• Journal of Korea Artificial Intelligence Association
• /
• 제2권1호
• /
• pp.7-14
• /
• 2024

In this paper, we explore the application of RNA-sequencing data and ensemble machine learning to predict lung cancer and treatment strategies for lung cancer, a leading cause of cancer mortality worldwide. The research utilizes Random Forest, XGBoost, and LightGBM models to analyze gene expression profiles from extensive datasets, aiming to enhance predictive accuracy for lung cancer prognosis. The methodology focuses on preprocessing RNA-seq data to standardize expression levels across samples and applying ensemble algorithms to maximize prediction stability and reduce model overfitting. Key findings indicate that ensemble models, especially XGBoost, substantially outperform traditional predictive models. Significant genetic markers such as ADGRF5 is identified as crucial for predicting lung cancer outcomes. In conclusion, ensemble learning using RNA-seq data proves highly effective in predicting lung cancer, suggesting a potential shift towards more precise and personalized treatment approaches. The results advocate for further integration of molecular and clinical data to refine diagnostic models and improve clinical outcomes, underscoring the critical role of advanced molecular diagnostics in enhancing patient survival rates and quality of life. This study lays the groundwork for future research in the application of RNA-sequencing data and ensemble machine learning techniques in clinical settings.

• BMB Reports
• /
• 제57권8호
• /
• pp.352-362
• /
• 2024

Hematopoietic stem cell transplantation (HSCT) remains an indispensable therapeutic strategy for various hematological diseases. This review discusses the pivotal role of bone marrow (BM) niches in influencing the efficacy of HSCT and evaluates the current animal models, emphasizing their limitations and the need for alternative models. Traditional animal models, mainly murine xenograft, have provided significant insights, but due to species-specific differences, are often constrained from accurately mimicking human physiological responses. These limitations highlight the importance of developing alternative models that can more realistically replicate human hematopoiesis. Emerging models that include BM organoids and BM-on-a-chip microfluidic systems promise enhanced understanding of HSCT dynamics. These models aim to provide more accurate simulations of the human BM microenvironment, potentially leading to improved preclinical assessments and therapeutic outcomes. This review highlights the complexities of the BM niche, discusses the limitations of current models, and suggests directions for future research using advanced model systems.

• BMB Reports
• /
• 제35권4호
• /
• pp.420-427
• /
• 2002

Partial nerve injury is the main cause of neuropathic pain disorders in humans. Acupuncture has long been used to relieve pain. It is known to relieve pain by controlling the activities of the autonomic nervous system. Although the mechanism of neuropathic pain and analgesic effects of electroacupuncture (EA) have been studied in a rat model system, its detailed mechanism at the molecular level remains unclear. To identify genes that might serve as either markers or explain these distinct biological functions, a cDNA microarray analysis was used to compare the expression of 8,400 genes among three sample groups. Messenger RNAs that were pooled from the spinal nerves of 7 normal. 7 neuropathic pain, and 7 EA treatment rat models were compared. Sixty-eight genes were differentially expressed more than 2-fold in the neuropathic rat model when compared to the normal, and restored to the normal expression level after the EA treatment. These genes are involved in a number of biological processes, including the signal transduction, gene expression, and nociceptive pathways. Confirmation of the differential gene expression was performed by a dot-blot analysis. Dot-blotting results showed that the opioid receptor sigma was among those genes. This indicates that opioid-signaling events are involved in neuropathic pain and the analgesic effects of EA. The potential application of these data include the identification and characterization of signaling pathways that are involved in the EA treatment, studies on the role of the opioid receptor in neuropathic pain, and further exploration on the role of selected identified genes in animal models.

• 한국전자현미경학회:학술대회논문집
• /
• 한국현미경학회 2005년도 제36차 추계학술대회 및 제4회 HVEM 이용자 워크샵
• /
• pp.33-35
• /
• 2005

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2006년도 Grop Science and Biotechnology in the 21st Century
• /
• pp.10-10
• /
• 2006

• 대한약학회:학술대회논문집
• /
• 대한약학회 2001년도 Proceedings of International Convention of the Pharmaceutical Society of Korea
• /
• pp.86-90
• /
• 2001

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권19호
• /
• pp.8057-8062
• /
• 2014

Purpose: The aim of the study was to evaluate the correlation of ultrasound features with breast cancer molecular status. Materials and Methods: A retrospective review was performed of ultrasound findings in 263 patients diagnosed with breast invasive ductal carcinoma for comparison with immunohistochemistric results were obtained from each lesion. Relationships between ultrasound findings and molecular status were investigated by using multiple regression analysis by means of stepwise logistic regression. Differences in ultrasound criteria were assessed among women with different molecular status. Results: ER positivity was associated with small size, lobulate, angular or spiculated margin contours, absence of calcification, posterior tumor shadowing and low elasticity score; PR positivity was associated with small size, lobulate or angular or spiculated margin contours and absence of calcification; HER2 positivity was associated with presence of calcification and absence of any echogenic halo. The calculated models of predicted molecular status were accurate and discriminating with AUCs of 0.78, 0.74, and 0.74, respectively. Conclusions: Breast cnacer ultrasound features show some correlation with the molecular status. These models may help to expand the scope of ultrasound in predicting tumor biology.

