@SurgeBiswas: New paper from the @nablabio team expanding generative drug design to multispecifics, the intracellular proteome, and p…
Summary
Nabla Bio's new paper (JAM-2) expands generative drug design to multispecifics and the intracellular proteome, achieving zero-shot design of a KRAS G12V-targeting bispecific that recruits T cells for picomolar cell killing.
View Cached Full Text
Cached at: 06/24/26, 04:19 AM
New paper from the @nablabio team expanding generative drug design to multispecifics, the intracellular proteome, and pushing the limits of atomic precision.
A tour de force of computation + wet-lab and some incredible results, including zero-shot design of a KRAS G12V pMHC-targeting bispecific that recruits primary T-cells from human donors and achieves picomolar cell killing.
Much more in our post and report
Congrats @SurgeBiswas. I think you guys might have accidentally missed citing our work that is highly relevant and comparable published last year.
Similar Articles
@nablabio: Today, we expand zero-shot drug design beyond binding to the design of multifunctional medicines, the intracellular pro…
Nabla Bio unveils JAM-2, a model for zero-shot drug design achieving atomic-precision, computationally designed multispecific antibodies and dual-variant KRAS multispecifics with high potency and selectivity, validated with Cryo-EM and wet-lab experiments.
@arcinstitute: Congrats to @BrianHie, @SynBioGaoLab, and team on Germinal, now out in @NatureBiotech. Their pipeline designs epitope-t…
Arc Institute announces Germinal, a generative AI system for de novo antibody design published in Nature Biotechnology. It designs epitope-targeted antibodies with nanomolar affinity testing only tens of designs per target, making custom antibody design more accessible.
ShallowBench: Benchmarking Generative Drug Design Models on Shallow-Pocket Targets
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.
Reading the Cell, Designing the Cure: Perturbation-Conditioned Molecular Diffusion for Function-Oriented Drug Design
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.
AgForce Enables Antigen-conditioned Generative Antibody Design
This paper identifies three failure modes in existing antibody design methods (antigen blindness, vocabulary collapse, convergence to marginal distribution) and proposes AgForce, a novel encoder-decoder architecture using graph neural networks and mixture density networks, achieving state-of-the-art binding quality and sequence recovery on the Chimera-Bench benchmark.