PEMT

PEMT (Patent Enrichment for Molecular Targets) extracts and links patent literature, chemical structures, and gene information to characterize patent landscapes for drug discovery.

Key Features:

• Integration with public databases: Uses ChEMBL and SureChEMBL to associate chemical structures and gene names with patent metadata while adhering to FAIR principles.
• Semantic analysis: Applies semantic technologies and metadata annotation parsing to interpret complex patent documents.
• Patent landscape construction: Subselects International Patent Classification (IPC) codes to establish detailed patent landscapes around genes and chemical entities.

Scientific Applications:

• Drug discovery target assessment: Provides patent-derived evidence linking genes and chemical structures to support therapeutic target and compound evaluation.
• Patent landscaping and competitive intelligence: Identifies areas of innovation and competition by mapping patents to genes and chemical entities via IPC codes.
• Rare disease research prioritization: Generates gene–patent lists informed by epidemiological data to guide research priorities in rare diseases.

Methodology:

Extracts patent information via metadata annotations, links chemical structures and gene names using ChEMBL and SureChEMBL identifiers, employs semantic analysis to parse documents, and uses IPC code subselection to define patent landscapes.