Secondary Structure Prediction Model Research Articles

Impact of Multi-Factor Features on Protein Secondary Structure Prediction.

Protein secondary structure prediction (PSSP) plays a crucial role in resolving protein functions and properties. Significant progress has been made in this field in recent years, and the use of a variety of protein-related features, including amino acid sequences, position-specific score matrices (PSSM), amino acid properties, and secondary structure trend factors, to improve prediction accuracy is an important technical route for it. However, a comprehensive evaluation of the impact of these factor features in secondary structure prediction is lacking in the current work. This study quantitatively analyzes the impact of several major factors on secondary structure prediction models using a more explanatory four-class machine learning approach. The applicability of each factor in the different types of methods, the extent to which the different methods work on each factor, and the evaluation of the effect of multi-factor combinations are explored in detail. Through experiments and analyses, it was found that PSSM performs best in methods with strong high-dimensional features and complex feature extraction capabilities, while amino acid sequences, although performing poorly overall, perform relatively well in methods with strong linear processing capabilities. Also, the combination of amino acid properties and trend factors significantly improved the prediction performance. This study provides empirical evidence for future researchers to optimize multi-factor feature combinations and apply them to protein secondary structure prediction models, which is beneficial in further optimizing the use of these factors to enhance the performance of protein secondary structure prediction models.

PSO Based Neuro-fuzzy Model for Secondary Structure Prediction of Protein

PSO Based Neuro-fuzzy Model for Secondary Structure Prediction of Protein

Swarm optimization-based neural network model for secondary structure prediction of proteins

Proteins form the basis of all major life processes that sustain life. The functionality of a protein is a direct consequence of its underlying structure. Protein structure prediction thus serves to ascertain the function of similar or dissimilar proteins, accordingly. Secondary structure prediction paves way for 3D structures that eventually decides protein properties. It also aims to facilitate probable structures for proteins whose structures remain undiscovered. Although experimental approaches have been quite efficient in extracting protein secondary structure from its amino acid sequence, yet it is often cumbersome and time intensive to achieve it in vitro. Hence, computational approaches are required to predict secondary structures for the diverse amino acids constituting these proteins. However, the available computational models fail to register good prediction accuracy due to inadequate modelling of sequence-structure relationship. Also, the dearth of global exploration-based methods further makes them ineffective in catering to the evolving proteomic data. Accordingly, PSO (Particle swarm optimization) has been explored to propose a neural network model for protein secondary structure prediction (PSSP). Six standard datasets namely- PSS504, RS126, EVA6, CB396, Manesh and CB513 have been utilized for the training and testing of the neural network. The proposed model is evaluated on the basis of its Q3 accuracy, precision, and recall. The 10, 20, 30 and 40 fold cross validation in combination with sensitivity analysis and has been carried out for verification of results. The proposed model is found to outperform most of the existing models by demonstrating a better average Q3 accuracy lying above 81% for PSSP.

Molecular phylogeny and morphology of Cephaleuros (Trentepohliales, Chlorophyta) from southern China

ABSTRACT Cephaleuros is a subaerial green alga widely distributed in tropical and subtropical regions. In this study, we investigated the taxonomy of Cephaleuros in southern China. Eight morphospecies (C. virescens, C. karstenii, C. expansus, C. drouetii, C. diffusus, C. tumidae-setae, C. lagerheimii and C. parasiticus) were identified according to previous descriptions, among which C. karstenii was the most frequently recorded. Subsequently, molecular phylogeny of Cephaleuros was inferred from 18S rDNA, ITS rDNA, 28S rDNA and rbcL sequences. Cephaleuros was subdivided into nine clades based on ITS analysis, which were recovered in phylogenies of two concatenated datasets (18S+ITS+28S and 18S+ITS+28S+rbcL). Molecular analyses revealed that Cephaleuros was composed of two main lineages, with one lineage comprising mostly samples of C. karstenii and C. virescens and the other comprising other species. The molecular phylogenies were not congruent with conventional morphological classifications, although some clades were distinguished by one or more diagnostic features. While the morphological features used to distinguish Cephaleuros spp were not reliable, the rbcL gene proved to be a good marker for identification of Cephaleuros. The ITS2 secondary structure prediction model showed that Cephaleuros spp have one ring structure with four helices, with Helix III being the longest without a branch in clades 3, 5 and 8. The present study represents the most detailed taxonomic assessment of Cephaleuros available to date. Further taxonomic research incorporating samples from the type locality is necessary for the reassessment of C. virescens.

