20230086091. APTAMERIC PEPTIDE LIBRARY FORMATION USING GENERATIVE ADVERSARIAL NETWORK (GAN) MACHINE LEARNING MODELS simplified abstract (University of Florida Research Foundation, Incorporated)

APTAMERIC PEPTIDE LIBRARY FORMATION USING GENERATIVE ADVERSARIAL NETWORK (GAN) MACHINE LEARNING MODELS

Organization Name

University of Florida Research Foundation, Incorporated

Inventor(s)

Zachary F. Greenberg of Gainesville FL (US)

Mei He of Gainesville FL (US)

Kiley S. Graim of Gainesville FL (US)

APTAMERIC PEPTIDE LIBRARY FORMATION USING GENERATIVE ADVERSARIAL NETWORK (GAN) MACHINE LEARNING MODELS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20230086091 titled 'APTAMERIC PEPTIDE LIBRARY FORMATION USING GENERATIVE ADVERSARIAL NETWORK (GAN) MACHINE LEARNING MODELS

Simplified Explanation

The patent application is about designing aptameric peptides that can bind to specific receptors and creating libraries of these peptides. These libraries can be used in drug delivery and therapeutic applications, where the designed peptides are implanted on exosome surfaces to deliver cargo to specific tissues. The application describes the use of a generative adversarial network (GAN) machine learning model to generate peptides that are similar to existing peptides but have specific binding properties and physiochemical properties.

• The patent application describes a method for designing aptameric peptides that can bind to specific receptors.
• The method involves creating libraries of these designed peptides for use in drug delivery and therapeutic applications.
• The designed peptides can be implanted on exosome surfaces to deliver cargo to specific tissues.
• The application proposes the use of a generative adversarial network (GAN) machine learning model to generate peptides with specific binding and physiochemical properties.
• The GAN model takes representations of existing peptides as input and outputs representations of designed peptides.
• The peptide design process is based on peptide vectorization and encoding schemas using the amino acids within a peptide.

Potential Applications

This technology has potential applications in the following areas:

• Drug delivery: The designed aptameric peptides can be used to deliver drugs to specific tissues, increasing the effectiveness and reducing side effects.
• Therapeutics: The aptameric peptide libraries can be used to develop new therapeutic agents that target specific receptors.
• Biomedical research: The ability to design peptides with specific binding properties can aid in studying receptor-ligand interactions and developing new treatments.

Problems Solved

This technology solves the following problems:

• Targeted drug delivery: By designing aptameric peptides that specifically bind to receptors, drugs can be delivered directly to the desired tissues, increasing efficacy and reducing off-target effects.
• Limited peptide libraries: Traditional methods of peptide library generation may not provide peptides with the desired binding properties. The use of a GAN model allows for the creation of designed peptides with specific binding and physiochemical properties.

Benefits

The benefits of this technology include:

• Enhanced drug delivery: The designed aptameric peptides can improve the targeting and delivery of drugs, leading to more effective treatments.
• Customizable peptide libraries: The GAN model allows for the generation of designed peptides with specific binding properties, providing researchers with a customizable library for their specific needs.
• Accelerated peptide design process: The use of machine learning models can speed up the process of designing peptides with desired properties, reducing the time and resources required for development.

Original Abstract Submitted

various embodiments generally relate to intelligently designing aptameric peptides for binding with a specific receptor and forming aptameric peptide libraries with the designed peptides. the aptameric peptides libraries can be tissue-specific and be used in drug delivery and therapeutic applications, in which designed peptides can be implanted on exosome surfaces for exosomal cargo delivery to a specific tissue. various embodiments of the present disclosure involve the use of a generative adversarial network (gan) machine learning model configured (e.g., trained) and used to output designed peptides that are similar to pre-existing peptides of a peptide dataset but that specifically bind to a selected receptor and have various selected physiochemical properties. in various embodiments, gan machine learning models may receive representations of the pre-existing peptides and may output representations of designed peptides according to peptide vectorization and encoding schemas based at least in part on the amino acids within a peptide.