H
Hiroto Saigo
Researcher at Kyushu University
Publications - 43
Citations - 1521
Hiroto Saigo is an academic researcher from Kyushu University. The author has contributed to research in topics: Graph (abstract data type) & Computer science. The author has an hindex of 15, co-authored 39 publications receiving 1382 citations. Previous affiliations of Hiroto Saigo include Max Planck Society & Kyushu Institute of Technology.
Papers
More filters
Journal ArticleDOI
Protein homology detection using string alignment kernels
TL;DR: New kernels for strings adapted to biological sequences are proposed, which are called local alignment kernels, which measure the similarity between two sequences by summing up scores obtained from local alignments with gaps of the sequences.
Journal ArticleDOI
A novel representation of protein sequences for prediction of subcellular location using support vector machines
TL;DR: A novel representation of protein sequences that involves local compositions of amino acids and twin amino acids, and local frequencies of distance between successive (basic, hydrophobic, and other) amino acids is proposed.
Journal ArticleDOI
gBoost: a mathematical programming approach to graph classification and regression
TL;DR: A mathematical programming boosting method (gBoost) that progressively collects informative patterns that can learn more efficiently than the simpler method based on frequent substructure mining, because the output labels are used as an extra information source for pruning the search space.
Journal ArticleDOI
Large‐scale prediction of disulphide bridges using kernel methods, two‐dimensional recursive neural networks, and weighted graph matching
TL;DR: New methods for predicting disulphide bridges in proteins are developed that can be applied both in situations where the bonded state of each cysteine is known and in ab initio mode where the state is unknown, overcoming one of the major limitations of previous approaches.
Proceedings ArticleDOI
Partial least squares regression for graph mining
TL;DR: This work proposes an iterative mining method based on partial least squares regression (PLS), which showed competitive prediction accuracies in many chemical datasets and its efficiency was significantly superior to graph boosting (gBoost) and the naive methodbased on frequent graph mining.