modernscientist

Applied Research Manager, Bio-Foundation Models at @NVIDIA. Biophysics and machine learning. Opinions are my own. She/her.

[modernscientist @modernscientist]

My team at #NVIDIA is hiring for multiple life sciences applied deep learning scientists. Help us build #BioNeMo!
- Protein Structure & Design https://t.co/lw8pMAvuJe
- Cheminformatics & Virtual Screening https://t.co/ZrTltLvNll
- Geometric Deep Learning https://t.co/SUwhA7YJic

[NVIDIA Healthcare @NVIDIAHealth]

(2/2) Try Litmus Bench 👇
https://t.co/FIkebk7rAi

[NVIDIA Healthcare @NVIDIAHealth]

🧠 Most LLMs can recall chemistry facts. Few can reason about the science.

⚠️ The problem: Most chemistry benchmarks are multiple-choice, and up to 1 in 5 answers are wrong. High scores often don’t reflect true understanding.

✅ The solution: Litmus Bench fixes this with exact question-answer pairs grounded in verified chemistry data.

🔓 Now open-source with a NeMo Gym environment, Litmus Bench is the chemistry boost used by Nemotron 3 Ultra and is ready to add to your training and evaluation stack.

Let's build models that think in molecules.

(1/2)

[Kyle Tretina, Ph.D. @AllThingsApx]

Shout-out to the team that contributed to the model development and NIM, including the below people and more!

Danny Reidenbach, @saint__ai, Rajesh K. Ilango, @modernscientist @johnny_israeli

[Recursion @RecursionPharma]

Today we announced a collaboration and $50 million investment from @nvidia to accelerate our groundbreaking foundation models in AI-enabled drug discovery.

Read the press release: https://t.co/xCEh0nlaaa
Read the blog from our CTO @bmabey: https://t.co/eIu012QgTu

[modernscientist @modernscientist]

@diracGnome I meant "including materials sciences", sorry!

[modernscientist @modernscientist]

My team at #NVIDIA is hiring for multiple life sciences applied deep learning scientists. Help us build #BioNeMo!
- Protein Structure & Design https://t.co/lw8pMAvuJe
- Cheminformatics & Virtual Screening https://t.co/ZrTltLvNll
- Geometric Deep Learning https://t.co/SUwhA7YJic

[modernscientist @modernscientist]

@diracGnome We're pretty focused on life sciences applications for the time being. Longer term possible that we'd expand to one of many possibilities, including life sciences

[modernscientist @modernscientist]

@JeremyAbramson ♥️

[modernscientist @modernscientist]

@nicholdav Please do apply! And thank you!

[modernscientist @modernscientist]

@nparmalee Congratulations -- this is an amazing feat, regardless of time.

[Gabriele Corso @GabriCorso]

Very cool to see that @nvidia's CEO has just announced their new BioNeMo cloud service in his keynote and highlighted DiffDock as the molecular docking algorithm they have chosen to integrate! Great to see the power of open-source science! https://t.co/aWP7yoP4gb

[modernscientist @modernscientist]

@NVIDIA 's #BioNeMo cloud service for LLMs and Generative AI models in life sciences is the hard work of many brilliant individuals and teams across NVIDIA. I am incredibly proud of what we've built.

https://t.co/6TiKMIXzvR…

[modernscientist @modernscientist]

@Dixie3Flatline https://t.co/ydhm6T4vML

[Jacob Stern @jacobastern]

In protein design, "adversarial sequences" are protein sequences predicted to fold into a certain structure but which are insoluble in practice. Our new preprint introduces BayesDesign, a design algorithm less prone to generating insoluble sequences. Link: https://t.co/dbaGIfNwt9

[modernscientist @modernscientist]

Incredibly excited about this! 🧵👇

[Christian Dallago @sacdallago]

At the end of last week @nvidia announced early access to the BioNeMo Service (https://t.co/55y0etxx3q). Beyond access to the first NVIDIA trained pLM inspired by the successes of the community, this is the first glimpse into something NVIDIAns have engineered for months…

[Claire McWhite @clairemcwhite]

New preprint with @ProfMonaSingh. We present vcMSA, a totally new algorithm for multiple sequence alignment that's based on clustering protein language representations of amino acids. No gaps penalties, substitution matrices, or guide trees required. https://t.co/TR1Tz3zPCj

[modernscientist @modernscientist]

@nparmalee Found ya!

[modernscientist @modernscientist]

I’m testing the waters on Mastodon at [email protected]

[Omar Sanseviero 🇫🇷 @RAISE Paris @osanseviero]

Since early in the year at @huggingface we have been building an amazing Moonshot team to contribute to the OS ecosystem in different domains😍

ML for Art, Healthcare, Proteins, Mobile ML, and more to come! Very cool things to come 🔥

[Richard Sever @cshperspectives]

Massive news: eLife to abolish accept/reject decisions: papers will just be “peer reviewed”. Others can argue about this, but lots of interesting consequences. 1/9 https://t.co/FedRxI62iC