In Silico Compound Screening Using Fuzzy Logic and Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High Throughput Screening (HTS) in drug discovery is inefficient and costly due to the need to screen thousands of compounds, resulting in overwhelming data that makes it difficult to identify biochemical significance.
Innovation Solution
A computer system utilizing Fuzzy logic membership functions and artificial neural networks to classify compounds as active or inactive, reducing the number of compounds that need to be screened by identifying active compounds in silico based on chemical features and membership values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If High Throughput Screening (HTS) is used to screen thousands of compounds, then the rate of data generation increases, but the cost and time of drug discovery increase significantly
Solution Approach 1:
The patent applies preliminary action by performing in silico filtering and classification of compounds before actual HTS experimentation. The system pre-processes compound libraries using computational models to identify promising candidates, thereby reducing the number of compounds that need to be physically screened and accelerating the overall drug discovery timeline
Solution Approach 2:
The patent uses computational copies and simulations of compound-screening interactions instead of physical screening for all compounds. By creating virtual models of compound-target interactions and using in silico screening, the system reduces the need for expensive and time-consuming wet-lab experiments while maintaining high data generation rates
2Reliability
If High Throughput Screening (HTS) is used to screen thousands of compounds, then active compounds can be identified, but the overall cost of drug discovery increases
Solution Approach 1:
The patent extracts and removes compounds that are unlikely to be active before performing expensive HTS experiments. By using computational filtering to eliminate non-promising compounds from the library, the system reduces the number of compounds requiring physical screening, thereby lowering material costs, reagent costs, and overall experimental expenses while maintaining reliable identification of active compounds
Solution Approach 2:
The patent changes the parameters of the screening process by introducing computational classification metrics and membership values that prioritize compounds for screening. By transforming the compound library into ranked categories based on computational predictions, the system optimizes resource allocation to focus experimental efforts on the most promising candidates, reducing overall costs while maintaining high reliability
3Quantity of substance
If HTS data from thousands of compounds is collected, then comprehensive screening results are obtained, but it becomes difficult to glean biochemical significance
Solution Approach 1:
The patent applies local quality by providing different levels of analysis and interpretation for different subsets of compounds. Instead of treating all compounds uniformly, the system applies specialized computational models and classification methods to specific compound categories, enabling more meaningful biochemical interpretation of HTS data while managing information complexity
Solution Approach 2:
The patent adds another dimension to the analysis by introducing computational membership values and classification metrics that overlay the raw HTS data. This additional layer of computational interpretation transforms the large volume of screening data into structured, interpretable categories, making biochemical significance more accessible without losing the comprehensive nature of the screening
Data Source
AI summary
Embodiments are directed to identifying active compounds for a targeted medium from a library of compounds. In one scenario, a computer system receives high throughput screening (HTS) data for a subset of compounds that have been HTS-screened. The computer system determines labels for a subset of compounds based on labels identified in the HTS-screened compounds as being part of an active class or part of an inactive class, access chemical features corresponding to the HTS-screened compounds, apply Fuzzy logic membership functions to calculate membership values for active and inactive compounds to determine the degree to which each compound belongs to the active class or to the inactive class, train an artificial neural network (ANN) to identify active compounds in silico based on the Fuzzy logic membership functions, and process another subset of compounds in silico to identify active and inactive compounds using the trained artificial neural network.