View source for 20240029822. A PEPTIDE BASED VACCINE GENERATION SYSTEM WITH DUAL PROJECTION GENERATIVE ADVERSARIAL NETWORKS simplified abstract (NEC Laboratories America, Inc.)

=A PEPTIDE BASED VACCINE GENERATION SYSTEM WITH DUAL PROJECTION GENERATIVE ADVERSARIAL NETWORKS=


==Organization Name==

[[:Category:NEC Laboratories America, Inc.|NEC Laboratories America, Inc.]]


[[Category:NEC Laboratories America, Inc.]]

==Inventor(s)==

[[:Category:Renqiang Min of Princeton NJ (US)|Renqiang Min of Princeton NJ (US)]][[Category:Renqiang Min of Princeton NJ (US)]]

[[:Category:Hans Peter Graf of South Amboy NJ (US)|Hans Peter Graf of South Amboy NJ (US)]][[Category:Hans Peter Graf of South Amboy NJ (US)]]

[[:Category:Ligong Han of Edison NJ (US)|Ligong Han of Edison NJ (US)]][[Category:Ligong Han of Edison NJ (US)]]

==A PEPTIDE BASED VACCINE GENERATION SYSTEM WITH DUAL PROJECTION GENERATIVE ADVERSARIAL NETWORKS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240029822 titled 'A PEPTIDE BASED VACCINE GENERATION SYSTEM WITH DUAL PROJECTION GENERATIVE ADVERSARIAL NETWORKS

==Simplified Explanation==

The abstract describes a computer-implemented method for generating new binding peptides to major histocompatibility complex (MHC) proteins. The method involves training a generative adversarial network (GAN) using a set of binding peptide sequences and a set of non-binding peptide sequences. The GAN consists of a generator and a discriminator, which are iteratively updated to distinguish between real and fake peptide sequences. The training also includes optimizing the GAN training objective while learning two projection vectors for a binding class with two cross-entropy losses.

* The method uses a generative adversarial network (GAN) to generate new binding peptides to MHC proteins.
* The GAN consists of a generator and a discriminator, which are trained iteratively to distinguish between real and fake peptide sequences.
* The training includes optimizing the GAN training objective and learning two projection vectors for a binding class.
* The method discriminates between binding and non-binding peptide sequences in the training data.
* The generated binding peptide sequences are compared to non-binding peptide sequences in the training data.

Potential applications of this technology:
* Drug discovery: The generated binding peptides can be used to identify potential drug candidates that target specific MHC proteins.
* Vaccine development: The generated binding peptides can be used to design vaccines that stimulate an immune response against specific pathogens.
* Personalized medicine: The generated binding peptides can be used to develop personalized therapies based on an individual's MHC profile.

Problems solved by this technology:
* Limited peptide diversity: Traditional methods for generating binding peptides have limited diversity, while this method can generate a wide range of new binding peptides.
* Time-consuming and costly experimentation: This method reduces the need for extensive experimentation by generating binding peptides computationally.
* Target specificity: The method focuses on generating binding peptides specifically for MHC proteins, improving target specificity and reducing off-target effects.

Benefits of this technology:
* Increased efficiency: The computational generation of binding peptides reduces the time and cost associated with experimental screening.
* Enhanced peptide diversity: The method allows for the generation of a diverse range of binding peptides, increasing the chances of finding effective candidates.
* Improved target specificity: By specifically targeting MHC proteins, the method improves the specificity of binding peptides, reducing potential side effects.


==Original Abstract Submitted==

a computer-implemented method is provided for generating new binding peptides to major histocompatibility complex (mhc) proteins. the method includes training, by a processor device, a generative adversarial network gan having a generator and a discriminator only on a set of binding peptide sequences given training data comprising the set of binding peptide sequences and a set of non-binding peptide sequences. a gan training objective includes the discriminator being iteratively updated to distinguish generated peptide sequences from sampled binding peptide sequences as fake or real and the generator being iteratively updated to fool the discriminator. the training includes optimizing the gan training objective while learning two projection vectors for a binding class with two cross-entropy losses. a first loss discriminating binding peptide sequences in the training data from non-binding peptide sequences in the training data. a second loss discriminating generated binding peptide sequences from non-binding peptide sequences in the training data.



[[Category:G16B15/30]]
[[Category:G06N3/08]]
[[Category:G16B40/20]]
[[Category:G06N3/045]]