Rishal Aggarwal

If you like to sample from the Boltzmann distribution and are in San Diego for NeurIPS, be sure to check out Rishal's (@rishalchich.bsky.social) poster (#2110). Great work with Nick Boffi (@nmboffi.bsky.social) and Jacky Chen.
neurips.cc/virtual/2025...
arxiv.org/abs/2507.00846

Our new preprint PharmacoForge: Pharmacophore Generation with Diffusion Models is out now! PharmacoForge quickly generates pharmacophores for a given protein pocket that identify key binding features and find useful compounds in a pharmacophore search. Check it out! 🧪 doi.org/10.26434/che...

Happy to introduce 🔥LaM-SLidE🔥!

We show how trajectories of spatial dynamical systems can be modeled in latent space by

--> leveraging IDENTIFIERS.

📚Paper: arxiv.org/abs/2502.12128
💻Code: github.com/ml-jku/LaM-S...
📝Blog: ml-jku.github.io/LaM-SLidE/
1/n

Long & windy road of academic publishing! Few journal rejections and two years (!!!) after preprint, AIMNet2 paper was just published @chemsocrev.rsc.org With 69 citations to it as of now, it's immediately part of 2025 HOT🌶️ Article collection. pubs.rsc.org/en/content/a... #chemsky #compchem

Thanks to everyone for helping make #ICLR2025 successful. 🥳 It was an honor to serve as General Chair.

The best part was using @iclr-conf.bsky.social as my personal meme account the past two years (first as Senior Program Chair). I hope that future ICLR organizers continue the tradition. 🤪

Please welcome AITHYRA, the Research Institute for Artificial Intelligence of the Austrian Academy of Science on social media. Follow us and connect via Bluesky and LinkedIn 👋

Metagenomic-scale analysis of the predicted protein structure universe Protein structure prediction breakthroughs, notably AlphaFold2 and ESMfold, have led to an unprecedented influx of computationally derived structures. The AlphaFold Protein Structure Database now prov...

Our latest preprint is out on bioRxiv!

A collaboration between the groups of @martinsteinegger.bsky.social , David Jones and Christine Orengo, we clustered AlphaFold Database and ESMatlas, a whopping 821 million proteins!

We reveal biome-specific groups & over 11k novel domain combinations.

Hello, we are AITHYRA!
I am very excited to share with you the corporate identity of AITHYRA, the Research Institute for Biomedical AI.

Check out the brand design video (sound on!) to learn more.

**REMINDER**
One week left to apply for Starting PI positions (Life Science and AI/ML). Come join us!

"De novo prediction of protein structural dynamics"

I'll be presenting an overview of the field tomorrow at a workshop. Link to a PDF copy of the presentation: delalamo.xyz/assets/post_...

Sara with .5 mode selfie (thanks kids) in front of aacr sign

Who is at #AACR25? I’m here representing my group’s work at the intersection of AI and drug resistance in cancer, and want to hear about what you’re doing!(1/4)

@iclr-conf.bsky.social blog posts are now live at iclr-blogposts.github.io/2025/blog! Unfortunately I won't be able to present our blog post at the conference in person 😔, but I am happy to chat about it online if you find it interesting! Poster attached 🙂.

With this baseline, we emphasize that such generative methods should focus on computational efficiency and transferability in their model design and benchmarks.

Work done with Daniel ( @countrsignal.bsky.social ), Justin ( @shaojus.bsky.social ), and Minhyek ( @minhyekj.bsky.social )

New "blogpost" from our lab, that got accepted at ICLR 2025! We compare an old MCMC method known as Sequential Monte Carlo to generative models trained on energy functions (iDEM/iEFM) and show that MCMC does better. Check it out here: rishalaggarwal.github.io/ebmvsmcmc/

PharmRL: pharmacophore elucidation with deep geometric reinforcement learning - BMC Biology Background Molecular interactions between proteins and their ligands are important for drug design. A pharmacophore consists of favorable molecular interactions in a protein binding site and can be ut...

New paper at the turn of the new year :)

Check out our latest paper on using reinforcement learning for pharmacophore elucidation on protein binding sites. It comes with a google colab notebook for use.

bmcbiol.biomedcentral.com/articles/10....

Last week several of our students presented their research at NeurIPS 2024 in Vancouver. We are so proud of the excellent work that they've accomplished and shared with the scientific community! 🧪
Check out each of their papers below:

AlphaFold3 still tends to overfit regions that AF2 multimer predicts to be disordered. Almost all disordered regions become helices in AF3.

Going into @workshopmlsb.bsky.social , a few thoughts on the PLINDER dataset. This is a monumental and highly appreciated undertaking for extracting protein-ligand interactions from the PDB. First the good...

I'm presenting a new paper "Exploring Discrete Flow Matching for 3D De Novo Molecule Generation" at @workshopmlsb.bsky.social this week! More info in this thread but reach out if want to chat at NeurIPS about generative models or molecular design. arxiv.org/abs/2411.16644

More excellent work from the indomitable @ian-dunn.bsky.social Come check it out at @workshopmlsb.bsky.social

Excited about BioEmu?

Opening this position for just a few days over #NeurIPS2024. Looking especially for Bioinformatics + Structural Biology skills, MD/Stat Mech skills and/or #deeplearning architecture design + engineering skills

aka.ms/ai4science-r...

CACHE Challenge #1: Docking with GNINA Is All You Need We describe our winning submission to the first Critical Assessment of Computational Hit-Finding Experiments (CACHE) challenge. In this challenge, 23 participants employed a diverse array of structure...

Our paper describing our winning submission (tied with @olexandr.bsky.social) is out with some extra computational analysis of the predicted binding modes. We didn't do anything fancy (but the hits weren't that great either...).

pubs.acs.org/doi/10.1021/...

do not assess & compare their methods on fair footing & in a meaningful way

For good or for bad, in the end, BLINDED COMMUNITY CHALLENGES are the only fair way to assess methods

Meaning: the proof is in the pudding. The methods who want to be taken seriously should ...

Dimensionality reduced embedding space showing that ligand and their targets colocate and genomes self organize.

SPRINT Enables Interpretable and Ultra-Fast Virtual Screening against Thousands of Proteomes Andrew T. McNutt ∗ University of Pittsburgh anm329@pitt.edu Abhinav K. Adduri∗ CMU, Arc Institute abhinav.adduri@arcinstitute.org Caleb N. Ellington∗ Carnegie Mellon University cellingt@cs.cmu.edu Monica T. Dayao Carnegie Mellon University mdayao@cs.cmu.edu Eric P. Xing CMU, MBZUAI, Petuum Inc. epxing@cs.cmu.edu Hosein Mohimani Carnegie Mellon University hoseinm@cs.cmu.edu David R. Koes University of Pittsburgh dkoes@pitt.edu

We're looking forward to presenting this @workshopmlsb.bsky.social . This work was conceived and led by a group CPCB (@cmupittcompbio.bsky.social) students and learns a co-embedding of proteins and ligands to support ultra fast virtual screening. arxiv.org/pdf/2411.15418