Nima Alidoust
@nalidoust
Followers
2K
Following
5K
Media
88
Statuses
2K
CEO and Co-Founder, @tahoe_ai (previously Vevo) , Princeton PhD *15 زن، زندگی، آزادی
Joined March 2015
We’ve raised $30M to build the foundational dataset for Virtual Cell Models: 1Bn single-cell datapoints, mapping 1M drug-patient interactions, to be shared with one partner. Our goal: Move the frontier - From models to precision medicines that help patients. @tahoe_ai 🧵
35
34
323
Nice POC walkthrough of integrating genetic and chemical perturbation!
What if we combine genetic & chemical perturbations to infer previously unknown MoA of compounds? Drug perturbations in Tahoe-100M aligned with CRISPR data allowed us to do that at scale. In our new blog post, we share an example of how powerful this combination can be. 🧵
1
4
30
If you want to know where the leading edge of applications on Tahoe100M is, check out our latest work. This is what phenotype looks like in the era of frontier datasets in Bio!
What if we combine genetic & chemical perturbations to infer previously unknown MoA of compounds? Drug perturbations in Tahoe-100M aligned with CRISPR data allowed us to do that at scale. In our new blog post, we share an example of how powerful this combination can be. 🧵
0
2
3
11- This blueprint—uniting CRISPR genetics with small‑molecule perturbations—fuels our upcoming 1B+ cell atlas: more cells, more contexts, greater confidence in mechanism & phenocopy.
1
0
2
10- The paradigm shift: treat drugs as programmable phenotypic levers—design compounds to recreate desired transcriptional states.
1
0
1
9- Beyond anecdotes: Using HumanNetV3’s gene networks, drugs align transcriptionally with CRISPR targets that are functionally closer than random. Similarity reflects real biology, not noise.
1
0
1
8- Follow‑up assays: In two cancer lines, Elimusertib suppressed pERK—phenocopying Trametinib/Binimetinib. A presumed ATR agent moonlighting as a MAPK pathway suppressor.
1
0
1
7- But can it find novel, previously unknown mechanisms? Yes and some of it are real plot twists: Elimusertib (reported ATR inhibitor) clustered tightly with MEK inhibitors by transcriptional profile.
1
0
1
6- Sanity check ✅ Trametinib (MEK1/2) and RMC‑6236 (pan‑RAS) land on the RAS/RAF/MEK/ERK axis—even though MEK1/2 and KRAS weren’t in the CRISPR set. Pathway‑level convergence reveals mechanism without the exact nodes.
1
0
3
5- In other words, by finding transcriptional phenocopies of compounds in genetic perturbation data, we can infer what pathways and genes the compound is perturbing.
1
0
1
4- Outcome: a drug–gene similarity map for target deconvolution, pathway mapping, and phenocopy‑driven design of new compounds targeting a desired pathway.
1
0
1
3- We paired that with Myllia’s CROP‑seq: 218 CRISPR targets in A549. We unify drug & gene maps via gene‑set scoring (MSigDB, Vision), enabling direct comparison of drug‑ vs gene‑induced signatures.
1
0
1
2- Refresher on Tahoe‑100M: Millions of single‑cell transcriptional profiles for ~400 compounds across 50 cancer models, each at 3 doses—capturing dose‑dependent biology with unprecedented depth.
1
0
2
What if we combine genetic & chemical perturbations to infer previously unknown MoA of compounds? Drug perturbations in Tahoe-100M aligned with CRISPR data allowed us to do that at scale. In our new blog post, we share an example of how powerful this combination can be. 🧵
3
17
79
Excited for the @CartographyBio team! IMO developing the most innovative T cell engager therapeutics pipeline for cancers with high unmet need. Looking forward to partnering with our new investors, @scienceman2023 @pfizer, @Amgen, @LGE_Global, and others, and very grateful for
We're excited to share the close of our $67M Series B financing, which will enable us to advance our lead program into the clinic & continued acceleration of additional oncology programs from our drug discovery platforms. Our CEO shares more below. Details: https://t.co/OyqGLYqQO2
0
7
39
🌟 Thank You to Our Diamond Sponsor: Tahoe Therapeutics! 🌟 We're thrilled to announce that Tahoe Therapeutics is supporting scverse conference 2025 as a Diamond Sponsor! 💎 Details in thread! 🧵 @tahoe_ai
#ComputationalBiology #SingleCell #DrugDiscovery #TahoeTherapeutics
1
4
6
Today in @ScienceMagazine, we report a new DNA editing technology to seamlessly write massive changes into the right place in the human genome. The reason gene editing hasn't transformed human health is that current gene editing technologies like CRISPR are very limited. The
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
74
675
3K
I fucking love this.
Today, we report Germinal, a method for efficient de novo antibody design, with @santimillef and @SynBioGaoLab. Germinal achieves success rates of 4-22% across diverse epitopes. We make the work fully open, without doing lame things like posting a preprint without methods. 🧵
1
4
72
During Thanksgiving break last year, our AI co-scientist team @GoogleDeepMind @GoogleResearch - @Mysiak @alan_karthi met Prof @jrpenades @CostaT_Lab of @ImperialCollege. They were nearing a breakthrough on how bacteria share resistance genes and proposed a test for our AI
16
104
665
Was great to chat about virtual cells and @arcinstitute with @JorgeCondeBio and @eriktorenberg on the @a16z pod. More next week!
Pod episode with Arc Institute co-founder @pdhsu coming next week. We asked Patrick why it makes sense to simulate virtual cells when we still can’t measure much of what happens inside real cells. His answer: scaling laws. The massive scale of what we can see makes up for what
6
9
178