Aly

Researcher in AI & Cancer

[Aly @alyosak]

“No one is ever satisfied where he is....Only the children know what they’re looking for....”
― Antoine de Saint-Exupéry, The Little Prince

[Aly @alyosak]

Code is dead. And we have killed it. How many systems have we torn down? How many libraries have we cast aside? Who will erase the traces of the bugs we left behind? And will a single update ever redeem all that we have broken?

[Bo Wang @BoWang87]

A new Nature paper from Johns Hopkins (by Prof. Lin @DingchangLin ) just solved one of the hardest problems in biology: how do you record what every cell in a tissue experienced over time, not just what it looks like right now?

The answer: GEMINI — Granularly Expanding Memory for Intracellular Narrative Integration.

It works exactly like tree rings.

Cells are genetically engineered to express a computationally designed protein assembly. As the assembly grows inside the cell, it captures cellular activity as fluorescent ring patterns — each ring a timestamp, each ring's properties encoding signal intensity. Look at a cross-section under a microscope and you can read the cell's history backward, with ~15-minute resolution.

The key: cells build the recorder themselves. GEMINI doesn't interfere with normal function — it just quietly writes.

What they demonstrated:

In a full tumor xenograft, GEMINI captured every cancer cell's activity history across the entire tumor while it continued to grow normally. For the first time, researchers can look back and see how different regions of the same tumor responded differently to therapy over time — not snapshots, but film.

In a mouse brain, GEMINI recorded neural activity dynamics without disrupting behavior, coordination, or memory. It could temporally resolve the history of a brain seizure.

Why this matters:

Every tool we have in biology gives you state — what the cell looks like now. Sequencing, imaging, proteomics — all snapshots. GEMINI gives you trajectory. It's the difference between a photograph and a video, applied to every cell in an organ simultaneously.

The team is explicit that AI-based decoding tools will be central to reading GEMINI's output at whole-brain scale. This is the data layer that makes temporal single-cell atlases possible.

Paper: https://t.co/TsObknQqga

Congratulations @DingchangLin

[Aly @alyosak]

“The key question to keep asking is, Are you spending your time on the right things? Because time is all you have. ”
― Randy Pausch, The Last Lecture

[Lasse Middendorf @LasseMiddendorf]

AI is everywhere in biology right now, but how do these models actually hold up once they hit the lab?

Our latest review on generative AI for enzyme design cuts through the hype to see what’s actually working in the lab🧪

⬇️LINK

[Jure Leskovec @jure]

Excited to share the launch of @phylo_bio 🚀 — a research lab studying agentic biology, spun out of our open-source AI scientist @ProjectBiomni.

As scientific cofounder, I’m proud of what this team has built: Biomni Lab, the first Integrated Biology Environment where agents handle the mechanics and scientists focus on questions, mechanisms, and discovery.

Onward 🚀
🔬 Try it free: https://t.co/Ca5oJHN35k
📢 We’re hiring: https://t.co/YGGwOU5YUa

[Deniz Kavi @kavi_deniz]

The Baker Lab designs protein on/off switches

1/🧵

Instead of optimizing for how tightly a given protein binds to a target, Adam and team develop a method to control the duration of binding.

[bioRxiv Bioinfo @biorxiv_bioinfo]

XenoSignal: Investigating Intra- and Inter-Species Ligand-Receptor Interactions Using AlphaFold3 https://t.co/fDOCUgCM71 #biorxiv_bioinfo

[Jake P. Taylor-King @wildtypehuman]

To all of the folk saying we need deep learning for RNA-seq prediction...

[Aly @alyosak]

It all began the moment I came across optimal transport theory—I got hooked. It turned into a personal mission to prove it could work for spatial transcriptomics. I just couldn’t let it go… until it finally did.

[Aly @alyosak]

Thrilled to share spOT-NMF: a reference-free method to deconvolve spatial transcriptomics using Optimal Transport 🧬🧠
https://t.co/nSHcMtQGvM

#SpatialTranscriptomics #OptimalTransport #Bioinformatics

[Jake P. Taylor-King @wildtypehuman]

The economic rationale for biomolecular foundation models

https://t.co/JZZEHhUFG4

[Aly @alyosak]

Two days ago, I dreamt someone published a paper claiming cell size = 2um. I woke up convinced it was real and spent hours hunting for the source like it was the cure for cancer… only to realize: it was just a dream.

My brain really said, "publish or perish," even in my sleep.

[Chaitanya K. Joshi @chaitjo]

Flow matching has gained popularity recently

which is better, diffusion or flow matching?

They are formally equivalent

Our purpose is to help practitioners understand and use these frameworks interchangeably

-- **regardless of what it’s called**

[Aly @alyosak]

He kept chasing his big dreams with all his strength until he collapsed, so may God have mercy on someone who gave their life for their ambitions.

[Aly @alyosak]

I can’t wait for 'Foundation Models of Foundation Models: All You Need' to redefine complexity, only to perform worse than a good old linear model.

[Aly @alyosak]

Having no choices is tough, but having too many can be even more challenging. I wish there were a predictive model to help navigating the path to the right career choice.

[Aly @alyosak]

" We don't know the probabilities of future events. Still, you have to take action, and so you do it on gut feeling. That's the world we live in. "

[Yan Holtz @R_Graph_Gallery]

🚨 Stop chasing the p-value!

Increasing your sample size will always yield a significant result.
Even for trivial differences.

🎮 I created a little interactive playground to illustrate this issue:
https://t.co/7yv33PWxIb

Always pair p-values with effect sizes!

[Aly @alyosak]

Sometimes, the places we aspire to reach are not as grand as we imagine, but they teach us resilience, recalibration, and the art of finding meaning in the unexpected

[Aly @alyosak]

"Experience is what you get when you didn't get what you wanted"

- The Last Lecture, Randy Pausch