Kalin Nonchev
Doctoral Candidate in Computer Science, ETH Zurich
| About me | |
|---|---|
 |
My name is Kalin and I am from Karlovo, Bulgaria. I am a doctoral candidate under the supervision of Prof. Gunnar Rätsch in the Institute for Machine Learning at ETH Zurich. During my bachelor’s in bioinformatics at the TU Munich and LMU, I worked with Prof. Julien Gagneur on rare disease genomics. I held a scholarship awarded by the Bavarian Ministry of Science, Research, and Art and the German Academic Exchange Service (DAAD). During my master’s at ETH Zurich, I contributed to projects in single-cell analysis at the Functional Genomics Center Zurich and medical device applications at Roche Diagnostics. My research focuses on understanding the gap between genotype and phenotype in rare diseases. I am committed to advancing machine learning research in biomedicine to improve clinical decision-making. A large part of the human genome is still not understood; hence I want to contribute my knowledge and time to the interpretation of multi-omics data. I believe this is the key to more accurate disease diagnoses for patients, and, more importantly, the well-proven rationale for their therapies. |
Research collaboration
I am very open to research collaborations and mentoring BSc and MSc students. Open projects. Please reach out if interested.
Highlights
- 1st place award at the Autoimmune Disease Machine Learning Challenge organized by the Broad Institute of MIT and Harvard and Crunch Lab
- Our approach outperformed over 8000 submissions in predicting spatial transcriptomics from H&E images.
- Invited talk at the University of Basel, Department of Biomedicine and EMBL Heidelberg, Judith Zaugg, 2025, Basel, Switzerland
- Conference Biological Data Science CSHL 2024, New York, US - DeepSpot: Leveraging Spatial Context for Enhanced Spatial Transcriptomics Prediction from H&E Images poster presentation.
- Conference Intelligent Systems for Molecular Biology (ISMB) 2024, Montreal, Canada - Representation learning for multi-modal spatially resolved data poster presentation.
- 1st place award at Mammoth International Contest On Omics Sciences in Europe 2024 organized by China National GeneBank, BGI Genomics, MGI and CODATA
- Our approach outperformed over 150 participants in representation learning for spatial transcriptomics.
- Belgrade Bioinformatics Conference 2024, Belgrade, Serbia
- Talk as a finalist at the Mammoth International Contest On Omics Sciences in Europe 2024 organized by China National GeneBank, BGI Genomics, MGI and CODATA.
- Conference Kipoi Summit “New horizons in Computational Regulatory Genomics” 2023, Zugspitze, Germany
- Talk on “Representation learning for multi-modal spatially resolved data”
- Conference PharmaCamp “Drug discovery in the era of Precision Medicine and Digitalization” 2023, Bern, Switzerland
- Open Day Functional Genomics Center Zurich 2022, Zurich, Switzerland
- Poster titled “Single-cell RNA analysis of Xenograft Tumor and its Host Environment”
- Healthcare Xplorer Challenge Conference of Roche 2022, Zurich, Switzerland
- Talk on “Interpretable Machine Learning models for automated quality assessment of measurement results” aiming to enhance the development of medical and diagnostic products through machine learning
Publications
- DeepSpot: Leveraging Spatial Context for Enhanced Spatial Transcriptomics Prediction from H&E Images
Kalin Nonchev, Sebastian Dawo, Karina Selina, Holger Moch, Sonali Andani, Tumor Profiler Consortium, Viktor Hendrik Koelzer, and Gunnar Rätsch
MedRxiv 2025 | GitHub - Representation learning for multi-modal spatially resolved transcriptomics data
Kalin Nonchev, Sonali Andani, Joanna Ficek-Pascual, Marta Nowak, Bettina Sobottka, Tumor Profiler Consortium, Viktor Hendrik Koelzer, and Gunnar Rätsch
MedRxiv 2024 | GitHub
| Some movies… | Some books… | Some quotes… |
|---|---|---|
Well, I have to finish this resume in the near future…