Onai (United States)

Designing de novo protein binders to multidomain assemblies remains challenging due to their structural complexity, conformational diversity, and broad functional epitopes. Here, we present an iterative epitope–expansion strategy that enables structure-guided design of compact miniproteins targeting human immunoglobulin E (IgE). Direct attempts to design binders against the full Fc epsilon RI-binding interface of IgE produced candidates with poor in silico confidence and limited experimental success. Instead, by first targeting a nearby, geometrically tractable seed epitope on the IgE CE3 domain, we obtained initial binders that served as anchors for progressive, structure-guided expansion toward the full receptor-binding interface. Iteration through an integrated AI–human–wet-lab design loop yielded a second-round miniprotein with approximately 30-fold improved affinity and substantial structural overlap with the Fc epsilon RI-binding site. Alanine-scanning mutagenesis confirmed that loss-of-function substitutions mapped precisely to the designed binding interfaces, validating the structural models. Polyspecificity profiling revealed that two of three binders exhibited low off-target binding comparable to antibody benchmarks, whereas one design displayed elevated polyspecificity that was strongly amplified upon Fc fusion. Notably, a previously published high-affinity miniprotein benchmark exhibited similar format-dependent liabilities, underscoring an underappreciated developability risk in the de novo miniprotein literature. Competition assays further demonstrated that two binders occupy regions of IgE that overlap with the Fc epsilon RI binding interface, as evidenced by loss of miniprotein binding when Fc epsilon RI is pre-bound to IgE Fc, consistent with the intended design geometry. Together, these results establish epitope expansion as a generalizable strategy for steering generative protein design toward challenging multidomain epitopes and highlight the necessity of tightly coupled AI–human–experimental workflows for achieving both functional specificity and developability in de novo binder discovery.

O presente trabalho consiste em uma proposta de utilização do Método Pivot-to de Gestão de Projetos Exponenciais (MPGP) como instrumento de sistematização para integrar os ODS na estratégia dos negócios.O MPGP é

With advances in neural network architectures for computer vision and language processing, multiple modalities of a video can be used for complex content analysis. Here, we propose an architecture that combines visual, audio, and text data for video analytics. The model leverages six different modules: action recognition, voiceover detection, speech transcription, scene captioning, optical character recognition (OCR) and object recognition. The proposed integration mechanism combines the output of all the modules into a text-based data structure. We demonstrate our model’s performance in two applications: a clustering module which groups a corpus of videos into labelled clusters based on their semantic similarity, and a ranking module which returns a ranked list of videos based on a keyword. Our analysis of the precision-recall graphs show that using a multi-modal approach offers an overall performance boost over any single modality.

This paper presents our attempt to develop a personalized exam preparation tool for Java/OOP classes based on a fine-grained concept model of Java knowledge. Our goal was to explore two most popular student model-based approaches: open student modeling and problem sequencing. The result of our work is a Java exam preparation tool, Knowledge Zoom. The tool combines an open concept-level student model component, Knowledge Explorer and a concept-based sequencing component, Knowledge Maximizer into a single interface. This paper presents both components of Knowledge Zoom, reports results of its evaluation, and discusses lessons learned.