Secondary structure prediction of protein based on multi scale convolutional attention neural networks.

To fully extract the local and long-range information of amino acid sequences and enhance the effective information, this research proposes a secondary structure prediction model of protein based on a multi-scale convolutional attentional neural network. The model uses a multi-channel multi-scale parallel architecture to extract amino acid structure features of different granularity according to the window size. The reconstructed feature maps are obtained via multiple convolutional attention blocks. Then, the reconstructed feature map is fused with the input feature map to obtain the enhanced feature map. Finally, the enhanced feature map is fed to the Softmax classifier for prediction. While the traditional cross-entropy loss cannot effectively solve the problem of non-equilibrium training samples, a modified correlated cross-entropy loss function may alleviate this problem. After numerous comparison and ablation experiments, it is verified that the improved model can indeed effectively extract amino acid sequence feature information, alleviate overfitting, and thus improve the overall prediction accuracy.

Graphene oxide-assisted non-immobilized SELEX of chiral drug ephedrine aptamers and the analytical binding mechanism

Here, we describe a study of screen characterization of aptamers targeting the chiral drug ephedrine using the non-immobilized graphene oxide (GO) SELEX. The improved method of long and short chains was here used to prepare the ssDNA library. The Resonance Rayleigh Scattering (RRS) method was first used to monitor the screening process. Through high-throughput sequencing, the genetic sequence data of 90,487 aptamers were obtained. Through the analysis of the parameters of free energy value and secondary structure prediction model of high repeatability sequence, the 10 candidate sequences were identified. Finally, a best-fit aptamer named EP08 was identified by combining the dissociation experiment. The binding affinity and binding mechanism of the aptamer and target were analyzed using an isothermal titration colorimetry (ITC) experiment and circular dichromatic (CD) experiment. The binding affinity (Kd) of the EP08 aptamer to ephedrine is approximately 2.86 ± 0.24 μM. This novel DNA aptamer will help in the future development of a new method for the identification and detection of chiral drug ephedrine.

Transcriptome-wide interrogation of RNA secondary structure in living cells with icSHAPE.

icSHAPE (in vivo click selective 2-hydroxyl acylation and profiling experiment) captures RNA secondary structure at a transcriptome-wide level by measuring nucleotide flexibility at base resolution. Living cells are treated with the icSHAPE chemical NAI-N3 followed by selective chemical enrichment of NAI-N3-modified RNA, which provides an improved signal-to-noise ratio compared with similar methods leveraging deep sequencing. Purified RNA is then reverse-transcribed to produce cDNA, with SHAPE-modified bases leading to truncated cDNA. After deep sequencing of cDNA, computational analysis yields flexibility scores for every base across the starting RNA population. The entire experimental procedure can be completed in ∼5 d, and the sequencing and bioinformatics data analysis take an additional 4-5 d with no extensive computational skills required. Comparing in vivo and in vitro icSHAPE measurements can reveal in vivo RNA-binding protein imprints or facilitate the dissection of RNA post-transcriptional modifications. icSHAPE reactivities can additionally be used to constrain and improve RNA secondary structure prediction models.

A probabilistic model for secondary structure prediction from protein chemical shifts

Protein chemical shifts encode detailed structural information that is difficult and computationally costly to describe at a fundamental level. Statistical and machine learning approaches have been used to infer correlations between chemical shifts and secondary structure from experimental chemical shifts. These methods range from simple statistics such as the chemical shift index to complex methods using neural networks. Notwithstanding their higher accuracy, more complex approaches tend to obscure the relationship between secondary structure and chemical shift and often involve many parameters that need to be trained. We present hidden Markov models (HMMs) with Gaussian emission probabilities to model the dependence between protein chemical shifts and secondary structure. The continuous emission probabilities are modeled as conditional probabilities for a given amino acid and secondary structure type. Using these distributions as outputs of first- and second-order HMMs, we achieve a prediction accuracy of 82.3%, which is competitive with existing methods for predicting secondary structure from protein chemical shifts. Incorporation of sequence-based secondary structure prediction into our HMM improves the prediction accuracy to 84.0%. Our findings suggest that an HMM with correlated Gaussian distributions conditioned on the secondary structure provides an adequate generative model of chemical shifts.

