TEXT INFLUENCED MOLECULAR INDEXING SYSTEM AND COMPUTER-IMPLEMENTED AND/OR COMPUTER-ASSISTED METHOD FOR SAME

摘要

An extension of the vector space model for computing chemical similarity usingtextual and chemical descriptors is described. The method uses a chemicaland/or textual description of a molecule/chemical and a decomposes amolecule/chemical descriptor matrix by a suitable technique such as a singularvalue decomposition to create a low dimensional representation of the originaldescriptor space. Similarities between a user probe and the textual and/orchemical descriptors are then computed and ranked.