ジャーナル: Science / 年: 2023 タイトル: Top-down design of protein architectures with reinforcement learning. 著者: Isaac D Lutz / Shunzhi Wang / Christoffer Norn / Alexis Courbet / Andrew J Borst / Yan Ting Zhao / Annie Dosey / Longxing Cao / Jinwei Xu / Elizabeth M Leaf / Catherine Treichel / Patrisia ...著者: Isaac D Lutz / Shunzhi Wang / Christoffer Norn / Alexis Courbet / Andrew J Borst / Yan Ting Zhao / Annie Dosey / Longxing Cao / Jinwei Xu / Elizabeth M Leaf / Catherine Treichel / Patrisia Litvicov / Zhe Li / Alexander D Goodson / Paula Rivera-Sánchez / Ana-Maria Bratovianu / Minkyung Baek / Neil P King / Hannele Ruohola-Baker / David Baker / 要旨: As a result of evolutionary selection, the subunits of naturally occurring protein assemblies often fit together with substantial shape complementarity to generate architectures optimal for function ...As a result of evolutionary selection, the subunits of naturally occurring protein assemblies often fit together with substantial shape complementarity to generate architectures optimal for function in a manner not achievable by current design approaches. We describe a "top-down" reinforcement learning-based design approach that solves this problem using Monte Carlo tree search to sample protein conformers in the context of an overall architecture and specified functional constraints. Cryo-electron microscopy structures of the designed disk-shaped nanopores and ultracompact icosahedra are very close to the computational models. The icosohedra enable very-high-density display of immunogens and signaling molecules, which potentiates vaccine response and angiogenesis induction. Our approach enables the top-down design of complex protein nanomaterials with desired system properties and demonstrates the power of reinforcement learning in protein design.
履歴
登録
2022年11月11日
登録サイト: RCSB / 処理サイト: RCSB
改定 1.0
2023年5月10日
Provider: repository / タイプ: Initial release
改定 1.1
2024年6月19日
Group: Data collection / カテゴリ: chem_comp_atom / chem_comp_bond