• 한국컴퓨터정보학회논문지
• /
• 제21권3호
• /
• pp.65-71
• /
• 2016

To reduce the expenses for development a novel drug, systems biology has been studied actively. Target prediction, a part of systems biology, contributes to finding a new purpose for FDA(Food and Drug Administration) approved drugs and development novel drugs. In this paper, we propose a classification model for predicting novel target genes based on relation between target genes and disease related genes. After collecting known target genes from TTD(Therapeutic Target Database) and disease related genes from OMIM(Online Mendelian Inheritance in Man), we analyzed the effect of target genes on disease related genes based on PPI(Protein-Protein Interactions) network. We focused on the distinguishing characteristics between known target genes and random target genes, and used the characteristics as features for building a classifier. Because our model is constructed using information about only a disease and its known targets, the model can be applied to unusual diseases without similar drugs and diseases, while existing models for finding new drug-disease associations are based on drug-drug similarity and disease-disease similarity. We validated accuracy of the model using LOOCV of ten times and the AUCs were 0.74 on Alzheimer's disease and 0.71 on Breast cancer.

• BMB Reports
• /
• 제49권7호
• /
• pp.376-381
• /
• 2016

Several lines of evidence have revealed that phosphorylation of amyloid precursor protein (APP) at Thr668 is involved in the pathogenesis of Alzheimer's disease (AD). Okadaic acid (OA), a protein phosphatase-2A inhibitor, has been used in AD research models to increase tau phosphorylation and induce neuronal death. We previously showed that OA increased levels of APP and induced accumulation of APP in axonal swellings. In this study, we found that in OA-treated neurons, phosphorylation of APP at Thr668 increased and accumulated in axonal swellings by c-jun N-terminal kinase (JNK), and not by Cdk5 or ERK/MAPK. These results suggest that JNK may be one of therapeutic targets for the treatment of AD.

• Asian-Australasian Journal of Animal Sciences
• /
• 제29권6호
• /
• pp.782-792
• /
• 2016

As the most common neurodegenerative diseases, Alzheimer's disease (AD) and Parkinson's disease (PD) are two of the main health concerns for the elderly population. Recently, microRNAs (miRNAs) have been used as biomarkers of infectious, genetic, and metabolic diseases in humans but they have not been well studied in domestic animals. Here we describe a computational biology study in which human AD- and PD-associated miRNAs (ADM and PDM) were utilized to predict orthologous miRNAs in the following domestic animal species: dog, cow, pig, horse, and chicken. In this study, a total of 121 and 70 published human ADM and PDM were identified, respectively. Thirty-seven miRNAs were co-regulated in AD and PD. We identified a total of 105 unrepeated human ADM and PDM that had at least one 100% identical animal homolog, among which 81 and 54 showed 100% sequence identity with 241 and 161 domestic animal miRNAs, respectively. Over 20% of the total mature horse miRNAs (92) showed perfect matches to AD/PD-associated miRNAs. Pigs, dogs, and cows have similar numbers of AD/PD-associated miRNAs (63, 62, and 59). Chickens had the least number of perfect matches (34). Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses suggested that humans and dogs are relatively similar in the functional pathways of the five selected highly conserved miRNAs. Taken together, our study provides the first evidence for better understanding the miRNA-AD/PD associations in domestic animals, and provides guidance to generate domestic animal models of AD/PD to replace the current rodent models.

• 동의신경정신과학회지
• /
• 제28권4호
• /
• pp.359-371
• /
• 2017

Objectives: The objective of this study was to review the effect of oral administration of herbal medicines on the improvement of memory in Alzheimer's disease animal model reported in Korean domestic journals. Methods: The Korean databases (Koreantk, KISS) were searched with memory as a popular search term. During the searches, only animal study reports were reviewed. Data of animal models, intervention, observation methods of measuring indicators were extracted from the databases. Results: Typically, 36 articles were reviewed. Twenty-two studies used scopolamine to induce Alzheimer's disease, 24 studies used complex herbal medicines, and 12 studies used simple herbal medicines. Polygalae Radix and Acori Rhizoma were the most frequently used herbal medicines to improve memory in Alzheimer model. To evaluate the effect of herbal medicines, 36 studies used macroscopy, 16 studies used molecular biological analysis, 21 studies used biochemical analysis, 15 studies used histological analysis, and 11 studies used hematological analysis. Each study showed significant improvement with respect to memory indicators. Conclusions: Overall, the results suggest that treatment employing herbal medicines is an effective option to treat memory impairment in Alzheimer's disease.

