Kernels for small molecules and the prediction of mutagenicity, toxicity and anti-cancer activity

By S. Joshua Swamidass, Jonathan H. Chen, Jocelyne Bruand, Peter Phung, Liva Ralaivola, Pierre Baldi. 2005

206 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology, Computational Chemistry & Drug Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

In Molecular Biology

In Computational Chemistry & Drug Discovery

Citations in the corpus

ATOM3D: Tasks On Molecules in Three Dimensions (2020, background): “have long been pursued as an attractive source of information in molecular learning and chemoinformatics, but until recently have achieved underwhelming results relative to 1D and 2D representations (Swamidass et al., 2005; Azencott et al., 2007). However, due to increases in data availability and m”
Graph kernels based on tree patterns for molecules (2006, methodology): “On the same dataset, Swamidass et al. (2005) recently reported state-of-the-art results using a voted perceptron coupled with various kernels based on linear fragments extracted from the 2D structure of the molecules. These kernels are variants of the non-tottering walk kernels that we investigated,”
A survey on graph kernels (2019, background): “Molecular graphs are not only a common benchmark dataset for graph kernels, but several kernels were specifically proposed for this domain, e.g., (Horváth et al. 2004; Swamidass et al. 2005; Ceroni et al. 2007; Mahé and Vert 2009; Fröhlich et al. 2005).”
Fast Neighborhood Subgraph Pairwise Distance Kernel (2010, methodology): “The roughly balanced subset used by (Swamidass et al., 2005) has become a popular benchmark for QSAR algorithm research, often referred to as either NCI-60 or just NCI.”
Comparison of descriptor spaces for chemical compound retrieval and classification (2006, methodology): “Note that Path Fragments are exactly the same patterns as the linear paths in fingerprints [10] and the path-based generalized fingerprints in [38].”
Machine Learning Prediction of Cancer Cell Sensitivity to Drugs Based on Genomic and Chemical Properties (2012, background): “Indeed, extensive work has been done on Quantitative Structure-Activity Relationship (QSAR) approaches to predicting whole-cell activity of molecules based of their chemical properties [13-16], including applications to predicting anti-cancer activity in drugs [17,18].”
jCompoundMapper: An open source Java library and command-line tool for chemical fingerprints (2011, methodology): “The Tanimoto similarity can be used instead if only the occurrence of a pattern is taken into account”
Accurate and efficient target prediction using a potency-sensitive influence-relevance voter (2015, unknown): “Part of their power comes from being able to use Tanimoto similarity between fingerprints explicitly [39].”
Classification of small molecules by two- and three-dimensional decomposition kernels (2007, methodology): “…statistical learning algorithms for structured data have been successfully applied to QSAR problems, including recursive neural networks (Micheli et al., 2001) and kernel machines (Horva´th et al., 2004; Kashima et al., 2003; Mahe et al., 2005; Menchetti et al., 2005; Swamidass et al., 2005).”