• Bioinformatics and Biosystems
• /
• 제1권2호
• /
• pp.89-94
• /
• 2006

Mass spectrometry (MS) is widely applied for high throughput proteomics analysis. When large-scale proteome analysis experiments are performed, it generates massive amount of data. To search these proteomics data against protein databases, fully automated database search algorithms, such as Mascot and SEQUEST are routinely employed. At present, it is critical to reduce false positives and false negatives during such analysis. In this review we have focused on aspects of automated protein identification using tandem mass spectrometry (MS/MS) spectra and validation of the protein identifications of two most common automated protein identification algorithms Mascot and SEQUEST.

• Genomics & Informatics
• /
• 제1권2호
• /
• pp.80-86
• /
• 2003

Human Papillomavirus (HPV) infection is known as the main factor for cervical cancer which is a leading cause of cancer deaths in women worldwide. Because there are more than 100 types in HPV, it is critical to discriminate the HPVs related with cervical cancer from those not related with it. In this paper, the risk type of HPVs using their textual explanation. The important issue in this problem is to distinguish false negatives from false positives. That is, we must find high-risk HPVs as many as possible though we may miss some low-risk HPVs. For this purpose, the AdaCost, a cost-sensitive learner is adopted to consider different costs between training examples. The experimental results on the HPV sequence database show that the consideration of costs gives higher performance. The improvement in F-score is higher than that of the accuracy, which implies that the number of high-risk HPVs found is increased.

• Journal of Genetic Medicine
• /
• 제12권2호
• /
• pp.61-65
• /
• 2015

Whole genome sequencing (WGS)-based noninvasive prenatal test (NIPT) is the first method applied in the clinical setting out of various NIPT techniques. Several companies, such as Sequenom, BGI, and Illumina offer WGS-based NIPT, each with different technical and bioinformatic approaches. Sequenom, BGI, and Illumina utilize z-, t-, and L-scores, as well as normalized chromosome values, respectively, for trisomy detection. Their outstanding performance has been demonstrated in clinical studies of more than 100,000 pregnancies. The sensitivity and specificity for detection of trisomies 13, 18, and 21 were above 98%, as reported by all three companies. Unlike other techniques, WGS-based NIPT can detect other trisomies as well as clinically significant segmental duplications/deletions within a chromosome, which could expand the scope of NIPT. Incorrect results could be due to low fetal fraction, fetoplacental mosaicism, confined placental mosaicism or maternal copy number variation (CNV). Among those, maternal CNV is a significant contributor of false positive results and therefore genome wide scanning plays an important role in preventing the occurrence of false positives. In this article, the bioinformatic techniques and clinical performance of three major companies are comprehensively reviewed.

• 대한임베디드공학회논문지
• /
• 제15권5호
• /
• pp.243-249
• /
• 2020

Event detection in wireless sensor networks is a key requirement in many applications. Acoustic sensors are one of the most frequently used sensors for event detection in sensor networks, but they are sensitive and difficult to handle because they vary greatly depending on the environment and target characteristics of the sensor field. In this paper, we propose a learning-based improvement of CFAR algorithm for increasing node-level event detection performance in acoustic sensor networks, and verify the effectiveness of the designed algorithm by comparing and evaluating the event detection performance with other algorithms. Our experimental results demonstrate the superiority of the proposed algorithm by increasing the detection accuracy by more than 45.16% by significantly reducing false positives by 7.97 times while slightly increasing the false negative compared to the existing algorithm.

• Journal of Korean Neurosurgical Society
• /
• 제66권1호
• /
• pp.53-62
• /
• 2023

Objective : Deep learning is a machine learning approach based on artificial neural network training, and object detection algorithm using deep learning is used as the most powerful tool in image analysis. We analyzed and evaluated the diagnostic performance of a deep learning algorithm to identify skull fractures in plain radiographic images and investigated its clinical applicability. Methods : A total of 2026 plain radiographic images of the skull (fracture, 991; normal, 1035) were obtained from 741 patients. The RetinaNet architecture was used as a deep learning model. Precision, recall, and average precision were measured to evaluate the deep learning algorithm's diagnostic performance. Results : In ResNet-152, the average precision for intersection over union (IOU) 0.1, 0.3, and 0.5, were 0.7240, 0.6698, and 0.3687, respectively. When the intersection over union (IOU) and confidence threshold were 0.1, the precision was 0.7292, and the recall was 0.7650. When the IOU threshold was 0.1, and the confidence threshold was 0.6, the true and false rates were 82.9% and 17.1%, respectively. There were significant differences in the true/false and false-positive/false-negative ratios between the anterior-posterior, towne, and both lateral views (p=0.032 and p=0.003). Objects detected in false positives had vascular grooves and suture lines. In false negatives, the detection performance of the diastatic fractures, fractures crossing the suture line, and fractures around the vascular grooves and orbit was poor. Conclusion : The object detection algorithm applied with deep learning is expected to be a valuable tool in diagnosing skull fractures.

• Genomics & Informatics
• /
• 제5권4호
• /
• pp.143-151
• /
• 2007

To understand the mechanism of transcriptional regulation, it is essential to detect promoters and regulatory elements. Various kinds of methods have been introduced to improve the prediction accuracy of regulatory elements. Since there are few experimentally validated regulatory elements, previous studies have used criteria based solely on the level of scores over background sequences. However, selecting the detection criteria for different prediction methods is not feasible. Here, we studied the calibration of thresholds to improve regulatory element prediction. We predicted a regulatory element using MATCH, which is a powerful tool for transcription factor binding site (TFBS) detection. To increase the prediction accuracy, we used a regulatory potential (RP) score measuring the similarity of patterns in alignments to those in known regulatory regions. Next, we calibrated the thresholds to find relevant scores, increasing the true positives while decreasing possible false positives. By applying various thresholds, we compared predicted regulatory elements with validated regulatory elements from the Open Regulatory Annotation (ORegAnno) database. The predicted regulators by the selected threshold were validated through enrichment analysis of muscle-specific gene sets from the Tissue-Specific Transcripts and Genes (T-STAG) database. We found 14 known muscle-specific regulators with a less than a 5% false discovery rate (FDR) in a single TFBS analysis, as well as known transcription factor combinations in our combinatorial TFBS analysis.

