Knowledge-Based Approach to de Novo Design Using Reaction Vectors Export

@article{citeulike:4411498, abstract = {PMID: 19382767 A knowledge-based approach to the de novo design of synthetically feasible molecules is described. The method is based on reaction vectors which represent the structural changes that take place at the reaction center along with the environment in which the reaction occurs. The reaction vectors are derived automatically from a database of reactions which is not restricted by size or reaction complexity. A structure generation algorithm has been developed whereby reaction vectors can be applied to previously unseen starting materials in order to suggest novel syntheses. The approach has been implemented in KNIME and is validated by reproducing known synthetic routes. We then present applications of the method in different drug design scenarios including lead optimization and library enumeration. The method offers great potential for capturing and using the growing body of data on reactions that is becoming available through electronic laboratory notebooks.}, author = {Patel, Hina and Bodkin, Michael J. and Chen, Beining and Gillet, Valerie J.}, citeulike-article-id = {4411498}, citeulike-linkout-0 = {http://dx.doi.org/10.1021/ci800413m}, citeulike-linkout-1 = {http://pubs.acs.org/doi/abs/10.1021/ci800413m}, day = {22}, doi = {10.1021/ci800413m}, journal = {Journal of Chemical Information and Modeling}, keywords = {cheminformatics, design, drug, knowledge, workflow}, month = {May}, number = {5}, pages = {1163--1184}, posted-at = {2009-10-26 13:22:32}, priority = {2}, title = {Knowledge-Based Approach to de Novo Design Using Reaction Vectors}, url = {http://dx.doi.org/10.1021/ci800413m}, volume = {49}, year = {2009} }

TY - JOUR ID - citeulike:4411498 L3 - citeulike-article-id:4411498 N2 - PMID: 19382767 A knowledge-based approach to the de novo design of synthetically feasible molecules is described. The method is based on reaction vectors which represent the structural changes that take place at the reaction center along with the environment in which the reaction occurs. The reaction vectors are derived automatically from a database of reactions which is not restricted by size or reaction complexity. A structure generation algorithm has been developed whereby reaction vectors can be applied to previously unseen starting materials in order to suggest novel syntheses. The approach has been implemented in KNIME and is validated by reproducing known synthetic routes. We then present applications of the method in different drug design scenarios including lead optimization and library enumeration. The method offers great potential for capturing and using the growing body of data on reactions that is becoming available through electronic laboratory notebooks. IS - 5 JF - Journal of Chemical Information and Modeling EP - 1184 TI - Knowledge-Based Approach to de Novo Design Using Reaction Vectors VL - 49 SP - 1163 KW - cheminformatics KW - design KW - drug KW - knowledge KW - workflow AU - Patel, Hina AU - Bodkin, Michael AU - Chen, Beining AU - Gillet, Valerie PY - 2009/05/22/ UR - http://dx.doi.org/10.1021/ci800413m ER -