Johnny Yu (@iamjohnnyyu) 's Twitter Profile
Johnny Yu

@iamjohnnyyu

CSO and co-founder at Vevo Tx, UCSF PhD.
Building the next big thing in single-cell drug discovery!

ID: 1048056118918897665

linkhttp://vevo.ai calendar_today05-10-2018 03:43:45

666 Tweet

386 Followers

697 Following

Johnny Yu (@iamjohnnyyu) 's Twitter Profile Photo

For anyone interested in where virtual cell is going - this is a very timely and landmark piece of work. A few take aways: - Data matters! 💾 High quality, unified datasets like Tahoe100M vastly improve model performance - Embeddings are getting good enough for tasks 🔨 - with

Nima Alidoust (@nalidoust) 's Twitter Profile Photo

I f*** love this. And to put even more momentum behind this awesome movement by our Arc Institute friends: 🥁Tahoe Therapeutics will give $25K to the best model that is also open-sourced with weights on Hugging Face for everyone's use! + maybe a mention on X by clem 🤗? ;)

Johnny Yu (@iamjohnnyyu) 's Twitter Profile Photo

Completely agree. Pre-training on quality data for the first time allows for context generalization - > an important milestone in Virtual Cell Not all data is created equal! 🖥️🧬

Jay Bhattacharya, MD, PhD (@nihdirector_jay) 's Twitter Profile Photo

Today, NIH announced a new policy to cap how much publishers can charge NIH-supported scientists to make their work publicly accessible. This reflects our broader effort to restore public trust in public health by creating an open, honest, and transparent research atmosphere.

Today, <a href="/NIH/">NIH</a> announced a new policy to cap how much publishers can charge NIH-supported scientists to make their work publicly accessible. This reflects our broader effort to restore public trust in public health by creating an open, honest, and transparent research atmosphere.
Nima Alidoust (@nalidoust) 's Twitter Profile Photo

We love it when others build dev tools for building on Tahoe-100M. Today, we highlight scDataset in our Tahoe Therapeutics blog. Developed by Davide D'Ascenzo & Sebastiano Cultrera di Montesano, it makes it easier to train DL models on datasets with the daunting scale of Tahoe-100M (see poster in ICML '25)

We love it when others build dev tools for building on Tahoe-100M. Today, we highlight scDataset in our <a href="/tahoe_ai/">Tahoe Therapeutics</a> blog. Developed by <a href="/davide_dascenzo/">Davide D'Ascenzo</a> &amp; <a href="/sebacultrera/">Sebastiano Cultrera di Montesano</a>, it makes it easier to train DL models on datasets with the daunting scale of Tahoe-100M (see poster in ICML '25)
Alexander Wei (@alexwei_) 's Twitter Profile Photo

2/N We evaluated our models on the 2025 IMO problems under the same rules as human contestants: two 4.5 hour exam sessions, no tools or internet, reading the official problem statements, and writing natural language proofs.

2/N We evaluated our models on the 2025 IMO problems under the same rules as human contestants: two 4.5 hour exam sessions, no tools or internet, reading the official problem statements, and writing natural language proofs.
Nima Alidoust (@nalidoust) 's Twitter Profile Photo

Tahoe Therapeutics is one of The Future 50. Thanks Mario Gabriele and The Generalist for including us. Why they chose us? “Tahoe Therapeutics has succeeded in generating biological data on an internet scale to power the next generation of drug discovery.”

<a href="/tahoe_ai/">Tahoe Therapeutics</a> is one of The Future 50. Thanks Mario Gabriele and The Generalist for including us. 

