Hello from Singapore 🇸🇬! Thrilled to be at #ICLR2025 presenting our work on fragment-based drug discovery 🧩. We go beyond virtual screening with a generative, structure-aware approach.
📃 https://openreview.net/forum?id=bZW1HLT1gI
🔗 https://github.com/rneeser/LatentFrag
A thread 🧵👇
📃 https://openreview.net/forum?id=bZW1HLT1gI
🔗 https://github.com/rneeser/LatentFrag
A thread 🧵👇
Comments
Fragment-based design = build better drugs by combining small fragment that each have key interactions.
But:
❗Fragments bind weakly
❗Standard screening is inefficient
So we built a contrastive learning model to learn how fragments interact with protein pockets. 🧬
💡 Fragment encoder:
We first train a protein–fragment encoder with contrastive loss to map both fragments and protein surfaces into a shared latent space.
It captures interaction-relevant features, which can be used directly for fast virtual screening 🚀.
We then extended this to a generative flow matching framework:
🧠 It learns distributions over fragment latents & spatial arrangements
🧪 Conditioned directly on protein surfaces
✅ No decoder needed
✅ Chemically realistic by construction
This means:
🔹 You can flexibly explore new fragment libraries
🔹 No retraining required
🔹 Outputs stay valid & structure-aware
🔹 More expressive than vanilla virtual screening
All in one unified latent space ✨
We also propose a robust evaluation framework:
✅ “Hard” fragment recovery
✅ “Soft” pharmacophoric similarity
This gives a nuanced view of what the model learns – and shows improvements over docking-based screening baselines.
I’ll be presenting this work at:
🧬 GEMbio workshop: Sun 27th (Hall 4#4)
🔬 AI4Mat workshop: Mon 28th (Topaz Concourse).
If you're around #ICLR2025, let’s chat! 😊