nabbo (bio/acc)

different shades of delhi

@biocheMichael congratulations, absolutely deserved

Fabricagen has been accepted into the #NVIDIA #Inception program! I am excited to explore the benefits and join the developer program.

@tanaylohia exactly, i'm a full linux guy now, thankfully protonDB is so good with games i don't miss windows at all

Windows PCs have become absolutely unusable nowadays. It's sad how much AI is degrading everything else as nothing else matters than brrr-ing those GPUs rn.

omarchy on desktop, not a bad experience at all

"a single smart drug molecule that finds diseased cells by their DNA and destroys them" Do you mean A MAGIC PILL TO CURE ALL DISEASES?

LiteFold just got featured in @YourStoryCo It’s been 8 months since Cory and I officially started @try_litefold. We began by building better interfaces and workflows for computational biology, followed by Rosalind, our AI Co-Scientist for therapeutic design. Now we’re gradually moving toward developing our own in-house scientific and AI research focused on next-generation therapeutic models and research environments and partnerships. Still very early. Really cant wait to share whats coming. Story link in the comments

AlphaFold-based models like Boltz-2 and BioEmu train on atomic conformational structures in order to predict protein dynamics. But is it possible to train these models directly on cryo-EM map ensembles, harnessing conformational data that is typically not deposited in the PDB? Introducing CryoSampler: a new approach for fine-tuning Boltz-2 with raw supervision on cryo-EM map ensembles. 1/6🧵

it should be a crime to bundle the dataset with the model checkpoint

has anyone been able to use protenix’s training-free guidance, or am i the only one struggling?

A newly published systematic analysis of what some call the “dark proteome” suggests scientists have missed thousands of nontraditional genes that lurk in previously overlooked stretches of the genome and make smaller than average proteins. scim.ag/3P5o07l

two years ago, i loved using GUIs and now, i just use terminal for everything

I’ve always believed the No.1 application of AI should be to improve human health. That work started with AlphaFold, and now at @IsomorphicLabs with the mission to reimagine drug discovery and one day solve all disease! We are turbocharging that goal with $2.1B in new funding.

What if we could design ligands that not only bind a target, but functionally direct it toward activation or inhibition? In our #ICML2026 Spotlight, we present TD3B, a discrete diffusion framework for directional allosteric binder generation! 🦉 📜: arxiv.org/abs/2605.09810 🤗: huggingface.co/ChatterjeeLab/…

@vishoza such a heartwarming story :⁠^⁠)

@TensorTwerker Nothing like a good walk to clear your head. I adopted a dog one year into my PhD and walks with him were my problem solving sessions. Ended up dedicating my thesis to him!

today I walked for my stupid mental health

biotech is the best place to be right now

thinking of posting stuff on linkedin

cross docking really makes these models hallucinate

god bless OCR models

BREAKING: First sequencing of the Hantavirus from the outbreak. -99% identical to a June 2018 case from a patient in Argentina -10.4 SNV/year mutation rate - The Andes genome is about 12 kb across three RNA segments. At 10⁻⁴ to 10⁻³ substitutions/site/year, that translates very roughly to 1-12 SNV per year -Completely in line with a natural spillover in Argentina from the rodent host in 2018 and now in 2026 Source: virological.org/t/complete-seq…

@thsottiaux lmao good ol days when I used to sail the high seas

We are Codex. We are legion. We do not miss. We do ship. Expect us. DM me if you have a track record of solving near impossible problems and want to work on the future of computing. We work across research, infra, agent harness and products. Currently hiring in San Francisco only.

@parmita This is the most popular opinion

Unpopular opinion: every "virtual cell" foundation model is a guess about cells nobody has watched. They train on dead snapshots. They predict trajectories they've never seen. They call this AI for biology. Ground truth or it's astrology.