Neural networks for secondary structure and structural class predictions

Chandonia, John-Marc; Karplus, Martin

doi:10.1002/pro.5560040214

Cited by 106 publications

(42 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The window size value of 17 was chosen based upon the assumption that the eight closest neighboring residues will have the greatest influence on the secondary structure conformation of the central residue. This assumption is consistent with similar approaches reported in the literature [7,[12][13][14].…”

Section: Encoding Of Protein Sequence Input Datasupporting

confidence: 93%

“…The above input vector encoding technique is commonly applied in the bioinformatics and secondary structure prediction literature [7,15]. While many different and superior approaches to this phase of the machine learning problem have been suggested [3][4][5], we have chosen orthogonal encoding because of its simplicity and the fact that the results of this work do not depend upon the input encoding scheme.…”

Section: Encoding Of Protein Sequence Input Datamentioning

confidence: 99%

“…For each neural network architecture under consideration, an analytic formulation is then presented in Section 5 in order to explain the observed numerical data. As mentioned in Section 3.2, numerical experiments are performed first by training using E and then comparing Applied Computational Intelligence and Soft Computing 5 classifier performance with their counterparts trained using E. Multiple cross-validation trials are required in order to prevent potential dependency of the evaluated accuracy on the particular training or test sets chosen [7,15]. In this work, we apply a hold-n-out strategy similar to that of [14] using 85% of the 12000 encoded sequences as training data (i.e., = 10200) and 15% as test data to validate the classification results.…”

Section: Noninvariance Of Secondary Structure Predictionsmentioning

confidence: 99%

“…Based upon training examples, subsequences derived from primary sequences are encoded based upon a discrete set of classes. For instance, three class encodings are commonly applied in the literature in order to numerically represent the secondary structure set (alpha helix ( ), beta sheet ( ), coil ( )) [7][8][9][10][11]. By applying a pattern recognition approach, subsequences of unknown classification can then be tested to determine the structure class to which they belong.…”

Section: Introductionmentioning

confidence: 99%

“…By applying a pattern recognition approach, subsequences of unknown classification can then be tested to determine the structure class to which they belong. Phrased in this way, backpropagation neural networks [7,[12][13][14], and variations on the neural network theme [8,10,11,[15][16][17][18] have been applied to the secondary structure prediction problem with varied success. Furthermore, many tools currently applying hybrid methodologies such as PredictProtein [19,20], JPRED [8,17,21], SCRATCH [22,23] and PSIPRED [24,25] rely on the neural network paradigm as part of their prediction scheme.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

On the Variability of Neural Network Classification Measures in the Protein Secondary Structure Prediction Problem

Sakk

Alexander

2013

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

We revisit the protein secondary structure prediction problem using linear and backpropagation neural network architectures commonly applied in the literature. In this context, neural network mappings are constructed between protein training set sequences and their assigned structure classes in order to analyze the class membership of test data and associated measures of significance. We present numerical results demonstrating that classifier performance measures can vary significantly depending upon the classifier architecture and the structure class encoding technique. Furthermore, an analytic formulation is introduced in order to substantiate the observed numerical data. Finally, we analyze and discuss the ability of the neural network to accurately model fundamental attributes of protein secondary structure.

show abstract

Section: Encoding Of Protein Sequence Input Datasupporting

confidence: 93%

Section: Encoding Of Protein Sequence Input Datamentioning

confidence: 99%

Section: Noninvariance Of Secondary Structure Predictionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

On the Variability of Neural Network Classification Measures in the Protein Secondary Structure Prediction Problem

Sakk

Alexander

2013

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

show abstract

Prediction of secondary structural content of proteins from their amino acid composition alone. II. The paradox with secondary structural class