• Genomics & Informatics
• /
• 제3권1호
• /
• pp.15-23
• /
• 2005

Background MicroRNAs (miRNAs) are a class of noncoding RNAs found in various organisms such as plants and mammals. However, most of the mRNAs regulated by miRNAs are unknown. Furthermore, miRNA targets in genomes cannot be identified by standard sequence comparison since their complementarity to the target sequence is imperfect in general. In this paper, we propose a kernel-based method for the efficient prediction of miRNA targets. To help in distinguishing the false positives from potentially valid targets, we elucidate the features common in experimentally confirmed targets. Results The performance of our prediction method was evaluated by five-fold cross-validation. Our method showed 0.64 and 0.98 in sensitivity and in specificity, respectively. Also, the proposed method reduced the number of false positives by half compared with TargetScan. We investigated the effect of feature sets on the classification of miRNA targets. Finally, we predicted miRNA targets for several miRNAs in the Caenorhabditis elegans (C. elegans) 3' untranslated region (3' UTR) database. Condusions The targets predicted by the suggested method will help in validating more miRNA targets and ultimately in revealing the role of small RNAs in the regulation of genomes. Our algorithm for miRNA target site detection will be able to be improved by additional experimental­knowledge. Also, the increase of the number of confirmed targets is expected to reveal general structural features that can be used to improve their detection.

• 한국동물위생학회지
• /
• 제27권1호
• /
• pp.95-101
• /
• 2004

Babesia bovis rap-1 and B equi ema-1 intergenic(IG) nucleotides were analyzed and compared for identifying putative promoter sites using computer programs. The reason to initiate this research was to determine if IG nucleotides of Babesia genes that are predicted to be involved in erythrocyte invasion have functions regulating gene transcription and translation, which can be applied to functional gene knockout. Four IG sequences used included BbIG5(B bovis rap-1 5' IG), BblG3(B bovis rap-1 3' IG), BeIG5(B equi ema-1 5' IG) and BeIG3(B equi ema-1 3' IG). BbIG5 contained a putative promoter at nucleotide 197-246 with a predicted TATA-box and a transcription start site. BbIG3 had a putative promoter at nucleotide 270-320 with two predicted TATA-boxes and a transcription start site. BeIG3 had a putative promoter at nucleotide 155-205 with a predicted TATA-box and a transcription start site. Putative promoter sites in these three sequences mentioned above were identified with score cutoff 0.8, which means detection of about 40% recognized promoters with 0.1-0.4% false positives. In contrast, BeIG5 had a putative promoter at nucleotide 163-213 with score cutoff 0.8, but neither TATA-box nor transcription start site were recognized. However, BeIG5 had a putative promoter at nucleotide 388-438 with a predicted TATA-box and a transcription start site when score cutoff was decreased to 0.18, which means detection of about 70% recognized promoters with 2.2-5.3% false positives. These sequences with putative promoters can be tested if they have functions regulating gene transcription and translation.

• 전자공학회논문지
• /
• 제54권2호
• /
• pp.115-122
• /
• 2017

본 논문은 딥러닝 알고리즘을 기반으로 하여 시각장애인을 위한 표지판을 검출하고 인식하는 시스템을 제안한다. 제안된 시스템은 크게 표지판 검출 단계와 표지판 인식 단계로 나눠지는데 표지판 검출 단계에서는 영상에서 응집 채널 특징을 추출한 뒤 아다부스트 분류기를 적용하여 표지판 관심영역을 검출하였고, 표지판 인식 단계에서는 검출한 표지판 관심영역들에 합성곱 신경망을 적용하여 어떤 표지판인지 인식하였다. 본 논문에서는 미검출된 표지판의 개수가 최대한 감소하도록 아다부스트 분류기를 설계하였고, 딥러닝 알고리즘을 사용하여 인식 정확도를 높임으로써 검출 단계에서 발생한 양성 오류들을 제거시켰다. 실험 결과, 제안된 방법의 양성 오류 개수가 다른 방법들의 양성 오류 개수보다 효과적으로 감소했음을 확인하였다.

• 한국전자통신학회논문지
• /
• 제19권1호
• /
• pp.189-196
• /
• 2024

지능형 선별 관제 시스템의 잦은 오탐지로 인해 관제 요원들의 업무 능률 및 시장 신뢰도 저하 문제가 꾸준히 보고되고 있다. 오탐지 문제 개선을 위해 새 AI 모델을 개발하거나 교체하는 것은 기회비용이 크므로, 훈련 데이터 세트 품질을 향상하여 문제를 개선하는 것이 현실적이다. 그러나 소규모 조직은 데이터 세트 수집 및 정제 역량이 부족한 실정이다. 이에 본 논문에서는 사람 자세 추정 모델을 중심으로 엣지 디바이스와 카메라 센서 퓨전을 활용한 사람 자세 데이터 자동 수집 시스템을 제안한다. 이 시스템은 네트워크 말단에서 현장 데이터를 직접 수집하고 레이블링하는 과정을 실시간으로 처리하도록 만들어, 중앙으로 집중되는 연산 부하를 분산시킨다. 또한 현장 데이터를 직접 레이블링하므로 새로운 훈련 데이터 구축에 도움을 준다.