Protein secondary structure prediction based on an improved support vector machines approach.

By Hyunsoo Kim, Haesun Park. 2003

231 citations recorded by the source corpus.

Subfields: Materials Chemistry, Molecular Biology

How researchers see this paper

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

In Materials Chemistry

In Molecular Biology

Citations in the corpus

A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction (2014, methodology): “Although several methods (such as [8], [18], [23]) have used Sov scores in their evaluations, it is still not common practice for secondary structure predictors to report their results in terms of this alternative scoring criterion.”
Improving protein secondary structure prediction based on short subsequences with local structure similarity (2010, methodology): “In this category, Artificial Neural Networks (ANNs), Support Vector Machines (SVMs) and Hidden Markov Models (HMMs) are the most widely used machine learning algorithms [15-21].”
Hidden-Unit Conditional Random Fields (2011, methodology): “0% SVM (Kim and Park, 2003) 23.”
Knowledge-based machine learning methods for macromolecular 3D structure prediction (2016, methodology): “Support vector machines (SVM) have also been applied for SS prediction (Hua and Sun, 2001; Kim and Park, 2003; Ward et al, 2003; Guo et al, 2004; Duan et al, 2008).”
Improved prediction of protein-protein binding sites using a support vector machines approach. (2005, background): “…accessibility (Yuan et al., 2002), β-edge strands (Siepen et al., 2003), single nucleotide polymorphisms (Krishnan and Westhead, 2003), protein secondary structure (Hua and Sun, 2001; Kim and Park, 2003), protein quaternary structure (Zhang et al., 2003) and T-cell epitopes (Zhao et al., 2003).”
Learning sparse models for a dynamic Bayesian network classifier of protein secondary structure (2011, methodology): “In this table, a variety of secondary structure prediction methods – SVMpsi [27], JNET [28], YASSSP [29], DBNfinal [5], DBNpred (our method), DBNN [5], PSIPRED [30], SVM_D3 [31], DESTRUCT [32], DISSPred [6], and DSPRED (our method) – are evaluated with respect to the CB513 benchmark.”
A Unified Multitask Architecture for Predicting Local Protein Properties (2012, background): “The profile matrix elements (typically in the range 1⁄2{7,7") are scaled to the required range 1⁄20,1" by using the following scaling function [54]:”
Conditional Neural Fields (2009, methodology): “To obtain good performance, we also linearly transform X into values in [0, 1] as suggested by Kim et al[24].”