niklas_a_s Profile Banner
Niklas Schmacke Profile
Niklas Schmacke

@niklas_a_s

Followers
290
Following
301
Media
11
Statuses
332

Shared PostDoc in Veit Hornung’s lab and Fabian Theis’ lab in Munich. Let‘s go.

Joined September 2011
Don't wanna be here? Send us removal request.
@BeroutiMarleen
Marleen Bérouti
7 days
One week ago, I finally defended my PhD ✨ I am deeply grateful to my supervisor @v_hornung, as well as to all collaborators and present and past lab members who made these past years fly by. Looking forward to everything that comes next.
0
3
9
@mtlushan
Jack D. Carson
17 days
I would say my biggest takesway from spending the last 8 months singlemindedly studying bioML is that understanding the biology actually is important
30
43
537
@fabian_theis
Fabian Theis
27 days
🚀 Excited to share our preprint scConcept: a contrastive pretraining framework for technology-agnostic single-cell representations. We move beyond reconstruction to learn rich, cell-level embeddings for diverse omics. 📘
Tweet card summary image
biorxiv.org
Recent large-scale single-cell foundation models have shown promise for exploring cellular states, yet they often underperform compared to simpler, domain-specific methods, raising concerns about...
3
19
122
@fabian_theis
Fabian Theis
1 month
Munich is now the #2 AI ecosystem in Europe (after Paris) and #11 globally, per Dealroom’s Global Tech Ecosystem Index 2025! 🇩🇪🤖🇫🇷 Proud of the growing strength of the Bavarian AI ecosystem 👉 https://t.co/Z4KgwtP9Gh 🔗 https://t.co/LmO0xPSJyJ #AI #Munich #baiosphere
Tweet card summary image
dealroom.co
This report is the conclusion of a data-driven analysis of 201 tech ecosystems. This set of actionable benchmarks is meant as a tool to help ecosystems understand and measure their maturity and...
1
2
33
@fabian_theis
Fabian Theis
1 month
🧬 Excited to share Nicheformer out now in Nature Methods! A transformer foundation model linking single-cell & spatial omics, learning spatial context from gene expression to map tissue organization. Led by Ale Tejada & Anna Schaar 👏 👉 https://t.co/ba9DX7h2xg
1
55
234
@fabian_theis
Fabian Theis
2 months
🚀 Our new Science paper is out (w/ B DeMeo, D Burkhardt, A Shalek, M Cortes): https://t.co/NSfnCblwHh We show that active learning + transcriptomic perturbations can guide which exps to run next, boosting phenotypic hit rates >13x. AI not just predicting bio, but designing it.🔁
8
78
398
@naturemethods
Nature Methods
2 months
scooby achieves DNA sequence-based single-cell level modeling of RNA-seq coverage and ATAC-seq insertion profiles by adapting a deep learning model that predicts bulk RNA-seq coverage. @thisisjohahi @lauradmartens @gagneurlab @TU_Muenchen https://t.co/NEEyeEgtAZ
0
28
103
@NatureBiotech
Nature Biotechnology
2 months
AlphaDIA enables DIA transfer learning for feature-free proteomics https://t.co/SN2zhq9zUY
0
11
22
@niklas_a_s
Niklas Schmacke
2 months
Using machine learning from biological structures to increase the resolution of microscopy images during acquisition. Very cool! Acting as an engine optimizing iterative data acquisition in real time instead of just being an endpoint is a compelling use case for ML in biology.
@bravo_abad
Jorge Bravo Abad
2 months
Fourier-based transformers for adaptive optics—no guide stars, no wavefront sensor High-resolution tissue imaging often breaks down inside real specimens: cells bend light, blurring fine structure and wasting photons. Classical adaptive optics fixes this using guide stars—tiny
0
0
2
@fabian_theis
Fabian Theis
2 months
🚀 Excited to share scPortrait! Led by Sophia Mädler & Niklas Schmacke w/ the Mann lab — a new @scverse tool for standardized single-cell image data. Enables ML-ready extraction, >1B cell processing, cross-omics, & cancer macrophage insights. 🔗 https://t.co/VXHrCBgdDh
2
62
326
@niklas_a_s
Niklas Schmacke
2 months
Want your biology AI model to learn spatial relationships? Add images as a modality! scPortrait enables fast, standardized generation and use of single-cell image datasets, powering AI/ML-based discovery. GitHub ⭐️: https://t.co/EEiqWnkLgZ Preprint 📚:
Tweet card summary image
biorxiv.org
Machine learning increasingly uncovers rules of biology directly from data, enabled by large, standardized datasets. Microscopy images provide rich information on cellular architecture and are...
@labs_mann
Matthias Mann Lab
3 months
Our preprint on scPortrait is out! We built a framework + format to turn microscopy into standardized single-cell image datasets. scPortrait scales >100M cells, integrates with scverse, & enables cross-modality modeling from morphology to transcriptomics https://t.co/50rSlikuQj
0
4
12
@Leopoldina
Nationale Akademie der Wissenschaften Leopoldina
3 months
🎉🎬 @zeynepakata erhält den „ZukunftsWissen“-Preis von Leopoldina & Commerzbank-Stiftung. Die Informatikerin @TU_Muenchen @HelmholtzMunich spricht über ihre Forschung zur erklärbaren #KI. Zum vollständigen Video auf YouTube: https://t.co/wKK2oYneJY
1
4
9
@IMPvienna
IMP
3 months
Marleen Bérouti (@BeroutiMarleen) from the lab of Veit Hornung @LMU_Muenchen (Ludwig-Maximilians-Universität München). 👏🏾 2/
1
3
11
@scverse_team
scverse
4 months
🎉 scverse conference 2025 Registration & Call for Abstracts NOW OPEN! 🎉 We're excited to announce that registration and the call for abstracts are officially open for the scverse Conference 2025! Details in thread! 🧵 1/3
1
8
22
@Lo_Zanzi
Ivan Zanoni
4 months
#InterferonPower! Thrilled for our latest work @CellCellPress! With @dfrboehmer, we dug into tons of papers & created what we hope will be a go-to resource for immunologists & non-immunologist about type I, II, III (& IV😉) #interferons! Free link 👉 https://t.co/gYwGir0npB
13
119
405
@erturklab
Ali Max Erturk
4 months
We discovered that the skull bone marrow has direct connections to brain surface & mirrors brain inflammation, making it a new site for diagnosing & monitoring brain pathologies. Kolabas…Ertürk, Cell: https://t.co/o8jTfgI1Ms https://t.co/2sPQra6sHZ https://t.co/NWNp39efaX
6
43
152
@MolecularCell
Molecular Cell
4 months
DIY innate immune sensing: Crafting fresh DNA to detect viruses https://t.co/snMhHlcXRa
0
10
49
@naturemethods
Nature Methods
5 months
Really excited to share this Perspective from John Danial covering how technology is moving the field of fluorescence microscopy toward structural biology.
Tweet card summary image
nature.com
Nature Methods - This Perspective introduces a framework for defining, measuring and reporting resolution in super-resolution microscopy and details the current state of the art in using...
1
54
154