CrossDocked2020
PulseAugur coverage of CrossDocked2020 — every cluster mentioning CrossDocked2020 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AI agents reuse molecular optimization experience for drug design
Researchers have investigated how AI agents can reuse past experiences to optimize molecular structures for drug design. The study focused on whether keys derived from previous editing sessions could effectively guide n…
-
New diffusion models advance structure-based drug design for single and dual targets
Researchers have developed two new diffusion models for structure-based drug design. PocketVE, presented in arXiv cs.LG, is a protein-pocket-conditioned framework that enhances molecular property guidance and geometric …
-
New SurfSpec framework improves drug design specificity without off-target data
Researchers have developed SurfSpec, a new framework for structure-based drug design that enhances specificity by analyzing the geometric mismatch between a ligand and its target pocket. This method provides a lower bou…
-
SurfSpec framework improves drug lead specificity using geometric mismatch
Researchers have developed SurfSpec, a novel framework for lead optimization in structure-based drug design. This method enhances specificity by focusing on the geometric mismatch between a ligand and its target pocket,…
-
New benchmark ShallowBench targets AI drug design for shallow pockets
Researchers have developed ShallowBench, a new benchmark designed to evaluate generative AI models used in drug design, specifically focusing on targets with shallow binding pockets. Existing models perform poorly on th…
-
LLM agents use probing for better drug design
Researchers have developed a new framework called PROBE to improve molecular optimization for LLM agents in drug design. This method addresses the challenge of balancing binding affinity and druggability by first analyz…
-
MolPIF model unifies continuous and discrete molecular generation
Researchers have developed MolPIF, a novel parameter interpolation flow model designed to unify the generation of continuous atomic coordinates and discrete atom types in molecular design. This approach addresses limita…