• 한국융합학회논문지
• /
• 제10권3호
• /
• pp.23-30
• /
• 2019

본 연구는 당뇨병 치료제 후보약물 정보를 이용하여 항당뇨에 영향을 미치는 물질구조를 발견하는데 목적이 있다. 정량적구조 활성관계를 이용한 기계 학습 모델을 만들고 부분최소자승 알고리즘을 통해 실험데이터 별로 결정계수를 파악한 후 변수중요도척도를 활용하여 주요 분자표현자를 도출하였다. 연구 결과, 후보약물 구조정보를 반영한 molecular access system fingerprint 데이터로 분석한 결과가 in vitro 데이터를 이용한 분석 결과보다 설명력이 높았으며, 항당뇨에 영향을 미치는 주요 분자표현자 역시 다양하게 도출할 수 있었다. 제안된 항당뇨 예측 및 주요인자 분석 방법을 활용한다면 유사한 과정을 반복 실험하는 기존 신약개발 방식과는 달리, 많은 비용과 시간이 소요되는 후보물질 스크리닝 (screening) 기간을 최소화하고, 신약개발 탐색기간도 단축하는 계기가 될 수 있을 것으로 기대한다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2007년도 가을 학술발표논문집 Vol.34 No.2 (B)
• /
• pp.17-21
• /
• 2007

Drug discovery is a long process with a low rate of successful new therapeutic discovery regardless of the advances in information technologies. Identification of candidate proteins is an essential step for the drug discovery and it usually requires considerable time and efforts in the drug discovery. The drug discovery is not a logical, but a fortuitous process. Nevertheless, considerable amount of information on drugs are accumulated in UniProt, NCBI, or DrugBank. As a result, it has become possible to try to devise new computational methods classifying drug target candidates extracting the common features of known drug target proteins. In this paper, we devise a method for drug target protein classification by using weighted feature summation and Support Vector Machine. According to our evaluation, the method is revealed to show moderate accuracy $85{\sim}90%$. This indicates that if the devised method is used appropriately, it can contribute in reducing the time and cost of the drug discovery process, particularly in identifying new drug target proteins.

• 한국컴퓨터정보학회논문지
• /
• 제22권3호
• /
• pp.131-138
• /
• 2017

New drug development is time-consuming and costly. Hence, it is necessary to repurpose old drugs for finding new indication. We suggest the way that repurposing old drug using massive literature data and biological network. We supposed a disease-drug relationship can be available if signal pathways of the relationship include significant genes identified in literature data. This research is composed of three steps-identifying significant gene using co-occurrence in literature; analyzing the shortest path on biological network; and scoring a relationship with comparison between the significant genes and the shortest paths. Based on literatures, we identify significant genes based on the co-occurrence frequency between a gene and disease. With the network that include weight as possibility of interaction between genes, we use shortest paths on the network as signal pathways. We perform comparing genes that identified as significant gene and included on signal pathways, calculating the scores and then identifying the candidate drugs. With this processes, we show the drugs having new possibility of drug repurposing and the use of our method as the new method of drug repurposing.

• Toxicological Research
• /
• 제26권1호
• /
• pp.1-8
• /
• 2010

The process of new drug development consists of several stages; after identifying potential candidate compounds, preclinical studies using animal models link the laboratory and human clinical trials. Among many steps in preclinical studies, toxicology and safety assessments contribute to identify potential adverse events and provide rationale for setting the initial doses in clinical trials. Gene modulation is one of the important tools of modern biology, and is commonly employed to examine the function of genes of interest. Advances in new drug development have been achieved by exploding information on target selection and validation using genetically modified animal models as well as those of cells. In this review, a recent trend of genetically modified methods is discussed with reference to safety assessments, and the exemplary applications of gene-modulating tools to the tests in new drug development were summarized.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권1호
• /
• pp.11-18
• /
• 2022

신약 디자인은 단백질 수용체와 같은 생물학적 표적과 상호작용할 수 있는 약물 후보물질을 식별하는 과정이다. 전통적인 신약 디자인 연구는 약물 후보 물질 탐색과 약물 개발 단계로 구성되어 있으나, 하나의 신약을 개발하기 위해서는 10년 이상의 장시간이 요구된다. 이러한 기간을 단축하고 효율적으로 신약 후보 물질을 발굴하기 위하여 심층 학습 기반의 방법들이 연구되고 있다. 많은 심층학습 기반의 모델들은 SMILES 문자열로 표현된 화합물을 재귀신경망을 통해 학습 및 생성하고 있으나, 재귀신경망은 훈련시간이 길고 복잡한 분자식의 규칙을 학습시키기 어려운 단점이 있어서 개선의 여지가 남아있다. 본 연구에서는 self-attention과 variational autoencoder를 활용하여 SMILES 문자열을 생성하는 딥러닝 모델을 제안한다. 제안된 모델은 최신 신약 디자인 모델 대비 훈련 시간을 1/26로 단축하는 것뿐만 아니라 유효한 SMILES를 더 많이 생성하는 것을 확인하였다.

