Hannah Spitzer

18 posts

Hannah Spitzer

@HannahSpitzer1

Machine learning researcher with focus on biomedical and neuroscience applications

Munich Katılım Aralık 2018

23 Takip Edilen300 Takipçiler

Hannah Spitzer@HannahSpitzer1·9 Nis

Our cross-species pancreas development analysis is out! A huge thanks to @Carina_K_YANG for this amazing collaboration, and having patience with me while I learnt about pancreas development 👍

Heiko Lickert@LickertHeiko

Thrilled to share our work “A multimodal cross-species comparison of pancreas development”. doi.org/10.21203/rs.3.… A tremendous collaborative effort led by @Carina_K_YANG & @HannahSpitzer1, and other members of @LickertHeiko @fabian_theis, Eckhard Wolf labs.

English

311

Hannah Spitzer@HannahSpitzer1·1 Haz

@_lysine7 @lucaspelkmans @fabian_theis @naturemethods @scottbscience Hi! CAMPA was developed for exactly such a use-case - when you want to quantitatively compare subcellular structure in multiple conditions. It is trained on data from all conditions and learns consistent subcellular landmarks which we then use to compare.

English

Nature Methods@naturemethods·30 May

In case you missed it yesterday! CAMPA (Conditional Autoencoder for Multiplexed Pixel Analysis) learns representations of molecular pixel profiles from multiplexed images that can be clustered to quantify subcellular landmarks and capture interpretable cellular phenotypes. (1/n)

English

20.5K

Hannah Spitzer@HannahSpitzer1·1 Haz

I‘m very proud that CAMPA is finally out in @naturemethods! This was one of my main postdoc projects and an awesome collaboration with @scottbscience - also thanks to @fabian_theis and @lucaspelkmans for all of your support and guidance!

Fabian Theis@fabian_theis

@naturemethods @lucaspelkmans Happy that CAMPA is out @naturemethods - led by @HannahSpitzer1 & @scottbscience w @lucaspelkmans we developed a conditional autoencoder for multiplexed image analysis, learning subcellular landmarks consistent across perturbations. github.com/theislab/campa nature.com/articles/s4159…

English

5.7K

Hannah Spitzer@HannahSpitzer1·1 Haz

@_lysine7 @fabian_theis @lucaspelkmans @naturemethods @scottbscience Yes, as long as you have a multiplexed dataset of these proteins, CAMPA will allow you to analyse their spatial patterns and how they change in different conditions - always with respect to the subcellular landmarks we can identify with CAMPA.

English

Hannah Spitzer@HannahSpitzer1·16 Ağu

Interested in how to do interpretable lesion detection in a large real-world multi-centre cohort? Check out our new paper on this - an amazing team effort together with @mathrip3 @sophieadler @KonradWagstyl

Sophie Adler@sophieadler

We are SO EXCITED that our paper "Interpretable surface-based detection of focal cortical dysplasias: a @meld_project study" is published in @Brain1878 academic.oup.com/brain/advance-… 🧵👇

English

Hannah Spitzer@HannahSpitzer1·11 May

@sjogren_rickard @scottbscience @fabian_theis @pelkmanslab In general, for the VAE the usual hyperparameter tuning was necessary. We used parameters obtained on the 184A1 dataset for the HeLa dataset as well — so they seem to be fairly general.

English

Scott Berry@scottbscience·9 May

Happy to share #CAMPA 🏕, our new analysis method for highly multiplexed subcellular protein imaging. The first collaboration between @fabian_theis group and @pelkmanslab led by @HannahSpitzer1 and me. biorxiv.org/content/10.110… 🧵 1/10

GIF

English

228

Hannah Spitzer@HannahSpitzer1·11 May

@sjogren_rickard @scottbscience @fabian_theis @pelkmanslab The nbhood is useful to make the latent space robust to noise, similar to smoothing. Its size will impact the minimal size of structures that you can find — we used 3px, as we were eg interested in small PML bodies. So choice of nbhood size depends on the resolution of your data.

English

Hannah Spitzer@HannahSpitzer1·9 May

Very excited to share our new work on learning consistent subcellular landmarks! #CAMPA allows for quantitative analysis of multiplexed protein imaging in different conditions. Check out the manuscript biorxiv.org/content/10.110… and the code campa.readthedocs.io

Scott Berry@scottbscience

English

Hannah Spitzer retweetledi

Giovanni Palla@g_palla1·31 Oca

Squidpy 🌌🍤🐍🎉 is out in @naturemethods ! Truly collab effort with @HannahSpitzer1 Michal Klein @fabian_theis lab! nature.com/articles/s4159…

English

261

Hannah Spitzer retweetledi

Fabian Theis@fabian_theis·16 Kas

Excited that our Squidpy & @napari_imaging integration project was awarded by @cziscience 🥳🎉 We'll develop a Napari plugin to visualize & integrate sets of spatial omics data, bringing closer the #scanpy community with the #skimage imaging community. chanzuckerberg.com/science/progra…

English

145

Hannah Spitzer@HannahSpitzer1·2 Tem

Finally, we added new example datasets! You can access SeqFISH, MERFISH, Slide-seqV2, Visium, Mibi-tof, 4i, IMC datasets through the Squidpy API to try out all the new functions! #analysis-of-spatial-datasets-using-squidpy" target="_blank" rel="nofollow noopener">squidpy.readthedocs.io/en/stable/tuto… Thanks to @macosko @AleksGoeva for providing pre-processed Slide-seqV2 data!

English

Hannah Spitzer@HannahSpitzer1·2 Tem

This release also brings you sepal from @aalmaander for spatially variable genes, new graph building methods, and extended functions for spatial statistics. squidpy.readthedocs.io/en/stable/tuto…

English

Hannah Spitzer@HannahSpitzer1·2 Tem

We are very excited to release Squidpy 1.1 🌌🦑🍤 squidpy.readthedocs.io/en/stable/ Lots of new features in the thread below! This is joint work with @g_palla1 Michal Klein and @fabian_theis group. @scanpy_team @HelmholtzMunich @ICBmunich

English

195

Hannah Spitzer retweetledi

Fabian Theis@fabian_theis·22 Şub

Excited to share 'Squidpy', our toolbox for spatial single cell analysis. Led by @g_palla1 & @HannahSpitzer1, we extend #Scanpy's infrastructure and analyses to store, manipulate & interactively visualize spatial omics data. Read at biorxiv.org/content/10.110… squidpy.readthedocs.io

English

187

579

Hannah Spitzer retweetledi

Helmholtz AI@helmholtz_ai·10 Şub

Congratulations @HannahSpitzer1!

Susanne Wenzel@wenzel_susanne

Congrats to @HannahSpitzer1 who defended her thesis today. Well done! @fz_juelich @BigBrainProject @helmholtz_ai

English

Hannah Spitzer@HannahSpitzer1·30 Eki

I am proud to be nominated as AI newcomer for the #KI50 @informatikradar for my work on automatic segmentation of brain areas done @fz_juelich! I would appreciate your vote: ki50.de/ki-newcomer/na…

English

Keşfet

@Carina_K_YANG @lucaspelkmans @fabian_theis @naturemethods @scottbscience @sophieadler @pelkmanslab @napari_imaging