Ian Dunn
@ian_dunn_
Followers
325
Following
4K
Statuses
194
PhD Candidate @CMUPittCompBio, advised by @david_koes. Interested in deep learning for molecular structures and accelerating drug discovery.
Pittsburgh, PA
Joined November 2018
I'm presenting a new paper "Exploring Discrete Flow Matching for 3D De Novo Molecule Generation" at @workshopmlsb this week! More info in this thread but reach out if want to chat at NeurIPS about generative models or molecular design.
2
1
11
RT @lipmanya: Our **Flow Matching Tutorial** from #NeurIPS2024 is now publicly available: @helibenhamu @RickyTQCh…
0
92
0
RT @k_neklyudov: 🧵(1/5) Have you ever wanted to combine different pre-trained diffusion models but don't have time or data to retrain a new…
0
53
0
@amelie_iska Haven’t looked into it but it’s an analysis worth doing. Inference-time guidance is a nice idea (some have tried it iirc), but also a band-aid for a model that can’t figure out reasonable structures on its own; we probably need guidance + better models.
0
0
1
FlowMol at your fingertips! We just released a colab notebook to make using FlowMol super easy. Come chat with us tomorrow at @workshopmlsb !
I'm presenting a new paper "Exploring Discrete Flow Matching for 3D De Novo Molecule Generation" at @workshopmlsb this week! More info in this thread but reach out if want to chat at NeurIPS about generative models or molecular design.
0
0
10
Our work is fully open-source and we invite feedback from the community. Code is available here:
2
0
0
Our paper on the Koes Group’s winning (tied for first w/ @olexandr ) submission to the first CACHE Challenge was also just published in JCIM.
0
7
36
First CACHE Challenge paper now published!
CACHE Challenge #1: Targeting the WDR Domain of LRRK2, A Parkinson’s Disease Associated Protein @CherylArrowsmi1 @ian_dunn_ @aledmedwards @friedo91 @fgentile9 @olexandr @spiwokv @MKCMU @Sumera_Perveen @janhjensen @mattschap
#JCIM Vol64 Issue22 #compchem
0
0
2
RT @olexandr: Finally, a community-wide paper @JCIM_JCTC led by @mattschap describing results of CACHE Challenge #1: Targeting the WDR Dom…
0
15
0
RT @oliviaviessmann: Our work on all-atom tokenization of any biomolecular structure is on arxiv now! @BiologyAIDa…
0
20
0
RT @mattschap: Announcing CACHE2 results! Crowdsourcing and conventional methods did as well as novel ML. Teams started from 4 fragments in…
0
25
0
RT @GoogleDeepMind: We’re presenting AlphaProteo: an AI system for designing novel proteins that bind more successfully to target molecules…
0
833
0
RT @MoAlQuraishi: ESM3 is out from EvolutionaryScale! 98B params (~GPT3 scale). Multimodal over sequence, structure, and function with cool…
0
65
0
RT @charlieharris01: Great post on AlphaFold3 from @inductive_bio that I'm surprised has not got more attention🤔 - AF3 paper benchmarked V…
0
26
0
RT @leonklein26: Excited to share our latest preprint: "Transferable Boltzmann Generators"! We propose a framework based on flow matching a…
0
17
0
RT @charlieharris01: New blog post alert! 🚨 I write about AlphaFold3, how it works, where it works well ✅ (and where we think it might not…
0
13
0