Feiyang Huang

turning health records into patient states

PhDing CompBio @MSKCancerCenter w @wesleytansey | federated healthcare @CAIAorg

[Ziad Bakouny, MD, MSc @ZiadBakouny]

Some patients treated with cancer systemic therapy develop only minor side effects, others develop life-changing toxicities.

We have no tools to predict who will fall into which bucket.

Excited to share our ~3 years of work to try to figure this out:
https://t.co/vGZl8UQfeA

[Ed Reznik @EdReznik]

And if you're interesting in joining us in our adventure into toxicity, germline genetics, and precision safety, consider applying to this open postdoctoral position.

[Feiyang Huang @fyng_h]

@ZiadBakouny and my mentors @wesleytansey @EdReznik who taught me to dream big

[Feiyang Huang @fyng_h]

We often frame cancer treatment as an risk-benefit tradeoff. In reality, we characterize benefit far better than risk.

Why? because adverse event data, systematically collected across cancer types and treatments, did not exist until now.

The playbook:

[Ed Reznik @EdReznik]

Incredibly excited to report today on the determinants of toxicity to systemic therapy in cancer patients. Led by many including Alex Guo, Feiyang Huang, Saksham Mohan, River Walser, and the fearless @ZiadBakouny. Co-led by Wes Tansey and Jian Carrot-Zhang https://t.co/axflh9pMRS

[Feiyang Huang @fyng_h]

So grateful to have worked alongside this brilliant cast that even Chris Nolan wouldn't have been able to assemble:

@ZiadBakouny our
Odysseus and clinical mind, Saksham our LLM whisperer, Alex and River whose talents spans modeling, genetics, and proteins

[Sukrit Singh @sukritsingh92]

📣The Singh Lab opens at Fox Chase Cancer Center in Spring 2027, where I will be starting as an Assistant Professor! Excited to continue studying how biophysics shapes drug response.

I am hiring across all levels & fields! Apply on the "Join" page (& RT): https://t.co/WHgvdosChH

[Cody Fenwick @codytfenwick]

My favorite AI joke:

Current models are getting close to PhD-level intelligence. After that, they're expected to achieve the intelligence of someone who decided not to do a PhD.

[Michael Baym @baym]

I’ve made a disturbing realization. This single E. coli has been consistently doubling every 20 minutes. It took only 13 hours for it to fill a liter. At this rate, in a day and a half it’ll be the size of the whole earth, which would have an over 10% chance of killing everyone

[MattyG @meawoppl]

Wife told me these wouldn’t fit.

Little did she know I had trained for this moment for years.

[Hoyin Chu @hoyin_chu]

Excited to share my first protein design story is now fully published at @natBME ! Very fortunate to have been able to work along the very talented @arthurwchow and Betty Li, who showed some the most jaw-dropping in vivo data I have ever seen! Come check out our paper!

[Derek Thompson @DKThomp]

Marvelous examination of how to spot 2026-era AI writing, via the Economist

- AI likes long sentences with less punctuation; “and” is its most overused word
- relatedly, lists of three things, which drives up use of "and" as well
- polysyllabic adjectives: “significant”, “increasingly”
- scientific jargon ("rate-limiting," “parameter”)
- nominalizations (making nouns from verbs: eg, “expansion” from “expand”)
- ofc, everyone's favorite: "it's not X, it's Y"

[Bowen Jing @bjing2016]

Binder design has come of age thanks to generative models—but how can we access the wider array of dynamic, multistate protein functions, so elegantly employed by nature?

@mihirbafna14 and I are excited to share SwitchCraft, a framework for designing such functions. (1/7)

[Peyman Milanfar @docmilanfar]

when you are beating the benchmarks

[Ed Reznik @EdReznik]

Very excited to report on our lab’s unexpected adventure into subtyping cancer cachexia by way of anatomy, where we study the evolution of the bodies (not the genomes!) of patients with cancer during profound weight loss. Led by Sonia Boscenco. https://t.co/QP2k3CrHl2

[Feiyang Huang @fyng_h]

We think there's more to clinical AI than chatbots.

More coming soon!

[Cancer AI Alliance @CAIAorg]

In our latest blog , we are taking a closer look at one of CAIA's AI innovation projects, featuring a team from @MSKCancerCenter!

The goal is to bring together the entire history of a patient to predict the next phase of their medical experience.

https://t.co/wQNnvQogdk

[Caleb Lareau @CalebLareau]

We’re unwrapping a new method today @MSKCancerCenter!

Led by @SydneyBlattman, @NabihMaslah, @AustinAVarela, Ronan Chaligne and @dana_peer, plus colleagues at @10xGenomics, we’re delighted to share Genotyping In Fixed Transcriptomes (GIFT):

https://t.co/n62R2flHuc

1/n

[Nathan Spencer @NateSpencerWx]

@alexandr_wang Fixed it for ya!

[David West @davidwest_irl]

@Ronalfa Every computational pathology paper