Dominik Klein
@Dominik1Klein
Followers
390
Following
110
Media
13
Statuses
66
@EllisforEurope PhD student @HelmholtzMunich, Student Researcher @Apple. Interested in ML, Single-Cell Genomics, and People.
Joined March 2021
From cell lines to full embryos, drug treatments to genetic perturbations, neuron engineering to virtual organoid screens — odds are there’s something in it for you! . Built on flow matching, CellFlow can help guide your next phenotypic screen.
1/ Excited to share CellFlow, a new approach for complex perturbation modeling in single-cell genomics based on flow matching. From cytokine screens to cell fate and organoid engineering, we show CellFlow’s broad power across many diverse tasks. 👉 Paper:
1
2
27
RT @GrayCampLab: Learned a lot working with @josch_f @fabian_theis @dominik1klein @dbobrovskiy_ @TreutleinLab on CellFlow: generative singl….
0
27
0
RT @peholderrieth: Come to our oral presentation on Generator Matching at ICLR 2025 tomorrow (Saturday). Learn about a generative model tha….
0
11
0
Head to for tutorials, and get in touch—Plenty of exciting directions to explore!.
1
0
3
Big shoutout to co-lead @josch_f , and the fantastic team @dbobrovskiy_ Lea @SorenBecker @ale__palmaa Leander @Alejandro__TL @Guillaume_hu @HsiuChuan_Lin @NadyaAzbukina @fatima_snc @theo_uscidda @arturszalata @manuel_gander Aviv Regev @TreutleinLab @GrayCampLab @fabian_theis.
2
0
5
RT @theo_uscidda: Our work on geometric disentangled representation learning has been accepted to ICLR 2025! 🎊See you in Singapore if you w….
0
18
0
Intrigued? Also go check out our follow-up work @NeurIPS ( w @theo_uscidda and @ICLR24 w @LucaEyring, @theo_uscidda ( how to bring neural networks into this.
0
1
2
1
0
3
This was a highly collaborative project, thanks to everyone involved, in particular to the co-leads @g_palla, @MariusLange8 , Michal Klein, @zoe_piran, as well as Manuel Gander, @Laetitia_Ppx, Michael Sterr, @LamaSaber95, @Diana61204366, @AimeeBastidas, @pacotael, @MartaTarquis,.
1
0
3
Good to see moscot finally published in @Nature! Check out the paper (, the research briefing (, and to learn more about it!.
1/ Excited to see published in @Nature! We scaled Optimal Transport (OT) in single-cell genomics & added multimodality together with spatiotemporal trajectory inference, finding exciting new biology in the pancreas! 🚀 Read at
3
13
80
GIF art by @theo_uscidda ! Let’s meet and talk :).
Excited about optimal transport, flow matching, and single-cell genomics? Join Dominik, Marco, and me tomorrow (Wed 11th) at 4:30 PM at our poster #1111. Looking forward to great discussions! 🧬 @Dominik1Klein @fabian_theis @CuturiMarco
0
0
11
Let‘s chat science and anything else #NeurIPS2024.
1/2 🚀 Discrete Optimal Transport (OT) has proved useful in a wide variety of tasks in single-cell genomics, see e.g. Can we combine this powerful concept this with novel generative models? 🤔 .🌟 Enter GENOT: Generative Entropic Neural OT.
0
0
7
6/6 The paper was a fantastic collaboration with the amazing co-lead @theo_uscidda, @fabian_theis, and Marco Cuturi supervising the project during my internship at @Apple @HelmholtzMunich @CompHealthMuc @TU_Muenchen @ENSAEparis.
0
0
6
5/6 Check out our paper “GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics” to find many more applications for trajectory inference and perturbation modeling!
1
0
7
4/6 Generate #geneexpression if you only have access to #ATAC measurements, but make sure to use a Fused GW coupling (top) to optimally pair your cells instead of using an outer coupling (purely generative model, bottom).
1
0
7
3/6 We introduce balanced and unbalanced neural OT estimators for #Wasserstein, #GromovWasserstein and #FusedGromovWasserstein problems, working for any cost, presenting the first neural estimators for many of these tasks!
1
0
7
2/6 Optimal Transport is prevalent in single-cell genomics due to destructive sequencing, and has been applied in various tasks, see e.g. #moscot (. But it scales at least linearly + does not allow for out-of-sample estimation. So we need neural solvers!.
1
0
6
1/6 Looking for neural estimators of entropic #OptimalTransport or simply cool applications of #FlowMatching? Excited by novel generative modeling tools for #SingleCell data? Check out our #GENOT #NeurIPS paper
2
15
88
RT @MariusLange8: I am excited to share that moslin, our work on single-cell lineage tracing, is out in Genome Biology! We use lineage trac….
0
20
0