iiinova — where your digital self keeps evolving

Reposted by Lucas Arnoldt

Julius Upmeier zu Belzen @juliusuzb.bsky.social · 05/08/2026

🧬 New preprint! An interpretable omnigenic neural network architecture for the human genome We introduce the Omnigenic Model (OGM), a neural network architecture for human genetics. It uses biological system structure to aggregate genetic variation for disease risk prediction.

doi.org

1155

Lucas Arnoldt @larnoldt.bsky.social · 16/06/2025

NetworkVI is a group effort by @juliusuzb.bsky.social, Luis Herrmann, Khue Nguyen, supervised by @fabiantheis.bsky.social & Benjamin Wild & Roland Eils at @bihatcharite.bsky.social and @www.helmholtz-munich.de‬. Code: github.com/LArnoldt/networkVI 🧠 Open-source & ready to use!

github.com

GitHub - LArnoldt/networkvi

Contribute to LArnoldt/networkvi development by creating an account on GitHub.

032

Lucas Arnoldt @larnoldt.bsky.social · 16/06/2025

We demonstrate how NetworkVI identifies immune evasion mechanisms via GO programs in a CRISPR-perturbed melanoma dataset not detectable with standard methods. This highlights the medical utility of interpretable multimodal models.

100

Lucas Arnoldt @larnoldt.bsky.social · 16/06/2025

NetworkVI also incorporates a GO-specific covariate attention mechanism, allowing the model to adjust for sample-level metadata (e.g., donor or condition), improving both performance and interpretability in heterogeneous datasets.

100

Lucas Arnoldt @larnoldt.bsky.social · 16/06/2025

These scores reveal associations between genes and GO terms, helping to identify active biological processes and their regulatory drivers in a given condition or perturbation. This opens a path toward mechanistic interpretation beyond enrichment tests.

100

Lucas Arnoldt @larnoldt.bsky.social · 16/06/2025

NetworkVI’s architecture incorporates prior biological knowledge: 1. Gene-gene interactions from TADs 2. The structure of the Gene Ontology This enables inference of gene and GO term importance scores at modality- and cell-specific resolution.

110

Lucas Arnoldt @larnoldt.bsky.social · 16/06/2025

📊 NetworkVI achieves state-of-the-art performance on bimodal and trimodal data: ✅ Accurate integration ✅ Imputation of missing modalities ✅ Query-to-reference mapping ✅ Interpretation of cell type– and perturbation-specific signatures

100

Lucas Arnoldt @larnoldt.bsky.social · 16/06/2025

Current multimodal single-cell integration methods act as black boxes, lacking meaningful interpretability. We introduce NetworkVI, a VAE that performs integration via gene-gene interactions and the Gene Ontology for biologically grounded analysis. www.biorxiv.org/content/10.1...

biorxiv.org

110