System and method for identifying similar molecules

• US 8,140,267 B2
• Filed: 06/30/2006
• Issued: 03/20/2012
• Est. Priority Date: 06/30/2006
• Status: Active Grant

• Current Assignee: Globalfoundries US Incorporated (GlobalFoundries, Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Boyer, Stephen Kane, Breyta, Gregory, Kanungo, Tapas, Kreulen, Jeffrey Thomas, Rhodes, James J.
• Primary Examiner(s): SIMS, JASON M
• Application Number:
  US11/428,147
• Publication Number:
  US 20080004810A1
• Time in Patent Office: 2,090 Days
• Field of Search: None
• US Class Current: 702/19
• CPC Class Codes: G16C 20/40 Searching chemical structures or physicochemical data
• CPC Class Codes: G16C 20/80 Data visualisation

Abstract

A vectorization process is employed in which chemical identifier strings are converted into respective vectors. These vectors may then be searched to identify molecules that are identical or similar to each other. The dimensions of the vector space can be defined by sequences of symbols that make up the chemical identifier strings. The International Chemical Identifier (InChI) string defined by the International Union of Pure and Applied Chemistry (IUPAC) is particularly well suited for these methods.

Claims

1. A method, comprising:

converting chemical names to respective chemical identifier strings, the chemical identifier strings including symbols and having a common format, the chemical identifier strings including strings of differing numbers of symbols;

constructing respective vectors from the chemical identifier strings, the vectors having a common vector space that is based on information extracted from a plurality of the chemical identifier strings, each of the vectors being constructed by comparing information in its corresponding chemical identifier string with the vector space;

storing at least some of the vectors in at least one memory device; and

using a computer to search at least some of the stored vectors to identify certain chemical structures that are at least similar to each other.

2. The method of claim 1, wherein the identified chemical structures include structures that are identical to each other.

3. The method of claim 1, wherein the chemical identifier strings are InChI strings.

4. The method of claim 1, further comprising:

extracting chemical names from the text of different documents; and

identifying particular documents from which said certain chemical structures were extracted.

5. The method of claim 4, wherein said particular documents include patents having named assignees and inventors, the method further comprising identifying at least one of the assignees and the inventors.

6. The method of claim 1, wherein a vector corresponding to a query molecule is used to identify said certain chemical structures.

7. The method of claim 1, comprising evaluating at least one of cosine distance calculations and Tanimoto coefficient calculations to identify said certain chemical structures.

8. The method of claim 1, wherein prior to searching, the vectors are normalized to unit vectors.

9. The method of claim 1, wherein at least one million chemical names are converted to the common format.

10. The method of claim 1, wherein the chemical names include IUPAC names, the method further comprising:

converting IUPAC names to respective structures; and

converting said respective structures to respective chemical identifier strings having the common format.

11. The method of claim 1, wherein said respective vectors are constructed by:

extracting sequences of symbols from each of the plurality of chemical identifier strings; and

defining a vector for each of the plurality of the strings, the common vector space including dimensions given by a plurality of the extracted sequences.

12. The method of claim 1, wherein at least some of the chemical names are extracted from at least one document having text that has been tokenized, so that tokens correspond to terms within the document, the method further comprising:

evaluating each token against at least 2 different Markov models to determine respective relative probabilities that the token corresponds to the Markov models, wherein at least one of the Markov models is directed to chemical terms;

for each token, comparing the relative probabilities with each other to determine which Markov model is more likely to be associated with the token; and

identifying tokens most likely to correspond to said at least one Markov model directed to chemical terms, so that chemical terms within the document are identified.

13. The method of claim 1, wherein the stored vectors include sparse vector representations.

24. The method of claim 11, wherein the plurality of sequences are extracted from InChI strings.

25. The method of claim 11, wherein the plurality of sequences include consecutive symbols containing carbon connectivity information.

26. The method of claim 25, wherein the plurality of sequences that include consecutive symbols include every possible sequence that has no greater than a predetermined number of symbols.

