A Tri-Gram Based Feature Extraction Technique Using Linear Probabilities of Position Specific Scoring Matrix for Protein Fold Recognition

Paliwal, Kuldip K.; Sharma, Alok; Lyons, James; Dehzangi, Abdollah

doi:10.1109/tnb.2013.2296050

Cited by 66 publications

(39 citation statements)

References 50 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, to this corpus, we apply SG, CBOW, and GloVe described in Section 2.1. Note that the above word definition and splitting for protein sequences are common approaches in bioinformatics and similar to previous work such as [14], [21], [22], [23].…”

Section: Words Of Proteins and Representation Learningmentioning

confidence: 77%

Protein Fold Recognition with Representation Learning and Long Short-Term Memory

Tsubaki

Shimbo

Matsumoto

2017

IPSJ Transactions on Bioinformatics

View full text Add to dashboard Cite

Predicting the 3D structure of a protein from its amino acid sequence is an important challenge in bioinformatics. Since directly predicting the 3D structure is hard to achieve, classifying a protein into one of the "folds", which are pre-defined structural labels in protein databases such as SCOP and CATH, is generally used as an intermediate step to determine the 3D structure. This classification task is called protein fold recognition (PFR), and much research has addressed the problem of either (i) feature extractions from amino acid sequences or (ii) classification methods of the protein folds. In this paper, we propose a new approach for PFR with (i) learning feature representations with unsupervised methods from a large protein database instead of manual feature selection and using external tools. (ii) learning deep neural architectures, recurrent neural networks (RNNs) with long short-term memory (LSTM) units, and re-training the representations instead of fixing the extracted features. On a benchmark dataset, our approach outperforms existing methods that use various physicochemical features.

show abstract

Section: Words Of Proteins and Representation Learningmentioning

confidence: 77%

Protein Fold Recognition with Representation Learning and Long Short-Term Memory

Tsubaki

Shimbo

Matsumoto

2017

IPSJ Transactions on Bioinformatics

View full text Add to dashboard Cite

show abstract

“…These techniques included PF1 and PF2 [3], PF [39], Occurrence (O) [40], AAC and AAC+HXPZV [2], which compute feature sets from the original protein sequences. In addition, ACC [18], Bi-gram [19], Tri-gram [20] and Alignment [21] are also included since they compute features directly from the evolutionary information present in PSSM. Moreover, features have been computed from the consensus sequences for PF1, PF2, O, AAC and AAC+HXPZV to obtain additional feature sets for comparison.…”

Section: Resultsmentioning

confidence: 99%

“…Ferredoxin-like 13 27 Small inhibitors, toxins, lectins 13 27 Furthermore, some of the classification techniques that have been explored include Linear Discriminant Analysis [24], K-Nearest Neighbors [25], Bayesian Classifiers [26]- [28], Support Vector Machines (SVM) [19]- [21], [28]- [30], Artificial Neural Networks (ANN) [31]- [33] and ensemble classifiers [34], [35]. Out of these mentioned classification techniques, SVM has showed promising results in protein fold recognition problem.…”

Section: Introductionmentioning

confidence: 99%

Protein Fold Recognition Using Genetic Algorithm Optimized Voting Scheme and Profile Bigram

Saini¹,

Raicar²,

Lal³

et al. 2016

JSW

Self Cite

View full text Add to dashboard Cite

Abstract:In biology, identifying the tertiary structure of a protein helps determine its functions. A step towards tertiary structure identification is predicting a protein's fold. Computational methods have been applied to determine a protein's fold by assembling information from its structural, physicochemical and/or evolutionary properties. It has been shown that evolutionary information helps improve prediction accuracy. In this study, a scheme is proposed that uses the genetic algorithm (GA) to optimize a weighted voting scheme to improve protein fold recognition. This scheme incorporates k-separated bigram transition probabilities for feature extraction, which are based on the Position Specific Scoring Matrix (PSSM). A set of SVM classifiers are used for initial classification, whereupon their predictions are consolidated using the optimized weighted voting scheme. This scheme has been demonstrated on the Ding and Dubchak (DD), Extended Ding and Dubchak (EDD) and Taguchi and Gromhia (TG) datasets benchmarked data sets.

show abstract

“…In the literature, Paliwal et al (2014) have used tri-gram features for protein fold recognition. They have computed the tri-gram features directly from position-specific scoring matrix (PSSM) generated by PSI-BLAST program (Altschul et al 1997).…”

Section: Introductionmentioning

confidence: 99%

Prediction of protein structural class using tri-gram probabilities of position-specific scoring matrix and recursive feature elimination

Tao

Liu

et al. 2015

Amino Acids

View full text Add to dashboard Cite

Knowledge of structural class plays an important role in understanding protein folding patterns. As a transitional stage in recognition of three-dimensional structure of a protein, protein structural class prediction is considered to be an important and challenging task. In this study, we firstly introduce a feature extraction technique which is based on tri-grams computed directly from position-specific scoring matrix (PSSM). A total of 8,000 features are extracted to represent a protein. Then, support vector machine-recursive feature elimination (SVM-RFE) is applied for feature selection and reduced features are input to a support vector machine (SVM) classifier to predict structural class of a given protein. To examine the effectiveness of our method, jackknife tests are performed on six widely used benchmark datasets, i.e., Z277, Z498, 1189, 25PDB, D640, and D1185. The overall accuracies of 97.1, 98.6, 92.5, 93.5, 94.2, and 95.9% are achieved on these datasets, respectively. Comparison of the proposed method with other prediction methods shows that our method is very promising to perform the prediction of protein structural class.

show abstract

A Tri-Gram Based Feature Extraction Technique Using Linear Probabilities of Position Specific Scoring Matrix for Protein Fold Recognition

Abstract: Abstract-In biological sciences, the deciphering of a three dimensional structure of a protein sequence is considered to be an important and challenging task.

Cited by 66 publications

References 50 publications

Protein Fold Recognition with Representation Learning and Long Short-Term Memory

Protein Fold Recognition with Representation Learning and Long Short-Term Memory

Protein Fold Recognition Using Genetic Algorithm Optimized Voting Scheme and Profile Bigram

Prediction of protein structural class using tri-gram probabilities of position-specific scoring matrix and recursive feature elimination

Contact Info

Product

Resources

About