Ran Blekhman

9.6K posts

Ran Blekhman banner
Ran Blekhman

Ran Blekhman

@blekhman

Professor of Medicine at @UChicago. Decoding the human microbiome. https://t.co/v7TIGaAfYu

Chicago Katılım Kasım 2012
478 Takip Edilen6.8K Takipçiler
Sabitlenmiş Tweet
Ran Blekhman
Ran Blekhman@blekhman·
These are challenging times for science, but I'm happy to share a bright moment: our work is on the cover of Cell today! We built a compendium of human gut microbiomes integrating 168K worldwide samples, revealing patterns of microbiome variation across the globe
Cell@CellCellPress

The new issue is out👉cell.com/cell/current Featuring an engineered Newcastle disease virus that selectively and safely lysed tumors in refractory cancer patients, the identification of rhodoquinone as a mammal mitochondrial electron carrier, and a metagenome-informed metaproteomics approach unravelling the interplay between the host, gut microbiome, and diet to identify disease biomarkers. 📷credit: SciStories⁠

English
3
13
89
11.5K
Ran Blekhman
Ran Blekhman@blekhman·
I've said it before: the bottleneck is not speed. This DNA model is 275x faster, but it creates a tree of life that groups drosophila with plants. How is AI going to solve cancer if it can't get the most basic biology right?
Leandro von Werra@lvwerra

We are releasing Carbon: a crazy fast DNA model Carbon is 275x faster than the next best model. So fast you can process the whole human genome on a single GPU in <2 days. Here are the tricks we used: When modelling DNA sequences a lot of the performance comes down to tokenizing the sequences in a smart way. BPE tokenizer struggle because there are no whitespaces and character (called base in DNA) level tokenizers waste a lot of compute on too many tokens. Carbon is built with a unique tokenizer: we split sequences in chunks of 6 bases, but during both training and inference we can work with single base resolution. That's similar to having word tokens but resolving them at the character level. All possible thanks to the DNA tokens unique structure. The architecture combined with the tokenizer makes the model 275x faster than the previous SoTA (Evo2) at this size. We built an interactive demo so you can explore how the model can generate DNA sequences, investigate the structure of genes, predict the effect of mutations, generate and fold proteins and even reconstruct parts of the tree of life. huggingface.co/spaces/Hugging…

English
8
8
92
14.2K
Ran Blekhman
Ran Blekhman@blekhman·
Some thoughts on where AI in genomics stands right now, building on a symposium we recently hosted. Seven points, ranging from why scaling DNA models hasn't delivered, to why metadata is the real bottleneck, to the weird backlash against AI in academia open.substack.com/pub/blekhman/p…
Ran Blekhman tweet media
English
5
30
87
7.6K
Ran Blekhman retweetledi
Sambhawa Priya
Sambhawa Priya@sambhawa_priya·
🔬How do clinical exposures shape the gut microbiome, and how do longitudinal clinical–microbiome signatures predict patient outcomes? Come find out at my poster #194 today at 7:30 pm at @cshlmeetings Biology of Genomes 2026! #bog26 @blekhman
English
0
1
1
277
Ran Blekhman
Ran Blekhman@blekhman·
Looking forward to #DDW2026! I will be presenting new work on host–microbiome interactions at single-cell resolution, led by Liz Gibbons in my lab Sunday, 8-9:30, W190a, session "AI-based approaches to unraveling gut microbiome complexity" Come find me - happy to talk!
Ran Blekhman tweet media
English
1
0
3
418
Ran Blekhman
Ran Blekhman@blekhman·
🧬 AI in Genomics Symposium next week! We're bringing together leading scientists from across academia and industry pushing the boundaries of AI in genomics research Join us May 8 at the University of Chicago - KCBD Auditorium, 9:30–5:00, reception to follow
Ran Blekhman tweet media
English
1
8
22
2.1K
Clement Chow
Clement Chow@ClementYChow·
Should I come back
English
5
0
26
2.3K
Ran Blekhman
Ran Blekhman@blekhman·
Visited Zion National Park for the first time - impossible to convey how beautiful it is
Ran Blekhman tweet media
English
0
0
4
185
Ran Blekhman
Ran Blekhman@blekhman·
Southern Utah countryside. The Google Pixel 10 has an amazing camera
Ran Blekhman tweet mediaRan Blekhman tweet mediaRan Blekhman tweet media
English
0
0
1
272
Ran Blekhman
Ran Blekhman@blekhman·
Layers. Today in Chicago
Ran Blekhman tweet media
English
0
0
2
231
Ran Blekhman
Ran Blekhman@blekhman·
We're searching for the next Director of the Duchossois Family Institute at UChicago The most exciting leadership role in microbiome science right now: lead faculty, cutting-edge cores, an FDA-approved facility for microbiome therapeutics Apply here: apply.interfolio.com/182203
Ran Blekhman tweet media
English
0
6
11
1.8K
Ran Blekhman
Ran Blekhman@blekhman·
AI has huge promise for genomics -- but it has consistently failed at microbiome-based prediction. My new post on why simple models keep winning, where deep learning actually earns its place, and where the field is headed. blekhman.substack.com/p/ai-keeps-fai…
Ran Blekhman tweet media
English
7
44
193
13.5K

Keşfet

@cshlmeetings @PracheeAC @ClementYChow @elonmusk @BarackObama @taylorswift13 @cristiano @BillGates