• Journal of Pharmaceutical Investigation
• /
• 제36권4호
• /
• pp.263-269
• /
• 2006

Deficiencies in the early ADMET(absorption, distribution, metabolism, elimination and toxicity) information on drug candidate extract a significant economic penalty on pharmaceutical firms. Microscale cell culture analogue-microscale gastrointestinal(${\mu}CCA-{\mu}GI$) device using Caco 2, L2 and HEp G2/C3A cells, which mimic metabolic process after absorption occurring in humans was used to investigate the toxicity of the model chemical, acetaminophen(AAP). The toxicity of acetaminophen determined after induction of CYP 1A1/2 in Caco 2 cells was not significant. In a coculture system, although no significant reduction in viability of HEp G2/C3A and L2 cells was found, approximately 5 fold increase in the CYP 1A1/2 activity was observed. These results appear to be related to organ-organ interaction. The oral administration of a drug requires addition of the absorption process through small intestine to the current ${\mu}CCA$ device. Therefore, a perfusion coculture system was employed for the evaluation of the absolution across the small intestine and resulting toxicity in the liver and lung. This system give comprehensive and physiologic information on oral uptake and resulting toxicity as in the body. The current ${\mu}CCA$ device can be used to demonstrate the toxic effect due to organ to organ interaction after oral administration,

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2001년도 제2회 생물정보학 국제심포지엄
• /
• pp.139-149
• /
• 2001

Since 1990, the National Cancer Institute(NCI) has screened more than 60.000 compounds against a panel of 60 human cancer cell lines. The 50-percent growth-inhibitory concentration (GI$_{50}$) values encode unexpectedly rich, detailed information on mechanisms of drug action and drug resistance. Each compound's pattern is like a fingerprint, essentially unique among the many billions of distinguishable possibilities. These activity patterns are being used in conjunction with molecular structural features of the tested agents to explore the NCI's database of more than 460, 000 compounds, and they are providing insight into potential target molecules and modulators of activity in the 60 cell lines. For example, the information is being used to search for candidate anticancer drugs that are not dependent on intact p53 suppressor gene function for their activity. It remains to be seen how effective this information-intensive strategy will be at generating new clinically active agents.s.

• 한국응용약물학회:학술대회논문집
• /
• 한국응용약물학회 2007년도 Proceedings of The Convention
• /
• pp.19-27
• /
• 2007

An important potential of metabolomics-based approach is the possibility to develop fingerprints of diseases or cellular responses to classes of compounds with known common biological effect. Such fingerprints have the potential to allow classification of disease states or compounds, to provide mechanistic information on cellular perturbations and pathways and to identify biomarkers specific for disease severity and drug efficacy. Metabolic profiles of biological fluids contain a vast array of endogenous metabolites. Changes in those profiles resulting from perturbations of the system can be observed using analytical techniques, such as NMR and MS. $^1H$ NMR was used to generate a molecular fingerprint of serum or urinary sample, and then pattern recognition technique was applied to identity molecular signatures associated with the specific diseases or drug efficiency. Several metabolites that differentiate disease samples from the control were thoroughly characterized by NMR spectroscopy. We investigated the metabolic changes in human normal and clinical samples using $^1H$ NMR. Spectral data were applied to targeted profiling and spectral binning method, and then multivariate statistical data analysis (MVDA) was used to examine in detail the modulation of small molecule candidate biomarkers. We show that targeted profiling produces robust models, generates accurate metabolite concentration data, and provides data that can be used to help understand metabolic differences between healthy and disease population. Such metabolic signatures could provide diagnostic markers for a disease state or biomarkers for drug response phenotypes.

• Archives of Pharmacal Research
• /
• 제26권12호
• /
• pp.1002-1008
• /
• 2003

Ferulic acid (3-methoxy, 4-hydroxy cinnamic acid) is a flavoid component possessing antioxidant property. The compound is currently under development as a new drug candidate for the treatment of the dementia. The objective of this preformulation study was to determine the physicochemical properties of ferulic acid. The n-octanol to water partition coefficients of ferulic acid were 0.375 and 0.489 at the pHs of 3 and 10, respectively. Accelerated stability study for ferulic acid indicated that the t 90 value for the drug was estimated to be 459 days at $25^{\circ}C$. Ferulic acid was also found to be unstable under the relative humidity of more than 76%, probably because of the hygroscopic nature of the drug. In order to study compatibility of ferulic acid with typical excipients, potential change in differential scanning calorimetry spectrum was studied in 1: 1 binary mixtures of ferulic acid and typical pharmaceutical excipients (e.g., Aerosil, Avicel, CMC, Eudragit, lactose, PEG, PVP, starch and talc). Avicel, CMC, PVP and starch were found to be incompatible with ferulic acid, indicating the addition of these excipients may complicate the manufacturing of the formulation for the drug. Particle size distribution of ferulic acid powder was in the size range of 10-190 $\mu$m with the mean particle size of 61 $\mu$m. The flowability of ferulic acid was apparently inadequate, indicating the granulation may be necessary for the processing of the drug to solid dosage forms. Two polymorphic forms were obtained by recrystallization from various solvents used in formulation. New polymorphic form of ferulic acid, Form II, was obtained by recrystallization from 1,4-dioxane. The equilibrium solubility for Form I was approximately twice of that for Form II. The dissolution rate of Form II was higher than that of Form I in the early phase (<6 min). Therefore, these physicochemical information has to be taken in the consideration for the formulation of ferulic acid.

• Mass Spectrometry Letters
• /
• 제6권2호
• /
• pp.48-51
• /
• 2015

Kinsenoside is a principle bioactive compound of Anoectochilus formosanus. It exhibits various pharmacological effects such as antihyperglycemic, antioxidant, anti-inflammatory, immunostimulating, and hepatoprotective activities and has recently been developed as an antidiabetic drug candidate. In this study, as part of an in vitro pharmacokinetic study, the stability of kinsenoside in rat and human liver microsomes was evaluated. Kinsenoside was found to have good metabolic stability in both rat and human liver microsomes. These results will provide useful information for further in vivo pharmacokinetic and metabolism studies.