Sign in

pdhsu.bsky.social

@pdhsu.bsky.social
1K followers 1.1K following 29 posts
PostsRepliesMedia
pdhsu.bsky.social @pdhsu.bsky.social · 15/05/2025
Read the full preprint below 👇 If you're interested in the interface of bioengineering, DNA and virtual cell foundation models, and agentic reasoning, shoot me a note. We're hiring postdocs and ML researchers and starting some crazy new projects www.biorxiv.org/content/10.1...
biorxiv.org
Megabase-scale human genome rearrangement with programmable bridge recombinases
Bridge recombinases are a class of naturally occurring RNA-guided DNA recombinases. We previously demonstrated they can programmably insert, excise, and invert DNA in vitro and in bacteria. Here, we r...
030
pdhsu.bsky.social @pdhsu.bsky.social · 15/05/2025
This work was a wonderful collaboration with Silvana Konermann, led by star graduate student Nick Perry with key contributions from the amazing Liam Bartie, Dhruva Katrekar, Gabe Gonzalez, Matt Durrant, James Pai, Alison Fanton, Masa Hiraizumi, Chiara Ricci-Tam, and Hiroshi Nishimasu Arc is on 🔥
120
pdhsu.bsky.social @pdhsu.bsky.social · 15/05/2025
Bridge recombinases can modify the genome from single gene insertions to megabase-sized rearrangements We're excited about programmable genome design at unprecedented length scales, especially when combined with AI-generated DNA sequences of high complexity (e.g. Evo 2)
100
pdhsu.bsky.social @pdhsu.bsky.social · 15/05/2025
Most people think of recombinases for payload insertion (e.g. of CARs or corrective genes) We provide a therapeutic proof-of-concept with bridge-mediated excision of the BCL11A enhancer for sickle cell anemia and of expanded repeat sequences found in Friedreich's ataxia
120
pdhsu.bsky.social @pdhsu.bsky.social · 15/05/2025
But unlike other tools, bridge editing is not limited to insertion! We use IS622 for programmable, precise, and scarless genome rearrangements, inverting up to 0.93 Mb and excising up to 0.13 Mb
100
pdhsu.bsky.social @pdhsu.bsky.social · 15/05/2025
We then performed a systematic deep mutational scan of IS622 and combined a rationally engineered, high activity recombinase mutant with our enhanced bridge RNAs to demonstrate 20% insertion efficiency into the human genome
110
pdhsu.bsky.social @pdhsu.bsky.social · 15/05/2025
Using these enhanced bridge RNAs, we discovered design principles for maximizing the specificity of insertion into the human genome, achieving as high as 82% specificity genome-wide
100
pdhsu.bsky.social @pdhsu.bsky.social · 15/05/2025
In a tour de force of molecular engineering, our team conducted computational ortholog mining, human cell activity screening, and structure-guided bridge RNA engineering to enhance the activity of IS622, a bridge system that showed promising but low activity in human cells
110
pdhsu.bsky.social @pdhsu.bsky.social · 15/05/2025
Bridge recombination systems are elegant molecular tools that utilize a recombinase enzyme and a programmable bridge RNA to "bridge" and recombine two distinct DNA molecules This is a universal mechanism for insertion, excision, or inversion of any two DNA sequences
110
pdhsu.bsky.social @pdhsu.bsky.social · 15/05/2025
Genomes encode biological complexity, which is determined by combinations of DNA mutations across millions of bases In new work @arcinstitute.org, we report the discovery and engineering of the first programmable DNA recombinases capable of megabase-scale human genome rearrangement
22913
Reposted by @pdhsu.bsky.social
Andrew Dunn @andrewedunn.bsky.social · 30/04/2025
This was a fun one — new Endpoints Slack interview with @pdhsu.bsky.social : endpts.com/endpoints-sl...
endpts.com
The Endpoints Slack interview: Arc Institute's Patrick Hsu on investing, AI and new ways of research
An interview with Patrick Hsu, 31, Harvard PhD grad and CRISPR pioneer, who co-founded Arc Institute and helped develop Evo 2, a biology-focused AI model.
