Combining Pairwise Sequence Similarity and Support Vector Machines for Detecting Remote Protein Evolutionary and Structural Relationships

By Li Liao, William Stafford Noble. 2003

376 citations recorded by the source corpus.

How researchers see this paper

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

In Molecular Biology

Citations in the corpus

MRFalign: Protein Homology Detection through Alignment of Markov Random Fields (2014, methodology): “Improvement in these alignment-free methods results from the application of discriminative learning approaches such as SVM– Fisher [26], SVM-pairwise [27], SVM with the spectrum kernel [28] and SVM with the mismatch kernel [29].”
Biological Sequence Modeling with Convolutional Kernel Networks (2017, neutral): “GPkernel [H˚andstad et al., 2007] 0.902 0.591 SVM-pairwise [Liao and Noble, 2003] 0.849 0.555 Mismatch [Leslie et al., 2004] 0.878 0.543 LA-kernel [Saigo et al., 2004] 0.919 0.686 LSTM [Hochreiter et al., 2007 [Leslie et al., 2004, Saigo et al., 2004].”
Linear-Time Computation of Similarity Measures for Sequential Data (2008, background): “…measures based on the Hamming distance are restricted to sequences of equal length and measures derived from the Levenshtein distance (e.g., Liao and Noble, 2003; Vert et al., 2004), come at the price of computational complexity: No linear-time algorithm for determining the shortest trace…”
Support Vector Machines and Kernels for Computational Biology (2008, background): “The simplest way is to represent a sequence in terms of its BLAST/Smith-Waterman scores against a database of sequences [39].”
A comprehensive review and comparison of different computational methods for protein remote homology detection (2018, methodology): “on the alignment methods, such as SVM-Pairwise [58], SVM-LA”
Protein remote homology detection based on bidirectional long short-term memory (2017, methodology): “Several kernels have been proposed to calculate the similarity between protein samples, such as mismatch kernel [27], motif kernel [28], LA kernel [29], SW-PSSM [30], SVM-Pairwise [31], etc.”
Soft Ngram Representation and Modeling for Protein Remote Homology Detection (2017, methodology): “ca/gist/ [4].”
ROC analysis: applications to the classification of biological sequences and 3D structures (2008, methodology): “Liao and Noble [24] calculated the significance of database-wide comparisons using a two-tailed signed rank test between the individual AUC values calculated for the individual classification tasks [37].”
Probabilistic multi-class multi-kernel learning: on protein fold recognition and remote homology detection (2008, methodology): “As a generalization of the proposed methodology to other related problem-domains, we consider the simulated remote homology problem (RHD) as described in the works of Liao and Noble (2003); Lingner and Meinicke (2006); Leslie et al. (2004); Saigo et al. (2004).”
Similarity-based Classification: Concepts and Algorithms (2009, methodology): “Liao et al. [31] also propose to apply an SVM on similarity feature vectors; they use a Gaussian radial basis function (RBF) kernel.”
Bioinformatics Original Paper Integrating Multi-attribute Similarity Networks for Robust Representation of the Protein Space (positive): “The kernel for a similarity measure is created using a technique similar to the SVM-Pairwise (Liao and Noble, 2003) method, in which a protein is represented as a vector of similarity scores, and the kernel between two proteins is defined using the Gaussian kernel with the optimum parameters found…”
Improving protein fold recognition by random forest (2014, methodology): “In the future, we plan to further evaluate the performance of RF-Fold on a standard protein homology detection dataset [50], independent CASP datasets [51], and to build a protein tertiary structure prediction web server based on RF-Fold for the community to use.”