RT @AndrewYNg: I am alarmed by the proposed cuts to U.S. funding for basic research, and the impact this would have for U.S. competitivenes….

Congrats to the @FutureHouseSF team, especially @SGRodriques and @andrewwhite01.

also as a fellow bird software package developer I commend you 😂.

I have never done improv - but this is a perspective I learned vicariously through the handful of one off “yes and” improv shows I saw as an undergrad. A gentle reminder to me that varied interests & experiences shape perspective and these soft skills aren’t easily taught.

One thing that’s admirable to me about FutureHouse’s work is that they are not inundated by the critique or the lofty goal itself. It’s easy to criticize any science but it’s harder to take an idea (and all its limitations) and have a forward thinking vision of what it could mean.

RT @Victorshi2020: Amazing. In *two* minutes, Pete Buttigieg got Andrew Shulz to see why government research is necessary. That is why th….

RT @BarackObama: Harvard has set an example for other higher-ed institutions – rejecting an unlawful and ham-handed attempt to stifle acade….

RT @j_g_allen: Now economists know how scientists felt when he said “inject bleach”.

RT @pudgypenguins: Should Penguins impose reciprocal tariffs on the USA?

RT @SStevenWang: Cutting NIH to save budget is like cutting the front lobe of brain to lose weight. It’s <1% of body weight yet it governs….

Checkout more in the paper here!

Importantly, STARLING is an open-source tool targeting ease of use and widespread availability. STARLING is available to install and run locally or online through a simple interface via Google Colab.

We also show how one can integrate STARLING with protein design tools to build de novo disordered protein sequences with target ensemble properties.

STARLING can be used to develop hypotheses as to how an IDR’s sequence may determine its conformational ensemble and/or how it may influence interactions with other IDRs.

STARLING dramatically lowers the barrier to the computational interrogation of IDR function through the lens of emergent biophysical properties in addition to traditional bioinformatic approaches.

We benchmark STARLING against decades of elegant biophysical research of disordered proteins, including smFRET, SAXS, and NMR experiments, and find that STARLING displays remarkable agreement.

STARLING produces high-quality predictions at a blazingly fast rate on GPUs and Apple Silicon and is still performant on CPUs.

We formulate IDR ensemble construction as a process of generating instantaneous distance maps in a sequence-conditioned manner, where each map represents a structure based on pairwise inter-residue distances.

STARLING is a latent denoising diffusion model inspired by recent progress in text-to-image generative models.

STARLING presents a generalization of this recent work by enabling the generation of IDR ensembles from which any observable and its distribution can be computed.