A Subgroup Discovery Approach for Relating Chemical Structure and Phenotype Data in Chemical Genomics

Lan Umek, Petra Kaferle, Mojca Mattiazzi, Aleš Erjavec, Črtomir Gorup, Tomaž Curk, Uroš Petrovič, Blaž Zupan
Proceedings of the third International Workshop on Machine Learning in Systems Biology, PMLR 8:136-144, 2009.

Abstract

We report on development of an algorithm that can infer relations between the chemical structure and biochemical pathways from mutant-based growth fitness characterizations of small molecules. Identification of such relations is very important in drug discovery and development from the perspective of argument-based selection of candidate molecules in target-specific screenings, and early exclusion of substances with highly probable undesired side-effects. The algorithm uses a combination of unsupervised and supervised machine learning techniques, and besides experimental fitness data uses knowledge on gene subgroups (pathways), structural descriptions of chemicals, and MeSH term-based chemical and pharmacological annotations. We demonstrate the utility of the proposed approach in the analysis of a genome-wide S. cerevisiae chemogenomics assay by Hillenmeyer et al. (Science, 2008).

Cite this Paper

BibTeX
@InProceedings{pmlr-v8-umek10a, title = {A Subgroup Discovery Approach for Relating Chemical Structure and Phenotype Data in Chemical Genomics}, author = {Umek, Lan and Kaferle, Petra and Mattiazzi, Mojca and Erjavec, Aleš and Gorup, Črtomir and Curk, Tomaž and Petrovič, Uroš and Zupan, Blaž}, booktitle = {Proceedings of the third International Workshop on Machine Learning in Systems Biology}, pages = {136--144}, year = {2009}, editor = {Džeroski, Sašo and Guerts, Pierre and Rousu, Juho}, volume = {8}, series = {Proceedings of Machine Learning Research}, address = {Ljubljana, Slovenia}, month = {05--06 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v8/umek10a/umek10a.pdf}, url = {https://proceedings.mlr.press/v8/umek10a.html}, abstract = {We report on development of an algorithm that can infer relations between the chemical structure and biochemical pathways from mutant-based growth fitness characterizations of small molecules. Identification of such relations is very important in drug discovery and development from the perspective of argument-based selection of candidate molecules in target-specific screenings, and early exclusion of substances with highly probable undesired side-effects. The algorithm uses a combination of unsupervised and supervised machine learning techniques, and besides experimental fitness data uses knowledge on gene subgroups (pathways), structural descriptions of chemicals, and MeSH term-based chemical and pharmacological annotations. We demonstrate the utility of the proposed approach in the analysis of a genome-wide S. cerevisiae chemogenomics assay by Hillenmeyer et al. (Science, 2008).} }
Endnote
%0 Conference Paper %T A Subgroup Discovery Approach for Relating Chemical Structure and Phenotype Data in Chemical Genomics %A Lan Umek %A Petra Kaferle %A Mojca Mattiazzi %A Aleš Erjavec %A Črtomir Gorup %A Tomaž Curk %A Uroš Petrovič %A Blaž Zupan %B Proceedings of the third International Workshop on Machine Learning in Systems Biology %C Proceedings of Machine Learning Research %D 2009 %E Sašo Džeroski %E Pierre Guerts %E Juho Rousu %F pmlr-v8-umek10a %I PMLR %P 136--144 %U https://proceedings.mlr.press/v8/umek10a.html %V 8 %X We report on development of an algorithm that can infer relations between the chemical structure and biochemical pathways from mutant-based growth fitness characterizations of small molecules. Identification of such relations is very important in drug discovery and development from the perspective of argument-based selection of candidate molecules in target-specific screenings, and early exclusion of substances with highly probable undesired side-effects. The algorithm uses a combination of unsupervised and supervised machine learning techniques, and besides experimental fitness data uses knowledge on gene subgroups (pathways), structural descriptions of chemicals, and MeSH term-based chemical and pharmacological annotations. We demonstrate the utility of the proposed approach in the analysis of a genome-wide S. cerevisiae chemogenomics assay by Hillenmeyer et al. (Science, 2008).
RIS
TY - CPAPER TI - A Subgroup Discovery Approach for Relating Chemical Structure and Phenotype Data in Chemical Genomics AU - Lan Umek AU - Petra Kaferle AU - Mojca Mattiazzi AU - Aleš Erjavec AU - Črtomir Gorup AU - Tomaž Curk AU - Uroš Petrovič AU - Blaž Zupan BT - Proceedings of the third International Workshop on Machine Learning in Systems Biology DA - 2009/03/02 ED - Sašo Džeroski ED - Pierre Guerts ED - Juho Rousu ID - pmlr-v8-umek10a PB - PMLR DP - Proceedings of Machine Learning Research VL - 8 SP - 136 EP - 144 L1 - http://proceedings.mlr.press/v8/umek10a/umek10a.pdf UR - https://proceedings.mlr.press/v8/umek10a.html AB - We report on development of an algorithm that can infer relations between the chemical structure and biochemical pathways from mutant-based growth fitness characterizations of small molecules. Identification of such relations is very important in drug discovery and development from the perspective of argument-based selection of candidate molecules in target-specific screenings, and early exclusion of substances with highly probable undesired side-effects. The algorithm uses a combination of unsupervised and supervised machine learning techniques, and besides experimental fitness data uses knowledge on gene subgroups (pathways), structural descriptions of chemicals, and MeSH term-based chemical and pharmacological annotations. We demonstrate the utility of the proposed approach in the analysis of a genome-wide S. cerevisiae chemogenomics assay by Hillenmeyer et al. (Science, 2008). ER -
APA
Umek, L., Kaferle, P., Mattiazzi, M., Erjavec, A., Gorup, Č., Curk, T., Petrovič, U. & Zupan, B.. (2009). A Subgroup Discovery Approach for Relating Chemical Structure and Phenotype Data in Chemical Genomics. Proceedings of the third International Workshop on Machine Learning in Systems Biology, in Proceedings of Machine Learning Research 8:136-144 Available from https://proceedings.mlr.press/v8/umek10a.html.

Related Material