METHOD AND SYSTEM FOR AUTOMATED INFERENCE CREATION OF PHYSICO-CHEMICAL INTERACTION KNOWLEDGE FROM DATABASES OF CO-OCCURRENCE DATA

摘要

Methods and system for automated inference of physico-chemical interactionknowledge from databases of term co-occurrence data. The co-occurrence dataincludes co-occurrences between chemical or biological molecules or co-occurrences between chemical or biological molecules and biological processes.Likelihood statistics are determined and applied to decide if co-occurrencedata reflecting physico-chemical interactions is non-trivial. A next node oran unknown target representing chemical or biological molecules in abiological pathway is selected based on co-occurrence values. The method andsystem may be used to further facilitate a user's understanding of biologicalfunctions, such as cell functions, to design experiments more intelligentlyand to analyze experimental results more thoroughly. Specifically, the presentinvention may help drug discovery scientists select better targets forpharmaceutical intervention in the hope of curing diseases. The method andsystem may also help facilitate the abstraction of knowledge from informationfor biological experimental data and provide new bioinformatic techniques.