Protein homology detection using string alignment kernels

By Hiroto Saigo, Jean-Philippe Vert, Nobuhisa Ueda, Tatsuya Akutsu. Bioinform., 2004

417 citations recorded by the source corpus.

Subfields: Ecology, General Agricultural and Biological Sciences

View Paper: https://www.semanticscholar.org/paper/3022fa48187e3099c59f2afa62068bd68befe9e9

How researchers see this paper

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

In Ecology

1. Padraig Cunningham
2. Marco Cuturi
3. Mathieu Blondel
4. Christina S. Leslie
5. Derek Greene

In General Agricultural and Biological Sciences

1. Padraig Cunningham
2. Marco Cuturi
3. Mathieu Blondel
4. Derek Greene

Citations in the corpus

• Early Detection of Fake News on Social Media Through Propagation Path Classification with Recurrent and Convolutional Networks (2018, neutral): “The problem of sequence/time series classification has been widely explored in the literature (Lesh, Zaki, and Ogihara 1999; Deshpande and Karypis 2002; Saigo et al. 2004; Dong and Pei 2007).”
• Practical solutions to the problem of diagonal dominance in kernel document clustering (2006, positive): “Specifically, Saigo et al. (2004) suggested adding a shift σ = |λn|, where λn is the negative eigenvalue of the kernel matrix with largest absolute value.”
• Bioinformatics Original Paper Integrating Multi-attribute Similarity Networks for Robust Representation of the Protein Space (neutral): “A number of kernels such as string kernels (Haussler, 1999; Lodhi et al., 2000; Saigo et al., 2004) have been especially developed for biological data (Schoelkopf et al., 2004).”
• Supervised classification and mathematical optimization (2013, neutral): “However, many potential kernels, such as those found in [172, 207, 215], violate such assumptions.”
• Modelling input texts: from Tree Kernels to Deep Learning (2015, neutral): “Structural kernels have been successfully applied to ease the design of machine learning systems in diverse domains, ranging from bioinformatics [78,82,130] and data-mining [10, 30,139,162,173,181,184,191] to Natural Language Processing (NLP) [23,34,37,73,79,142].”
• Biological Sequence Modeling with Convolutional Kernel Networks (2017, neutral): “Typical applications include classifying protein domains into superfamilies [24, 32], predicting whether a DNA or RNA sequence binds to a protein [1], its splicing outcome [15], or its chromatin accessibility [16], predicting the resistance of a bacterial strain to a drug [11], or denoising a ChIP-s”
• Predicting linear B-cell epitopes using string kernels (2008, positive): “String kernels String kernels (Haussler, 1999; Lodhi et al., 2002; Leslie et al., 2002, 2004; Saigo et al., 2004) are a class of kernel methods that have been successfully used in many sequence classification tasks (Leslie et al.”
• A comprehensive review and comparison of different computational methods for protein remote homology detection (2018, neutral): “the LA kernel [59] is proposed, which measures the similarity”
• Semi-supervised Protein Classification Using Cluster Kernels (2003, positive): “Finally, classifiers such as support vector machines (SVMs) use both positive and negative examples and provide state-of-the-art performance when used with appropriate distance metrics (i.e., appropriate kernels) (Jaakkola et al., 2000; Leslie et al., 2002; Liao and Noble, 2002; Saigo et al., 2004 ”