http://http://repository.i3l.ac.id:80/handle/123456789/366 EP Report for Bioinformatics Student 2026-04-21T18:56:49Z http://http://repository.i3l.ac.id:80/handle/123456789/1273 Title: Exploring Polygenic Risk Score Calculation Pipelines Using Linux Command Line Interface Authors: Austin, Felicia Abstract: Polygenic risk scores (PRS) has become one of the most marketable research topics as medicine focused more into personalized healthcare. By using PRS, an individual's gene can guide both the patient and the healthcare professionals in making decisions regarding themself. As such, many different workflows and tools have been developed over the years in an effort to make PRS calculation easier, while still maintaining a good, proper result. Such tools include plink2, prspipe, and PRSice-2. Although those tools have their own documentation, an adaptation to use them with real life data has its own challenges. Many of which were due to data limitation, which eliminates the possibility of it being used in this specific case such as in the case of prspipe and PRSice-2. Meanwhile, plink2 as the most promising tool was also limited due to the small amount of sample which causes a skewed result. Therefore, this report can only be used as a proof of exploration towards the various workflows with limited conclusion. 2025-01-31T00:00:00Z http://http://repository.i3l.ac.id:80/handle/123456789/1272 Title: The Role of lncRNA XIST in Cancer: An In-Silico Approach Authors: Aminuddin, Mohamad Zafran Abstract: The lncRNA XIST was identified to play a core role in regulating gene expression and cancer development. XIST is known to be an X-chromosome inactivation (XCI) which silences one of the X-chromosomes. The current study is thus an in silico investigation of XIST expression status and associated genes in some types of cancer. Computational tools, including GEPIA2, UALCAN, cBioPortal, UCSC Xena, KMplotter, StringDB, Metacore, and IPA were used to make a systematic analysis of the XIST expression, gender-based comparisons, and association studies with proteins linked to XIST. Differential expression analysis, survival analysis, and pathway enrichment studies will be performed to validate findings and identify potential therapeutic targets. This study provides important insights based on in-silico analysis, experimental validation is crucial to confirm the findings and better understand the underlying biological mechanisms of XIST in colon adenocarcinoma (COAD). These findings emphasize the subtle role of XIST in COAD and suggest further research to understand its impact on cancer biology and possibly its role as a biomarker. 2025-01-31T00:00:00Z http://http://repository.i3l.ac.id:80/handle/123456789/1054 Title: EfficientNet Based Detection of Lung Cancer Based on Histopathological Image Authors: Lunoto, Dennis Abstract: Lung cancer is the most malignant tumor with the highest mortality in the world. Early diagnosis and prognosis are important to improve the patient’s survival rate. With AI, screening which is one of the methods of detection is more sensitive and accurate allowing better analysis. This will in turn assist medical professionals in their line of work and improve the medical field overall. This research will explore a deep learning based on convolutional neural network (CNN), You Only Look Once (Yolo)’s Yolo5, LeNet5, as well as a transfer learning method using four EfficientNet models including EfficientNetB0, EfficientNetB1, EfficientNetB2, and EfficietNetB3. 2024-01-31T00:00:00Z http://http://repository.i3l.ac.id:80/handle/123456789/1010 Title: Cardiomegaly Detection using Computer Vision Authors: Fisranda, Ferdinand Abstract: Cardiomegaly or enlargement of the heart, is a designated umbrella term for various conditions that lead to the enlargement of the heart. Early detection and intervention would increase the chance of survival, however, detection of cardiomegaly is usually done with chest X-rays and might be difficult to do as diagnosis of cardiomegaly involves the detection of subtle and small changes in the heart. Convolutional Neural Network (CNN) is a type of Artificial Intelligence (AI) specifically in computer vision that has proven itself to be able to process medical images in a fast, accurate, and highly precise manner. Integrating computer vision into the healthcare system as diagnosis assistant will have huge benefits for cardiomegaly diagnosis. Many CNN algorithm has been developed over the years, in this study we are comparing 4 popular CNN: YOLOv5, YOLOv8, ResNet, and EfficientNet, And their ability to detect cardiomegaly in X-ray images. We found that YOLOv8x has the best overall accuracy with an accuracy of 0.867 in detecting cardiomegaly, however, YOLOv5s has the best accuracy in detecting true negative cases with an accuracy of 0.834 in true negative cases 2024-01-18T00:00:00Z