• Clinical and Experimental Reproductive Medicine
• /
• 제26권3호
• /
• pp.407-417
• /
• 1999

Objective: Mammalian follicle cells are the most important somatic cells which help oocytes grow, mature and ovulate and thus are believed to provide oocytes with various functional and structural components. In the present study we have examined whether cumulus or granulosa cells might playa role in establishing the plasma membrane structure of mouse oocytes during meiotic maturation. Design: In particular the differential resistances of mouse oocytes against chymotrypsin treatment were examined following culture with or without cumulus or granulosa cells, or in these cell-conditioned media. Results: When mouse denuded oocytes, freed from their surrounding cumulus cells, were cultured in vitro for $17{\sim}18hr$ and then treated with 1% chymotrypsin, half of the oocytes underwent degeneration within 37.5 min ($t_{50}=37.5{\pm}7.5min$) after the treatment. In contrast cumulus-enclosed oocytes showed $t_{50}=207.0$. Similarly, when oocytes were co-cultured with cumulus cells which were not associated with the oocytes but present in the same medium, the $t_{50}$ of co-cultured oocytes was $177.5{\pm}13.1min$. Furthermore, when oocytes were cultured in the cumulus cell-conditioned medium, $t_{50}$ of these oocytes was $190.0{\pm}10.8min$ whereas $t_{50}$ of the oocytes cultured in M16 alone was $25.5{\pm}2.9min$. Granulosa cell-conditioned medium also increased the resistance of oocytes against chymotrypsin treatment such that $t_{50}$ of oocytes cultured in granulosa cell-conditioned medium was $152.5{\pm}19.0min$ while that of oocytes cultured in M16 alone was $70.0{\pm}8.2min$. To see what molecular components of follicle cell-conditioned medium are involved in the above effects, the granulosa cell-conditioned medium was separated into two fractions by using Microcon-10 membrane filter having a 10 kDa cut-off range. When denuded oocytes were cultured in medium containing the retentate, $t_{50}$ of the oocytes was $70.0{\pm}10.5min$. In contrast, $t_{50}$ of the denuded oocytes cultured in medium containing the filtrate was $142.0{\pm}26.5min$. $T_{50}$ of denuded oocytes cultured in medium containing both retentate and filtrate was $188.0{\pm}13.6min$. However, $t_{50}$ of denuded oocytes cultured in M16 alone was $70.0{\pm}11.0min$ and that of oocytes cultured in whole granulosa cell-conditioned medium was $156.0{\pm}27.9min$. When surface membrane proteins of oocytes were electrophoretically analyzed, no difference was found between the protein profiles of oocytes cultured in M16 alone and of those cultured in the filtrate. Conclusions: Based upon these results, it is concluded that mouse follicle cells secrete a factor(s) which enhance the resistance of mouse oocytes against a proteolytic enzyme treatment. The factor appears to be a small molecules having a molecular weight less than 10 kDa.

• 지능정보연구
• /
• 제23권1호
• /
• pp.95-108
• /
• 2017

최근 알파고의 등장으로 딥러닝 기술에 대한 관심이 고조되고 있다. 딥러닝은 향후 미래의 핵심 기술이 되어 일상생활의 많은 부분을 개선할 것이라는 기대를 받고 있지만, 주요한 성과들이 이미지 인식과 자연어처리 등에 국한되어 있고 전통적인 비즈니스 애널리틱스 문제에의 활용은 미비한 실정이다. 실제로 딥러닝 기술은 Convolutional Neural Network(CNN), Recurrent Neural Network(RNN), Deep Boltzmann Machine (DBM) 등 알고리즘들의 선택, Dropout 기법의 활용여부, 활성 함수의 선정 등 다양한 네트워크 설계 이슈들을 가지고 있다. 따라서 비즈니스 문제에서의 딥러닝 알고리즘 활용은 아직 탐구가 필요한 영역으로 남아있으며, 특히 딥러닝을 현실에 적용했을 때 발생할 수 있는 여러 가지 문제들은 미지수이다. 이에 따라 본 연구에서는 다이렉트 마케팅 응답모델, 고객이탈분석, 대출 위험 분석 등의 주요한 분류 문제인 이진분류에 딥러닝을 적용할 수 있을 것인지 그 가능성을 실험을 통해 확인하였다. 실험에는 어느 포르투갈 은행의 텔레마케팅 응답여부에 대한 데이터 집합을 사용하였으며, 전통적인 인공신경망인 Multi-Layer Perceptron, 딥러닝 알고리즘인 CNN과 RNN을 변형한 Long Short-Term Memory, 딥러닝 모형에 많이 활용되는 Dropout 기법 등을 이진 분류 문제에 활용했을 때의 성능을 비교하였다. 실험을 수행한 결과 CNN 알고리즘은 비즈니스 데이터의 이진분류 문제에서도 MLP 모형에 비해 향상된 성능을 보였다. 또한 MLP와 CNN 모두 Dropout을 적용한 모형이 적용하지 않은 모형보다 더 좋은 분류 성능을 보여줌에 따라, Dropout을 적용한 CNN 알고리즘이 이진분류 문제에도 활용될 수 있는 가능성을 확인하였다.