27. The method of claim 11, wherein the plurality of sequences include consecutive symbols containing hydrogen connectivity information.

28. The method of claim 11, wherein each of the plurality of sequences has no greater than a predetermined number of symbols.

29. The method of claim 11, wherein the vector space includes dimensions defined by information taken from chemical formulae of the chemicals.

30. The method of claim 29, wherein the dimensions of the vector space include dimensions defined by elements of the chemical formulae.

14. At least one tangible, non-transitory computer-useable medium, said at least one medium having a computer-readable program, wherein the program upon being processed on a computer causes the computer to implement the steps of:

converting chemical names to chemical identifier strings, the chemical identifier strings including respective symbols and having a common format, the chemical identifier strings including strings of differing numbers of symbols;

constructing respective vectors from the chemical identifier strings, the vectors having a common vector space that is based on information extracted from a plurality of the chemical identifier strings, each of the vectors being constructed by comparing information in its corresponding chemical identifier string with the vector space;

storing at least some of the vectors in at least one memory device; and

searching at least some of the stored vectors to identify certain chemical structures that are at least similar to each other.

15. A method, comprising:

using a computer to extract chemical entities from different documents, the chemical entities including entities having different formats with respect to at least one of name and chemical identifier string;

representing the chemical entities as respective chemical identifier strings having a common format, the chemical identifier strings including strings of differing numbers of symbols;

constructing respective vectors from the commonly formatted chemical identifier strings, the vectors having a common vector space that is based on information extracted from a plurality of the chemical identifier strings, each of the vectors being constructed by comparing information in its corresponding chemical identifier string with the vector space;

storing at least some of the vectors in at least one memory device; and

searching at least some of the stored vectors.

16. The method of claim 15, said step of constructing respective vectors comprising:

extracting sequences of symbols from each of the commonly formatted chemical identifier strings; and

defining a vector for each of the commonly formatted strings, the vectors having a common vector space that includes dimensions given by a plurality of the extracted sequences.

17. The method of claim 16, wherein the commonly formatted strings are InChI strings.

18. The method of claim 16, wherein the commonly formatted strings include information in the InChI format, as well as additional information related to functional properties of the chemical entities, the method further including searching the additional information.

19. The method of claim 15, the chemical entities including chemical names, chemical formula, chemical structures, and chemical identifier strings.

20. The method of claim 15, wherein at least some of the chemical entities are extracted from at least one document having text that has been tokenized, so that tokens correspond to terms within the document, the method further comprising:

evaluating each token against at least 2 different Markov models to determine respective relative probabilities that the token corresponds to the Markov models, wherein at least one of the Markov models is directed to chemical terms;

for each token, comparing the relative probabilities with each other to determine which Markov model is more likely to be associated with the token; and

identifying tokens most likely to correspond to said at least one Markov model directed to chemical terms, so that chemical terms within the document are identified.

21. At least one tangible, non-transitory computer-useable medium, said at least one medium having a computer-readable program, wherein the program upon being processed on a computer causes the computer to implement the steps of:

extracting chemical entities from different documents, the chemical entities including entities having different formats with respect to at least one of name and chemical identifier string;

representing the chemical entities as respective chemical identifier strings having a common format, the chemical identifier strings including strings of differing numbers of symbols;

constructing respective vectors from the commonly formatted chemical identifier strings, the vectors having a common vector space that is based on information extracted from a plurality of the chemical identifier strings, each of the vectors being constructed by comparing information in its corresponding chemical identifier string with the vector space;

storing at least some of the vectors in at least one memory device; and

searching at least some of the stored vectors.

22. A system, comprising:

said at least one medium of claim 21; and

a processor in communication with said at least one medium, the processor and said at least one medium together forming at least part of a computer system.

23. A computer-implemented method, comprising:

processing the program of said at least one medium of claim 21 to implement the steps of claim 21; and

delivering to a client output resulting from implementing the steps of claim 21.