Compound Substitution Program Using Partial Structure Frequency Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods face difficulties in specifying compounds with similar properties by substituting partial structures, as the similarity in structure does not always translate to similar properties, leading to inaccurate identification of compounds with analogous characteristics.
Innovation Solution
A compound substitution program that analyzes input compounds, identifies partial structures, and substitutes them with related structures based on a knowledge graph and score calculations to determine compounds with similar properties, ensuring the generated compounds have a score equal to or above a threshold, thereby accurately identifying similar compounds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If compound substitution is performed based solely on structural similarity, then compounds with similar structures can be identified, but the accuracy of identifying compounds with similar properties deteriorates
Solution Approach 1:
The patent introduces a scoring mechanism that evaluates multiple parameters including appearance frequency of partial structure groups in text data, not just structural similarity. This multi-parameter evaluation system changes the basis of compound selection from purely structural to property-informed, resolving the contradiction between structural similarity and property similarity accuracy
Solution Approach 2:
The system uses appearance frequency information from text data as feedback to evaluate and score potential compound substitutions. This feedback loop ensures that substituted compounds are not only structurally similar but also have comparable properties as evidenced by their co-occurrence patterns in chemical literature, thereby improving property similarity reliability
2Manufacturing precision
If traditional compound substitution methods are used, then processing speed is maintained, but the precision of compound specification deteriorates
Solution Approach 1:
The patent pre-calculates and stores appearance frequency information of partial structure groups in text data before substitution is needed. This preliminary preparation allows the substitution process to quickly access pre-computed frequency data rather than calculating it in real-time, maintaining processing speed while enabling precision through frequency-based scoring
Data Source
AI summary
A non-transitory computer-readable recording medium stores a compound substitution program for causing a computer to execute processing including: specifying a first partial structure included in a first compound; referring to information that indicates a relationship between a plurality of partial structures and selecting a second partial structure related to the first partial structure; determining whether or not a score calculated based on an appearance status of a group that includes the first partial structure and the second partial structure in a plurality of pieces of text data is equal to or more than a threshold; and generating information that indicates a second compound obtained by substituting the first partial structure of the first compound with the second partial structure, in a case where it is determined that the score is equal to or more than the threshold.