• Title/Summary/Keyword: ADAM 10

Search Result 245, Processing Time 0.027 seconds

Novel Optimizer AdamW+ implementation in LSTM Model for DGA Detection

  • Awais Javed;Adnan Rashdi;Imran Rashid;Faisal Amir
    • International Journal of Computer Science & Network Security
    • /
    • v.23 no.11
    • /
    • pp.133-141
    • /
    • 2023
  • This work take deeper analysis of Adaptive Moment Estimation (Adam) and Adam with Weight Decay (AdamW) implementation in real world text classification problem (DGA Malware Detection). AdamW is introduced by decoupling weight decay from L2 regularization and implemented as improved optimizer. This work introduces a novel implementation of AdamW variant as AdamW+ by further simplifying weight decay implementation in AdamW. DGA malware detection LSTM models results for Adam, AdamW and AdamW+ are evaluated on various DGA families/ groups as multiclass text classification. Proposed AdamW+ optimizer results has shown improvement in all standard performance metrics over Adam and AdamW. Analysis of outcome has shown that novel optimizer has outperformed both Adam and AdamW text classification based problems.

Gene Expression of ADAM-8, 9, 10, 12, 15, 17 and ADAMTS-1 in Ovariectomized Mice Uteri (난소를 제거한 생쥐 자궁조직에서의 ADAM-8, 9, 10, 12, 15, 17 그리고 ADAMTS-1의 유전자 발현)

  • Kim, Ji-Young;Huh, Ju-Young;Kim, Hae-Kwon
    • Development and Reproduction
    • /
    • v.8 no.2
    • /
    • pp.99-111
    • /
    • 2004
  • The present study aimed to investigate whether the expression of ADAM-8, 9, 10, 12, 15, 17 and ADAMTS-1 genes is controlled by ovarian steroid hormones. Ovariectomized mice were injected with 17 ${\beta}$-estradiol ($E_2$), progesterone ($P_4$, or $E_2+P_4$. Uterine tissues were processed for RT-PCR and immunoblotting. The results of RT-PCR showed that administration of $E_2$ increases the level of ADAM-8, 12 and ADAM17 expression compared to $P_4$ or control group. In contrast, administration of $P_4$ markedly stimulated the expression of ADAM-9, 10, 15 and ADAMTS-1, whereas $E_2$ did not. Immunoblotting analysis using anti-mouse ADAM polyclonal antibodies demonstrated that $E_2$ alone or $E_2+P_4$ treatment results in the strong expression of ADAM-8, 12 and ADAM17 proteins but $P_4$ alone or control group gave weak expression. In contrast, $P_4$ alone or $E_2$ plus $P_4$ treatment increased the expression level of ADAM-9, 10, 15 and DAMTS-1 proteins. $E_2$ alone or control group did not increase the expression. These results indicate that expression of ADAM-8, 12 and ADAM17 genes is upregulated by $E_2$ and that of ADAM-9, 10, 15 and ADAMTS-1 gene is upregulated by $P_4$.

  • PDF

난소를 제거한 생쥐 자궁조직에서 ADAM-8, -9, -10, -12, -15, -17, -TS1의 발현

  • 김지영;배인희;이승재;최영민;김해권
    • Proceedings of the Korean Society of Developmental Biology Conference
    • /
    • 2003.10a
    • /
    • pp.59-59
    • /
    • 2003
  • ADAM은 metalloprotease/disintegrin domain을 가진 transmembrane glycoprotein으로서 지금까지 30종류 이상의 ADAM 및 10종류 이상의 ADAM-TS 단백질이 알려져 있다. 이들의 기능은 포유동물의 수정 시 sperm-egg binding과 fusion, myoblast fusion, integrin과의 결합 등에 직접 관여하거나, TNF-alpha 등의 생체신호전달물질이 세포로부터 분비될 때에 이들의 구조를 변화시켜 활성화시키는 효소로서의 작용, 그리고 dendritic cell differentiation 등에 관여하는 것으로 알려져 있다. 본 연구에서는 난소가 제거된 생쥐를 이용하여 자궁조직의 ADAM-8, -9, -10, -12, -15, -17 그리고 -TS1의 gene의 발현이 $17 \beta $-estradiol에 의하여 조절되는 지를 알아보았다. 생후 6 - 8주 된 암컷 생쥐의 난소를 제거하고, 2 주 후에 $17 \beta $-estradiol ($E_2$), progesterone ($P_4$) 혹은 이 둘 혼합액 ($E_2 + P_4$)을 sesame oil에 녹여 근육주사하였다. 2, 6, 12 시간 후 각각 자궁 조직을 얻고 유전자의 발현 양상을 알아보기 위하여 시료로부터 total RNA을 추출하여 역전사 중합효소반응 (RT-PCR)을 실시하였다. Densitometry를 이용, rpL7에 대한 ADAMS의 mRNA 발현 양을 상대적으로 분석하였다. 그 결과 ADAM-8과 -15는 6시간째에서, ADAM-10과 -TS1은 2시간째에서 sesame oil을 주사하거나 $P_4$만을 주사한 군보다 E$_2$를 주사한 군에서 mRNA의 양이 현저하게 증가하였고 ADAM-12는 2시간째에서 ADAM-17은 12시간째에서 sesame oil을 주사하거나 $P_$만을 주사한 군보다 E$_2$를 주사한 군에서 mRNA의 양이 현저하게 증가하였다. 이러한 결과로 미루어 ADAM-8, -10, -15 그리고 TS1은 progesterone에 의하여, ADAM-12와 17은 $17 \beta $-estradiol에 의하여 유전자의 발현이 upregulation 되는 것으로 생각되어진다.

