Small molecules that recruit the cell's protein disposal machinery to selectively destroy disease-causing proteins, including previously "undruggable" targets. PROTACs and molecular glues represent fundamentally new pharmacology.
Targeted protein degradation meets deep learning. Where the biology is ready, where the data is not, and what it means for drug programs targeting tau and alpha-synuclein.
Apr 12, 2026 · 9 min read
Phase 1 data for ARV-102 shows meaningful target engagement in cerebrospinal fluid after 28 days, marking the first clinical proof-of-concept for protein degradation in neurodegenerative disease.
Mar 18, 2026 · 7 min read
Predicts single-chain and multimer protein 3D structures from amino acid sequence using MSA-based deep learning. Set the modern benchmark on CASP14.
First fully open-source model achieving AlphaFold3-level accuracy for joint structure prediction of proteins, nucleic acids, and small molecules.
Extends Boltz-1 to jointly predict 3D complex structure AND protein-ligand binding affinity. Approaches FEP accuracy at 1,000x lower compute cost.
Multi-modal foundation model for joint structure prediction of proteins, small molecules, DNA, RNA, and glycosylations. Performs well in single-sequence mode.
Single-sequence protein structure prediction using the ESM-2 protein language model (15B parameters). No MSA required — fast inference directly from sequence.
Single-sequence structure prediction using a protein language model plus geometry-inspired transformer. First MSA-free method to approach AF2 accuracy.