Sesame model advances structure-aware molecular generation for drug design

Researchers have introduced Sesame, a novel diffusion-based molecular generation model designed for drug discovery. This model uniquely conditions on partial molecular structures and protein-ligand interactions, expressed as spatial density maps. Sesame supports both *de novo* generation and fragment-conditioned lead optimization, allowing chemists to guide molecule growth from a starting scaffold. AI

IMPACT Enhances AI capabilities in drug discovery by enabling more precise and guided molecular generation.

RANK_REASON The cluster describes a new research paper detailing a novel AI model for molecular generation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Arvind Thiagarajan
• arXiv
• Hugging Face
• Spatial Evoformer for a Structure-Aware Molecular Engine

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →