Sign in

Ilia Igashov

@igashov.bsky.social
164 followers 52 following 8 posts

PhD student at LPDI, EPFL 🇨🇭 AI & Structural Biology

PostsRepliesMedia
Ilia Igashov @igashov.bsky.social · 13/03/2025
That's true 😁 We have kernel density estimate plots and statistical tests in Appendix (Fig. 18 and 19)
010
Ilia Igashov @igashov.bsky.social · 11/03/2025
While DrugFlow is really good in distribution learning, we also show that it can be easily tuned to generate molecules with optimised target properties. For example, we can boost docking efficiency and synthetic accessibility, or reduce the level of swill in samples @wpwalters.bsky.social
110
Ilia Igashov @igashov.bsky.social · 11/03/2025
Our adaptive size mechanism allows DrugFlow to remove excessive atoms on the fly, adjusting the molecular size to the provided pocket constraints. In our experiments, we demonstrate that DrugFlow can avoid steric clashes if the provided molecular size is too big.
110
Ilia Igashov @igashov.bsky.social · 11/03/2025
DrugFlow's atom-level confidence score is able to detect unlikely samples and correlates with molecular size and docking efficiency. In particular, DrugFlow tends to assign low confidence in cases when it introduces steric clashes with the protein or produces strange geometries.
110
Ilia Igashov @igashov.bsky.social · 11/03/2025
🚨 Check out DrugFlow, our new generative model for structure-based drug design. DrugFlow provides an atom-level confidence score for each designed molecule, and can adjust molecular size on the fly! Additional details in thread 🧵 #ICLR2025
1237
Ilia Igashov @igashov.bsky.social · 23/01/2025
(2/2) SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints openreview.net/forum?id=uvH...
openreview.net
SynFlowNet: Design of Diverse and Novel Molecules with Synthesis...
Generative models see increasing use in computer-aided drug design. However, while performing well at capturing distributions of molecular motifs, they often produce synthetically inaccessible...
000
Ilia Igashov @igashov.bsky.social · 23/01/2025
(1/2) Multi-domain Distribution Learning for De Novo Drug Design openreview.net/forum?id=g3V...
openreview.net
Multi-domain Distribution Learning for De Novo Drug Design
We introduce DrugFlow, a generative model for structure-based drug design that integrates continuous flow matching with discrete Markov bridges, demonstrating state-of-the-art performance in...
121
Ilia Igashov @igashov.bsky.social · 23/01/2025
Really excited: 2/2 our papers got accepted at #ICLR2025! Thanks to all amazing co-authors and hope to see you in Singapore! 🇸🇬 If you're interested in generative models and RL agents for drug design check our papers in the thread 🧵
141
Reposted by Ilia Igashov
Arne Schneuing @rne.bsky.social · 21/11/2024
Excited about the intersection of AI and molecular sciences? Join us at the 'AI & the Molecular World' track @appliedmldays.bsky.social in Lausanne on Feb 13! The call for talks is now open: t.co/zisz2g3HLU (please submit your proposals before January 5th)
142