Internship Report I3L's Student http://http://repository.i3l.ac.id:80/handle/123456789/100 2026-04-21T15:20:23Z 2026-04-21T15:20:23Z Putta, Dhannyo http://http://repository.i3l.ac.id:80/handle/123456789/1271 2025-05-08T04:19:59Z 2025-01-31T00:00:00Z

Title: Student Activity and Capstone Project in Machine Learning Cohort of Bangkit Academy 2024 Authors: Putta, Dhannyo Abstract: Bangkit Academy, part of the Study Independent MSIB program, ran from September 6 to December 31, 2024, offering a comprehensive learning path in machine learning as part of this internship. Over the course of four months, the program featured a variety of activities, including online courses on Dicoding and Coursera, Instructor-Led Training (ILT), and the completion of a capstone group project. The machine learning courses covered intermediate to advanced topics, such as Python programming for operating systems, linear algebra for data science, supervised and unsupervised learning, TensorFlow for machine learning and deep learning, generative AI, and more. The ILT sessions were live online classes led by experts from leading companies, offering insights into the practical application of machine learning in the industry. The final capstone project encouraged collaboration between different learning paths to develop an app addressing real-world problems, integrating the knowledge and skills gained throughout the program.

2025-01-31T00:00:00Z Shemuel, Josia http://http://repository.i3l.ac.id:80/handle/123456789/1270 2025-05-08T04:14:02Z 2025-01-31T00:00:00Z

Title: Molecular Dynamics Simulaon of the Fo Domain of Trypanosoma brucei FoF1-ATP Synthase to Uncover Water Channel Pathways Authors: Shemuel, Josia Abstract: Trypanosoma brucei is a unicellular parasite responsible for causing human African trypanosomiasis (HAT). The unique life cycle of the parasite, infecting tsetse flies and humans, is supported by its reversible FoF1-ATP synthase. The study aims to characterize the water channel pathways within the Fo domain of T. brucei FoF1-ATP synthase to elucidate its proton translocation mechanism. The Fo domain was inserted into POPC and DOPC membrane systems, with each membrane system being replicated three times. Equilibration and production simulation for each replicate was performed for 20 ns and 100 ns, respectively. The lumenal and cytoplasmic half-channels were solvated in all replicates during the simulation, solvating the key-glutamate E102. A DOPC was shown to insulate the lumenal half-channel, replacing the role of the absent bH2. The lumenal half-channel was solvable through the rear entry, involving structurally determined key residues H75, H19, D202, and H155, as well as manually identified residues Y74, N150, and Y199. The cytoplasmic half-channel had a more open configuration, solvating key residues D223, R139, and R146, as well as manually identified residues E132, RQ219, S135, S142, and T143. The key-arginine was crucial in separating both half-channels; its rotamer is supported by coordinating water molecules with Q209. Phylogenetic analysis of subunit-a revealed that T. brucei is evolutionarily divergent from other species.

2025-01-31T00:00:00Z Margaretha, Febrina http://http://repository.i3l.ac.id:80/handle/123456789/1268 2025-05-08T04:06:56Z 2025-01-31T00:00:00Z

Title: Integrating tertiary structural representations for miRNA - drug interaction prediction Authors: Margaretha, Febrina Abstract: miRNAs are small non-coding RNAs that regulate gene expression and are dysregulated in many diseases. Its aberrant expression led to an interest in therapeutic intervention, where it can target drugs that are undruggable by proteins by acting as a gene regulator. Thus, exploring potential drugs from their aberrant miRNA information may facilitate novel treatments to tackle the current disease complexity. With the long process of wet-lab screening, it is imperative to provide a rapid miRNA and drug interaction screening to accelerate the drug discovery processes. This study proposes MDITransNet, a miRNA-drug interaction (MDI) neural network model that incorporates structural information of miRNA and molecular graphs of drugs that is trained under an adapted transformer block module of structure prediction. MDITransNet was able to retain a notable performance than conventional machine learning models with an area under the receiving operating curve (AUC) of 92% and 87% on the non-redundant test set, hairpin, and mature, respectively.

2025-01-31T00:00:00Z Heerlie, Devita Mayanda http://http://repository.i3l.ac.id:80/handle/123456789/1267 2025-05-08T04:04:18Z 2025-01-31T00:00:00Z

Title: Exploring Giant Virus (Nucleocytoviricota) Diversity Across Ecosystems from Viral Metagenomics Data Authors: Heerlie, Devita Mayanda Abstract: Giant viruses, belonging to the Nucleocytoviricota phylum, are abundant in marine environments but their role in these ecosystems remains largely unexplored. These large-genome viruses are crucial for shaping microbial communities in marine waters, influencing nutrient cycling and ecosystem dynamics. The diversity of giant viruses between two different environment, Southern East China Sea and Kenting National Park, was examined in this study using metagenomics in the through Metagenome Assembled Genome (MAG) analysis, going through the process of assembly, giant virus detection, mapping, sorting, binning, and dereplication. We identified 91 MAGs across four sampling sites. Phylogenetic analysis revealed that Imitervirales was the most abundant order in both environments. Sample 20104 from the Southern East China Sea was the most diverse, hosting two unique orders not found in other samples. Bray-Curtis Dissimilarity metrics indicated similar diversity between Southern East China Sea samples, while Kenting National Park samples were more distinct. Despite similar order-level composition, functional gene analysis showed significant differences between the sites, unique genes involves in signal transduction and immune system genes in the Southern East China Sea and unique fatty acid metabolism genes in Kenting National Park. This highlights giant viruses' distinct composition and function in these environments, emphasizing their role in influencing marine ecosystem health and stability.

2025-01-31T00:00:00Z