Gene Circuit Simulating Artificial Neural Network

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current gene circuit designs are unable to simulate complex operations at a speed comparable to computers and perform complex calculations, limiting their practical applications in various fields.

Innovation Solution

A gene circuit structure comprising an input layer, multiple hidden layers, and an output layer, where each node is regulated by promoters or gene products, simulating an artificial neural network to perform classification or regression analysis, with specific genes and activation functions like Sigmoid or ReLU, enabling the simulation of complex operations at a molecular level.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If current gene circuit designs (basic logic loops and detecting/sensing circuits) are used, then the circuit structure is simple and easy to construct, but the processing speed is slow and complex calculation capability is lacking

Engineering Contradiction:
Improveprocessing speed and complex calculation capabilityVSAvoidgene circuit structure complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent copies the artificial neural network architecture into the gene circuit system, using genes and regulatory elements to replicate the structure and function of ANN nodes, weights, and activation functions. This allows the gene circuit to perform complex calculations at molecular level while maintaining the computational efficiency of neural networks

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The gene circuit is segmented into multiple functional layers (input layer, hidden layers, output layer) with each layer containing specific genes regulated by promoters. This modular segmentation enables complex operations to be distributed across layers, improving processing speed while keeping individual circuit components manageable and constructible

Inventive Principle:
Principle #1Segmentation

2Adaptability or versatility

If gene circuits are designed to perform complex operations at molecular level, then application potential in biology and medicine is enhanced, but the construction complexity and difficulty increase

Engineering Contradiction:
Improveapplication potential in biological and medical fieldsVSAvoidconstruction ease
Core Design Contradiction:
Adaptability or versatilityVSEase of manufacture

Solution Approach 1:

The patent creates a universal gene circuit platform based on neural network architecture that can be applied to multiple biological and medical applications including disease diagnosis, drug response prediction, and biological system analysis. The standardized layer-based structure with regulated genes serves as a multi-functional template that can be adapted to different applications without redesigning the entire circuit

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent performs preliminary design and optimization of the gene circuit architecture using artificial neural network principles before biological implementation. The circuit structure, including gene selection, promoter regulation, and layer configuration, is pre-planned to ensure ease of construction while achieving complex computational functions in target applications

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20240046079A1Gene circuit simulating artificial neural network and construction method therefor
Publication Date: 2024.02.08 CHI U SEAK
  • US20240046079A1 patent drawing
  • US20240046079A1 patent drawing
  • US20240046079A1 patent drawing

AI summary

A genetic circuit simulating an artificial neural network, comprising at least one input layer, at least two hidden layers, and at least one output layer. The input layer comprises several input layer nodes, each of the hidden layers comprises several hidden layer nodes, the output layer comprises several output layer nodes, input vectors of each input layer node comprise a promoter and an input gene, each hidden layer node comprises a hidden layer gene, and each hidden layer gene is regulated and controlled by the promoter of the gene of that layer or a gene product of the gene of the previous layer; the output node outputs a genetic circuit result; the regulation and control to the hidden layer gene and the output layer node by the product of the gene of the previous layer conforms with an activation function; the regulation and control to the input layer node by the input promoter conforms with an activation function. A genetic circuit structure is used to simulate an artificial neural network, so that complex operation is simulated at the molecular level, and complex application in the fields of biology, medicine, chemistry, electronics and the like is achieved.