  • PDF

착상과 관련한 생쥐자궁조직에서의 ADAM-8, 9, 10, 12, 15, 17, TS1의 mRNA 및 단백질의 발현

  • 김지영;허주영;이승재;양현원;최영민;김해권
    • Proceedings of the Korean Society of Embryo Transfer Conference
    • /
    • 2002.11a
    • /
    • pp.107-107
    • /
    • 2002
  • ADAM은 metalloprotease/disintegrin domain을 가진 transmembrane glycoprotein 으로서 지금까지 30개 이상의 ADAM 및 10개 이상의 ADAMTS 단백질이 알려져 있다. 이들의 기능은 포유동물의 수정시 sperm-egg binding과 fusion, myoblast fusion, integrin과의 결합 등에 직접 관여하거나, TNF-alpha 등의 생체 신호전달물질이 세포로부터 분비될 때에 이들의 구조를 변화시켜 활성화시키는 효소작용, 그리고 dendritic cell differentiation 등에 관여하는 것으로 알려져있다. 그러나 자궁내막 조직에서의 유전자 및 단백질 발현 여부에 관해서는 거의 보고되어 있지 않고 있다. 먼저 RT-PCR 방법을 이용하여 자궁에서 mRNA의 양을 $\beta$-actin의 양에 대하여 상대적으로 측정한 결과, 임신 1일부터 5일까지는 ADAM-9, 10, 17, TS1의 mRNA 경우 거의 비슷하게 발현되었으며 ADAM-8과 15는 3일째, ADAM-12는 2일째와 4일째에 현저하게 증가하였다 임신 6일부터 8일까지의 자궁조직을 각각 embryo가 착상된 곳과 그렇지 않은 곳으로 나누어 조사한 결과 상대적으로 착상이 된 곳에서 mRNA가 많이 발현 되었으며 특히 ADAM-8, 12, 15의 mRNA의 경우 현저한 차이를 보였다. Immunoblotting 방법을 이용하여 임신 1일부터 5일까지의 단백질의 발현 양상을 조사한 결과 임신 ADAM-8은 3일 이후 감소되는 양상을 보였으며 ADAM-9, 15, TS1은 5일째에 증가하는 양상을 보였다. ADAM-10은 2일째 감소하다가 다시 증가하고 ADAM-12, 17은 3, 4일째 증가하다가 5일째 감소하는 상을 보였다. 한편 임신 6일부터 8일까지는 embryo가 착상된 곳이 그렇지 않은 곳보다 조사된 모든 ADAMs 단백질이 상대적으로 많이 발현되는 양상을 보였다. 이러한 결과로 미루어 ADAMs은 임신 초기 착상과정과 임신 단계에 따른 자궁의 조직 재구성에 중요한 역할을 할 것으로 생각된다.

  • PDF

Expression of ADAM-8, 9, 10, 12, 15, 17 and ADAMTS-1 Genes in Mouse Uterus During Periimplantation Period (착상 전후시기의 생쥐 자궁조직에서의 ADAM-8, 9, 10, 12, 15, 17과 ADAMTS-1 유전자의 발현)

