Venn-Abers predictors for improved compound iterative screening in drug discovery

Ruben Buendia, Ola Engkvist, Lars Carlsson, Thierry Kogej, Ernst Ahlberg
Proceedings of the Seventh Workshop on Conformal and Probabilistic Prediction and Applications, PMLR 91:201-219, 2018.

Abstract

Iterative screening, where selected hits from a given round of screening are used to enrich a compound activity prediction model for the next iteration, enables more efficient screening campaigns. The portion of the compound library that should be screened in each iteration is often arbitrarily decided. This is because no accurate information between screening size and the number of hits to be retrieved exists. In this article, a novel method based on Venn-Abers predictors was used to determine the optimal number of compounds to be screened in order to get a desired number of hits. We found that Venn-Abers predictors provide accurate information to support a reliable and flexible decision about the portion size of the compound library that should be screened in each iteration. In addition, the method exhibited great ability in producing an enriched subset in terms of hits and their diversity.

Cite this Paper

BibTeX
@InProceedings{pmlr-v91-buendia18a, title = {Venn-{A}bers predictors for improved compound iterative screening in drug discovery}, author = {Buendia, Ruben and Engkvist, Ola and Carlsson, Lars and Kogej, Thierry and Ahlberg, Ernst}, booktitle = {Proceedings of the Seventh Workshop on Conformal and Probabilistic Prediction and Applications}, pages = {201--219}, year = {2018}, editor = {Gammerman, Alex and Vovk, Vladimir and Luo, Zhiyuan and Smirnov, Evgueni and Peeters, Ralf}, volume = {91}, series = {Proceedings of Machine Learning Research}, month = {11--13 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v91/buendia18a/buendia18a.pdf}, url = {https://proceedings.mlr.press/v91/buendia18a.html}, abstract = {Iterative screening, where selected hits from a given round of screening are used to enrich a compound activity prediction model for the next iteration, enables more efficient screening campaigns. The portion of the compound library that should be screened in each iteration is often arbitrarily decided. This is because no accurate information between screening size and the number of hits to be retrieved exists. In this article, a novel method based on Venn-Abers predictors was used to determine the optimal number of compounds to be screened in order to get a desired number of hits. We found that Venn-Abers predictors provide accurate information to support a reliable and flexible decision about the portion size of the compound library that should be screened in each iteration. In addition, the method exhibited great ability in producing an enriched subset in terms of hits and their diversity.} }
Endnote
%0 Conference Paper %T Venn-Abers predictors for improved compound iterative screening in drug discovery %A Ruben Buendia %A Ola Engkvist %A Lars Carlsson %A Thierry Kogej %A Ernst Ahlberg %B Proceedings of the Seventh Workshop on Conformal and Probabilistic Prediction and Applications %C Proceedings of Machine Learning Research %D 2018 %E Alex Gammerman %E Vladimir Vovk %E Zhiyuan Luo %E Evgueni Smirnov %E Ralf Peeters %F pmlr-v91-buendia18a %I PMLR %P 201--219 %U https://proceedings.mlr.press/v91/buendia18a.html %V 91 %X Iterative screening, where selected hits from a given round of screening are used to enrich a compound activity prediction model for the next iteration, enables more efficient screening campaigns. The portion of the compound library that should be screened in each iteration is often arbitrarily decided. This is because no accurate information between screening size and the number of hits to be retrieved exists. In this article, a novel method based on Venn-Abers predictors was used to determine the optimal number of compounds to be screened in order to get a desired number of hits. We found that Venn-Abers predictors provide accurate information to support a reliable and flexible decision about the portion size of the compound library that should be screened in each iteration. In addition, the method exhibited great ability in producing an enriched subset in terms of hits and their diversity.
APA
Buendia, R., Engkvist, O., Carlsson, L., Kogej, T. & Ahlberg, E.. (2018). Venn-Abers predictors for improved compound iterative screening in drug discovery. Proceedings of the Seventh Workshop on Conformal and Probabilistic Prediction and Applications, in Proceedings of Machine Learning Research 91:201-219 Available from https://proceedings.mlr.press/v91/buendia18a.html.

Related Material