Constantin Ahlmann-Eltze (@const-ae.bsky.social)

238 posts

Constantin Ahlmann-Eltze (@const-ae.bsky.social)

@const_ae

Postdoc at UCL with @JL_Reading. Previously at EMBL working with @wolfgangkhuber. Biostats, R, cancer immunology Find me on 🦋 at https://t.co/qOh57AUB49

London เข้าร่วม Aralık 2010

680 กำลังติดตาม1.2K ผู้ติดตาม

Constantin Ahlmann-Eltze (@const-ae.bsky.social)@const_ae·10 Oca

@NadigAjay Thanks :) I discussed the idea a bit in #issuecomment-2508931767" target="_blank" rel="nofollow noopener">github.com/const-ae/lemur… However, such a test would require some additional statistical groundwork. I would love it if someone picked this up :)

English

266

Ajay Nadig@NadigAjay·10 Oca

@const_ae Congratulations on this great work! Do you think LEMUR could be used to perform a global test for whether a treatment is associated with transcriptome-wide gene expression? (maybe testing whether R(treated) differs from R(control))

English

Constantin Ahlmann-Eltze (@const-ae.bsky.social)@const_ae·3 Oca

After 4y in the making, I am super excited that my main PhD project is published 🎉🥳🎉🎉🥳 nature.com/articles/s4158… LEMUR is a tool to analyze multi-condition single-cell data and model differential expression as a continuous function of the cell-state space. Some highlights⬇️

Constantin Ahlmann-Eltze (@const-ae.bsky.social) tweet media

English

2.2K

Constantin Ahlmann-Eltze (@const-ae.bsky.social) รีทวีตแล้ว

Clint Miller@clintomics·3 Oca

New single-cell analysis framework, LEMUR, disentangles covariates and latent cell states from multi-condition data to predict counterfactual gene expression and identify cell neighborhoods with similar DEGs without clustering. doi.org/10.1038/s41588… @NatureGenet @wolfgangkhuber

English

Constantin Ahlmann-Eltze (@const-ae.bsky.social)@const_ae·6 Oca

For the Monday morning crowds :) Also, take a look at my blog post, in which I compress the full lemur package into 100 lines of code and explain the core algorithm. const-ae.name/post/2025-01-0…

Constantin Ahlmann-Eltze (@const-ae.bsky.social)@const_ae

English

366

Constantin Ahlmann-Eltze (@const-ae.bsky.social)@const_ae·3 Oca

Big shout out to everyone involved: my supervisor @wolfgangkhuber and everyone else who helped along the journey: @OliverStegle @s_anders_m @zauggj @LSaund11 bsky.app/profile/ronnyb… And lastly, this link should work even without a Nature subscription: rdcu.be/d5puu

English

230

Constantin Ahlmann-Eltze (@const-ae.bsky.social)@const_ae·3 Oca

Finally, we demonstrate LEMURs usefulness on - a treatment vs. ctrl dataset from glioblastoma, - Zebrafish developmental time course, and - a spatially resolved Alzheimer dataset where we find intriguing DE patterns

English

288

Constantin Ahlmann-Eltze (@const-ae.bsky.social) รีทวีตแล้ว

Aino-Maija Leppä@amleppa·25 Kas

Extremely proud to see my PhD project exploring intra-tumor heterogeneity in complex karyotype AML finally out in @NatureGenet ! 🎉👩🏻‍🔬 They say that 10,000 hours make you an expert, so I guess after more than five years of work I’m half-way there 😅 ⬇️1/5 nature.com/articles/s4158…

English

125

7.4K

Constantin Ahlmann-Eltze (@const-ae.bsky.social) รีทวีตแล้ว

Hadley Wickham@hadleywickham·30 Eki

The #rstats community on bluesky seems to be really picking up steam, so you can also find me over there: bsky.app/profile/hadley…

English

12.2K

Constantin Ahlmann-Eltze (@const-ae.bsky.social)@const_ae·2 Eki

@kasparmartens Very nice work. I like your mean-perturbation-effect baseline, and the LLM embeddings from the sequence and text are a cool idea. I will update the Discussion to incorporate this :)

English

Kaspar Märtens 💙💛@kasparmartens·2 Eki

@const_ae Really nice work! These findings are also generally aligned with what we’ve seen in perturbation prediction. Actually we have a paper on the topic of unseen single-gene perturbation prediction, see openreview.net/forum?id=eb3nd…

English

123

Constantin Ahlmann-Eltze (@const-ae.bsky.social)@const_ae·20 Eyl

There's a lot of excitement about foundation models and their ability to learn biology 🧬💻 But current tools for perturbation prediction perform worse than simple linear models! We need more careful benchmarking to make progress. biorxiv.org/content/10.110…

English

253

31.9K

Constantin Ahlmann-Eltze (@const-ae.bsky.social) รีทวีตแล้ว

Charlotte Bunne@_bunnech·25 Eyl

🚀Interested in doing a PostDoc in my lab? Consider applying for a🇨🇭SNSF Swiss Postdoctoral Fellowship 2024. If you have any questions, join the information event tomorrow via Zoom (register via shorturl.at/zP93m) or reach out to us via bunnelab.com! 🧬Who should apply? Check that you fulfill the requirements. And: We are in particular interested in candidates with background in computational biology or machine learning applied to the biomedical domain!

Swiss National Science Foundation@snsf_ch

📢 #Call for SNSF Swiss Postdoctoral Fellowships 2024 This highly competitive call is aimed at researchers who wish to obtain a position in a non-profit research institution in Switzerland for a period of 12 to 24 months. 🗓️Deadline: 2 December 2024 sohub.io/6afa

English

16.6K

Constantin Ahlmann-Eltze (@const-ae.bsky.social)@const_ae·22 Eyl

@science_wallet That sounds exciting, can't wait to see what you are cooking up :)

English

170

Thomas Walle@science_wallet·21 Eyl

@const_ae We had the same experience when comparing Spectra for gene program inference with autoencoder based models doi.org/10.1038/s41587… And now also when benchmarking cell typing model generalization to truly independent external data (preprint coming soon doi.org/10.5281/zenodo…

English

313

Constantin Ahlmann-Eltze (@const-ae.bsky.social)@const_ae·21 Eyl

Great thread by Anshul, one of the pioneers of deep learning for biology, summarizing our preprint!

Anshul Kundaje@anshulkundaje

biorxiv.org/content/10.110… Nice benchmark of single cell "foundation models" (scGPT, scFoundation) and GEARS (a GNN model) further hyped as "virtual cell models" against linear baselines on perturbation prediction. Long-story short: they can't beat the linear baselines. 1/

English

Constantin Ahlmann-Eltze (@const-ae.bsky.social)@const_ae·20 Eyl

@pan_cancer @Alejandro__TL replied on Github and clarified that Prophet in its current form is not intended for predicting perturb-seq experiments, but that they are considering adding that feature in the future.

English

164

Constantin Ahlmann-Eltze (@const-ae.bsky.social)@const_ae·20 Eyl

@pan_cancer Yes, it would be great to include Prophet in the benchmark. I just asked how to best apply the software to genetic perturbation data (github.com/theislab/proph…) because I don't quite understand yet how to use the software :)

English

414

ค้นพบ

@NadigAjay @NatureGenet @OliverStegle @s_anders_m @zauggj @LSaund11 @kasparmartens @science_wallet