Pasta and Protein. Music and Mysteries. Life and Lessons. Computational biologist- sometimes at work :)
United States
Joined May 2009
- Tweets277
- Following768
- Followers430
- Likes1.7K
If you are interested in working at the intersection of AI, robotics/automation and biology, come and build the next generation of open source toolkits for scientific discovery w/ me at @argonne . Apply here: bit.ly/4pwYFjS
It was a privilege to present at the Caltech UChicago AI +
Science meeting following none other than @AnimaAnandkumar and @francesarnold and all the wonderful speakers including @KyleCranmer! Really thrilled to see how AI is impacting so many facets of scientific discovery!
Arvind Ramanathan (he/him) retweeted
MProt-DPO: Breaking the ExaFLOPS Barrier for Multimodal Protein Design Workflows with Direct Preference Optimization
• This paper presents MProt-DPO, an innovative framework that achieves ExaFLOPS-scale performance for protein design, combining AI and high-performance computing (HPC) to generate and optimize protein sequences across multiple supercomputers.
• Key breakthroughs include the integration of Direct Preference Optimization (DPO), allowing fine-tuning of protein language models based on preferred structural and functional characteristics, enhancing model capability to generate “fit” protein variants effectively.
• MProt-DPO utilizes multimodal input (sequence, structural, and natural language descriptors), bridging data from simulations and experiments to guide protein design towards desired functional landscapes.
• Achieved a record-breaking 4.11 ExaFLOPS sustained performance on Aurora, demonstrating scalability across five supercomputing systems, marking a milestone in protein engineering and HPC synergy.
@arvindr_ @AnimaAnandkumar @mpapka @ChaoweiX @Shengchao_Liu @archit_vasan @servesh_m @WardLT2 @argonne
📜Paper: computer.org/csdl/proceeding…
#ProteinDesign #HPC #MachineLearning #AI #ComputationalBiology
What's more fun when you can break the Exascale barrier for #protein design workflows with #artificalintelligence, that can be prompted with natural language. Read more here: alcf.anl.gov/news/argonne-te…
We show that it is possible to minimize hallucinations with such models by integrating experimental or simulation observables allowing the model to sample not only novel sequence space, but cover reliable ground in terms of protein fitness landscapes.
Interested in knowing about what @argonne is working on at the intersection of AI, robotics and scientific discovery? Look at our program line up for this year's Scientific Discovery in the AI Age meeting at Argonne. acadev.github.io/sdl-worksho…
We also have hands on tutorial sections, interactive sessions and lab tours to show how scientific discoveries are being transformed with generative AI.
Check out some recent work integrating MD simulations with rare event sampling and DeepDriveMD with the wonderful @ltchong and our group. Really enjoyed the research, discussions, and the directions this work is taking!
Unsupervised learning of progress coordinates during weighted ensemble simulations: Application to millisecond protein folding
- Improve rare events in protein folding (e.g., state transitions) through weighted ensemble simulation and an unsupervised deep learning model.
- Use a convolutional VAE to compress contact maps into latent space, and applies a Local Outlier Factor to identify outlier conformations, which are then replicated in the simulation.
- Training the CVAE on-the-fly works better than using a pretrained model.
Preprint: biorxiv.org/content/10.1101/…
Arvind Ramanathan (he/him) retweeted
Please join @icmlconf for "Equivariant Graph Neural Operator for Modeling 3D Dynamics"
by @MinkaiX, @jiaqihan99, @aaron_lou, @JeanKossaifi,@arvindr_, @jure, @StefanoErmon, and @AnimaAnandkumar
Wed 24 Jul 1:30 p.m. CEST — 3 p.m. CEST
Hall C 4-9 #203
xitter.cf/AnimaAnandkumar/status…
How do we capture local features across multiple resolutions? While standard convolutional layers work only on a fixed input-resolution, we design local neural operators that learn integral and differential kernels, and are principled ways to extend standard convolutions to varying resolutions and grids.
Layers of such local neural operators can be combined with global neural operators such as Fourier neural operators (FNO) to provide rich expressive architectures for learning PDEs.
We show improved performance on many PDEs such as Darcy flow, turbulent fluid flow and spherical shallow water equations.
arxiv.org/abs/2402.16845
@julberner @Azizzadenesheli
Arvind Ramanathan (he/him) retweeted
Amazing collaboration with w/ @jiaqihan99 (co-first) @aaron_lou @JeanKossaifi @arvindr_ @Azizzadenesheli @jure @StefanoErmon @AnimaAnandkumar
@NVIDIAAI @StanfordAILab
2/n
LLMs with biophysical scoring methods - thanks to Gautham @saforem2 @AnimaAnandkumar and the @argonne_lcf for this!
📢 another one, hot off the press 🔥 🚨
Protein Generation via Genome-scale Language Models with Bio-physical Scoring
dl.acm.org/doi/abs/10.1145/3…
( with @arvindr_ , @argonne_lcf )
Arvind Ramanathan (he/him) retweeted
The slides for Ian Foster's talk at eScience "Embodied Agents as Scientific Assistants" are now available here: anl.app.box.com/v/embodied-a…
Again, you cannot find a better mentor and an exciting group...
Learn how we can use AI/ML in driving massive bacterial membrane systems and do it in the beautiful city of Oxford! @ProfSyK and @argonne ...
This Post is from an account that no longer exists. Learn more
The position is unique in the sense that it involves access to @argonne_lcf computing resources and our autonomous laboratory infrastructure to validate findings from the simulations
Honored to be part of this! This is a truly once in a lifetime opportunity for motivated researchers- and you know how much fun it is to be part of @ProfSyK group and Oxford. There are plans to integrate with new AI techniques integrating with @argonne automated labs!
This Post is from an account that no longer exists. Learn more