Kalin Nonchev, MSc
"From error to error, one discovers the entire truth." - Sigmund Freud
PhD Student
- kalin.nonchev@inf.ethz.ch
- Address
-
ETH Zurich
Biomedical Informatics Group
Department of Computer Science
Universitätstrasse 6 - Room
- CAB F 51.1
- @nonchevk
Committed to advancing machine learning research in biomedicine to improve clinical decision-making.
My research focuses on understanding the gap between genotype and phenotype in human diseases. Machine learning algorithms are key tools for uncovering biological patterns and interpreting medical datasets. I believe this is the key to more accurate disease diagnoses for patients, and, more importantly, the well-proven rationale for their therapies.
I studied bioinformatics at the Technical University of Munich and Ludwig-Maximilian University of Munich, followed by a Master's at ETH Zurich. During my Bachelor's, I worked with Prof. Julien Gagneur on rare disease genomics. In my Master's, I contributed to transcriptomics projects at the Functional Genomics Center Zurich and Roche Diagnostics. Currently, I am a doctoral candidate under Prof. Gunnar Rätsch's supervision. Meanwhile, I'm grateful to work with exceptional people who continually push the boundaries in biomedical informatics.
I am very open to research collaborations and mentoring BSc and MSc students. Please reach out if interested. Find out more on my homepage https://kalinnonchev.github.io.
Latest Publications
Abstract Spatial transcriptomics technology remains resource-intensive and unlikely to be routinely adopted for patient care soon. This hinders the development of novel precision medicine solutions and, more importantly, limits the translation of research findings to patient treatment. Here, we present DeepSpot, a deep-set neural network that leverages recent foundation models in pathology and spatial multi-level tissue context to effectively predict spatial transcriptomics from H&E images. DeepSpot substantially improved gene correlations across multiple datasets from patients with metastatic melanoma, kidney, lung, or colon cancers as compared to previous state-of-the-art. Using DeepSpot, we generated 1 792 TCGA spatial transcriptomics samples (37 million spots) of the melanoma and renal cell cancer cohorts. We anticipate this to be a valuable resource for biological discovery and a benchmark for evaluating spatial transcriptomics models. We hope that DeepSpot and this dataset will stimulate further advancements in computational spatial transcriptomics analysis.
Authors Kalin Nonchev, Sebastian Dawo, Karina Selina, Holger Moch, Sonali Andani, Tumor Profiler Consortium, Viktor Hendrik Koelzer, and Gunnar Rätsch
Submitted MedRxiv
Abstract Spatial transcriptomics enables in-depth molecular characterization of samples on a morphology and RNA level while preserving spatial location. Integrating the resulting multi-modal data is an unsolved problem, and developing new solutions in precision medicine depends on improved methodologies. Here, we introduce AESTETIK, a convolutional deep learning model that jointly integrates spatial, transcriptomics, and morphology information to learn accurate spot representations. AESTETIK yielded substantially improved cluster assignments on widely adopted technology platforms (e.g., 10x Genomics™, NanoString™) across multiple datasets. We achieved performance enhancement on structured tissues (e.g., brain) with a 21% increase in median ARI over previous state-of-the-art methods. Notably, AESTETIK also demonstrated superior performance on cancer tissues with heterogeneous cell populations, showing a two-fold increase in breast cancer, 79% in melanoma, and 21% in liver cancer. We expect that these advances will enable a multi-modal understanding of key biological processes.
Authors Kalin Nonchev, Sonali Andani, Joanna Ficek-Pascual, Marta Nowak, Bettina Sobottka, Tumor Profiler Consortium, Viktor Hendrik Koelzer, and Gunnar Rätsch
Submitted MedRxiv