Methods for similarity searching of chemical reactions

1. A computer based method for identifying at least one pair of similar chemical reactions between a plurality of reactions each related to preparation of at least one product from at least one reagent, the method comprising:

generating for each reaction a structural representation involving dynamic and conventional bonds;

generating based on the structural representation, for each reaction, a set of fragment descriptors of a predetermined length comprising the dynamic bonds and a corresponding descriptor vector;

calculating similarity indices between descriptor vectors of the plurality of reactions;

comparing the similarity indices to identify at least one pair of similar reactions;

generating for a query reaction a structural representation involving dynamic and conventional bonds;

generating based on the structural representation generated for the query reaction a query descriptor vector;

calculating similarity indices between the query descriptor vector and other descriptor vectors corresponding to reactions listed in a database; and

comparing the similarity indices between the query descriptor vector and other descriptor vectors to identify at least one reaction similar to the query reaction in the database.

2. The method of claim 1 , further comprising retrieving reaction condition information related to the at least one pair of similar reactions.

3. The method of claim 1 , further comprising classifying reactions listed in a database according to the similarity indices calculated for each pair of reactions in the database.

4. The method of claim 1 , wherein the descriptor vector comprises a CGR vector.

5. The method of claim 4 , wherein the CGR vector for each reaction comprises attributes representative of a number of occurrences of corresponding fragment descriptors in the set of fragment descriptors.

6. The method of claim 4 , wherein the CGR vector for each reaction comprises attributes representative of the presence of corresponding fragment descriptors in the set of fragment descriptors.

7. The method of claim 1 , wherein calculating similarity indices comprises calculating a distance selected from one of Hamming distance, Euclidean distance, Soergel distance, Tanimato coefficients, Dine coefficients and Cosine coefficients.

8. The method of claim 1 , wherein comparing the similarity indices comprises comparing the similarity indices to a cut-off value.

9. The method of claim 8 , further comprising enabling a user to select the cut-off value.

10. The method of claim 1 , further comprising identifying in the query fragments which are transformed according to the information in the database and that are not transformed in the query.

11. A computer program product comprising computer instructions recorded on a computer medium for performing the method of claim 1 when running on a computer system.

12. A database search engine performing the method of claim 1 to subdivide a large database into a focussed database.

13. A method to pilot an automated synthesis platform, the method comprising:

enabling drawing of a query reaction;

selecting at last one appropriate reagent and reaction condition using the method of claim 1 ; and

performing an automatic control of a robot to launch the query reaction with the at least one appropriate reagent and reaction condition.

14. A method for performing chemical testing, the method comprising:

performing a plurality of chemical reactions in a plurality of reactors, wherein for each chemical reaction, the reaction condition is determined by implementing the method of claim 1 based on the result of a query aimed at sorting the reaction condition for a similar chemical reaction.