Wojtek Treyde
@wtreyde.bsky.social
PhD student at the University of Oxford
💻 Computational chemistry & ML for drug discovery 💊
Previously Columbia & Heidelberg
💻 Computational chemistry & ML for drug discovery 💊
Previously Columbia & Heidelberg
🚀 By virtue of its simplicity, QuickBind can serve as both an effective virtual screening tool and a minimal test bed for exploring new model architectures and innovations.
December 8, 2024 at 5:22 PM
🚀 By virtue of its simplicity, QuickBind can serve as both an effective virtual screening tool and a minimal test bed for exploring new model architectures and innovations.
🚀 By virtue of its simplicity, QuickBind can serve as both an effective virtual screening tool and a minimal test bed for exploring new model architectures and innovations.
December 8, 2024 at 5:20 PM
🚀 By virtue of its simplicity, QuickBind can serve as both an effective virtual screening tool and a minimal test bed for exploring new model architectures and innovations.
🔍 We investigated the mechanistic basis by which QuickBind makes predictions and found that it has learned key physicochemical properties of molecular docking.
December 8, 2024 at 5:20 PM
🔍 We investigated the mechanistic basis by which QuickBind makes predictions and found that it has learned key physicochemical properties of molecular docking.
💊 To facilitate high-throughput virtual screening applications, we augmented QuickBind with a binding affinity module and demonstrate its capabilities for multiple clinically-relevant drug targets.
December 8, 2024 at 5:20 PM
💊 To facilitate high-throughput virtual screening applications, we augmented QuickBind with a binding affinity module and demonstrate its capabilities for multiple clinically-relevant drug targets.
🔬 QuickBind predicts how a small molecule will bind to a target protein, a key component of early-stage computational drug discovery.
⚖️ We assessed QuickBind on widely used benchmarks and found that it provides an attractive trade-off between model accuracy and runtime.
⚖️ We assessed QuickBind on widely used benchmarks and found that it provides an attractive trade-off between model accuracy and runtime.
December 8, 2024 at 5:19 PM
🔬 QuickBind predicts how a small molecule will bind to a target protein, a key component of early-stage computational drug discovery.
⚖️ We assessed QuickBind on widely used benchmarks and found that it provides an attractive trade-off between model accuracy and runtime.
⚖️ We assessed QuickBind on widely used benchmarks and found that it provides an attractive trade-off between model accuracy and runtime.
I presented QuickBind in a Spotlight Presentation at MLCB 2024 in Seattle, and it's now been published in the corresponding volume of PMLR (proceedings.mlr.press/v261/treyde2...).
QuickBind: A Light-Weight And Interpretable Molecular Docking Model
Predicting a ligand’s bound pose to a target protein is a key component of early-stage computational drug discovery. Recent developments in machine learning methods have focused on improving pose q...
proceedings.mlr.press
December 8, 2024 at 5:19 PM
I presented QuickBind in a Spotlight Presentation at MLCB 2024 in Seattle, and it's now been published in the corresponding volume of PMLR (proceedings.mlr.press/v261/treyde2...).