Fabian Theis ✓

@fabian_theis · Munich, Bavaria · joined 10 Mar 2010

Computational biologist @HelmholtzMunich, prof @TU_Muenchen & associate PI @sangerinstitute. Dad of 4 and mountain lover. Department news, see @CompHealthMuc

38 426Followers

430Following

4 348Posts total

109.7KViews on collected posts

Últimas publicaciones

Fabian Theis ✓@fabian_theis14 Sep

Topping-out ceremony at the ZDMG 🏗️ The shell of the Center for Digital Medicine and Health now stands on the campus of TUM Klinikum rechts der Isar. Bavaria's Science Minister Markus Blume joined us. Three signals I'm taking away: 🤝 Top-tier medicine is teamwork. Medicine, htt

1.8K views · 12 likes · 2 reposts · 0 replies Open on X →

Fabian Theis ✓@fabian_theis9 Sep

This feels like one of those moments when the future arrives all at once. OpenAI has published a solution to the Navier–Stokes existence and smoothness problem. This is one of seven Millennium Prize Problems selected by the Clay Mathematics Institute in 2000, carrying a $1 https

9.5K views · 90 likes · 14 reposts · 5 replies Open on X →

Fabian Theis ✓@fabian_theis17 Jul

Great discussions, inspiring talks, and plenty of new ideas at the Helmholtz Virtual Cell Workshop, held this Tuesday at Helmholtz Munich! 🧬🤖 It was a pleasure to bring together researchers from across the Helmholtz Health community and beyond to discuss how AI, foundation https

6.4K views · 63 likes · 8 reposts · 2 replies Open on X →

Fabian Theis ✓@fabian_theis10 Jul

@fabian_theis curious how it handles a missing modality, like no imaging just labs 44 views · 0 likes · 0 reposts · 0 replies Open on X →

Fabian Theis ✓@fabian_theis9 Jul

What if AI could learn the shared structure of human health across diseases, modalities, and time? Excited to share our new preprint introducing RisQ, an AI model that learns a shared representation of health across diseases, modalities, and time. 🚀 Some highlights: 🧬 A https:

9.8K views · 111 likes · 31 reposts · 1 replies Open on X →

Fabian Theis ✓@fabian_theis13 May

@fabian_theis Waddington’s Developmental Landscape Meets AI :) 47 views · 1 likes · 0 reposts · 0 replies Open on X →

Fabian Theis ✓@fabian_theis12 Dec 2024

8/ What sets RegVelo apart? •Interpretability: Models splicing kinetics + GRNs together. •Actionability: Enables predictions of gene interactions & perturbation outcomes. •Dynamic insights: Captures GRN changes over time. 2.2K views · 3 likes · 0 reposts · 1 replies Open on X →

Fabian Theis ✓@fabian_theis12 Dec 2024

9/ Overall, RegVelo learns dynamics GRNs. This work has been led by @KenWang89437252 & @PhilippWeiler7 in collab with @zhi_yuan_hu and @saukaspengler @TSS_Lab, so grateful for these interactions. Read more here: https://t.co/8Na9TD8ANr and checkout code at https://t.co/6pPeCbHT5I 2.3K views · 9 likes · 0 reposts · 2 replies Open on X →

Fabian Theis ✓@fabian_theis12 Dec 2024

7/ Why it matters: RegVelo isn’t just about modeling—it’s actionable. It allows systematic in silico perturbations of cell dynamics that can guide experimental designs and uncover mechanisms driving cellular fate. 🚀 1.4K views · 4 likes · 0 reposts · 1 replies Open on X →

Fabian Theis ✓@fabian_theis12 Dec 2024

6/ We further applied RegVelo to zebrafish neural crest development, generating new single-cell experiments (Smart-Seq3, 10x, Perturb-seq). Using RegVelo, we identified tfec & elf1 as key regulators for the pigment lineage and experimentally validated their roles. 🐟 https://t.co/

1.6K views · 3 likes · 0 reposts · 1 replies Open on X →

Fabian Theis ✓@fabian_theis12 Dec 2024

5/ Hematopoiesis is a prime example of a well-studied system where std RNA velocity fails due to its dynamic regulation. We showed that RegVelo overcomes this limitation, validated our inferred GRN, and rediscovered known key regulators with our in-silico perturbation scheme. htt

1.6K views · 3 likes · 0 reposts · 1 replies Open on X →

Fabian Theis ✓@fabian_theis12 Dec 2024

4/ How does RegVelo perform?  We validated RegVelo on: •Simulated & cell-cycle data (with ground truth) •Murine pancreatic endocrinogenesis •Human hematopoiesis •Zebrafish development It faithfully maps cellular changes & identifies lineage drivers! 🔬 https://t.co/56i4nfsTri

1.8K views · 2 likes · 0 reposts · 1 replies Open on X →

Fabian Theis ✓@fabian_theis12 Dec 2024

3/ To bridge the gap between cellular dynamics and gene regulation, we present RegVelo, an end-to-end deep learning framework integrating GRN-informed transcription into genome-wide models of splicing dynamics. https://t.co/We8rXAxLyL

2.1K views · 2 likes · 0 reposts · 1 replies Open on X →

Fabian Theis ✓@fabian_theis12 Dec 2024

2/ Why RegVelo? RNA velocity is a powerful concept for ~mechanistic modeling of cell dynamics, but existing methods ignore gene-gene interactions. Tools like Pando, CellOracle, and Dynamo treat GRNs separately w/o their dynamics, potentially limiting their ability to generalize. 2.5K views · 4 likes · 0 reposts · 1 replies Open on X →

Fabian Theis ✓@fabian_theis12 Dec 2024

1/🚀 Excited to share RegVelo, our new computational model combining RNA velocity with gene regulatory network (GRN) dynamics to model cellular changes and predict in silico perturbations. Here's how it works and why it matters! 🧵👇 https://t.co/8Na9TD8ANr https://t.co/CBiEHLg8b3

66.6K views · 401 likes · 99 reposts · 8 replies Open on X →

Frente a cuentas del mismo tamaño

5 publicaciones de los últimos 90 días, junto al rango de 10K–100K seguidores. llega a mucha gente, pero pocos de esos espectadores reaccionan.

Visualizaciones medianas6 369esta cuenta972mediana de 10K–100K

Alcance, %16.57%esta cuenta3.58%mediana de 10K–100K

Interacción, %1.16%esta cuenta1.60%mediana de 10K–100K

Métrica	Esta cuenta	Mediana de 10K–100K	Proporción
Visualizaciones medianas por publicación	6 369	972	6.55×
Alcance (visualizaciones ÷ seguidores)	16.57%	3.58%	4.63×
Tasa de interacción	1.16%	1.60%	0.73×

Otras cuentas de este rango → Comparar con otra cuenta → Cómo se construyen estas referencias →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

2.5K12 Dec

2.1K

1.8K

1.6K

1.4K

2.3K

2.2K

4713 May

9.8K9 Jul

4410 Jul

6.4K17 Jul

9.5K9 Sep

1.8K14 Sep

Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.20%12 Dec

0.14%

0.17%

0.25%

0.36%

0.49%

0.18%

2.13%13 May

1.47%9 Jul

0.00%10 Jul

1.16%17 Jul

1.16%9 Sep

0.76%14 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.60%.

What the audience does

Likes57.0%708 in total

Reposts12.4%154 in total

Replies2.0%25 in total

Quotes0.5%6 in total

Bookmarks28.1%349 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Últimas publicaciones

Frente a cuentas del mismo tamaño

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Cuentas similares