Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
Bioinformatics Overview 3
Published:
Computational Biology and Bioinformatics (M.Sc.) , University of Göttingen
This is my review of the master’s courses at the University of Göttingen.
Generally, there isn’t much going on in the summer…
Bioinformatics Overview 2
Published:
Computational Biology and Bioinformatics (M.Sc.) , University of Göttingen
This is my review of the master’s courses at the University of Göttingen.
Bioinformatics Overview 1
Published:
Computational Biology and Bioinformatics (M.Sc.) at the University of Göttingen
Overview of the Master’s Degree in Computational Biology and Bioinformatics
Application
Applications for this degree typically open from April 1 to May 15. Applicants must have a bachelor’s degree in biology or a related field, English proficiency at C1 level (IELTS 6.5), and must pass a knowledge test. The test covers general biology and includes some programming essay questions. The program spans two years, with the first three semesters dedicated to coursework, followed by an internship (preferably in the lab where you plan to write your master’s thesis), and finally, the thesis. The thesis can be undertaken in any lab that specializes in computational biology or bioinformatics, offering considerable flexibility.
projects
tictac for reinforcement learning
Published:
I made a simple tictac game, to try what I am learning in reinforcement learning in a simple c++ env. You can see an eaxmple of the it here smart agent vs random agent: 
xAI
Published:
As I advanced through my studies, I became deeply engaged in machine learning (ML). This experience has honed my coding skills and enabled me to leverage ML to tackle complex problems. It has also highlighted the potential of combining ML with biological systems to create innovative solutions. During an internship, I worked on Explainable AI (XAI) and explored ways to explain the decisions of Graph Neural Networks (GNNs) for cancer prediction using SHAP (Shapley) values. This hands-on experience with XAI further deepened my understanding of how advanced ML models can be made more interpretable for critical applications in healthcare. Because we haven’t published yet, can’t explain more.
Skin Cancer Detection with ViTs
Published:
Skin cancer is one of the most common types of cancer worldwide, with millions of new cases diagnosed each year. Early detection is critical in improving patient outcomes, as it increases the chances of successful treatment. In recent years, the advancement of artificial intelligence (AI) techniques has opened new possibilities for detecting skin cancer at an early stage using automated methods. Specifically, Vision Transformers (ViTs) have emerged as a powerful tool in the field of medical imaging, providing state-of-the-art performance in tasks like image classification and segmentation. 
The goal of this project is to explore the use of ViTs for the classification of skin cancer images. Using data from the ISIC 2024 Challenge, this project investigates the efficacy of ViTs in identifying high-risk cancerous lesions from high-resolution 3D Total Body Photography (3D-TBP) images. By comparing multiple variants of ViT models, this study aims to determine which architecture offers the best performance for skin cancer detection. The dataset used in this project is provided by the ISIC 2024 Challenge, which focuses on detecting skin cancer from high-resolution 3D-TBP images. These images pose a challenge due to their high resolution, requiring efficient model architectures that can handle large amounts of data while maintaining precision in prediction. The LeViT model achieved the highest accuracy (94%), while models like CaiT and Simple ViT also performed well. Token-to-Token ViT ran into memory issues, likely due to its high-resolution patching technique.
GANs for Biomedical Image Augmentation
Published:
Generative Adversarial Networks (GANs) are a class of neural networks consisting of two models: a generator and a discriminator. The generator creates fake data, while the discriminator evaluates it against real data. Both networks train together in a competitive process, where the generator improves at creating realistic outputs, and the discriminator becomes better at distinguishing between real and fake data. Over time, the generator learns to produce high-quality, realistic images that are hard for the discriminator to distinguish from real data.
master’s thesis
Published:
Image segmentation is a fundamental task in computer vision, with applications in medical imaging, autonomous driving, and object recognition. Recent advancements in machine learning have led to the development of powerful models like U-Net, diffusion models, and transformers, which show promise in segmenting images with high precision.
publications
talks
Bioinformatics gathering
Published:
I am organizing a series of talks by experts in the field. Our aim is, firstly, to help MSc students become familiar with the research being conducted in the city in the field of computational biology. Secondly, we aim to promote scientists and open-source bioinformatics tools. Thirdly, we want to facilitate networking and assist people in finding internships, master’s theses, or eventually a PhD. Also, I need to thank Maryam Abasi and Basecamp for their great hospitality and for allowing us to have meetings there.