Ahmet Sarigun

About

I am a Research Scientist at the MDC-BIMSB (Max Delbrück Center for Molecular Medicine - Berlin Institute for Medical Systems Biology, Berlin, Germany), within the Bioinformatics & Omics Data Science Platform at the Dr. Altuna Akalin Group.

I received my BSc degree from METU (Middle East Technical University, Turkey), Department of Chemistry.

I am currently working on Graph Representation Learning and had the chance to work with Ahmet Rifaioğlu during my undergraduate program. In 2021-2022, I worked on De novo drug Design using Adversarial Machine Learning with Tunca Doğan at Hacettepe University Biological Data Science Laboratory as research intern. I also did my summer internship in 2022 at Heidelberg University Hospital, Institute for Computational Biomedicine (AG Saez-Rodriguez's lab) to work on Deep Learning for Single Cell and Spatial Transcriptomics.

I am also interested in animations created by manim and started create those ones in Quantum Chemistry and contents can be found on YouTube.

Quantum Chemistry | Waves and Particles - A quick video that starts of a series of videos on quantum chemistry with waves and particles that we are going to go about understanding the ideas through fun animations.

As someone who has loved running and biking since high school, I have been trying to do 10K runs.

Evening Run at Devrim Stadium, METU, Turkey.

Evening Ride at Neuenheim, Germany.

Evening Ride at Neuenheim, Germany - GPS disabled, slippery of the line, deer on the road, canceling Wilhemsfeld tour just a few km away.

More running and biking routes can be found on Strava.

Also, whenever I take a break from doing research, I like to travel, hike, and take pictures.

Alstadt at Heidelberg, Germany - One of the most beautiful city I have visited.

Landscape at Kutahya, Turkey - Summer stars at night.

Kizilay at Ankara, Turkey - Sunset.

More photos can be found on Instagram.

Research

Publications

Graph Mixer Networks

• A novel framework that incorporates the principles of MLP-Mixers for graph-structured data.
  A Sarigun
  • arXiv, 2023
  • [Demo/Code] | [Blog/Story]
  

Multi-Mask Aggregators for Graph Neural Networks

• New aggregation method for GNNs, where the model learns a weighted mask for each aggregator before collecting neighboring messages.
  A Sarigun, AS Rifaioglu
  • OpenReview | 1st Learning on Graphs Conference, 2022
  • [Demo/Code] | [Poster]
  

DrugGEN: Target Specific De Novo Design of Drug Candidate Molecules with Graph Transformer-based Generative Adversarial Networks

• A new computational system creates drug candidate molecules to treat drug-resistant diseases using deep learning and a combination of transformer and graph neural network approaches in a generative adversarial setup.
  A Ünlü, E Çevrim, A Sarigun, H Ataş, A Koyaş, H Çelikbilek, DC Kahraman, A Olğaç, AS Rifaioğlu, T Doğan
  • arXiv, 2023
  • [Demo/Code]
  

Multimodal single cell data integration challenge: results and lessons learned

• NeurIPS 2021 Multimodal single cell data integration challenge.
  C Lance, et. al | Consortium Author
  • Proceedings of Machine Learning Research, 2022 | [Blog]
  • [Code]

Presentations

• FEXBind: Fast Explainable Binding Free Energy Prediction by Leveraging Molecular Mechanic Features and Molecular Structure with Graph Neural Networks, Undergraduate Research Project (June 2023)
• Multi-Mask Aggregators for Graph Neural Networks, 1st Learning on Graphs Conference (December 2022)
• Discovery of Functional Motifs by Association to Clinical Features with GNNExplainers, Heidelberg University Hospital, Institute for Computational Biomedicine (September 2022)
• De novo Drug Design using Deep Generative Models, Hacettepe University BioData Lab (September 2021)
• TransGAN: Two Transformers Can Make One Strong GAN | Paper | CENG 796 Deep Generative Models (May 2021) | Spring 2021 | YouTube Video | Slides | Unofficial Implementation

Contact

• Twitter
• GitHub
• LinkedIn
• YouTube
• Mastodon

Elements

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';