• Archives of Pharmacal Research
• /
• 제22권4호
• /
• pp.354-360
• /
• 1999

Inflammatory bowel disease (IBD) is a multifactorial disorder with unknown etiology and pathogenesis. DA-6034,$ 7-carboxymethyloxy-3^{l}, 4^{l},$ 5-trimethoxy flavone, is a synthetic flavonoid known to possess anti-inflammatory activity. This study was performed to evaluate the oral therapeutic effect of DA-6034 in three experimental animal models of IBD : two chemical-induced IBD models of rats and the human leukocyte antigen (HLA)-B27 transgenic rat model known to develop spontaneous colitis without the use of exogenous agents. Acute chemical colitis was induced by intracolonic instillation of 1.2 ml of 4% acetic acid solution. Prednisolone (1 mg/kg), sulfasalazine (100 mg/kg) and DA-6034 (0.3~3 mg/kg) were orally administered twice daily for 6 days in these rats. In addition, chronic chemical colitis was induced by intracolonic administration of trinitrobenzene sulfonic acid (TNBS) 30 mg in 50% ethanol and agents were orally administered for 6 or 20 days. In chemical-induced IBD models, all of these agents reduced the severity of colitis and specially, DA-6034 (3 mg/kg) showed more potent effect than other drugs in macroscopic lesion score. In HLA-B27 transgenic rats, DA-6034 (3 mg/kg) and prednisolone (0.5 gm/kg) were treated orally twice daily for 6 weeks. The HLA-B27 transgenic rats showed only mild colitis, compared with the chemical-induced colitis models. DA-6034 ameliorated the loose stool and decreased microscopic damage, which is the important indicator of this model. In conclusion, oral therapy of DA-6034 attenuated the macroscopic and histologic damages of the colon in all three experimental models of IBD, which suggest that DA-6034 could be a promising drug in the treatment of IBD.

• Journal of Ginseng Research
• /
• 제37권1호
• /
• pp.100-107
• /
• 2013

This study examined the effect of fermented ginseng (FG) on memory impairment and ${\beta}$-amyloid ($A{\beta}$) reduction in models of Alzheimer's disease (AD) in vitro and in vivo. FG extract was prepared by steaming and fermenting ginseng. In vitro assessment measured soluble $A{\beta}42$ levels in HeLa cells, which stably express the Swedish mutant form of amyloid precursor protein. After 8 h incubation with the FG extract, the level of soluble $A{\beta}42$ was reduced. For behavioral assessments, the passive avoidance test was used for the scopolamine-injected ICR mouse model, and the Morris water maze was used for a transgenic (TG) mouse model, which exhibits impaired memory function and increased $A{\beta}42$ level in the brain. FG extract was treated for 2 wk or 4 mo on ICR and TG mice, respectively. FG extract treatment resulted in a significant recovery of memory function in both animal models. Brain soluble $A{\beta}42$ levels measured from the cerebral cortex of TG mice were significantly reduced by the FG extract treatment. These findings suggest that FG extract can protect the brain from increased levels of $A{\beta}42$ protein, which results in enhanced behavioral memory function, thus, suggesting that FG extract may be an effective preventive or treatment for AD.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권14호
• /
• pp.5571-5575
• /
• 2014

Background: The ability to predict the survival time of breast cancer patients is important because of the potential high morbidity and mortality associated with the disease. To develop a predictive inference for determining the survival of breast cancer patients, we applied a novel Bayesian method. In this paper, we propose the development of a databased statistical probability model and application of the Bayesian method to predict future survival times for White Hispanic female breast cancer patients, diagnosed in the US during 1973-2009. Materials and Methods: A stratified random sample of White Hispanic female patient survival data was selected from the Surveillance Epidemiology and End Results (SEER) database to derive statistical probability models. Four were considered to identify the best-fit model. We used three standard model-building criteria, which included Akaike Information Criteria (AIC), Bayesian Information Criteria (BIC), and Deviance Information Criteria (DIC) to measure the goodness of fit. Furthermore, the Bayesian method was used to derive future survival inferences for survival times. Results: The highest number of White Hispanic female breast cancer patients in this sample was from New Mexico and the lowest from Hawaii. The mean (SD) age at diagnosis (years) was 58.2 (14.2). The mean (SD) of survival time (months) for White Hispanic females was 72.7 (32.2). We found that the exponentiated Weibull model best fit the survival times compared to other widely known statistical probability models. The predictive inference for future survival times is presented using the Bayesian method. Conclusions: The findings are significant for treatment planning and health-care cost allocation. They should also contribute to further research on breast cancer survival issues.

