TY - GEN

T1 - Ligand Affinity Prediction with Multi-pattern Kernels.

AU - Ullrich, Katrin

AU - Mack, Jennifer

AU - Welke, Pascal

N1 - DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2016/9/21

Y1 - 2016/9/21

N2 - We consider the problem of affinity prediction for protein ligands. For this purpose, small molecule candidates can easily become regression algorithm inputs if they are represented as vectors indexed by a set of physico-chemical properties or structural features of their molecular graphs. There are plenty of so-called molecular fingerprints, each with a characteristic composition or generation of features. This raises the question which fingerprint to choose for a given learning task? In addition, none of the standard fingerprints, however, systematically gathers all circular and tree patterns independent of size and the adjacency information of atoms. Since structural and neighborhood information are crucial for the binding capacity of small molecules, we combine the features of existing graph kernels in a novel way such that finally both aspects are covered and the fingerprint choice is included in the learning process. More precisely, we apply the Weisfeiler-Lehman labeling algorithm to encode neighborhood information in the vertex labels. Based on the relabeled graphs we calculate four types of structural features: Cyclic and tree patterns, shortest paths and the Weisfeiler-Lehman labels. We combine these different views using different multi-view regression algorithms. Our experiments demonstrate that affinity prediction profits from the application of multiple views, outperforming state-of-the-art single fingerprint approaches.

AB - We consider the problem of affinity prediction for protein ligands. For this purpose, small molecule candidates can easily become regression algorithm inputs if they are represented as vectors indexed by a set of physico-chemical properties or structural features of their molecular graphs. There are plenty of so-called molecular fingerprints, each with a characteristic composition or generation of features. This raises the question which fingerprint to choose for a given learning task? In addition, none of the standard fingerprints, however, systematically gathers all circular and tree patterns independent of size and the adjacency information of atoms. Since structural and neighborhood information are crucial for the binding capacity of small molecules, we combine the features of existing graph kernels in a novel way such that finally both aspects are covered and the fingerprint choice is included in the learning process. More precisely, we apply the Weisfeiler-Lehman labeling algorithm to encode neighborhood information in the vertex labels. Based on the relabeled graphs we calculate four types of structural features: Cyclic and tree patterns, shortest paths and the Weisfeiler-Lehman labels. We combine these different views using different multi-view regression algorithms. Our experiments demonstrate that affinity prediction profits from the application of multiple views, outperforming state-of-the-art single fingerprint approaches.

U2 - 10.1007/978-3-319-46307-0_30

DO - 10.1007/978-3-319-46307-0_30

M3 - Conference contribution/Paper

SN - 9783319463063

T3 - Lecture Notes in Computer Science

SP - 474

EP - 489

BT - Ligand Affinity Prediction with Multi-pattern Kernels.

PB - Springer Nature

T2 - 19th International Conference, DS 2016

Y2 - 19 October 2016 through 21 October 2016

ER -