Counting-based Output Prediction for Orphan Screening
K. Ullrich, C. Stahr, and T. Gärtner.. Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen & Adaptivitaet, Kassel, Germany, (2010)
Abstract
We investigate orphan screening, the search for small molecule ligands of proteins for which no binding ligands are known in advance. Predicting interactions between biologically active molecules is an important step towards effective drug discovery. We propose novel classification and ranking algorithms for orphan screening which are based on counting feature combinations in molecular fingerprints. For the training process we only use positive examples and additional knowledge about the considered proteins and ligands. This knowledge is available in form of protein similarity values a database of molecule compounds. Our algorithms have runtime linear in the number of unlabelled examples.
%0 Conference Paper
%1 kdml24
%A Ullrich, Katrin
%A Stahr, Christoph
%A Gärtner., Thomas
%B Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen & Adaptivitaet
%C Kassel, Germany
%D 2010
%E Atzmüller, Martin
%E Benz, Dominik
%E Hotho, Andreas
%E Stumme, Gerd
%K detection developer duplicate graph-based identification mining repositories room:0410 room:0446 session:Poster session:kdml2 sna software workshop:kdml
%T Counting-based Output Prediction for Orphan Screening
%U http://www.kde.cs.uni-kassel.de/conf/lwa10/papers/kdml24.pdf
%X We investigate orphan screening, the search for small molecule ligands of proteins for which no binding ligands are known in advance. Predicting interactions between biologically active molecules is an important step towards effective drug discovery. We propose novel classification and ranking algorithms for orphan screening which are based on counting feature combinations in molecular fingerprints. For the training process we only use positive examples and additional knowledge about the considered proteins and ligands. This knowledge is available in form of protein similarity values a database of molecule compounds. Our algorithms have runtime linear in the number of unlabelled examples.
@inproceedings{kdml24,
abstract = {We investigate orphan screening, the search for small molecule ligands of proteins for which no binding ligands are known in advance. Predicting interactions between biologically active molecules is an important step towards effective drug discovery. We propose novel classification and ranking algorithms for orphan screening which are based on counting feature combinations in molecular fingerprints. For the training process we only use positive examples and additional knowledge about the considered proteins and ligands. This knowledge is available in form of protein similarity values a database of molecule compounds. Our algorithms have runtime linear in the number of unlabelled examples.},
added-at = {2010-10-05T14:15:12.000+0200},
address = {Kassel, Germany},
author = {Ullrich, Katrin and Stahr, Christoph and Gärtner., Thomas},
biburl = {https://www.bibsonomy.org/bibtex/297c4df3b63e243af6ffe03364ffa4e7a/lwa2010},
booktitle = {Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen {\&} Adaptivitaet},
crossref = {lwa2010},
editor = {Atzmüller, Martin and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
interhash = {931c0b499db3b983784e697535d5753b},
intrahash = {97c4df3b63e243af6ffe03364ffa4e7a},
keywords = {detection developer duplicate graph-based identification mining repositories room:0410 room:0446 session:Poster session:kdml2 sna software workshop:kdml},
presentation_end = {2010-10-05 17:55:00},
presentation_start = {2010-10-05 17:45:00},
room = {0410},
session = {poster},
timestamp = {2010-10-05T14:15:13.000+0200},
title = {Counting-based Output Prediction for Orphan Screening},
track = {kdml},
url = {http://www.kde.cs.uni-kassel.de/conf/lwa10/papers/kdml24.pdf},
year = 2010
}