Ian Dunn
@ian-dunn.bsky.social
PhD Candidate in Computational Biology @ University of Pittsburgh. Working on deep generative models for molecular structure. iandunn.io
Pinned
Ian Dunn
@ian-dunn.bsky.social
· Sep 2
I'm excited to share FlowMol3! The 3rd (and final) version of our flow matching model for 3D de novo, small-molecule generation. FlowMol3 achieves state of the art performance over a broad range of evaluations while having ≈10x fewer parameters than comparable models.
I'm excited to share FlowMol3! The 3rd (and final) version of our flow matching model for 3D de novo, small-molecule generation. FlowMol3 achieves state of the art performance over a broad range of evaluations while having ≈10x fewer parameters than comparable models.
September 2, 2025 at 7:12 PM
I'm excited to share FlowMol3! The 3rd (and final) version of our flow matching model for 3D de novo, small-molecule generation. FlowMol3 achieves state of the art performance over a broad range of evaluations while having ≈10x fewer parameters than comparable models.
Reposted by Ian Dunn
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...
May 27, 2025 at 7:11 PM
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...
Reposted by Ian Dunn
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/
March 31, 2025 at 4:57 PM
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/
Reposted by Ian Dunn
Structural biology is in an era of dynamics & assemblies but turning raw experimental data into atomic models at scale remains challenging. @minhuanli.bsky.social and I present ROCKET🚀: an AlphaFold augmentation that integrates crystallographic and cryoEM/ET data with room for more! 1/14.
February 24, 2025 at 12:23 PM
Structural biology is in an era of dynamics & assemblies but turning raw experimental data into atomic models at scale remains challenging. @minhuanli.bsky.social and I present ROCKET🚀: an AlphaFold augmentation that integrates crystallographic and cryoEM/ET data with room for more! 1/14.
MLSB + the AI4Science field are clearly outgrowing the ML conference workshop format
December 15, 2024 at 6:38 PM
MLSB + the AI4Science field are clearly outgrowing the ML conference workshop format
FlowMol at your fingertips! We just released a colab notebook to make using FlowMol super easy. Come chat with us tomorrow at @workshopmlsb ! #NeurIPS2024 🧪 colab.research.google.com/github/Dunni...
December 15, 2024 at 12:34 AM
FlowMol at your fingertips! We just released a colab notebook to make using FlowMol super easy. Come chat with us tomorrow at @workshopmlsb ! #NeurIPS2024 🧪 colab.research.google.com/github/Dunni...
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
December 11, 2024 at 9:21 PM
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
Reposted by Ian Dunn
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/...
pubs.acs.org/doi/10.1021/...
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...
pubs.acs.org
December 10, 2024 at 12:26 PM
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/...
pubs.acs.org/doi/10.1021/...
Reposted by Ian Dunn
Here is how Boltz-1 (green), DynamicBind (magenta), and GNINA (blue) dock a collection of random molecules. GNINA, using a classical sampling algorithm (MCMC) hits all concave regions while the ML samplers have distinct preferences. Boltz is the most likely to induce a fit.
November 22, 2024 at 6:27 PM
Here is how Boltz-1 (green), DynamicBind (magenta), and GNINA (blue) dock a collection of random molecules. GNINA, using a classical sampling algorithm (MCMC) hits all concave regions while the ML samplers have distinct preferences. Boltz is the most likely to induce a fit.