• 대한화학회지
• /
• 제54권6호
• /
• pp.799-808
• /
• 2010

이 연구에서는 기체 분자의 운동 방식에 관한 예비 화학 교사들의 오개념을 조사하기 위해 교재 분석 및 개념 검사를 실시하였다. 연구 결과, 일반화학 교재는 간단한 모형과 기본적인 개념 설명을 통해 기체 분자 운동을 다루고 접근 방식에서 차이를 보일 뿐 아니라 회전 운동에서 무게 중심에 대한 언급이 없는 교재가 상당 수 있었다. 이에 비해 물리화학 교재는 주로 분광학적인 측면에서 접근하였고 심화된 내용을 다양한 모형을 통해 제시하였으며 조사한 모든 교재에서 회전 운동의 무게 중심을 언급했다. 한편, 예비 교사들은 기체 분자의 운동 방식에 대한 이해 정도 및 자신감이 상당히 낮았으며, 많은 오개념을 지니고 있었다. 이는 예비 화학 교사들이 자신의 선개념에 근거한 직관 및 교재에서 제시한 시각 자료에 의존하는 경향이 크기 때문으로 생각된다.

• 대한화학회지
• /
• 제53권6호
• /
• pp.653-662
• /
• 2009

흡수, 분포, 대사, 배설 특성 및 독성을 예측하기 위한 효과적인 툴을 개발하는 것은 신약개발의 초기단계에서 NCE(new chemical entity)에 대한 가장 중요한 업무 중의 하나이다. 최근에 이런 시도중의 하나로서 ADME/T(absorption, distribution, metabolism, excretion, toxicity)관련 성질들의 예측에 support vector machine(SVM)을 이용하고 있다. 그리고 SVM은 ADME/T 성질들을 정확하게 예측하는데 많이 사용 되고 있다. 그러나 SVM 모델링에 두 가지 문제가 있다. 특성 선택(feature selection) 과 매개변수 설정(parameter setting)은 여전히 해결해야 할 과제이다. 이 두 가지 문제들은 SVM 분류의 효율성과 정확도에 결정적인 영향을 끼친다. 특히 특성 선택과 최적화된 SVM 변수의 설정은 서로 영향을 주기 때문에 동시에 다루어져야 한다. 여기서 우리는 genetic algorithm(GA) – 특성 선택에 사용 – 과 grid search(GS) method– 변수최적화에 사용 – 두 가지를 통합하는 효과적인 해결책을 제시하였다. ADME/T관련 성질 중 하나인 심장부정맥을 야기시키는 hERG 이온채널 저해제 분류 모델이 여기서 제안된 GA-GS-SVM을 위해 할당되고 테스트 되었다. 1891개의 화합물을 가지는 트레이닝 셋으로 단일 모델 3개, 앙상블 모델 3개, 총 6개의 모델을 만들었고 175개의 외부 데이터를 테스트 셋으로 사용하여 검증하였다. 데이터의 불균형 문제를 해결하기 위하여 GA-GS-SVM 단일 모델에 의한 예측 정확도와 GA-GS-SVM 앙상블 모델 예측 정확도를 비교하였으며, 앙상블모델을 사용하여 예측의 정확도를 높일 수 있었다.

• Journal of Pharmaceutical Investigation
• /
• 제29권3호
• /
• pp.193-203
• /
• 1999

In order to investigate systematically the steady shear flow properties of aqueous po1y(ethylene oxide) (PEO) solutions having various molecular weights and concentrations, the steady flow viscosity has been measured with a Rheometrics Fluids Spectrometer (RFS II) over a wide range of shear rates. The effects of shear rate, concentration, and molecular weight on the steady shear flow properties were reported in detail from the experimentally measured data, and then the results were interpreted using the concept of a material characteristic time. In addition, some flow models describing the non-Newtonian behavior (shear-thinning characteristics) of polymeric liquids were employed to make a quantitative evaluation of the steady flow behavior, and the applicability of these models was examined by calculating the various material parameters. Main results obtained from this study can be summarized as follows: (1) At low shear rates, aqueous PEO solutions show a Newtonian viscous behavior which is independent of shear rate. At shear rate region higher than a critical shear rate, however, they exhibit a shear-thinning behavior, demonstrating a decrease in steady flow viscosity with increasing shear rate. (2) As an increase in concentration and/or molecular weight, the zero-shear viscosity is increased while the Newtonian viscous region becomes narrower. Moreover, the critical shear rate at which the transition from the Newtonian to shear-thinning behavior occurs is decreased, and the shear-thinning nature becomes more remarkable. (3) Aqueous PEO solutions show a Newtonian viscous behavior at shear rate range lower than the inverse value of a characteristic time $1/{\lambda}_E$, while they exhibit a shear-thinning behavior at shear rate range higher than $1/{\lambda}_E$. For aqueous PEO solutions having a broad molecular weight distribution, the inverse value of a characteristic time is not quantitatively equivalent to the critical shear rate, but the power-law relationship holds between the two quantities. (4) The Cross, Carreau, and Carreau-Yasuda models are all applicable to describe the steady flow behavior of aqueous PEO solutions. Among these models, the Carreau-Yasuda model has the best validity.