{"id":37835,"date":"2025-06-27T09:03:57","date_gmt":"2025-06-27T14:03:57","guid":{"rendered":"https:\/\/www.bu.edu\/hic\/?p=37835"},"modified":"2026-08-06T17:42:54","modified_gmt":"2026-08-06T21:42:54","slug":"predicting-the-future-of-protein-science","status":"publish","type":"post","link":"https:\/\/www.bu.edu\/hic\/2025\/06\/27\/predicting-the-future-of-protein-science\/","title":{"rendered":"Predicting the Future of Protein Science\u00a0\u00a0"},"content":{"rendered":"

By <\/em>Maureen Stanton<\/em><\/a><\/p>\n

A BU-led interdisciplinary research team, bringing together expertise in biomedical engineering, applied mathematics, and theoretical physics, has won top honors at the internationally renowned <\/span>\u00a0<\/span>CASP16 (Critical Assessment of Structure Prediction) competition<\/span><\/a>. The group earned top ranking in predicting multiprotein complexes, a critical benchmark of accuracy and innovation in computational modeling. Multiprotein complexes involve two or more interacting proteins that perform specific cellular functions. Accurately modeling these complexes is essential to understand cellular processes, improve understanding of disease progression, and design targeted therapeutic strategies.<\/span><\/span><\/p>\n

\"\"
Dima Kozakov, Research Professor, Biomedical Engineering, BU<\/figcaption><\/figure>\n

The team was led by Dima Kozakov<\/a>, Research Professor of <\/span>Biomedical Engineering at BU, and <\/span>Sandor Vajda<\/a>, Professor of Biomedical Engineering, Director of the Biomolecular Engineering Research Center, and Hariri Institute Faculty Affiliate at BU, with support from Dr. Taras Patsahan<\/a>, Deputy Director of Research and Head of the Soft Matter Theory Department at the Institute for Condensed Matter Physics of the National Academy of Sciences of Ukraine.<\/span><\/p>\n

Held every two years, CASP is the field\u2019s premier global competition, tasking top international teams with predicting the three-dimensional structures of proteins and protein complexes whose experimental structures have not yet been released. The competition provides a rigorous, blinded test of emerging computational methods.<\/span><\/p>\n

\"\"
Sandor Vajda, Professor, Biomedical Engineering; Director, Biomolecular Engineering Research Center; Hariri Institute Faculty Affiliate, BU<\/figcaption><\/figure>\n

According to the official evaluator\u2019s report, <\/span>the BU team’s work (identifier G274)<\/span><\/a> \u00a0<\/b>made significant advances in the accurate prediction of protein multimers\u2014one of the most complex challenges in structural biology. Evaluators noted that their models outperformed all other entries by a wide margin, achieving the highest accuracy in the category.<\/span><\/p>\n

The high prediction accuracy achieved by the team reflects a novel protocol jointly developed by the Kozakov laboratory and the Vajda laboratory<\/a> over the past three years. Central to this approach\u00a0<\/span>is integrating the physics of protein interactions and the geometry of the conformational space into the machine learning models.\u00a0<\/span><\/p>\n

Traditional machine learning approaches often rely on biased sampling shaped by training data, leading to inefficiency and reduced accuracy when predicting novel interactions outside the training set. In contrast, the Kozakov\/Vajda method employs systematic sampling of high-interest regions, significantly improving efficiency and accuracy in exploring the vast conformational landscape.\u00a0<\/span><\/p>\n

\"CASP16
Figure. Introducing systematic sampling to machine learning model for structure prediction on challenging class of antibody-antigen interactions<\/figcaption><\/figure>\n

\u201cWhile the approach demonstrated strong performance in specific CASP tasks, its core innovation\u2014combining machine learning with physics-based sampling\u2014is broadly applicable,\u201d says Kozakov. \u201cIt is particularly advantageous in scenarios with limited training data, where physics-informed guidance can compensate for data sparsity and improve predictive robustness across a range of biomolecular modeling challenges.\u201d<\/span><\/p>\n

This success not only highlights the team\u2019s technical innovation in algorithm design and modeling but also has broad implications for biomedical research. \u201cAccurate prediction of protein complexes accelerates our understanding of diseases, supports drug development, and enhances synthetic biology efforts,\u201d says Vajda. \u201cBy improving the tools available to interpret the molecular machinery of life, our collaboration offers potential to shape the future of precision medicine and therapeutic design.\u201d\u00a0<\/span><\/p>\n

Their achievement also reflects the critical role academic research plays alongside major industry leaders like DeepMind, a Google-owned AI research lab whose work, AlphaFord, was recognized as CASP14\u2019s top-ranked protein structure prediction method – and later earned the developers the Nobel Prize in Chemistry 2024. <\/span><\/p>\n

Learn more about this work on the Kozakov lab\u00a0and Vajda lab<\/a> websites.<\/p>\n

About this event<\/b>: CASP (Critical Assessment of Structure Prediction) is a biennial competition in computational biology that challenges teams worldwide to predict protein 3D structures before their experimental data are public. <\/span><\/span>CASP16 was the most recent event and was conducted over the summer months of 2024. Nearly 100 research groups from around the world submitted more than 80,000 models on 100+ modeling entities, yielding 300 targets in five prediction categories. Results were presented at the CASP-16 conference in Punta Cana, Dominican Republic, December 1-4, 2024, and evaluated by independent assessors.\u00a0<\/span><\/p>\n

\u00a0In 2018, CASP joined with a similar contest called CAPRI (Critical Assessment of Predicted Interactions), which focuses on predicting how molecules interact. Both events, challenge researchers <\/span>to submit models for a set of macromolecules and macromolecular complexes (proteins, RNA, ligands) for which the experimental structures are not yet public. <\/span>Independent assessors compare the models to experimental structures.\u00a0<\/span><\/p>\n

\u00a0<\/span><\/p>\n

 <\/p>\n","protected":false},"excerpt":{"rendered":"

By Maureen Stanton A BU-led interdisciplinary research team, bringing together expertise in biomedical engineering, applied mathematics, and theoretical physics, has won top honors at the internationally renowned \u00a0CASP16 (Critical Assessment of Structure Prediction) competition. The group earned top ranking in predicting multiprotein complexes, a critical benchmark of accuracy and innovation in computational modeling. Multiprotein complexes […]<\/p>\n","protected":false},"author":10316,"featured_media":41082,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[11829,11831],"tags":[],"_links":{"self":[{"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/posts\/37835"}],"collection":[{"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/users\/10316"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/comments?post=37835"}],"version-history":[{"count":29,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/posts\/37835\/revisions"}],"predecessor-version":[{"id":43413,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/posts\/37835\/revisions\/43413"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/media\/41082"}],"wp:attachment":[{"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/media?parent=37835"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/categories?post=37835"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/tags?post=37835"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}