Kalin Nonchev

PhD at @ETH Zurich, machine learning and biomedical data

[Kalin Nonchev @nonchevk]

How can we predict spatial transcriptomics from histology images to enable simple, affordable, and reliable analysis of spatially resolved gene expression in routine clinical use? 🤔 Introducing DeepSpot – a deep learning model designed to tackle this! 🧵👇

[Aayush Grover @AayushGrover8]

Excited to share that UniversalEPI is officially published in @OxfordJournals Nucleic Acids Research! 🚀

Check out the final paper and use the model here:
📄 Paper: https://t.co/OqwpTJjlQx
💻 Code: https://t.co/MTVQhVbFaE

(1/3) 🧵

[Aayush Grover @AayushGrover8]

1/ 🧬 Introducing Chiron3D: a framework that not only maps the 3D Genome from DNA but also decodes potential mechanical rules of loop extrusion through in silico editing. 🧵

Preprint: https://t.co/EV7XSEsqIq
Code: https://t.co/F9bcB5iCG3

#Genomics #AI

[Kalin Nonchev @nonchevk]

#iclr2026

[Kalin Nonchev @nonchevk]

Most spatial omics pipelines force a choice: integrate across modalities or scale across patients.
🙅 We don't think you should have to pick.
Preprint: https://t.co/DbQ40TTtCe
Code: https://t.co/ptAVOUWxvu

[Kalin Nonchev @nonchevk]

This work will be presented at ICLR 2026 – Learning Meaningful Representations of Life! 🎉

[Kalin Nonchev @nonchevk]

This project is based on Justina Dai's Bachelor's thesis and was carried out in close collaboration between the Biomedical Informatics Group at ETH Zürich (Gunnar Rätsch) and the Computational and Translational Pathology Lab at the University of Basel (Viktor H. Koelzer).

[bioRxiv Bioinfo @biorxiv_bioinfo]

Towards Cross-Sample Alignment for Multi-Modal Representation Learning in Spatial Transcriptomics https://t.co/B7I2t7Wf7H #biorxiv_bioinfo

[Crunch (Quant/acc) @crunchDAO]

Nearly 1,000 researchers from 62 countries took part, proving that open collaboration can push biomedical discovery faster than any single lab.

Read the full article 🔗https://t.co/ngIF7x2Oz3

[Andre Kahles (@[email protected]) @akkah21]

After years of research and continuous refinement, we’re thrilled to share that our paper on the MetaGraph framework — enabling Petabase-scale search across sequencing data — has been published today in Nature (https://t.co/WQgDjIYDZL).

[Kalin Nonchev @nonchevk]

This project, based on Glib Manaiev’s Master’s thesis, was carried out in close partnership between the Biomedical Informatics Group at @ETH (Gunnar Rätsch @gxr), the Computational and Translational Pathology Lab at @UZH_en and the @UniBasel_en (Viktor H. Koelzer).

[Kalin Nonchev @nonchevk]

Older spot-level spatial transcriptomics datasets shouldn’t be forgotten just because single-cell methods exist. 🧬

Instead of discarding this rich resource, we can bridge the gap.
DeepSpot2Cell makes it possible 👇

[Kalin Nonchev @nonchevk]

🎉 DeepSpot2Cell will be presented at NeurIPS 2025 Imageomics!

[Kalin Nonchev @nonchevk]

Preprint: https://t.co/NOcMPmlyPH
Code: https://t.co/dXf6967MJn

[Karsten Borgwardt @kmborgwardt]

Several postdoc positions and positions for scientific software engineers will become available in my department at the Max Planck Institute of Biochemistry in Munich over coming months. Topics include machine learning in bioengineering, in proteomics and in medicine. 1/2

[bioRxiv Bioinfo @biorxiv_bioinfo]

DeepSpot2Cell: Predicting Virtual Single-Cell Spatial Transcriptomics from H&E images using Spot-Level Supervision https://t.co/UA32nD9cCD #biorxiv_bioinfo

[Kalin Nonchev @nonchevk]

@Schmidt_Center @broadinstitute Thank you for organizing the challenge and building a community to tackle these important problems! @Schmidt_Center @broadinstitute