Alex

CTO and Chief Data Scientist at Foresite Labs. Lifter, runner, dog dad when I’m not working. Scientist, engineer, statistician when I am. Always a nerd

[Ann Huang @_annhuang]

1/12
Excited to share our team's latest work and the first @xaira_thera preprint! Here, we introduce FiCS Perturb-seq, an industrialized platform for generating scaleable, high-quality perturbation data.

📄 Read the preprint: https://t.co/2fjO2iHk1g

[Bo Wang @BoWang87]

After years of building AI models to decode the language of cells, I’m thrilled to announce my next chapter: I will join Xaira Therapeutics as SVP and Head of Biomedical AI.

Xaira’s vision is bold—and deeply aligned with my own: to build a virtual cell powered by AI, capable of unraveling the molecular basis of disease and matching the right therapy to the right patient. This is more than just drug discovery—it’s an opportunity to fundamentally rethink how we understand and treat human disease, from first principles to real-world cures.

With a $1B+ war chest, an all-star team, and the long view in mind, we’re setting out to do something transformative: create foundation models that can reason over biology and bring precision and speed to every step of therapeutic development.

At the same time, I’ll be maintaining my academic affiliations at University of Toronto, UHN, and Vector Institute during the next year to ensure a smooth transition—for my students, collaborators, and the many ongoing projects I deeply care about.

Grateful to my mentors, collaborators, students for getting me here. The best is yet to come.

Let’s build the future of medicine.

#AI #DrugDiscovery #FoundationModels #VirtualCell #Xaira #scGPT #Biomedicine

[XairaTherapeutics @Xaira_Thera]

We're excited to welcome Paulo Fontoura to our team as chief medical officer! He brings a wealth of experience and deep insight to help advance our mission of leveraging AI to transform drug discovery.

More info in today's announcement: https://t.co/XTcMTOjbZH

[Alex @awblocker]

@kareem_carr Agree 💯, should be better known. Super useful for approximating the effect of multiple comparisons on detectable effect sizes too!

[XairaTherapeutics @Xaira_Thera]

Congratulations to our co-founder, David Baker, and to John Jumper and @demishassabis of Google DeepMind, for sharing this year’s Nobel Prize in Chemistry! Their stunning breakthroughs have provided the foundation for our work at Xaira, and we couldn't be more proud.

[Karandeep Singh @kdpsinghlab]

If NVIDIA ever fails, it’s bc they got stuck at CUDA and never moved on to WUDA and SHUDA.

[Prof. Nikolai Slavov @slavov_n]

Read the methods before reading the results
Read the methods before reading the conclusions
Read the methods before evaluating the conclusions
Read the methods before making conclusions
Read the methods!

[Yann LeCun @ylecun]

- Regulators should regulate applications, not technology.
- Regulating basic technology will put an end to innovation.
- Making technology developers liable for bad uses of products built from their technology will simply stop technology development.
- It will certainly stop the distribution of open source AI platforms, which will kill the entire AI ecosystem, not just startups, but also academic research.
- the strangest aspect of all this is that all of these regulations are based on completely hypothetical science fiction scenario that very, very few people in the field are plausible.

[Alex @awblocker]

@cosgrove47 @ScientistsLift Great squat, and kudos on the whiskey selection

[Alex @awblocker]

Love what this team’s doing. Awesome work

[Nature Methods @naturemethods]

OpenFold developed by @gahdritz, @NazimBouatta, and @MoAlQuraishi is a trainable, open-source implementation of AlphaFold2. It is fast and memory efficient, and the code and training data are available under a permissive license.
https://t.co/CA00zft3O6

[Nature Methods @naturemethods]

OpenFold developed by @gahdritz, @NazimBouatta, and @MoAlQuraishi is a trainable, open-source implementation of AlphaFold2. It is fast and memory efficient, and the code and training data are available under a permissive license.
https://t.co/CA00zft3O6

[Alex @awblocker]

Fantastic lab!

[Pradeep Natarajan @pnatarajanmd]

🔥 Hiring a funded postdoctoral fellow position in human genetics! Come join us @CGM_MGH @broadinstitute @harvardmed!
🔥 Apply: https://t.co/4Q3Vac96kV

[Stanley Hsieh @Stanley_TH]

Head of Computational Biology @Xaira_Thera
https://t.co/LxBmrmDcLe

Come join us and work with exceptionally talented genomic & proteomic scientists, drug developers, protein designers, and more @awblocker. We can make the world a better place together @Xaira_Thera!

#hiring

[Alex @awblocker]

More details on @Xaira_Thera!

[XairaTherapeutics @Xaira_Thera]

Today we emerged from stealth mode! Jointly incubated by ARCH Venture Partners & @ForesiteLabs, and led by founding CEO Marc Tessier-Lavigne, we're excited to introduce our team & mission in today's release:
https://t.co/mKIqCdheSQ

[Alex @awblocker]

Very excited to build this with the team at @xaira_thera, Arch, and @ForesiteLabs!

[Foresite Labs @ForesiteLabs]

We joined forces with ARCH Venture Partners /
@rtnarch to incubate @xaira_thera, a biotech company using AI to re-engineer the entire drug discovery and development process. Read more: https://t.co/XTcBoMIS2h

[Alex @awblocker]

@rtnarch Absolutely mutual. Excited to build from here with this great team!

[Andrew Dunn @AndrewE_Dunn]

BREAKING: With over $1 billion & a star-studded cast, a new AI bio called Xaira Therapeutics is launching with massive ambitions to remake R&D, its leaders exclusively tell @RLCscienceboss and me.

A lot to unpack in this scoop — read it only @endpts:
https://t.co/0dFx10hZba

[Robert Nelsen @rtnarch]

It is a pleasure to work with Vik Bajaj and his team at Foresite Labs and well as David Baker, Hetu Kamisetty, and their teams, Olivia Zetter from ARCH, and to back Marc Tessier Lavigne again. Excited to try to cure disease and fix the system.

[Alex @awblocker]

@ScientistsLift Happens all the time. Think about it this way: anyone who got their PhD > 10 years ago or so probably didn’t take a class on deep learning. Causal inference as a course was also less common. As fields change, everyone ends up teaching courses they never took themselves

[Alex @awblocker]

@kareem_carr Congrats! So glad the Harvard stats community has such a great public voice