042
pdhsu.bsky.social @pdhsu.bsky.social · 24/03/2025
are there good CROs for cell line engineering and generation?
110
Reposted by @pdhsu.bsky.social
Arc Institute @arcinstitute.org · 25/02/2025
Today, we're launching the Arc Virtual Cell Atlas, a growing resource for computation-ready single-cell measurements. arc-website-git-ben-virtual-cell-atlas-tool-arc-institute.vercel.app/news/news/ar...
arc-website-git-ben-virtual-cell-atlas-tool-arc-institute.vercel.app
Arc Virtual Cell Atlas launches, combining data from over 300 million cells | Arc Institute
Arc Institute today launched the Arc Virtual Cell Atlas, a growing resource for computation-ready single-cell measurements, starting with data from over 300 million cells. The initial release of the A...
13917
Reposted by @pdhsu.bsky.social
Yusuf Roohani @yusufroohani.bsky.social · 25/02/2025
At the @arcinstitute.org we are building AI models of cell state from the ground up, rethinking every step, from data generation to biologically relevant evaluation Today we launch scBaseCamp, the largest public repository of single cell RNAseq data, uniformly processed from raw sequencing reads.
1165
Reposted by @pdhsu.bsky.social
Hani Goodarzi @genophoria.bsky.social · 25/02/2025
@thejohnnyyu.bsky.social, @therealnima.bsky.social, and I, are excited to tell you about Tahoe-100M! The largest publicly available single-cell dataset that measures the effect of 1200 genes on 50 cell line models. The Vevo team has outdone itself. #Tahoe100M www.biorxiv.org/content/10.1...
biorxiv.org
Tahoe-100M: A Giga-Scale Single-Cell Perturbation Atlas for Context-Dependent Gene Function and Cellular Modeling
Building predictive models of the cell requires systematically mapping how perturbations reshape each cell's state, function, and behavior. Here, we present Tahoe-100M, a giga-scale single-cell atlas ...
18134
Reposted by @pdhsu.bsky.social
Hani Goodarzi @genophoria.bsky.social · 25/02/2025
Watch @thejohnnyyu.bsky.social @therealnima.bsky.social (@vevotherapeutics.bsky.social), @pdhsu.bsky.social , Dave Burke and I (@arcinstitute.org) talking about virtual cells, and how #Tahoe100M, now on. @arcinstitute.org's Virtual Cell Atlas, can change the game! www.youtube.com/watch?v=ak_f...
youtube.com
No Priors Ep. 103 | With Vevo Therapeutics and the Arc Institute
YouTube video by No Priors: AI, Machine Learning, Tech, & Startups
086
Reposted by @pdhsu.bsky.social
Fay Lin @faylinphd.bsky.social · 19/02/2025
New from @arcinstitute.org is "the largest publicly available #AI model for biology to date"! Evo 2 now includes information from all domains in life to expand its capabilities in generative functional genomics. @pdhsu.bsky.social @brianhie.bsky.social tinyurl.com/3t83vseh
tinyurl.com
Arc Institute’s AI Model Evo 2 Designs the Genetic Code Across All Domains of Life
Evo 2 now includes information from humans, plants, and other eukaryotic species to expand its capabilities in generative functional genomics.
011
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
This was an insane team effort between Arc and Nvidia that convened machine learning and computational biology researchers across Stanford, UC Berkeley, and UCSF. Especially grateful to Jensen Huang for his belief and support of this vision and labor of love, and the entire Evo 2 team below
173
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
Finally, if Evo 2 sounded exciting, @arcinstitute.org is hiring. Check out open Arc jobs at arcinstitute.org/jobs or just email me directly. Our research group is hiring in molecular machine learning and the interface of computational and synthetic biology
162
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
and check out our blog post! arcinstitute.org/news/blog/evo2
arcinstitute.org
AI can now model and design the genetic code for all domains of life with Evo 2 | Arc Institute
Arc Institute develops the largest AI model for biology to date in collaboration with NVIDIA, bringing together Stanford University, UC Berkeley, and UC San Francisco researchers
100
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
and a few more :) NVIDIA BioNeMo: github.com/NVIDIA/bione... NVIDIA NIM (Generation): build.nvidia.com/nvidia/evo2-... NVIDIA NIM (Forward): build.nvidia.com/arc/evo2-40b HuggingFace Evo 2 40B: huggingface.co/arcinstitute... HuggingFace Evo 2 7B: huggingface.co/arcinstitute...
