MESSI uses discrete diffusion to deimmunize proteins, validated across enzyme families
sokrypton · x · 2026-10-17
Researchers introduce MESSI, a generative method using discrete diffusion to deimmunize proteins. Protein immunogenicity is a major driver of clinical drug failure, especially critical as generative AI enables de novo medicine design. MESSI reduces predicted MHC-II epitopes and experimentally retains or improves function in luciferases, PD-1 binders and uricases used in FDA-approved therapies.
More from Research
- New paper pushes (min,+)-matrix multiplication exponent to 2.9964, beating Anthropic-linked breakthrough — thegautamkamath · 2026-10-17
- SYNTH team's jspace analysis: Baguettotron layer topology radically differs from Gemma-270m — voooooogel · 2026-10-17
- Tangermeme published in Nature Methods: an 'everything-but-the-model' toolkit for genomic deep learning — anshulkundaje · 2026-10-17
- Context Inertia: when LLM agents latch onto a wrong hypothesis and won't let go — rseroter · 2026-10-17
- Microsoft's MAI-Base-2 blog source code leaks intermediate checkpoint validation losses — YouJiacheng · 2026-10-17
- Axolotl v0.21.0 ships 501B MoE QLoRA fine-tuning on a single 8xH200 node — ethayarajh · 2026-10-17