Chemical Literature Search via SMILES Notation and Mutation Rules

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Chemical literature references chemical compounds in various forms, making it difficult to search for specific compounds or classes of compounds effectively due to the lack of a standard naming scheme, leading to inefficiencies in querying and discovery processes.

Innovation Solution

A computer-implemented method that converts chemical literature into a standard notation, using regular expressions to identify compounds matching desired criteria, and applies mutation rules to discover new compounds not described in the literature, facilitating efficient searching and discovery of chemicals.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If chemical literature is searched using various naming schemes and formulas, then comprehensive chemical references can be found, but search effectiveness and efficiency deteriorate due to lack of standardization

Engineering Contradiction:
Improveability to find compounds across diverse referencesVSAvoidsearch efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent transforms chemical structure data into a standardized parameter format (SMILES notation), converting diverse chemical representations into a uniform searchable format. This parameter transformation enables efficient querying while maintaining the ability to represent all chemical compounds, directly resolving the contradiction between comprehensive search coverage and search efficiency

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent introduces a standardized chemical notation system as an intermediary between diverse chemical references and search queries. This intermediary layer (SMILES strings) mediates the translation between various chemical naming schemes and a unified search format, enabling both comprehensive coverage and efficient searching simultaneously

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If multiple naming schemes and formulas are used to reference compounds, then chemical diversity is captured, but query complexity increases making searching difficult

Engineering Contradiction:
Improvecoverage of chemical referencesVSAvoidquery complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent applies parameter transformation by converting all chemical compounds into a standardized notation format (SMILES), reducing the complexity of querying while maintaining comprehensive chemical reference coverage. This single standardized parameter replaces multiple diverse naming schemes, simplifying the search interface

Inventive Principle:
Principle #35Parameter changes

3Loss of information

If chemical structures are represented in various formats, then complete chemical information is preserved, but information processing efficiency decreases

Engineering Contradiction:
Improvechemical structure information completenessVSAvoidinformation processing efficiency
Core Design Contradiction:
Loss of informationVSProductivity

Solution Approach 1:

The patent transforms diverse chemical structure representations into a unified parameter format (SMILES notation) that preserves complete chemical structure information while dramatically improving processing efficiency. The standardized format maintains all structural details in a consistent, computationally efficient representation

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent segments chemical structure information into discrete, standardized units (SMILES strings) that can be efficiently processed and searched. This segmentation of chemical data into uniform tokens enables high-speed information processing while retaining complete structural information

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS8805874B2Molecular level similarity search and computer aided drug discovery process
Publication Date: 2014.08.12 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US8805874B2 patent drawing
  • US8805874B2 patent drawing
  • US8805874B2 patent drawing

AI summary

Systems, methods and articles of manufacture are disclosed for searching chemical compounds referenced in chemical literature. References to chemical compounds in the documents may be transformed to corresponding references using a standard notation for representing chemical compounds. Criteria specifying desired molecular characteristics may be received. A regular expression may be generated based on the received criteria. The chemical documents may be searched using the regular expression. Based on the search, a chemical document may be determined that references a chemical compound satisfying the received criteria. Further, the regular expression may be generated based on the received criteria and a received mutation rule. Based on the generated regular expression and the chemical documents, one or more chemical compounds may be discovered that satisfy both the received criteria and the received mutation rule, but that is are not referenced in the chemical documents.