Mismatch String Kernels for SVM Protein Classification

By Christina S. Leslie, Eleazar Eskin, Jason Aaron Edward Weston, William Stafford Noble. 2002

354 citations recorded by the source corpus.

Subfields: Statistical Learning Theory, Computational Biology & Bioinformatics

How researchers see this paper

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

In Statistical Learning Theory

In Computational Biology & Bioinformatics

Citations in the corpus

Biological Sequence Modeling with Convolutional Kernel Networks (2017, neutral): “Biological sequences are represented by a large set of descriptors, constructed for instance by Fisher score [Jaakkola et al., 2000], k-mer spectrum up to some mismatches [Leslie et al., 2003], or local alignment score [Saigo et al., 2004].”
Convolutional Kitchen Sinks for Transcription Factor Binding Site Prediction (2017, methodology): “We note that decreasing γ in Equation 1 relaxes the penalty of n-gram mismatches between disappoints, thereby capturing the behavior of the mismatch and gapped n-gram kernels [3, 13].”
Rational Kernels: Theory and Algorithms (2004, methodology): “We also study the relationship between rational kernels and some commonly used string kernels or similarity measures such as the edit-distance, the convolution kernels of Haussler (Haussler, 1999), and some string kernels used in the context of computational biology (Leslie et al., 2003).”
Neural methods for non-standard data (2004, background): “Thereby, the approaches differ with respect to the weighting of matches, whether partial matches are allowed, and whether substrings need to be contiguous [59, 63].”
HDLTex: Hierarchical Deep Learning for Text Classification (2017, methodology): “Other kernel methods used for information retrieval include string kernels such as the spectrum kernel [8] and the mismatch kernel [9], which are widely used with DNA and RNA sequence data.”
Bhattacharyya and Expected Likelihood Kernels (2003, methodology): “9 Sequence Experiments In another preliminary experiment, we computed the expected likelihood kernel on HMMs for the SCOP protein sequence dataset [10, 17, 19].”
Kernels for small molecules and the prediction of mutagenicity, toxicity and anti-cancer activity (2005, background): “Most of the kernels for discrete objects in the literature (Collins and Duffy, 2002; Leslie et al., 2003; Lodhi et al., 2002; Vert, 2002; Vishwanathan and Smola, 2003) are special cases of, or related to, convolution kernels (Haussler, 1999).”
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning) (2005, positive): “Thus, following Leslie et al. [2003], show that”
Modeling the language of life – Deep Learning Protein Sequences (2019, methodology): “This concept resembles 24 that of using k-mers for database searches [33], clustering [74], motifs [75, 76], and prediction 25 methods [66, 70, 77-81].”
Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detection (2017, neutral): “tural data like sequences[17] and graphs[5].”
In Silico Predictive Modeling of CRISPR/Cas9 guide efficiency (2015, background): “Additional features such as those based on string mismatch kernels 33 , gapped kmers 34 and structural information of the guide/gene 18 could also prove useful.”
Spam Filtering Using Inexact String Matching in Explicit Feature Space with On-Line Linear Classifiers (2006, methodology): “The use of inexact string matching kernels with Support Vector Machines has proven effective for learning from genomic data (Leslie et al., 2002a,b; Leslie and Kuang, 2004).”