Yi

film producer

[Yi @yyding]

@davidrliu @washingtonpost Congratulations. Truly extraordinary work.

[Yi @yyding]

@BoWang87 @moltbook About time!

[Yi @yyding]

@srikosuri @StJude Congratulations! So happy for her!

[Yi @yyding]

@zhaoweiasu This is truly an amazing news!

[Yi @yyding]

@thatsjonsense @blader Kept on grinding even when it looked impossible. A true founder!

[Yi @yyding]

@wwhchung @blader No wonder you guys are friends

[Yi @yyding]

@Nature Exciting! What are the off-target, idel and efficacy rates?

[Yi @yyding]

@Dr_Singularity Amazing news!

[BowTiedBiotech 🧪🔬🧬 @BowTiedBiotech]

🧬 The IRA’s Orphan Drug Blunder

The IRA was a flawed bill in many ways, but its worst feature may be how it punishes rare disease patients in the name of savings.

It technically exempts orphan drugs from Medicare price controls, but only if they treat a single rare disease. Approve a second indication, and the exemption vanishes.

So companies face a brutal choice: “If an experimental medicine works for two rare diseases, companies might have to jettison one use lest their drug become subject to price controls and return on its investment collapse.”

📉 The damage is already visible
A National Pharmaceutical Council analysis found the % of orphan drugs receiving a second designation fell by half post-IRA (12.1% → 6.3%). Several companies have already canceled studies.

And all because “many diseases share an underlying pathology such as a gene mutation” which makes a single drug potentially useful across multiple indications. That’s exactly the kind of efficiency we should reward. Instead, we penalize it.

💰 The same lawmakers who tout “innovation” now balk at the $5B cost of a fix. But if you believe innovation matters, this shouldn’t even be a debate.

To be blunt:
This is policy designed by people who don’t understand drug development.

“The orphan drug is a microcosm of the IRA’s disincentives to innovate.” And unless this fix passes, patients with rare diseases will keep paying the price.

https://t.co/rnPuli0Rae

[Yi @yyding]

@ilyasut We are rooting for you. Godspeed!

[Yi @yyding]

@blader @runwayco Congratulations! Cannot be more excited for you.

[Yi @yyding]

@CallMeHumanX @Rainmaker1973 Loyal is in pivot clinical stage for a senior dog longevity daily tablet.

[Yi @yyding]

@deedydas This will be extremely helpful for rare diseases, where traditional pharmaceutical companies have little monetary incentive

[Yi @yyding]

@Jiankui_He What are the off-target, ideals and efficacy rates?

[Yi @yyding]

@Jiankui_He Your impact and rewards are significantly more immediate when genetic editing is applied directly to patients, rather than being limited to embryonic gene editing

[GAMA Miguel Angel 🐦‍⬛🔑 @miangoar]

Friendly reminder that you should consider using Boltz-1/Boltz-2 instead of AlphaFold3 to do your research. Boltz models are MIT licensed, that means that you have permission for:
- Commercial use
- Modification
- Distribution
- Private use

min 1:54:30
https://t.co/SymqFwAFcz

[Bo Wang @BoWang87]

Got an email from my PhD student today—she had traveled to Tehran just a few weeks ago, right before war was unfolding.

No complaints. No requests. Just a quiet, steady project update—sent with the kind of calm strength that left me speechless.

I sat there staring at the screen, heart full.

Praying for her safety. Praying for peace. ❤️

[Bo Wang @BoWang87]

🚀 Xaira Therapeutics has just dropped a game-changer for AI-driven biology.

Today, we unveiled X-Atlas/Orion, the largest publicly available genome-wide Perturb-seq dataset to date—spanning 8.4 million single cells with perturbations across all ~20,000 human protein-coding genes.
This release is not just about scale—it’s about enabling a new era of causal, mechanistic foundation models for biology.

📝 Preprint on bioRxiv: https://t.co/y3i0AYzVOS
📂 Dataset on Figshare:
https://t.co/WboHM8T9Uo

🔍 What makes X-Atlas/Orion special:

📈 Unprecedented scale & quality: Each cell profiled with deep (~16k UMIs) transcriptomics and rich metadata

🧪 Quantitative dose-response modeling: Thanks to high-fidelity sgRNA detection and ~4 guides per gene, allowing continuous modeling of genetic effects

🧬 FiCS platform: A fully industrialized single-cell perturbation system enabling rapid, reproducible experiments at massive throughput

🧠 This isn’t just “data.” It’s the biological substrate for building virtual cell models that can generalize, predict, and ultimately power AI-native drug discovery.

💬 My final take:
This is a foundational moment for the field. The ability to model how genes affect cell state—quantitatively, causally, and at scale—is what we need to unlock predictive biology.

Kudos to the incredible team at Xaira for open-sourcing this resource so the entire community can build on it.
#PerturbSeq #SingleCell #Genomics #VirtualCell #FoundationModels #AIForBiology #Xaira #DrugDiscovery #SyntheticBiology #CausalAI

More press release: Press release :
🔗 GEN article : https://t.co/UI45lDkGB3
🔗 BusinessWire: https://t.co/qRFb9JUkI1

[Yi @yyding]

@srikosuri @StJude Congratulations! So happy for her and your family!