  • Kim, Ji Young;Koog, Min Ji;Bae, In Hee;Kim, Haekwon
    • Clinical and Experimental Reproductive Medicine
    • /
    • v.32 no.1
    • /
    • pp.33-46
    • /
    • 2005
  • 연구목적: ADAMs은 metalloprotease/disintegrin domain을 가진 transmemebrane glycoprotein으로써 지금까지 30개 이상의 ADAM 및 10개 이상의 ADAMTS가 알려져 있다. 이들의 기능은 포유동물의 수정 시 sperm-egg binding과 fusion, myoblast fusion, integrin과의 결합 등에 직접 관여하거나, TNF-alpha 등의 생체신호전달물질이 세포로부터 분비될 때에 이들의 구조를 변화시켜 활성화시키는 효소작용, 그리고 dendritic cell differentiation 등에 관여하는 것으로 알려져 있다. 그러나 자궁내막 조직에서의 유전자 및 단백질 발현 여부에 관해서는 거의 보고되어 있지 않고 있다. 본 연구에서는 착상 전후 시기의 생쥐 자궁조직에서 ADAM-8, 9, 10, 12, 15, 17 그리고 ADAMTS-1의 유전자가 발현하는 지를 알아보았다. 연구 재료 및 방법: 본 연구에서는 생쥐의 자궁조직을 대상으로 ADAM-8, 9, 10, 12, 15, 17 그리고 ADAMTS-1을 선정하여, 초기 임신 기간에서의 유전자 발현 여부를 조사하였고 이 결과를 바탕으로 자궁조직에서의 이들 유전자들의 생리적인 기능을 규명하고자 하였다. 결 과: 임신한 생쥐 자궁조직에서의 ADAM-8, 9, 10, 12, 15, 17 그리고 ADAMTS-1의 유전자 및 단백질의 발현 양상을 RT-PCR 방법을 이용하여 알아본 결과, 조사된 ADAM 종류와 임신 날짜별로 다르게 나타났다. ADAM-8의 유전자 전사체는 임신 1일째 매우 강하게 발현되었으나 임신 3일째로 진행되면서 감소하다가 이후 다시 임신 5일째가 되면서 증가하는 양상을 보였다. ADAM-9, 10, 17 그리고 ADAMTS-1의 경우는 임신 1일째에서 5일째까지 유전자의 발현 양상이 크게 변하지 않았고 ADAM-12와 ADAM-15의 유전자 전사체는 임신 1일에서 5일로 진행되면서 현저하게 증가되는 양상을 보였다. 이후 임신 6일에서 8일에서는 생쥐 배아가 착상된 부위와 비 착상부위로 나누어 유전자의 발현 양상을 관찰한 결과, 조사된 ADAM 모두 비착상 부위보다 착상부위에서 유전자 전사체의 발현이 크게 증가되는 것으로 나타났다. 결 론: 이상의 결과로 미루어 ADAM 유전자는 임신초기 착상과정과 임신 단계에 따른 자궁의 조직 재구성에 중요한 역할을 할 것으로 생각된다.

The ADAM15 ectodomain is shed from secretory exosomes

  • Lee, Hee Doo;Kim, Yeon Hyang;Koo, Bon-Hun;Kim, Doo-Sik
    • BMB Reports
    • /
    • v.48 no.5
    • /
    • pp.277-282
    • /
    • 2015
  • We demonstrated previously that a disintegrin and metalloproteinase 15 (ADAM15) is released into the extracellular space as an exosomal component, and that ADAM15-rich exosomes have tumor suppressive functions. However, the suppressive mechanism of ADAM15-rich exosomes remains unclear. In this study, we show that the ADAM15 ectodomain is cleaved from released exosomes. This shedding process of the ADAM15 ectodomain was dramatically enhanced in conditioned ovarian cancer cell medium. Proteolytic cleavage was completely blocked by phenylmethylsulfonyl fluoride, indicating that a serine protease is responsible for exosomal ADAM15 shedding. Experimental evidence indicates that the ADAM15 ectodomain itself has comparable functions with those of ADAM15-rich exosomes, which effectively inhibit vitronectininduced cancer cell migration and activation of the MEK/extracellular regulated kinase signaling pathway. We present a tumor suppressive mechanism for ADAM15 exosomes and provide insight into the functional significance of exosomes that generate tumor-inhibitory factors. [BMB Reports 2015; 48(5): 277-282]

Performance Analysis of Simulation of Asian Dust Observed in 2010 by the all-Season Dust Forecasting Model, UM-ADAM2 (사계절 황사단기예측모델 UM-ADAM2의 2010년 황사 예측성능 분석)

  • Lee, Eun-Hee;Kim, Seungbum;Ha, Jong-Chul;Chun, Youngsin
    • Atmosphere
    • /
    • v.22 no.2
    • /
    • pp.245-257
    • /
    • 2012
  • The Asian dust (Hwangsa) forecasting model, Asian Dust Aerosol Model (ADAM) has been modified by using satelliate monitoring of surface vegetation, which enables to simulate dusts occuring not only in springtime but also for all-year-round period. Coupled with the Unified Model (UM), the operational weather forecasting model at KMA, UM-ADAM2 was implemented for operational dust forecasting since 2010, with an aid of development of Meteorology-Chemistry Interface Processor (MCIP) for usage UM. The performance analysis of the ADAM2 forecast was conducted with $PM_{10}$ concentrations observed at monitoring sites in the source regions in China and the downstream regions of Korea from March to December in 2010. It was found that the UM-ADAM2 model was able to simulate quite well Hwangsa events observed in spring and wintertime over Korea. In the downstream region of Korea, the starting and ending times of dust events were well-simulated, although the surface $PM_{10}$ concentration was slightly underestimated for some dust events. The general negative bias less than $35{\mu}g\;m^{3}$ in $PM_{10}$ is found and it is likely to be due to other fine aerosol species which is not considered in ADAM2. It is found that the correlation between observed and forecasted $PM_{10}$ concentration increases as forecasting time approaches, showing stably high correlation about 0.7 within 36 hr in forecasting time. This suggests the possibility that there is potential for the UM-ADAM2 model to be used as an operational Asian dust forecast model.

