Tag
AI is accelerating biologic drug design by predicting candidate molecules and enabling multi-target therapies, with potential to cut discovery timelines by 50% and target previously undruggable diseases.
This paper benchmarks general-purpose LLMs against specialized diffusion models for generating binding molecules under 3D spatial constraints, finding that LLMs show promise despite currently lagging behind state-of-the-art approaches.
Vilya-1 is a deep learning model for predicting macrocycle structures and properties, using an all-atom representation to sample conformations and predict developability, substantially improving geometric accuracy over existing methods.
The article profiles chemist Tim Cernak, who applies AI-driven drug design (like AlphaFold) to develop precision treatments for wildlife, coining the field 'conservation chemistry' to address mass extinction with cutting-edge tools.
Introduces ShallowBench, a curated benchmark of 5,780 shallow-pocket protein targets, to evaluate generative drug design models on challenging low-pocketability targets like KRAS and MYC.
This paper introduces PROBE, a framework that uses LLM agents to iteratively optimize ligands in structure-based drug design by probing pocket-ligand complex responses before editing, achieving state-of-the-art results on CrossDocked2020.
Introduces AIMS-Fold, an inference-time guided-diffusion framework that integrates cross-linking mass spectrometry (XL-MS) and hydrogen-deuterium exchange (HDX-MS) data to improve protein co-folding predictions for induced proximity drug targets.
This paper formalizes transcriptome-based drug design (TBDD) as a generative inverse problem and proposes CURE, a multi-resolution transcriptome-guided diffusion framework that generates drug molecules conditioned on desired transcriptomic state transitions.