github.com
GitHub - NVIDIA/bionemo-framework: BioNeMo Framework: For building and adapting AI models in drug discovery at scale
BioNeMo Framework: For building and adapting AI models in drug discovery at scale - NVIDIA/bionemo-framework
110
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
Here are some useful links: Evo 2 preprint: arcinstitute.org/manuscripts/... Evo Designer: arcinstitute.org/tools/evo/ev... Evo Mech Interp Visualizer: arcinstitute.org/tools/evo/ev... Evo 2 code: github.com/arcinstitute...
arcinstitute.org
Manuscript | Arc Institute
Arc Institute is a independent nonprofit research organization headquartered in Palo Alto, California.
120
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
DNA is just the beginning. In middle school, we learn that genotype and the environment collaborate to create phenotype. We are incorporating Evo 2's understanding of genetic variation into Arc's virtual cell models that can be used for drug discovery and target ID
110
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
We're excited to see what the research community builds on top of this foundation model to enable the biological "app store"
110
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
Beyond pretraining scale, Evo 2 also scales at inference time. We demonstrate "generative epigenomics" by controlling the position and width of predicted chromatin accessibility to encode Morse code messages in the epigenome. Can you guess what's written below? .- .-. -.-.
110
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
Evo 2 can also be used for biological design. We demonstrate generation of entire human mitochondrial genomes with coherent synteny and even whole bacterial genomes and eukaryotic chromosomes (see the preprint for more detail)
110
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
A common critique of LLMs is that they're black box. To probe what Evo 2 is learning about biology (without any labels or annotations), we turned to mechanistic interpretability with Goodfire AI Intriguingly, this AI brain has features that may correspond to regulatory elements
121
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
With a simple supervised model trained on Evo 2 embeddings, its performance gets even better, reaching SOTA for coding mutations also
110
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
Without any variant-specific training, architectural optimization, or multiple sequence alignments, Evo 2 can predict the pathogenicity of breast cancer-associated mutations in genes like BRCA1 It's state of the art in doing this zero-shot for noncoding mutations
111
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
Great, but what can it do? Evo 2 is a generalist model that can predict the pathogenic effects of human genome variants across coding and noncoding mutations In other words, if you have a genetic mutation, Evo 2 has an opinion on whether or not it might cause disease
120
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
To enable this, we report a new frontier deep learning architecture, StripedHyena 2, with improved loss scaling and up to 3× speedup in throughput at 40B scale compared to Transformer baselines or previous generation hybrid models
120
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
Building on our previous Evo model trained on single-cell life, Evo 2 achieves generalist prediction and generation performance from molecular to genome scale But this time, it operates across all domains of life, including complex human genomes
110
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
This enables it to reason about and understand biological interactions across diverse length scales, from individual molecules to entire bacterial genomes or eukaryotic chromosomes
110
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
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
121
pdhsu.bsky.social @pdhsu.bsky.social · 19/02/2025
AI provides a universal framework that leverages data and compute at scale to uncover higher-order patterns Today, @arcinstitute.org in collaboration with Nvidia releases Evo 2—a fully open source biological foundation model trained on genomes spanning the entire tree of life.
26039
Reposted by @pdhsu.bsky.social
Dave Burke @daveyburke.bsky.social · 19/02/2025
Introducing Evo 2 from Arc Institute - an AI that can model and design the genetic code for all domains of life. It’s one of the largest-scale truly open source AI models for biology (and in fact more generally - most “open source” large language models are only “open weights”)
294