Acoustic Full-waveform Inversion using Adam Optimizer (Adam Optimizer를 이용한 음향매질 탄성파 완전파형역산)

  • Kim, Sooyoon;Chung, Wookeen;Shin, Sungryul
    • Geophysics and Geophysical Exploration
    • /
    • v.22 no.4
    • /
    • pp.202-209
    • /
    • 2019
  • In this study, an acoustic full-waveform inversion using Adam optimizer was proposed. The steepest descent method, which is commonly used for the optimization of seismic waveform inversion, is fast and easy to apply, but the inverse problem does not converge correctly. Various optimization methods suggested as alternative solutions require large calculation time though they were much more accurate than the steepest descent method. The Adam optimizer is widely used in deep learning for the optimization of learning model. It is considered as one of the most effective optimization method for diverse models. Thus, we proposed seismic full-waveform inversion algorithm using the Adam optimizer for fast and accurate convergence. To prove the performance of the suggested inversion algorithm, we compared the updated P-wave velocity model obtained using the Adam optimizer with the inversion results from the steepest descent method. As a result, we confirmed that the proposed algorithm can provide fast error convergence and precise inversion results.

Suppression of ADAM 10-induced Delta-1 Shedding Inhibits Cell Proliferation During the Chondro-Inhibitory Action of TGF-β3

  • Jin, Eun-Jung;Choi, Young-Ae;Sonn, Jong-Kyung;Kang, Shin-Sung
    • Molecules and Cells
    • /
    • v.24 no.1
    • /
    • pp.139-147
    • /
    • 2007
  • Although transforming growth factors (TGFs) are implicated in the process of endochondral ossification, which is initiated by the differentiation of mesenchymal cells into chondrocytes, it is not clear how $TGF-{\beta}3$ regulates the chondrogenic differentiation of limb bud mesenchymal cells. Here, differential display polymerase chain reaction (DD-PCR) screening and RT-PCR analysis revealed that transcripts of A Disintegrin And Metalloprotease 10 (ADAM 10) decreased during the chondro-inhibitory action of $TGF-{\beta}3$ on cultured chick leg bud mesenchymal cells. Electroporation of ADAM 10 morpholino antisense oligonucleotides inhibited the ectodomain shedding of delta-1, and cell proliferation and subsequent precartilage condensation, in a manner similar to that caused by $TGF-{\beta}3$. The suppression of mesenchymal cell proliferation induced by $TGF-{\beta}3$ and ADAM 10 morpholino antisense oligonucleotides was reversed by activation of ADAM 10 with phorbol 12-myristate 13-acetate (PMA) or knockdown of Notch-1 with siRNA. Collectively, these data indicate that, in cultured chick leg bud mesenchyme cells, $TGF-{\beta}3$ downregulates ADAM 10 and inhibits cell proliferation and subsequent precartilage condensation by inhibiting the ectodomain shedding of delta-1, and that this results in the activation of Notch signaling.

FAST-ADAM in Semi-Supervised Generative Adversarial Networks

  • Kun, Li;Kang, Dae-Ki
    • International Journal of Internet, Broadcasting and Communication
    • /
    • v.11 no.4
    • /
    • pp.31-36
    • /
    • 2019
  • Unsupervised neural networks have not caught enough attention until Generative Adversarial Network (GAN) was proposed. By using both the generator and discriminator networks, GAN can extract the main characteristic of the original dataset and produce new data with similarlatent statistics. However, researchers understand fully that training GAN is not easy because of its unstable condition. The discriminator usually performs too good when helping the generator to learn statistics of the training datasets. Thus, the generated data is not compelling. Various research have focused on how to improve the stability and classification accuracy of GAN. However, few studies delve into how to improve the training efficiency and to save training time. In this paper, we propose a novel optimizer, named FAST-ADAM, which integrates the Lookahead to ADAM optimizer to train the generator of a semi-supervised generative adversarial network (SSGAN). We experiment to assess the feasibility and performance of our optimizer using Canadian Institute For Advanced Research - 10 (CIFAR-10) benchmark dataset. From the experiment results, we show that FAST-ADAM can help the generator to reach convergence faster than the original ADAM while maintaining comparable training accuracy results.