@sim0nsays

Researcher at MIT, generative AI for biology

 New York, NY
Joined March 2009
  • Tweets1.3K
  • Following319
  • Followers2.6K
62Media
The picture was intended to be about AI in biology, but now it’s about everything.
Simon Kozlov@sim0nsaysMay 1
Replying to @sim0nsays
Here pLM redesigns most of the helix and introduces other mutations. What makes it work? I wish I knew. Understanding the mechanics of this solution alone requires an experimental effort comparable to this whole project, if not more. Which brings me to Feynman's famous quote. 8/
3
286
Homeworld Academy applications are closing today! Join our free 8-week remote course where early-career bioscientists will learn to identify high-potential climate applications for their biological research. Apply here by EOD today: homeworld.bio/academy
1
1
148
Simon Kozlov retweeted
Yo Akiyama@yoakiyamaJul 21
Excited to share our now published manuscript @CellCellPress highlighting advances in modeling the evolution of protein-protein interactions with MSA Pairformer. Big thanks to @ZhidianZ, @oliviatang116, @eunbelivable, Milot Mirdita, Martin Steinegger, and @sokrypton !🧵 (1/10) cell.com/cell/fulltext/S0092…

Expanding the scope of protein language modeling to protein-protein interactions with MSA Pairformer

Protein language models have excelled at modeling individual proteins, but extending these capabilities to protein complexes remains a major challenge. MSA Pairformer, a parameter-efficient protein...

cell.com
6
72
2
292
20,489
Simon Kozlov retweeted
Sergei Belousov
@bes_devJun 15
Harness engineering is essentially prompt engineering in a new form. The skills and instructions we write raise the chances of success, but they give no guarantees. Every written line stays a recommendation for the AI, and the model can always ignore it at its own discretion.
1
2
2
7
428
This is the way.
Ben Cohen
@blc_16May 10
Replying to @nirmal_dist
Going to use GEPA to optimize my Online Rubric evaluator prompt that's RLing my GEPA base model performance
1
424
Simon Kozlov retweeted
Sergei Belousov
@bes_devMay 4
How was your weekend? I spent mine launching the Space Shuttle. With NASA code from 1970 that nobody could run for 50 years.
26
127
8
3,404
208,834
Simon Kozlov retweeted
Eric Topol
@EricTopolApr 30
Not something you'd see everyday—changing the alphabet of life. All of life organisms are are built from 20 amino acids. Now genAI is enabling life to be built with 19 amino acids, making isoleucine dispensable. @ScienceMagazine science.org/doi/10.1126/scie…
8
51
3
205
25,331
「バリンとロイシンあればイソロイシンは要らないのでは？」ということで大腸菌で菌の viability を保って "we were able to individually recode all 50+ ribosomal subunits to replace all 382 isoleucine residues" とのこと。 それをやろうとした好奇心と根気がすごい。
Harris Wang@harriswangnycApr 30
1/ Excited to share our new paper in Science: “Toward life with a 19-amino acid alphabet through generative artificial intelligence design.” @ColumbiaSysBio @ColumbiaBME @Columbia science.org/doi/10.1126/scie… 🦠🧬🛠️🖥️💥

Toward life with a 19–amino acid alphabet through generative artificial intelligence design

Because all known living organisms are made from at least 20 canonical amino acids, the feasibility of life using a more simplified alphabet remains unclear. In this work, we leveraged computational...

science.org
1
24
130
21,934
Simon Kozlov retweeted
Ars Technica
@arstechnicaApr 30
Researchers try to cut the genetic code from 20 to 19 amino acids arstechnica.com/science/2026…

Researchers try to cut the genetic code from 20 to 19 amino acids

Using AI tools, the team reworked part of the ribosome to need one less amino acid.

arstechnica.com
1
2
1
5
4,214
Simon Kozlov retweeted
Scientific American
@sciamApr 30
An engineered E. coli strain survived after one amino acid was designed out of many of its ribosomal proteins—an early test of whether life’s chemistry can be simplified spklr.io/6017EKQy3

Scientists use AI to test whether life can run on only 19 amino acids

An engineered E. coli strain survived after one amino acid was designed out of many of its ribosomal proteins—an early test of whether life’s chemistry can be simplified

scientificamerican.com
2
15
1
47
8,173
Yours truly is a proper scientist now! TL;DR: we used AI to redesign parts of essential cell machinery with only 19 canonical amino acids instead of 20. Why? Great thread by @harriswangnyc provides more context and details. Let me talk a bit about the AI design part of this. 1/
Harris Wang@harriswangnycApr 30
1/ Excited to share our new paper in Science: “Toward life with a 19-amino acid alphabet through generative artificial intelligence design.” @ColumbiaSysBio @ColumbiaBME @Columbia science.org/doi/10.1126/scie… 🦠🧬🛠️🖥️💥

Toward life with a 19–amino acid alphabet through generative artificial intelligence design

Because all known living organisms are made from at least 20 canonical amino acids, the feasibility of life using a more simplified alphabet remains unclear. In this work, we leveraged computational...

science.org
4
14
1
98
16,082
more replies
No single model was able to solve every gene, it took all of them + developing novel methods. And even then, there are genes no model was able to solve - we had to use mutagenesis on last 3 stragglers. No model thinks these solutions are good, but they work in vivo. 9/
1
1
7
807
We're still far from solving biology with AI, but the progress is astonishing - the median number of designs to solve a gene was around 4. Huge thanks to @sokrypton @harriswangnyc for the mentorship and support, and all the collaborators! @lly_sam1 @charochereau @goGUrtecho ♥️
7
465
Load more