I deleted X from my phone a few days ago. Do it. Ur brain will start working again. Tweet from a device you're not literally ALWAYS holding in ur pocket. Make it an android. The app is worse. U won't scroll as much lol Make X less easy to access. It increases your quality of

What a privilege to be tired from work you once begged the universe for. what a privilege to feel overwhelmed by growth you used to dream about. what a privilege to be challenged by a life you created on purpose. what a privilege to outgrow things you used to settle for.

We are hiring! The Gao Research Group at the California Institute of Technology is seeking postdoctoral researchers with strong expertise in nucleic acid/aptamer-based sensing technologies for our wearable, implantable, and ingestible platforms. Caltech

Thrilled to be awarded the 2024 Tianqiao & Chrissy Chen Institute and Science Magazine Prize for AI Accelerated Research! This is a huge recognition for our past work on structure prediction foundation models, and the path ahead to pursue further. Looking forward to presenting more this October!

brute forcing through the shitty first 100 hours of learning anything is the cheat code. most people never make it past 10.

the best advice i ever got was to 'go out there and get your heart broken'. And this isn't just romantic life advice - it applies to work and friendships. Volunteer yourself, ask people to hang out, get rejected by people, places and things to find your product market fit

pretraining is an elegant science, done by mathematicians who sit in cold rooms writing optimization theory on blackboards, engineers with total absorb of distributed systems of titanic scale posttraining is hair raising cowboy research where people drinking a lot of diet coke

Biological foundation models have hit a plateau. Scaling isn't working as expected. Foundational concepts from evolutionary biology could have predicted this: 🧵 research.arcadiascience.com/pub/idea-phylo… [1/9]

What a privilege to be tired from work you once begged the universe for. what a privilege to feel overwhelmed by growth you used to dream about. what a privilege to be challenged by a life you created on purpose. What a privilege to outgrow things you used to settle for.

ICYMI: Finally some good news! The senate committee rejected the 40% budget cut for NIH and instead endorsed a $400 million budget increase! Science for the win.

The damage to young scientists…

Pay the taxes of life gladly. Not just from the government. Annoying people are a tax on being outside your house. Delays are a tax on travel. Haters are a tax on having a YouTube channel. There’s a tax on everything in life. You can whine. Or you can pay them gladly.

Researchers in the Kulik Lab have created polymers that are more resistant to tearing by incorporating stress-responsive molecules identified by a machine-learning model. chemistry.mit.edu/chemistry-news…

MSA Pairformer efficiently extracts structure, protein-protein interactions, and mutation effects from MSAs by decomposing the effects of phylogeny and structural contacts. Yo Akiyama Zhidian Zhang Milot Mirdita, Martin Steinegger, and Sergey Ovchinnikov

I have been thinking a lot about what it takes to be a biologist working in tech - the tradeoffs and impact of a job like that. Considering writing a blog about it.

Timeline cleanser: Dana defeated cancer and gave birth after CAR-T treatment. #TCell #Immunotherapy #CancerResearch ynet.co.il/health/article…

Transformer-guided design of lipid nanoparticles for RNA therapeutics Lipid nanoparticles (LNPs) are the workhorse of RNA delivery, but optimizing their lipid identities, ratios, and synthesis parameters is a vast experimental challenge. Alvin Chan and coauthors present COMET—a

Language-model–driven design of peptide therapeutics from sequence alone Peptide binders can target “undruggable” proteins, but most design methods require 3D structures—limiting reach to well-folded proteins. Leo Tianlai Chen and coauthors introduce PepMLM—a masked protein

average american bio-ml paper: we have created a very useful tool average european bio-ml paper: we have conclusive proof that the tool is useless average chinese bio-ml paper: we have used the tool to create a first-in-class therapeutic, here is n=58 proof of its efficacy

Support young scientists , EVERY BIT COUNTS ! donate.abrcms.org