@hippopedoid @GCLinderman With @__exa__ we also observed that on Samusik data default init. of UMAP preserves Tcell clusters (Fig-1d https://t.co/6ujWHGwbLq) It is in agreement with extend. data fig-6 of your article! 😀 https://t.co/9BGVg7Zdky
@__exa__ @abhivkoladiya Thanks. Is this https://t.co/ktoa8u4Dbs a follow-up work? It says that it "introduces" EmbedSOM but it looks like a different paper from the one published in F1000... This got me a bit confused. I'd like to read up on SOM/EmbedSOM
@hippopedoid First try (I probably messed up the parameters) but it alreadly looks better than UMAP and was in fact 2x faster. Thanks for pointing this out! (Dataset: samusik_all, colors as in https://t.co/ogRrOv9qdh ) https://t.co/74YZ9d6Af4
Always glad to see others independently using our datasets 🙂 https://t.co/6gtmCILxiO
Find updated version of our recent article on flow cytometry data embedding algorithm on BioRxiv!
Here is the 2nd version of #EmbedSOM preprint:https://t.co/u2u2lfs2El This time with new parameters: importance, adjust, emcoord(for various layouting possibilities), smooth and 3D embedding(using z-dim). #SingleCell #clustering #cytometry #phdchat https:/
The second version of #EmbedSOM preprint is out: https://t.co/mCMUdSwFLQ - a collab w/@__exa__: 3D embedding (zdim) and a couple of new features, e.g. grid layouting (emcoords='flat'), etc. for Levine_13 dataset. https://t.co/l4Opg8XxEW
@JoeYeong well kindof, I wrote it this summer :D There's a beta-version paper on bioRxiv here https://t.co/zgqJyf5XHI if you want some details (hopefully we're publishing a better version later this month).
Thanks to @SofieVanGassen from @saeyslab for introducing #EmbedSOM - a non linear embedding algo. by @__exa__ and @Drbal_Lab at German #CyTOF users meeting! Here is a GitHub link: https://t.co/x0FU7ukEqg and pre-print :https://t.co/bZBO3wi3QB https://t.co
@KapellosTS @grip54 @abhivkoladiya @scoopit ...but the actual method of squashing of the multidimensional space to 2D is different in both algorithms. Some details are available in the preprint (sections 2.2, 2.3 and 4.2.1) https://t.co/OA7fzovpzs
EmbedSOM : a new non-linear algorithm for visualization of single-cell distribution | #FlowSOM #EmbedSOM #CyTOF #tSNE #UMAP | Karel Drbal @Drbal_Lab @abhivkoladiya @CharlesUniPRG @IOCBPrague | Preprint @biorxivpreprint https://t.co/Hf6UubmHut R package :
@NP_Rudqvist @jmigueljd Please also try EmbedSOM. We have a new pre-print out today on BioRxiv: https://t.co/jlHbvx4fNW … … where we defined a non linear embedding algorithm called EmbedSOM (which quicker and accurate than tSNE and UMAP). Here is link to t
Our new preprint is out! #SingleCell #HighDimensional #Datavisualization using non-linear #embedding #algorithm #EmbedSOM-a #FlowSOM-trained embedding: faster than #tSNE nd #UMAP. A collabo. btwn @__exa__ from @IOCBPrague, @Drbal_Lab nd @CZphenogenomics .
#SingleCell high-dimensional #Datavisualization is a breeze with #EmbedSOM-a #FlowSOM-trained embedding: faster than #tSNE or #UMAP, check the video: https://t.co/QJEbmz83iF. The collaboration btwn @__exa__, @CharlesUniPRG, @IOCBPrague nd @CZphenogenomics.
Efficient unbiased data analysis is a major challenge for laboratories handling large cytometry datasets. https://t.co/N4bmU0HrTd
We present EmbedSOM, a non-linear embedding algorithm based on FlowSOM that improves the analyses by providing high-performance visualization of complex single cell distributions within cellular populations and their transition states. https://t.co/pezyq17
Rapid single-cell cytometry data visualization with EmbedSOM https://t.co/fx38UjLIzh #biorxiv_bioinfo
Rapid single-cell cytometry data visualization with EmbedSOM https://t.co/2S79qbhkvv #bioRxiv