• 대한한방내과학회지
• /
• 제42권4호
• /
• pp.563-571
• /
• 2021

Objectives: This pilot study aimed to confirm the possibility of applying our design to the main study, a retrospective medical record analysis of the diseases which have most frequently been treated with collaborations of Korean and Western medicine, and to identify what corrections and statistical models are needed to conduct the main study. Methods: Data were collected from a case report form developed for patients who received treatment in the medical institutions. Appropriate statistical techniques, like Propensity Score (PS) and Generalized Estimation Equation (GEE) models, were used to compare the indicators of collaboration and non-collaboration groups for patients in comparable diseases. Results: Using PS matching for each M and S disease group, the indicators were compared by balancing the collaboration and non-collaboration group, and the GEE models compared indicators between groups in each disease over follow-up. Through this process we identified two limitations, insufficient samples and a large deviation of the follow-up period. Conclusion: This pilot study confirmed that the study design and case report form are applicable. The main study will be conducted by collecting sufficient samples and reflecting deviation of follow-up period.

• 한국컴퓨터정보학회논문지
• /
• 제27권5호
• /
• pp.21-28
• /
• 2022

심혈관질환은 심장질환과 혈관질환 등 순환기계통에 생기는 모든 질병을 통칭한다. 심혈관질환은 2019년 사망의 1/3을 차지하는 전 세계 사망의 주요 원인이며, 사망자는 계속 증가하고 있다. 이와 같은 질병을 인공지능을 활용해 환자의 데이터로 미리 예측이 가능하다면 질병을 조기에 발견해 치료할 수 있을 것이다. 본 연구에서는 심혈관질환 중 하나인 심장질환을 예측하는 모델들을 생성하였으며 Accuracy, Precision, Recall의 측정값을 지표로 하여 모델들의 성능을 비교한다. 또한 Decision Tree의 성능을 향상시키는 방법에 대해 기술한다. 본 연구에서는 macOS Big Sur환경에서 Jupyter Notebook으로 Python을 사용해 scikit-learn, Keras, TensorFlow 라이브러리를 이용하여 실험을 진행하였다. 연구에 사용된 모델은 Decision Tree, KNN(K-Nearest Neighbor), SVM(Support Vector Machine), DNN(Deep Neural Network)으로 총 4가지 모델을 생성하였다. 모델들의 성능 비교 결과 Decision Tree 성능이 가장 높은 것으로 나타났다. 본 연구에서는 노드의 특성배치를 변경하고 트리의 최대 깊이를 3으로 지정한 Decision Tree를 사용하였을 때 가장 성능이 높은 것으로 나타났으므로 노드의 특성 배치 변경과 트리의 최대 깊이를 설정한 Decision Tree를 사용하는 것을 권장한다.

• Journal of Multimedia Information System
• /
• 제4권4호
• /
• pp.233-238
• /
• 2017

Automatic identification of disease in plants from their leaves is one of the most challenging task to researchers. Diseases among plants degrade their performance and results into a huge reduction of agricultural products. Therefore, early and accurate diagnosis of such disease is of the utmost importance. The advancement in deep Convolutional Neural Network (CNN) has change the way of processing images as compared to traditional image processing techniques. Deep learning architectures are composed of multiple processing layers that learn the representations of data with multiple levels of abstraction. Therefore, proved highly effective in comparison to many state-of-the-art works. In this paper, we present a plant disease identification methodology from their leaves using deep CNNs. For this, we have adopted GoogLeNet that is considered a powerful architecture of deep learning to identify the disease types. Transfer learning has been used to fine tune the pre-trained model. An accuracy of 85.04% has been recorded in the identification of four disease class in Apple plant leaves. Finally, a comparison with other models has been performed to show the effectiveness of the approach.