot of attention in recent decades. Aptamers are single-strand oligonucleotides that comprise tertiary structures and bind to specific target proteins. Aptamers are considered safer and more stable than traditional biomaterials. Therefore, Aptamers are used in various new drug development fields, such as laboratory tests for infectious diseases and cancer treatments. However, SELEX, a representative experiment for aptamer discovery, face at challenges since it takes a lot of time to determine aptamer sequences that bind to a given target protein. In this study, we developed a computer-based method to reduce the cost for aptamer discovery. And we also developed a transformer-based aptamer-protein interaction prediction classification model for discovering aptamer candidate sequences, and propose a system for generating aptamer candidate sequences using genetic algorithms. Nucleotide sequences could be generated using the designed system, and a molecular structure docking simulation called ZDOCK was used to measure the quality of the generated candidate sequences. As a result, generated sequences were confirmed that the docking score was similar or higher than that of the actual aptamers.
Å°¿öµå(Keyword) ½Å¾à °³¹ß   ¾ÐŸ¸Ó-´Ü¹éÁú »óÈ£ÀÛ¿ë   ¸Ó½Å ·¯´×   µö ·¯´×   Æ®·£½ºÆ÷¸Ó   À¯Àü¾Ë°í¸®Áò   Drug Discovery   Aptamer-Protein Interaction   Machine Learning   Deep Learning   Transformer   Genetic Algorithm  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå