• Journal of the Korean Data and Information Science Society
• /
• 제25권5호
• /
• pp.1151-1160
• /
• 2014

In DNA microarray studies, the number of genes far exceeds the number of samples and the gene expression measures are highly correlated. Partial least squares regression (PLSR) is one of the popular methods for dimensional reduction and known to be useful for the classifications of microarray data by several studies. In this study, we suggest a modified version of the partial least squares regression to analyze gene expression data with survival information. The method is designed as a new gene selection method using PLSR with an iterative procedure of imputing censored survival time. Mean square error of prediction criterion is used to determine the dimension of the model. To visualize the data, plot for variables superimposed with samples are used. The method is applied to two microarray data sets, both containing survival time. The results show that the proposed method works well for interpreting gene expression microarray data.

• 한국자원식물학회지
• /
• 제23권6호
• /
• pp.526-534
• /
• 2010

Genomes of clusters of related eukaryotes are now being sequenced at an increasing rate. In this paper, we developed an accurate, low-cost method for annotation of gene prediction and exon-intron structure. The gene prediction was adapted for delta 1-pyrroline-5-carboxylate-synthetase (p5cs) gene from China wild-type of the halophytic Leymus chinensis (Trin.), naturally adapted to highly-alkali soils. Due to complex adaptive mechanisms in halophytes, more attentions are being paid on the regulatory elements of stress adaptation in halophytes. P5CS encodes delta 1-pyrroline-5-carboxylate-synthetase, a key regulatory enzyme involved in the biosynthesis of proline, that has direct correlation with proline accumulation in vivo and positive relationship with stress tolerance. Using analysis of reverse transcription-polymerase chain reaction (RT-PCR) and PCR, and direct sequencing, 1076 base pairs (bp) of cDNA in length and 2396 bp of genomic DNA in length were obtained from direct sequencing results. Through gene prediction and exon-intron structure verification, the full-length of cDNA sequence was divided into eight parts, with seven parts of intron insertion. The average lengths of determinated coding regions and non-coding regions were 154.17 bp and 188.57 bp, respectively. Nearly all splice sites displayed GT as the donor sites at the 5' end of intron region, and 71.43% displayed AG as the acceptor sites at the 3' end of intron region. We conclude that this method is a cost-effective way for obtaining an experimentally verified genome annotation.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권10호
• /
• pp.397-402
• /
• 2019

암 환자에게 적절한 치료계획을 제공하기 위해 암의 진행양상 또는 환자의 생존 기간 등에 해당하는 환자의 예후를 정확히 예측하는 것은 생물정보학 분야에서 다루는 중요한 도전 과제 중 하나이다. 많은 연구에서 암 환자의 유전자 발현량 데이터를 이용하여 환자의 예후를 예측하는 기계학습 모델들이 많이 제안되어 오고 있다. 유전자 발현량 데이터는 약 17,000개의 유전자에 대한 수치값을 갖는 고차원의 수치형 자료이기에, 기존의 연구들은 특징 선택 또는 차원 축소 전략을 이용하여 예측 모델의 성능 향상을 도모하였다. 그러나 이러한 접근법은 특징 선택과 예측 모델의 훈련이 분리되어 있어서, 기계학습 모델은 선별된 유전자들이 생물학적으로 어떤 관계가 있는지 알기가 어렵다. 본 연구에서는 유전자 발현량 데이터를 이미지 형태로 변환하여 예후 예측이 효과적으로 특징 선택 및 예후 예측을 수행할 수 있는 기법을 제안한다. 유전자들 사이의 생물학적 상호작용 관계를 유전자 발현량 데이터에 통합하기 위해 Node2Vec을 활용하였으며, 2차원 이미지로 표현된 발현량 데이터를 효과적으로 학습할 수 있도록 합성곱 신경망 모델을 사용하였다. 제안하는 모델의 성능은 이중 교차검증을 통해 평가되었고, 유전자 발현량 데이터를 그대로 이용하는 기계학습모델보다 우월한 예후 예측 정확도를 가지는 것이 확인되었다. Node2Vec을 이용한 유전자 발현량의 새로운 이미지 표현법은 특징 선택으로 인한 정보의 손실이 없어 예측 모델의 성능을 높일 수 있으며, 이러한 접근법이 개인 맞춤형 의학의 발전에 이바지할 것으로 기대한다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권11호
• /
• pp.803-811
• /
• 2010

단백질의 세포내 위치와 단백질의 기능은 연관성이 크므로, 단백질의 세포내 위치 예측을 통해서 그 기능에 대한 정보를 얻을 수 있다. 예측 정확도를 높이기 위해서 아미노산 서열 정보이외의 외부 정보들을 효과적으로 이용하려는 연구가 활발하다. 본 논문에서는 아미노산 서열 유사성, 단백질 프로파일, 유전자 온톨로지, 모티프, 문헌 정보에 내재된 세포내 위치 예측 능력을 비교한다. 단백질간의 서열 유사성이 80% 이하인 PLOC 자료를 사용한 실험에서는 서열 유사성과 유전자 온톨로지를 이용하는 방법이 효과적이며, 94.8%의 예측정확도를 얻었다. 단백질 서열간의 유사성이 30% 이하로서 단백질간의 서열 유사성이 작은 BaCelLo IDS 자료는 유전자 온톨로지를 사용하는 것이 효과적이었고, 동물은 93.2%, 곰팡이는 86.6%의 예측정확도로 크게 향상된 성능을 얻었다.

• Genomics & Informatics
• /
• 제6권3호
• /
• pp.136-141
• /
• 2008

A large number of studies have been performed to identify biomarkers that will allow efficient detection and determination of the precise status of a patient’s disease. The use of microarrays to assess biomarker status is expected to improve prediction accuracies, because a whole-genome approach is used. Despite their potential, however, patient samples can differ with respect to biomarker status when analyzed on different platforms, making it more difficult to make accurate predictions, because bias may exist between any two different experimental conditions. Because of this difficulty in experimental standardization of microarray data, it is currently difficult to utilize microarray-based gene sets in the clinic. To address this problem, we propose a method that predicts disease status using gene expression data that are transformed by their ranks, a concept that is easily applied to two datasets that are obtained using different experimental platforms. NCI and colon cancer datasets, which were assessed using both Affymetrix and cDNA microarray platforms, were used for method validation. Our results demonstrate that the proposed method is able to achieve good predictive performance for datasets that are obtained under different experimental conditions.

• Genomics & Informatics
• /
• 제11권4호
• /
• pp.200-210
• /
• 2013

Studying biological networks, such as protein-protein interactions, is key to understanding complex biological activities. Various types of large-scale biological datasets have been collected and analyzed with high-throughput technologies, including DNA microarray, next-generation sequencing, and the two-hybrid screening system, for this purpose. In this review, we focus on network-based approaches that help in understanding biological systems and identifying biological functions. Accordingly, this paper covers two major topics in network biology: reconstruction of gene regulatory networks and network-based applications, including protein function prediction, disease gene prioritization, and network-based genome-wide association study.

• Computers and Concrete
• /
• 제24권4호
• /
• pp.295-302
• /
• 2019

Evolutionary algorithms based on conventional statistical methods such as regression and classification have been widely used in data mining applications. This work involves application of gene expression programming (GEP) for predicting compressive strength of fly ash geopolymer concrete, which is gaining increasing interest as an environmentally friendly alternative of Portland cement concrete. Based on 56 test results from the existing literature, a model was obtained relating the compressive strength of fly ash geopolymer concrete with the significantly influencing mix design parameters. The predictions of the model in training and validation were evaluated. The coefficient of determination ($R^2$), mean (${\mu}$) and standard deviation (${\sigma}$) were 0.89, 1.0 and 0.12 respectively, for the training set, and 0.89, 0.99 and 0.13 respectively, for the validation set. The error of prediction by the model was also evaluated and found to be very low. This indicates that the predictions of GEP model are in close agreement with the experimental results suggesting this as a promising method for compressive strength prediction of fly ash geopolymer concrete.

• Genomics & Informatics
• /
• 제19권1호
• /
• pp.10.1-10.7
• /
• 2021

Although many models have been proposed to accurately predict the response of drugs in cell lines recent years, understanding the genome related to drug response is also the key for completing oncology precision medicine. In this paper, based on the cancer cell line gene expression and the drug response data, we established a reliable and accurate drug response prediction model and found predictor genes for some drugs of interest. To this end, we first performed pre-selection of genes based on the Pearson correlation coefficient and then used ElasticNet regression model for drug response prediction and fine gene selection. To find more reliable set of predictor genes, we performed regression twice for each drug, one with IC₅₀ and the other with area under the curve (AUC) (or activity area). For the 12 drugs we tested, the predictive performance in terms of Pearson correlation coefficient exceeded 0.6 and the highest one was 17-AAG for which Pearson correlation coefficient was 0.811 for IC₅₀ and 0.81 for AUC. We identify common predictor genes for IC₅₀ and AUC, with which the performance was similar to those with genes separately found for IC₅₀ and AUC, but with much smaller number of predictor genes. By using only common predictor genes, the highest performance was AZD6244 (0.8016 for IC₅₀, 0.7945 for AUC) with 321 predictor genes.

• Industrial Engineering and Management Systems
• /
• 제16권1호
• /
• pp.64-79
• /
• 2017

Identifying disease genes from human genome is a critical task in biomedical research. Important biological features to distinguish the disease genes from the non-disease genes have been mainly selected based on traditional feature selection approaches. However, the traditional feature selection approaches unnecessarily consider many unimportant biological features. As a result, although some of the existing classification techniques have been applied to disease gene identification, the prediction performance was not satisfactory. A small set of the most important biological features can enhance the accuracy of disease gene identification, as well as provide potentially useful knowledge for biologists or clinicians, who can further investigate the selected biological features as well as the potential disease genes. In this paper, we propose a new stepwise random forests (SRF) approach for biological feature selection and disease gene identification. The SRF approach consists of two stages. In the first stage, only important biological features are iteratively selected in a forward selection manner based on one-dimensional random forest regression, where the updated residual vector is considered as the current response vector. We can then determine a small set of important biological features. In the second stage, random forests classification with regard to the selected biological features is applied to identify disease genes. Our extensive experiments show that the proposed SRF approach outperforms the existing feature selection and classification techniques in terms of biological feature selection and disease gene identification.

• 한국컴퓨터정보학회논문지
• /
• 제20권2호
• /
• pp.137-147
• /
• 2015

본 논문에서는 유전자 네트워크를 기반으로 유방암 환자의 예후를 예측하는 알고리듬을 제안한다. 유방암 환자의 마이크로어레이 데이터와 PPI(Protein-protein interaction)데이터를 이용하여 알고리듬의 분류자로 사용될 예후 특이 네트워크(Prognosis specific gene network)를 추출한다. PPI에 속한 모든 유전자 네트워크에 대하여 각각의 네트워크가 예후 좋음과 나쁨을 잘 구분하는지에 대한 점수를 피어슨 상관계수(Pearson's correlation coefficient)와 마이크로어레이 데이터를 이용하여 계산한다. 이들 중 가장 예후에 유의한 네트워크를 식별하고, 이 네트워크를 분류자로 사용하여 에스트로겐 수용체 음성 유방암 환자의 예후를 분류 분석 한다. 본 연구와 기존 연구의 알고리듬 정확도를 비교 분석 하기 위하여 독립 실험을 진행하고, 본 연구에서 제안된 알고리듬의 성능이 더 우수함을 보인다. 또한, Gene Ontology 데이터베이스를 활용하여 식별된 예후 특이 네트워크를 기능적으로 검증 한다.