Decoding Bio retweeted
1/ 🎁 Announcing prizes for the 10-day AI x Bio Hackathon!
Some highlights below 👇 (full list in the poster)
Apply by *this Friday, Oct 31*!
Decoding Bio retweeted
The @decodingbio annual snapshot is out! It was a privilege being an author this year with @anthonycosta and @DBBurkhardt! Check out our chapter on current research and future direction for virtual cells, and notable work by @arcinstitute, @NOETIK_ai and @Basecamp_Res
Decoding Bio retweeted
Many have tried, few have succeeded..... in SynBio.
Fun to work with an incredible squad @decodingbio to write about the past, present and future of SynBio.
Check out the full bio report in the link below 🧬
Thanks to @pablolubroth @ZahraKhwaja for organizing!
Decoding Bio retweeted
We're hosting a biotech operator & early scientists mixer with @Pranay_Shahh (@ARIA_research) and @pablolubroth (@decodingbio) at the @IDEALondon space!
Come drop by tomorrow!
RSVP: lu.ma/3b2ygzcs
Decoding Bio retweeted
𝐅𝐫𝐨𝐦 𝐍𝐘𝐒𝐄: BiotechTV is broadcasting from the @decodingbio AI x BIO Summit at the NYSE today. Catch @RS_Flinn’s coverage all day.
Decoding Bio retweeted
Replying to @askalphaxiv
@askalphaxiv and @decodingbio are now working together to help anyone discover, read, and discuss the latest in AI x Bio research!
Whenever Decoding covers an arXiv paper, we’ll link to AlphaXiv, where you can read comments from researchers and use on-site AI tools to summarize.
We are excited to announce our collaboration with @decodingbio!
Decoding Bio is a community of writers, scientists, founders, and funders focused on elevating the understanding of cutting edge developments in AI+Bio.
This collaboration with Decoding Bio will be an important first step in expanding alphaXiv beyond CS and physics. Stay tuned!
Decoding Bio retweeted
We are excited to announce our collaboration with @decodingbio!
Decoding Bio is a community of writers, scientists, founders, and funders focused on elevating the understanding of cutting edge developments in AI+Bio.
This collaboration with Decoding Bio will be an important first step in expanding alphaXiv beyond CS and physics. Stay tuned!
Replying to @_khaledsaab
@KhaledSaab11 et al. @GoogleDeepMind upgrade their medical AI AMIE with multi-modal reasoning and a state-aware diagnostic framework, outperforming primary care physicians in a randomized, double blinded diagnostic study.
Read more here: gstatic.com/amie/multimodal_…
Zhou et al. curate an expert-labelled dataset and formulate a novel framework Dual-Inf to improve LLM diagnoses and explanations for automatic differential diagnosis.
(corresponding author: @RuiZhang1229)
🧵 5/5
A study from @LeapLabTHU found that reinforcement learning with verifiable reward (RLVR) improves a model’s ability to select correct reasoning paths on the first try, but does not create new strategies beyond those already present in the base model.
🧵 4/5
@ShiwarskiLab developed a comprehensive tissue engineering platform to fabricate organ-on-a-chip devices. Using FRESH bioprinting to extrude cellulose-based scaffolds dubbed CHIPS, they printed a pancreatic-like system that excreted 8 ng of insulin in 24 hours.
🧵 3/5
@DarioAmodei, CEO of @AnthropicAI, argues interpretability is essential to guiding AI toward human benefit, highlighting findings like millions of overlapping features in LLMs and the ability to manipulate concepts like the Golden Gate Bridge within a model’s reasoning.
🧵 2/5
Monday madness calls for the next installment of a thread of what we read #atowwr: read on for the TL;DR of what's going on in biotech!
🧵 1/5
Replying to @decodingbio @maayan_baron
Links for further reading on pieces covered:
1. cellularalchemy.substack.com…
2. arxiv.org/abs/2504.08016
3. biorxiv.org/content/10.1101/…
4. nature.com/articles/s41588-0…
@maayan_baron et al. show that mutations in desmosome genes within keratinocytes can result in a skin microenvironment that favours malignant transformation in skin cutaneous melanoma.
🧵 5/5
Replying to @maayan_baron
@maayan_baron et al. show that mutations in desmosome genes within keratinocytes can result in a skin microenvironment that favours malignant transformation in skin cutaneous melanoma.
🧵 5/5
@andreww_lu et al. have developed a modular protein circuit which senses and kills cells expressing mutant Ras, with better efficacy and safety profiles than existing Ras inhibitors.
🧵 4/5
Replying to @decodingbio @z_chiang
@SooYongLee11 et al. show LLMs can slip into self‑reinforcing, psychopathological‑like loops; dysfunctional “thought” states sustained by network dynamics. Using synthetic data + a sparse autoencoder, they spot & nudge these states, flagging fresh AI‑safety risks.
🧵 3/5
Manipulating the epigenome is the alchemy of the modern biotechnologist. @z_chiang covers the history of decoding the epigenome in pursuit of health and longevity whilst highlighting the current state of the research, major hurdles, ethical debates, and prescient changes.
🧵 2/5




















