AI provides a universal framework that leverages data and compute at scale to uncover higher-order patterns

Today, @arcinstitute in collaboration with @nvidia releases Evo 2—a fully open source biological foundation model trained on genomes spanning the entire tree of life 🧵 Evo 2 is trained on 9.3T tokens of DNA with single-base resolution at 1M token context length 🥳

We release two models with 7B and 40B parameters along with weights, training and inference code, and pretraining data—making this one of the largest fully open AI models available

🧵Epigenetics require the coordinated interplay of diverse proteins and mechanisms. To systematically explore this, we invented the COMBINE platform to quantify the effect of >50,000 pairs🧦of long epigenetic effectors on endogenous human transcription biorxiv.org/content/10.110… COMBINE revealed diverse synergistic 🤝 and antagonistic 🤬 interactions between epigenetic protein domains, which we were able to study by calculating "synergy scores" for each individual pair and broader domain class (HDACs shown below)

What if we could universally recombine, insert, delete, or invert any two pieces of DNA?

In back-to-back @Nature papers, we report the discovery of bridge RNAs and 3 atomic structures of the first natural RNA-guided recombinase - a new mechanism for programmable genome design See our previous thread on preprint here:

Bridge RNA recombinases encode a mechanistically new class of guide RNAs

They are bispecific, unlike the CRISPR (2012) or RNA interference (1998) guide RNAs that specify only 1 target for a simple scissors cut

https://x.com/pdhsu/status/1750316518133694734

Is DNA all you need?

In new work, we report Evo, a genomic foundation model that learns across the fundamental languages of biology: DNA, RNA, and proteins. Evo is capable of both prediction tasks and generative design, from molecular to whole genome scale. This was a wonderful collaboration with @BrianHie led by @exnx, @MichaelPoli6, and @mgdurrant

Blog:
Preprint: arcinstitute.org/news/blog/evo
arcinstitute.org/manuscripts/Evo

Just shared at @KeystoneSymp a new @ArcInstitute discovery of the bridge RNA recombinase mechanism: a new class of natural RNA-guided systems that retains the key property of programmability from RNAi and CRISPR while enabling large-scale genome design beyond RNA and DNA cuts This was a remarkable detective story 🕵️that starts with transposons. These mobile genetic elements (MGEs) jump around genomes 🧬 and play a central and ancient role in evolution and speciation. IS110 is a poorly understood family of MGEs with unusually long noncoding sequences!

🧵 of insanely overlooked places to eat in SF:

yongzi ji for amazingly authentic HK-style wonton noodle soup. less than 10 things on the menu so you know it’s good. a hole in the wall run by an impossibly sweet older couple

pro-tip: add ~3:1 vinegar:soy sauce to taste saap ver (“damn good” in Thai) is the best Thai place in the city. the ambiance is boisterous while the food comes correct: an “asian spicy” order puts you straight into a fragrant hot ones episode

don’t sleep on the green beans and tofu or crispy basil duck (or pork belly)

Delighted to announce the Arc Institute @arcinstitute, a new, independent scientific institution dedicated to the study of complex human disease. Working with our partners @UCBerkeley @Stanford @UCSF, our mission is to accelerate progress in biomedical research and therapeutics. Learn more about Arc's headquarters, Core Investigators, Technology Centers, Translation Program, and more in this blog post written with my co-founders @SKonermann and @PatrickC: arcinstitute.org/blog/introduci…

The best coronavirus/SARS-CoV-2 biology lecture I have seen so far, by Britt Glaunsinger @UCBerkeley @berkeleyMCB @HHMINEWS @igisci. Covers where it comes from, how it gets into the cell, replicates in the host, and exploits the immune system against you.

An exonuclease (ExoN) is encoded in coronaviruses to enable their super large (30 kb) genomes. ExoN protects CoVs from inhibition by nucleoside analogs (e.g. Remdesivir @GileadSciences), suggesting a combo treatment w/ Remdesivir and an ExoN inhibitor could be effective

German study on viral load kinetics and seroconversion timescale, out in @nature. Highlights huge time sensitivity of swab testing, viral loads in upper respiratory tract tank after ~5 days of symptoms (swabs are yellow line, orange is sputum). Link to study, sorry: nature.com/articles/s4158…

Seroconversion is also slow! Only 50% after 7 days. This is important for applications of commercially available rapid serology tests, e.g. for back to work programs.