[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82957-en":3,"doc-seo-82957-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},82957,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Design-CP: Context Parallelism for Design of Protein Nanoparticles","Many all-atom generative protein models can design large multimeric complexes by jointly modeling all chains, yet quadratic token-and atom-pair representations quickly exceed single-GPU memory as chains and residues grow. Design-CP introduces two context-parallel inference strategies for RFdiffusion 3, using 1D row-sharding and 2D grid sharding with ring attention to distribute quadratic activations across multi-GPU meshes while preserving pretrained weights. Scaling and symmetry results enable end-to-end icosahedral nanoparticle design and practical multi-GPU deployment.","Design-CP: Context Parallelism for Design of Protein Nanoparticles  \nLorenzo Tarricone 1 2 Helen E. Eisenach 3 4 Aiko Muraishi 3 4 5 Charlotte M. Deane 1  \narXiv :2607 .05439v 1 [ cs .LG] 3 Jul 2026  \nAbstract  \nMany all-atom generative protein models can in principle design large multimeric complexes by jointly modelling all chains, but their quadratic token-and atom-pair representations quickly exceed single-GPU memory as the number of chainsand residues modelled grows. We introduce Design-CP, two context-parallel (CP) inference strategies for RFdiffusion 3 (1D row-sharding and 2D grid sharding with ring attention) that distribute the quadratic activations across a multiGPU mesh while preserving pretrained weights.  \nWe characterise their scaling when sampling icosahedral assemblies, showing that the maximum feasible asymmetric subunit (ASU) size grows with the expected square-root trend in GPU count and that 2D sharding achieves better wallclock scaling. Moreover, we show how strong point-group symmetry constraints make CP usable out of the box for end-to-end, all-atom design of icosahedral nanoparticles, yielding favourable in silico structural and interface metrics. Finally, we demonstrate octahedral nanoparticle design on a small cluster of workstation-grade 16 GB GPUs, illustrating how Design-CP can be a practical path towards democratising large-assembly protein design.  \n1. Introduction  \nDeep learning is transforming computational protein design from a predominantly physics-based endeavour into a data-driven discipline. Families of structure prediction models such as AlphaFold (Jumper et al., 2021 ; Abramsonet al., 2024), RoseTTAFold (Baek et al., 2021 ; 2023 ; Corley  \n1Department of Statistics, University of Oxford, Oxford, UK 2Ellison Institute of Technology Oxford, Oxford, UK 3Institute for Protein Design, University of Washington, Seattle, USA 4Department of Biochemistry, University of Washington, Seattle, USA 5Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, USA. Correspondence to: Charlotte Deane \u003C[deane@stats.ox.ac.uk](deane@stats.ox.ac.uk)> .  \nAccepted at the 2026 Workshop on Generative and Agentic AI for Biology (ICML 2026)  \net al., 2025) and Boltz (Wohlwend et al., 2024 ; Passaro et al., 2025) now achieve near-experimental accuracy on many single-chain targets. In parallel, a rapidly expanding family of denoising-based generative design frameworks including RFDiffusion (Watson et al., 2023 ; Butcher et al., 2025), Chroma (Ingraham et al., 2023), Genie (Lin & AlQuraishi, 2023 ; Lin et al., 2024), and Proteina (Geffner et al., 2025b ;a; Didi et al., 2026) enable the de novo creation of proteins with prescribed structural and functional properties. These advances have already yielded a tangible impact across diverse application domains. In therapeutic design alone, examples include de novo minibinders against therapeutically relevant targets such as bioactive peptide hormones (Vzquez Torres et al., 2024) and bacterial toxins (Ragotte et al., 2025) as well as the de novo design of epitope-targeted antibodies, from diffusion-based co-design of CDR sequence and structure on a fixed framework (Luo et al., 2022) to atomically accurate in-silico design of VHHsand scFvs (Bennett et al., 2026) .  \nThe success of these methods motivates scaling such generative tools to larger and more biologically complex targets, but this requires the ability to reliably design multimeric protein complexes. In nature, the majority of proteins carry out their functions not as isolated monomers but asoligomeric assemblies, such as homodimers, heteromeric complexes, and higher-order symmetric architectures (Goodsell & Olson, 2000 ; Marsh & Teichmann, 2015) . Designing symmetric assemblies de novo could unlock applications ranging from biomolecular machines inspired by rotary motors such as ATP synthase (Courbet et al., 2022) to vaccine scaffolds inspired by viral capsids (Butterfield et al.,","cbCaitE67atzWnvp","https://ap.wps.com/l/cbCaitE67atzWnvp","pdf",8600656,3,1,27,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What problem does Design-CP address in all-atom multimeric protein design?\",\"answer\":\"Quadratic token-and atom-pair representations in all-atom generators become too memory-intensive for single GPUs as the number of chains and residues increases. Design-CP distributes these quadratic activations across multiple GPUs during inference.\"},{\"question\":\"What are the two context-parallel inference strategies proposed in Design-CP?\",\"answer\":\"Design-CP introduces 1D row-sharding and 2D grid sharding with ring attention for RFdiffusion 3. Both distribute quadratic activations across a multi-GPU mesh while preserving pretrained weights.\"},{\"question\":\"How does Design-CP affect feasible assembly size and performance scaling?\",\"answer\":\"The work characterizes scaling for icosahedral assemblies and shows the maximum feasible asymmetric subunit size increases with an expected square-root trend in GPU count. It also reports better wallclock scaling with 2D sharding.\"}]",1784184323,68,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"design-cp-context-parallelism-for-design-of-protein-nanoparticles","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/design-cp-context-parallelism-for-design-of-protein-nanoparticles/82957/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does Design-CP address in all-atom multimeric protein design?","Question",{"text":75,"@type":76},"Quadratic token-and atom-pair representations in all-atom generators become too memory-intensive for single GPUs as the number of chains and residues increases. Design-CP distributes these quadratic activations across multiple GPUs during inference.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What are the two context-parallel inference strategies proposed in Design-CP?",{"text":80,"@type":76},"Design-CP introduces 1D row-sharding and 2D grid sharding with ring attention for RFdiffusion 3. Both distribute quadratic activations across a multi-GPU mesh while preserving pretrained weights.",{"name":82,"@type":73,"acceptedAnswer":83},"How does Design-CP affect feasible assembly size and performance scaling?",{"text":84,"@type":76},"The work characterizes scaling for icosahedral assemblies and shows the maximum feasible asymmetric subunit size increases with an expected square-root trend in GPU count. It also reports better wallclock scaling with 2D sharding.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]