By integrating virtual screening, molecular dynamics, and quantum mechanics approaches, this workflow enables structure-guided optimization of molecular glues, improving binding interactions, stability, and prioritization confidence. <\/p>\n\n\n\n
The result is a systematic, scalable approach <\/strong>to accelerate molecular glue discovery beyond traditional trial-and-error approaches. <\/p>\n\n\n\n Integrated computational workflow for molecular glues<\/strong> Rational glue optimisation strategy<\/strong> Case study: DDB1\u2013CDK12\u2013Cyclin K complex<\/strong> Advanced modelling techniques<\/strong> AI-driven compound prioritisation<\/strong> Molecular glues are transforming targeted protein degradation but optimization remains complex and resource-intensive. This poster presents an integrated computational chemistry workflow combining generative AI and physics-based modelling to enable faster, more rational molecular glue design and prioritization. <\/p>\n","protected":false},"featured_media":17484,"template":"","category":[679,686,760,743,695],"class_list":["post-17434","poster","type-poster","status-publish","has-post-thumbnail","hentry","category-computer-aided-drug-design","category-modalities","category-molecular-dynamics","category-tpd","category-virtual-screening"],"acf":[],"yoast_head":"\nWhat the Poster Covers<\/h2>\n\n\n\n
Combining generative AI, docking, MD simulations and QM analysis<\/p>\n\n\n\n
Structure-guided design targeting key protein\u2013protein interaction interfaces<\/p>\n\n\n\n
Application of the workflow to optimise and prioritise glue candidates<\/p>\n\n\n\n
Use of MMPBSA, FMO and electrostatic complementarity analysis<\/p>\n\n\n\n
Identification of optimised candidates with improved stability and binding profiles<\/p>\n","protected":false},"excerpt":{"rendered":"