Publications

2026

1. Mapping trans-eQTLs at single-cell resolution using Latent Interaction Variational Inference

   Danai Vagiaki, Tobias Heinen, Manu Saraswat, Brian Clarke, and Oliver Stegle

   bioRxiv, 2026

   Abs DOI

   Abstract Single-cell expression quantitative trait loci (eQTL) studies hold promise for linking genetic variants to changes in gene expression in individual cells, thereby offering deeper insights into the genetic basis of human traits and diseases. Existing methods for mapping cis effects rely on predefined cell types, pseudobulk aggregation, or single-gene association tests, and are thus limited in their ability to detect complex trans effects that act across gene networks and cell-type subpopulations. Here, we present L atent I nteraction V ariational I nference ( LIVI ), an interpretable deep learning framework for efficient mapping of trans genetic effects at cellular resolution. LIVI employs a structured sparse variational autoencoder architecture to decompose observed gene expression profiles into cell-state- and donor-specific variation. The model enables efficient donor-level association testing while retaining single-cell resolution and interpretation. Applied to the OneK1K dataset, LIVI discovered a greater number of trans -eQTLs than alternative latent variable methods, yielded trans -eQTLs missed by conventional single-gene testing strategies and revealed the cell types and genes implicated in polygenic risk for autoimmune diseases. All in all, we demonstrate that LIVI is a powerful approach for linking genetics to gene regulation and through to human traits.

2. Multimodal phenotyping defines variant-to-function maps for RBM20 in dilated cardiomyopathy

   Kai Fenzl, Linda H. Müller, Julia Kornienko, Maria Majchrowska, Nils Eikmeier, Benjamin Wehnert, Edukondalu Mullapudi, Brendan J. Floyd, Brian Clarke, Kristian Schweimer, Janosch Hennig, Daniel Schraivogel, Victoria N. Parikh, Matthias Wilmanns, and Lars M. Steinmetz

   bioRxiv, 2026

   Abs DOI

   Abstract Multiplex assays of variant effects have linked thousands of genotypes to fitness effects, yet we lack profound understanding of how variants impact molecular phenotypes. Here, we introduce a deep mutational scanning framework that quantifies disease-determining molecular phenotypes in human cells, allowing readouts of protein localization and splicing regulatory function at scale. Applied to the dilated cardiomyopathy (DCM)-associated protein RBM20, we profiled ∼4,300 amino acid substitutions across disease-linked protein domains. Complemented by structure-function investigations of RBM20 bound to its nuclear import receptor TNPO3, we discover new variant hotspots affecting protein function. Finally, we systematically probed nuclear relocalization to identify variants that may be amenable to this therapeutic strategy. Together, we create comprehensive variant-to-function maps that predict variant impact, enhance clinical interpretation, and stratify RBM20-mediated DCM into mechanistically distinct therapeutic classes.

2025

1. Predicting functional constraints across evolutionary timescales with phylogeny-informed genomic language models

   Chengzhong Ye, Gonzalo Benegas, Carlos Albors, Jianan Canal Li, Sebastian Prillo, Peter D. Fields, Brian Clarke, and Yun S. Song

   bioRxiv, 2025

   Abs DOI

   Genomic language models (gLMs) have emerged as a powerful approach for learning genome-wide functional constraints directly from DNA sequences. However, standard gLMs adapted from natural language processing often require extremely large model sizes and computational resources, yet still fall short of classical evolutionary models in predictive tasks. Here, we introduce GPN-Star (Genomic Pretrained Network with Species Tree and Alignment Representation), a biologically grounded gLM featuring a phylogeny-aware architecture that leverages whole-genome alignments and species trees to model evolutionary relationships explicitly. Trained on alignments spanning vertebrate, mammalian, and primate evolutionary timescales, GPN-Star achieves state-of-the-art performance across a wide range of variant effect prediction tasks in both coding and non-coding regions of the human genome. Analyses across timescales reveal task-dependent advantages of modeling more recent versus deeper evolution. To demonstrate its potential to advance human genetics, we show that GPN-Star substantially outperforms prior methods in prioritizing pathogenic and fine-mapped GWAS variants; yields unprecedented enrichments of complex trait heritability; and improves power in rare variant association testing. Extending beyond humans, we train GPN-Star for five model organisms – Mus musculus, Gallus gallus, Drosophila melanogaster, Caenorhabditis elegans, and Arabidopsis thaliana – demonstrating the robustness and generalizability of the framework. Taken together, these results position GPN-Star as a scalable, powerful, and flexible new tool for genome interpretation, well suited to leverage the growing abundance of comparative genomics data.Competing Interest StatementThe authors have declared no competing interest.National Institutes of Health, R35-GM134922, 3P40-OD011102-24S1 7772

2. Cell2fate infers RNA velocity modules to improve cell fate prediction

   Alexander Aivazidis, Fani Memi, Vitalii Kleshchevnikov, Sezgin Er, Brian Clarke, Oliver Stegle, and Omer Ali Bayraktar

   Nature Methods, Apr 2025

   DOI HTML

2024

1. Integration of variant annotations using deep set networks boosts rare variant association testing

   Brian Clarke, Eva Holtkamp, Hakime Öztürk, Marcel Mück, Magnus Wahlberg, Kayla Meyer, Felix Munzlinger, Felix Brechtmann, Florian R. Hölzlwimmer, Jonas Lindner, Zhifen Chen, Julien Gagneur, and Oliver Stegle

   Nature Genetics, Oct 2024

   DOI HTML
2. Scalar curvature along Ebin geodesics

   Christoph Böhm, Timothy Buttsworth, and Brian Clarke

   Journal für die reine und angewandte Mathematik (Crelle’s Journal), Jun 2024

   DOI HTML
3. Bicycle: Intervention-Based Causal Discovery with Cycles

   Martin Rohbeck, Brian Clarke, Katharina Mikulik, Alexandra Pettet, Oliver Stegle, and Kai Ueltzhöffer

   In Proceedings of the Third Conference on Causal Learning and Reasoning, Mar 2024

   HTML

2015

1. Gaussian measures on the of space of Riemannian metrics

   Brian Clarke, Dmitry Jakobson, Niky Kamran, Lior Silberman, and Jonathan Taylor

   Annales mathématiques du Québec, Oct 2015

   DOI HTML

2013

1. Ricci flow and the metric completion of the space of Kähler metrics

   Brian Clarke and Yanir A. Rubinstein

   American Journal of Mathematics, Nov 2013

   DOI HTML
2. Conformal deformations of the Ebin metric and a generalized Calabi metric on the space of Riemannian metrics

   Brian Clarke and Yanir A. Rubinstein

   Annales de l’Institut Henri Poincare (C) Non Linear Analysis, Mar 2013

   DOI HTML
3. The completion of the manifold of Riemannian metrics

   Brian Clarke

   Journal of Differential Geometry, Feb 2013

   DOI HTML
4. Geodesics, distance, and the CAT(0) property for the manifold of Riemannian metrics

   Brian Clarke

   Mathematische Zeitschrift, Feb 2013

   DOI HTML

2011

1. The Riemannian L2 topology on the manifold of Riemannian metrics

   Brian Clarke

   Annals of Global Analysis and Geometry, Feb 2011

   DOI HTML

2010

1. The metric geometry of the manifold of Riemannian metrics over a closed manifold

   Brian Clarke

   Calculus of Variations and Partial Differential Equations, Nov 2010

   DOI HTML