Ian Dunn
@ian-dunn.bsky.social
PhD Candidate in Computational Biology @ University of Pittsburgh. Working on deep generative models for molecular structure. iandunn.io
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
September 22, 2025 at 10:35 PM
The performance gains over previous FlowMol versions are due to 3 techniques which are cheap and architecture agnostic. We hypothesize that these techniques operate synergistically to reduce a common pathology in transport-based generative models.
September 2, 2025 at 7:12 PM
The performance gains over previous FlowMol versions are due to 3 techniques which are cheap and architecture agnostic. We hypothesize that these techniques operate synergistically to reduce a common pathology in transport-based generative models.
Our work is fully open-source and we invite feedback from the community. Code is available here: github.com/Dunni3/FlowMol
GitHub - Dunni3/FlowMol: Mixed continous/categorical flow-matching model for de novo molecule generation.
Mixed continous/categorical flow-matching model for de novo molecule generation. - Dunni3/FlowMol
github.com
December 11, 2024 at 9:21 PM
Our work is fully open-source and we invite feedback from the community. Code is available here: github.com/Dunni3/FlowMol
This opens a new set of questions, gives researchers a new way to quantify molecule quality, and the ability to test hypotheses as we further push de novo models to more faithfully match the distribution of real molecules.
December 11, 2024 at 9:21 PM
This opens a new set of questions, gives researchers a new way to quantify molecule quality, and the ability to test hypotheses as we further push de novo models to more faithfully match the distribution of real molecules.
But that's not the whole story. We introduce methods to quantify molecule quality at the level of functional groups + ring systems. "Valid" generated molecules tend to contain significantly more reactive functional groups than in the training data.
December 11, 2024 at 9:21 PM
But that's not the whole story. We introduce methods to quantify molecule quality at the level of functional groups + ring systems. "Valid" generated molecules tend to contain significantly more reactive functional groups than in the training data.
We test a handful of discrete flow matching methods for 3D de novo molecule design and provide some explanations for their differing performance. The result of this is a version of FlowMol with CTMC flows that achieves SOTA validity with fewer learnable parameters.
December 11, 2024 at 9:21 PM
We test a handful of discrete flow matching methods for 3D de novo molecule design and provide some explanations for their differing performance. The result of this is a version of FlowMol with CTMC flows that achieves SOTA validity with fewer learnable parameters.
formal post coming soon :p
November 29, 2024 at 12:35 AM
formal post coming soon :p