@blekhman profile picture
Ran Blekhman @blekhman

Professor of Medicine at @UChicago. Decoding the human microbiome. BlekhmanLab.org

Joined November 2012
  • Posts 9,615
  • Following 478
  • Followers 7,090
1,300 Photos and videos
Pinned Post
Ran Blekhman @blekhman
20 Feb 2025
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
20 Feb 2025
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
3
13
94
14,887
Claude Science is incredible. I gave it some sequencing data, and in 8 hours it did a full analysis, generated figures, wrote a paper, submitted it for publication, got rejected, revised and resubmitted, got rejected again, it is now applying for positions in industry
101
681
9,120
483,424
I wanted to like QED's new 1% preprint ranking. But the more I looked at the data, the more uncomfortable it made me. Here is my full peer review: open.substack.com/pub/blekhm…
9
25
109
59,393
It's pretty wild that AI is still so hard when there's only two bits (1 and 0)
Zach Ocean
 @zachocean_
Jun 25
it's pretty wild that biology is still so hard when there's only like 25k protein coding genes
1
37
3,706
Just start writing. My new post: substack.com/home/post/p-202…
7
584
Chicago in the summer is unbeatable
9
503
Excellent thread. We always use CLR transformation in metagenomics, so I was confused why it wasn't used in single-cell genomics Apparently the "CLR" function in the most common single-cell analysis tool failed all the benchmarks because it was implemented incorrectly 😶
Lior Pachter @lpachter
Jun 10
Arguably the most boring step in genomics is the first one: normalization. Settled science. Scale log. Move on. Except that here's been a huge blind spot in the field. And it matters for AIxBio. A 🧵about what I think may be one of the most important papers I've written. 1/
6
11
99
14,864
Ran Blekhman reposted
Arjun Raj
 @arjunrajlab
May 29
Can someone start a journal called “Cell Atlases” so that the rest of the journals can go back to publishing interesting things?
30
118
1,083
80,480
Reminder: giving an AI the prompt "You are a world expert in X" doesn't make it a world expert. It doesn't give the model additional knowledge or improve its reasoning. All it does is change the *style* of the output, so it sounds like an expert, even when it's wrong.
4
373
Wabash Avenue bridge, Chicago, today
1
5
363
1. An embryo can't have an IQ score. This is like saying the embryo has an 800 credit score or a 2000 chess Elo. It's nonsense 2. These polygenic scores have negligible predictive value for an individual's IQ - they explain a small proportion of variance at the population level
Gene Smith
 @GeneSmi96946389
May 22
A friend of mine had her embryos screened by Herasight and they found one with an IQ score in the 99.99th percentile
3
11
2,500
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
May 19
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/Huggin…
1:08
8
8
92
14,704
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/blekhm…
5
31
86
8,159
Also, the idea that peer-review provides some kind of protection against bad AI-generated content is absurd arstechnica.com/science/2024…

Scientists aghast at bizarre AI rat with huge genitals in peer-reviewed article

It's unclear how such egregiously bad images made it through peer-review.

arstechnica.com
2
384
This is genuinely funny. ArXiv exists because peer-review is slow, arbitrary, and not trustworthy. Now arXiv is making peer-review its judge, treating it as the only real trust signal.
Thomas G. Dietterich @tdietterich
May 14
The penalty is a 1-year ban from arXiv followed by the requirement that subsequent arXiv submissions must first be accepted at a reputable peer-reviewed venue. 4/
17
3
54
11,333
Happening today!!
Ran Blekhman @blekhman
Apr 29
🧬 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
1
1
442
Ran Blekhman reposted
Sambhawa Priya @sambhawa_priya
May 7
🔬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
1
1
311
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!
1
3
452
🧬 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
1
8
22
2,268
Visited Zion National Park for the first time - impossible to convey how beautiful it is
3
205
I wrote about why every lab should have AI use guidelines, and how to do it. open.substack.com/pub/blekhm…
14
1,257
Load more