Why they chose us? “Tahoe Therapeutics has succeeded in generating biological data on an internet scale to power the next generation of drug discovery.”
Hani Goodarzi (@genophoria) 's Twitter Profile Photo

I think it is worth talking about the 1 Billion cell milestone. This is not because 1Bn is a large and round number (or at least not entirely)! These number of cells, with the rich perturbative type of data that Tahoe Therapeutics's platform generates, puts the number of training tokens

Elliot Hershberg (@elliothershberg) 's Twitter Profile Photo

It's awesome to have the word out for Tahoe's Series A. Nima Alidoust and Johnny Yu are a killer CEO/CSO technical founder duo. Hani Goodarzi and Kevan Shokat are both incredible scientists. It's a dream team. The scale of ambition to go after 1 *billion* cells across a wide range of

Sunil Dhaliwal (@dhaliwas) 's Twitter Profile Photo

Financing news! Excited to share that Amplify Partners has led a $30M financing for Tahoe Therapeutics - the latest project in our growing digital biology portfolio. Rigorous science + powerful computing will shape the next decade of drug development, and Nima Alidoust, Johnny Yu,

Sunil Dhaliwal (@dhaliwas) 's Twitter Profile Photo

Ask any scientist about curing cancer and you'll get mixed signals. Good news: cancer death rates have dropped dramatically over 20 years. Bad news: 95% of cancer drugs still fail in clinical trials.

sarah guo // conviction (@saranormous) 's Twitter Profile Photo

it’s a pretty heady time in AI, but fundraising is not core business progress. It can serve as a constant distraction — do not let it be only validation that counts in the end- customer love, fat margin, then ring that bell in the public pen

Anne Carpenter, PhD (@drannecarpenter) 's Twitter Profile Photo

Vega Shah Now I’m even more proud we raised a pre seed in 2024. Glad our supporters will benefit from that down market boost! These times separate the “Hey let’s start a company” from the “We can’t NOT start this company”.

Garry Tan (@garrytan) 's Twitter Profile Photo

If you *only* used SAT to admit to elite colleges, share of admits from top 1% income falls 15.8% → 9.9% and representation from <$200k rises by +8.8%, with no reduction in post-college outcomes. It's 'holistic review' and 'ban SAT' policy that allows the most wealthy and

If you *only* used SAT to admit to elite colleges, share of admits from top 1% income falls 15.8% → 9.9% and representation from &lt;$200k rises by +8.8%, with no reduction in post-college outcomes. 

It's 'holistic review' and 'ban SAT' policy that allows the most wealthy and
Startup Archive (@startuparchive_) 's Twitter Profile Photo

Elon Musk on why he slept on the Tesla factory floor for 3 years “I was living in the factory in Fremont and the one in Nevada for three years straight. That was my primary residence. I’m not kidding. Literally. I slept on a couch, and at one point a tent on the roof, but for a

Garry Tan (@garrytan) 's Twitter Profile Photo

Taxpayer $ that were supposed to support SF are being stolen and misused by unaudited nonprofits. I pay my taxes and don't begrudge doing so— a vibrant public infra including public schools gave me a big boost in my life. What we can't stand is rampant waste fraud and abuse.

scverse (@scverse_team) 's Twitter Profile Photo

🧬 Tahoe Workshop at scverse conference 2025 📷 Disease Biology and Therapeutics in the Age of Frontier Datasets Tahoe Therapeutics #scverse2025 #ComputationalBiology #DrugDiscovery #TahoeTherapeutics #SingleCell #PerturbationBiology

🧬 Tahoe Workshop at scverse conference 2025 📷 

Disease Biology and Therapeutics in the Age of Frontier Datasets 

<a href="/tahoe_ai/">Tahoe Therapeutics</a> 

#scverse2025 #ComputationalBiology #DrugDiscovery #TahoeTherapeutics #SingleCell #PerturbationBiology
💥Susan Dyer Reynolds🗞️ (@susandreynolds) 's Twitter Profile Photo

So ⁦Daniel Lurie 丹尼爾·羅偉⁩ here are the crazy salaries at the mid-management heavy ⁦SFMTA⁩ — over 100 execs are making $200,000 to $350,000 in just salary. SFMTA has 1,000 employees making $165,000-$350,000 in just total salary. Maybe start cutting those before taxes.

So ⁦<a href="/DanielLurie/">Daniel Lurie 丹尼爾·羅偉</a>⁩ here are the crazy salaries at the mid-management heavy ⁦<a href="/SFMTA_Muni/">SFMTA</a>⁩ — over 100 execs are making $200,000 to $350,000 in just salary. SFMTA has 1,000 employees making $165,000-$350,000 in just total salary. Maybe start cutting those before taxes.