Profiles and Majority Voting-Based Ensemble Method for Protein Secondary Structure Prediction

Abstract

Machine learning techniques have been widely applied to solve the problem of predicting protein secondary structure from the amino acid sequence. They have gained substantial success in this research area. Many methods have been used including k-Nearest Neighbors (k-NNs), Hidden Markov Models (HMMs), Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), which have attracted attention recently. Today, the main goal remains to improve the prediction quality of the secondary structure elements. The prediction accuracy has been continuously improved over the years, especially by using hybrid or ensemble methods and incorporating evolutionary information in the form of profiles extracted from alignments of multiple homologous sequences. In this paper, we investigate how best to combine k-NNs, ANNs and Multi-class SVMs (M-SVMs) to improve secondary structure prediction of globular proteins. An ensemble method which combines the outputs of two feed-forward ANNs, k-NN and three M-SVM classifiers has been applied. Ensemble members are combined using two variants of majority voting rule. An heuristic based filter has also been applied to refine the prediction. To investigate how much improvement the general ensemble method can give rather than the individual classifiers that make up the ensemble, we have experimented with the proposed system on the two widely used benchmark datasets RS126 and CB513 using cross-validation tests by including PSI-BLAST position-specific scoring matrix (PSSM) profiles as inputs. The experimental results reveal that the proposed system yields significant performance gains when compared with the best individual classifier.

Effect of simple ensemble methods on protein secondary structure prediction

“…The so-called "Ideal Fold Selection" (IFS) predictor thus assembles the 7 best predicted folds to form the predicted conformational states of the entire dataset. Furthermore, a main condition for obtaining coherent secondary structures is that the shortest length of consecutive states H must be 3 and 2 for consecutive states E. To eliminate unrealistic structures, the resulting predictions for each conformational state are then refined by applying the heuristic-based filter used in Bouziane et al (2011). The results are thus reported in Table 9.…”

“…The claimed Q 3 score varies between 75 and 80 %, depending on the benchmark datasets used (Bouziane et al 2011). Presumably, all existing machine learning algorithms have been applied to the PSSP problem and further improvements of few percentage points are still required.…”

Prediction of G Protein-Coupled Receptors with SVM-Prot Features and Random Forest

“…All the GPCR superfamily contains seven highly conserved 7TM regions with the feature of hydrophobicity; these 7TM can be identified by Hidden Markov Models (HMMs) and machine-learning methods [ 68 ]. The GPCRs structure researchers revealed that the classical sequence contained the following: the seven-transmembrane segments [TM1–7], three extracellular loops [EL1–3], three intracellular loops [IL1–3], and the protein termini.…”

Online Feature Selection (OFS) with Accelerated Bat Algorithm (ABA) and Ensemble Incremental Deep Multiple Layer Perceptron (EIDMLP) for big data streams

“…An ensemble method combines the output of individual homogenous classifiers applied to the given big datasets. Output from each ensemble is selected and combined using majority voting rule [39]. DMLP is a multiple feed forward artificial neural network that maps input vectors to that of the output vectors.…”