Zero-shot antibody design in a 24-well plate

Abstract

Despite breakthroughs in protein design enabled by artificial intelligence, reliably designing functional antibodies from scratch has remained an elusive challenge. Recent works show promise but still require large-scale experimental screening of thousands to millions of designs to reliably identify hits. In this work, we introduce Chai-2, a multimodal generative model that achieves a 16% hit rate in fully de novo antibody design, representing an over 100-fold improvement compared to previous computational methods. We prompt Chai-2 to design[≤] 20 antibodies or nanobodies to 52 diverse targets, completing the workflow from AI design to wet-lab validation in under two weeks. Crucially, none of these targets have a preexisting antibody or nanobody binder in the Protein Data Bank. Remarkably, in just a single round of experimental testing, we find at least one successful hit for 50% of targets, often with strong affinities and favorable drug-like profiles. Beyond antibody design, Chai-2 achieves a 68% wet-lab success rate in miniprotein design - routinely yielding picomolar binders. The high success rate of Chai-2 enables rapid experimental validation and characterization of novel antibodies in under two weeks, paving the way toward a new era of rapid and precise atomic-level molecular engineering. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=56 SRC="FIGDIR/small/663018v1_ufig1.gif" ALT="Figure 1"> View larger version (38K): org.highwire.dtl.DTLVardef@69655borg.highwire.dtl.DTLVardef@17d44dborg.highwire.dtl.DTLVardef@133b7ddorg.highwire.dtl.DTLVardef@6c4319_HPS_FORMAT_FIGEXP M_FIG 52 antigens targeted by Chai-2. Blue boxes indicate targets with at least one successful binder out of [≤]20 assayed designs, representing 50% of the tested targets. Date: June 30, 2025 C_FIG