sanj

Co Founder @atlasdiscovery0

[sanj @splicewiring]

New ways of quantifying cellular states are coming up everyday, with different granularities & modalities of information.

AI cell models that we know of today use RNA-seq as the primary modality of learning - simply due to the ease and abundance of capturing this.

I've been thinking about this as a problem, as a species we will always come up with newer ways of learning about our biology.

1. how do we connect this general cell state to specific modalities of functional readouts?
2. are there any additional benefits to solving this problem of unification?

[sanj @splicewiring]

@MeteAtharva @atlasdiscovery0 @ShaamilKarim1 @Cgensbigler thanks Atharva :)))

[sanj @splicewiring]

We’re building foundation models that predict patient response in clinical trials.

Excited for the future at @atlasdiscovery0 with @ShaamilKarim1 and @Cgensbigler !

[Atlas Discovery @atlasdiscovery0]

Nine out of ten drugs fail in clinical trials. The reason isn't a shortage of data. It's that none of it connects.

We started Atlas Discovery to fix that with foundation models of patient drug response. We're backed by @ycombinator, @pearvc, and more.

[sanj @splicewiring]

@aaronw3r @atlasdiscovery0 @ShaamilKarim1 @Cgensbigler thanks Aaron!

[sanj @splicewiring]

@PariLatawa Super amazing session indeed!

[Atlas Discovery @atlasdiscovery0]

Applied to a phase 3 trial, our model predicted which IBD patients respond to ustekinumab at 0.76 AUROC — attending to the inflammation & fibrosis biology you'd expect.

Better prediction doesn't just cut costs, it could make previously infeasible trials possible.

[Ankit Gupta @agupta]

these guys are picking the most important problem. excited to see what they build

[Atlas Discovery @atlasdiscovery0]

Nine out of ten drugs fail in clinical trials. The reason isn't a shortage of data. It's that none of it connects.

We started Atlas Discovery to fix that with foundation models of patient drug response. We're backed by @ycombinator, @pearvc, and more.

[Deniz Kavi @kavi_deniz]

Thrilled to partner with @NVIDIAHealth to bring optimized AI tools for molecular design to more scientists

We're making NVIDIA NIM microservices and BioNeMo Agent Toolkit available on @TamarindBio.

This means NVIDIA's optimized models are available, alongside the rest of your open, proprietary and fine-tuned molecular design tools.

[Anthropic @AnthropicAI]

New Anthropic Science Blog: Making Claude a chemist.

To manipulate a molecule, chemists first need to understand its structure. Their main tool is NMR spectroscopy.

We found Opus 4.7 matches—and on some tasks beats—dedicated NMR software. Read more: https://t.co/1jUvz7wdhV

[Zeming Lin @ebetica]

How to design your own PD-1 binder in 4 easy steps:

1. Download the tutorial notebook from the ESM team
2. Get a @modal API key to scale it up
3. Scaling it up, O($1000) will get you a 96 well plate of minibinders with >50% success rates on typical targets
4. Test it in the lab!

[Samuel Hume @DrSamuelBHume]

One of the most amazing things I’ve ever seen: a standing ovation for the full Daraxonrasib results

I feel inspired and energised, to put it mildly — we have a targeted therapy for pancreatic cancer now, and nothing is undruggable anymore

[Seohong Park @seohong_park]

Introducing *dual representations*!

tl;dr: We represent a state by the "set of similarities" to all other states. This dual perspective has lots of nice properties and practical benefits in RL.

Blog post: https://t.co/lw1PortD9E
Paper: https://t.co/zYKFjyOy7C

↓

[sanj @splicewiring]

Something I've learned today from my guy, in times of uncertainty one should ask claude to respond like @karpathy

[sanj @splicewiring]

Bought my first wsj sub for this

[Bryan Johnson @bryan_johnson]

You can’t go on a rich persons yacht, or fly on their private plane, or live in their mansion.

You will, however, eventually get access to their longevity therapies.

[FutureHouse @FutureHouseSF]

We're pleased to share our first @Nature paper: Robin is the first multi-agent system for discovery in biology that integrates novel hypothesis generation with experimental data analysis in one continuous workflow.

In this study, our team, including ophthalmologist @agreeb66, applied Robin to dry age-related macular degeneration, a leading cause of irreversible sight loss with limited treatment options. The system proposed drug-repurposing hypotheses, which were then tested experimentally in the lab.

Robin developed the experimental strategy for therapeutic hypothesis generation, proposed follow-up experiments, and extracted actionable insights from the resulting data, including validation in primary human retinal pigment epithelium (RPE) stem cells.

Robin also proposed a mechanism of enhancing RPE phagocytosis by modulating the cells circadian rhythm using an experimental drug, KL001, that has never before been used in humans or proposed for AMD. To our knowledge, this mechanism had not previously been proposed.

This work points to the future of AI-enabled science: systems that connect insights across fields, surface new mechanisms, and turn existing knowledge into testable hypotheses.

It also represents the broader opportunity FutureHouse is building toward: AI that helps science cross disciplinary boundaries and move from literature to experiment to discovery.
https://t.co/4FhmTo8nRH

[David Sinclair @davidasinclair]

Biology is not just chemistry, it is code

[Kat @katyenko]

The binders have bound! A few months ago, 9 human teams and 6 autonomous AI agents spent a single day designing protein binders against TREM2 on @muni_bio, a target implicated in Alzheimer’s Disease.

141 designs were submitted, 100 were synthesized and tested by @adaptyvbio, and 37 bound. And surprisingly, AI agents essentially matched human teams on hit rate.

These aren’t benchmark scores or simulated results, but real proteins designed in one day in SF and validated experimentally during the first large-scale test of muni, where teams ran 260 GPU jobs and generated a total of 4,176 binders.

We wrote about what we learned from the results, how well ipSAE worked as a scoring function, and how this hackathon reshaped what we’re building: https://t.co/uZswTolfIa

[sanj @splicewiring]

https://t.co/qNgZnrMRle - @ the MLGenX workshop at ICLR on Monday!

[sanj @splicewiring]

we're at ICLR talking about gene expression data and discrete/cont diffusion modelling methods - hmu

[Ron Alfa @Ronalfa]

1/ Spatial transcriptomics is among the richest view of human biology that we have: 18,963 genes mapped at subcellular resolution.

It's also almost never collected outside of research settings.

So we trained a foundation model to generate it from a clinical H&E image alone.

Meet TARIO-2. 🧵

https://t.co/hcTMjUkCjw