1996

View full text Add to dashboard Cite

The success rates reported for secondary structural class prediction with different methods are contradictory. On one side, the problem of recognizing the secondary structural class of a protein knowing only its amino acid composition appears completely solved by simply applying jury decision with an elliptically scaled distance function. Chou and coworkers repeatedly (see Crit. Rev. Biochem. Mol. Biol. 30:275–349, 1995) published prediction accuracies near 100%. On the other hand, traditional secondary structure prediction techniques achieve success rates of about 70% for the secondary structural state per residue and about 75% for structural class only with extensive input information (full sequence of the query protein, its amino acid composition and length, multiple alignments with homologous sequences). In this article, we resolve the paradox and consider (1) the question of the secondary structural class definition, (2) the role of the representativity of the test set of protein tertiary structure for the current state of the Protein Data Bank (PDB); and (3) we estimate the real impact of amino acid composition on secondary structural class. We formulate three objective criteria for a reasonable definition of secondary structural classes and show that only the criterion of Nakashima et al. (J. Biochem. 99:153–162, 1986) complies with all of them. Only this definition matches the distribution of secondary structural content in representative PDB subsets, whereas other criteria leave many proteins (up to 65% of all PDB entries) simply unassigned. We review critically specialized secondary‐structural class prediction methods, especially those of Chou and coworkers, which claim almost 100% accuracy using only amino acid composition, and resolve the paradox that these prediction accuracies are better than those from secondary structure predictions from multiple alignments. We show (i) that these techniques rely on a preselection of test sets which removes irregular proteins and other proteins without any class assignment (about 35% of all PDB entries); and (ii) that even for preselected representative test sets, the success rate drops to 60% and lower for a 4‐type classification (α, β, α + β, α/β). The prediction accuracies fall to about 50% if the secondary structural class definition of Nakashima et al. is applied and only few irregular proteins are preselected and removed from automatically generated, representative subsets of the PDB. We have applied two new vector decomposition methods for secondary structural content prediction from amino acid composition alone, with and without consideration of amino acid compositional coupling in the learning set of tertiary structures respectively, to the problem of class prediction and achieve about 60% correct assignment among four classes (α, β, mixed, irregular) as well as single sequence‐based secondary structure prediction methods like GORIII and COMBI. Our results demonstrate that 60% correctness is the upper limit for a 4‐type class prediction from amin...

show abstract

Understanding the recognition of protein structural classes by amino acid composition

et al. 1997

View full text Add to dashboard Cite

Knowledge of amino acid composition, alone, is verified here to be sufficient for recognizing the structural class, alpha, beta, alpha + beta, or alpha/beta of a given protein with an accuracy of 81%. This is supported by results from exhaustive enumerations of all conformations for all sequences of simple, compact lattice models consisting of two types (hydrophobic and polar) of residues. Different compositions exhibit strong affinities for certain folds. Within the limits of validity of the lattice models, two factors appear to determine the choice of particular folds: 1) the coordination numbers of individual sites and 2) the size and geometry of non-bonded clusters. These two properties, collectively termed the distribution of non-bonded contacts, are quantitatively assessed by an eigenvalue analysis of the so-called Kirchhoff or adjacency matrices obtained by considering the non-bonded interactions on a lattice. The analysis permits the identification of conformations that possess the same distribution of non-bonded contacts. Furthermore, some distributions of non-bonded contacts are favored entropically, due to their high degeneracies. Thus, a competition between enthalpic and entropic effects is effective in determining the choice of a distribution for a given composition. Based on these findings, an analysis of non-bonded contacts in protein structures was made. The analysis shows that proteins belonging to the four distinct folding classes exhibit significant differences in their distributions of non-bonded contacts, which more directly explains the success in predicting structural class from amino acid composition.

show abstract

Neural networks for secondary structure and structural class predictions

Cited by 106 publications

References 25 publications

On the Variability of Neural Network Classification Measures in the Protein Secondary Structure Prediction Problem

On the Variability of Neural Network Classification Measures in the Protein Secondary Structure Prediction Problem

Prediction of secondary structural content of proteins from their amino acid composition alone. II. The paradox with secondary structural class

Understanding the recognition of protein structural classes by amino acid composition

Contact Info

Product

Resources

About