Thermodynamic examination of trinucleotide bulged RNA in the context of HIV-1 TAR RNA

RNA structures contain many bulges and loops that are expected to be sites for inter- and intra-molecular interactions. Nucleotides in the bulge are expected to influence the structure and recognition of RNA. The same stability is assigned to all trinucleotide bulged RNA in the current secondary structure prediction models. In this study thermal denaturation experiments were performed on four trinucleotide bulged RNA, in the context of HIV-1 TAR RNA, to determine whether the bulge sequence affects RNA stability and its divalent ion interactions. Cytosine-rich bulged RNA were more stable than uracil-rich bulged RNA in 1 M KCl. Interactions of divalent ions were more favorable with uracil-rich bulged RNA by approximately 2 kcal/mol over cytosine-rich bulged RNA. The UCU-TAR RNA (wild type) is stabilized by 1.7 kcal/mol in 9.5 mM Ca(2+) as compared with 1 M KCl, whereas no additional gain in stability is measured for CCC-TAR RNA. These results have implications for base substitution experiments traditionally employed to identify metal ion binding sites. To our knowledge, this is the first systematic study to quantify the effect of small sequence changes on RNA stability upon interactions with divalent ions.

Analysis of an optimal hidden Markov model for secondary structure prediction

BackgroundSecondary structure prediction is a useful first step toward 3D structure prediction. A number of successful secondary structure prediction methods use neural networks, but unfortunately, neural networks are not intuitively interpretable. On the contrary, hidden Markov models are graphical interpretable models. Moreover, they have been successfully used in many bioinformatic applications. Because they offer a strong statistical background and allow model interpretation, we propose a method based on hidden Markov models.ResultsOur HMM is designed without prior knowledge. It is chosen within a collection of models of increasing size, using statistical and accuracy criteria. The resulting model has 36 hidden states: 15 that model α-helices, 12 that model coil and 9 that model β-strands. Connections between hidden states and state emission probabilities reflect the organization of protein structures into secondary structure segments. We start by analyzing the model features and see how it offers a new vision of local structures. We then use it for secondary structure prediction. Our model appears to be very efficient on single sequences, with a Q3 score of 68.8%, more than one point above PSIPRED prediction on single sequences. A straightforward extension of the method allows the use of multiple sequence alignments, rising the Q3 score to 75.5%.ConclusionThe hidden Markov model presented here achieves valuable prediction results using only a limited number of parameters. It provides an interpretable framework for protein secondary structure architecture. Furthermore, it can be used as a tool for generating protein sequences with a given secondary structure content.

Choosing the Optimal Hidden Markov Model for Secondary-Structure Prediction

Proteins are major constituents of living cells, forming many cellular components and most enzymes. So, knowledge of 3D protein structures is essential to understand biological mechanisms. Researchers often use neural networks to predict secondary structure in proteins, but the networks can be hard to interpret. This alternative method uses an optimal and interpretable hidden Markov model to classify protein residues. These HMM models account for the transitions observed in 3D structures and allow a predictive approach. We've developed a method for finding an optimal HMM to classify residues into secondary-structure classes. HMMs both provide a probabilistic framework for sequence treatment and produce interpretable models.

Conformational Determinants of Tandem GU Mismatches in RNA: Insights from Molecular Dynamics Simulations and Quantum Mechanical Calculations

Structure and energetic properties of base pair mismatches in duplex RNA have been the focus of numerous investigations due to their role in many important biological functions. Such efforts have contributed to the development of models for secondary structure prediction of RNA, including the nearest-neighbor model. In RNA duplexes containing GU mismatches, 5'-GU-3' tandem mismatches have a different thermodynamic stability than 5'-UG-3' mismatches. In addition, 5'-GU-3' mismatches in some sequence contexts do not follow the nearest-neighbor model for stability. To characterize the underlying atomic forces that determine the structural and thermodynamic properties of GU tandem mismatches, molecular dynamics (MD) simulations were performed on a series of 5'-GU-3' and 5'-UG-3' duplexes in different sequence contexts. Overall, the MD-derived structural models agree well with experimental data, including local deviations in base step helicoidal parameters in the region of the GU mismatches and the model where duplex stability is associated with the pattern of GU hydrogen bonding. Further analysis of the simulations, validated by data from quantum mechanical calculations, suggests that the experimentally observed differences in thermodynamic stability are dominated by GG interstrand followed by GU intrastrand base stacking interactions that dictate the one versus two hydrogen bonding scenarios for the GU pairs. In addition, the inability of 5'-GU-3' mismatches in different sequence contexts to all fit into the nearest-neighbor model is indicated to be associated with interactions of the central four base pairs with the surrounding base pairs. The results emphasize the role of GG and GU stacking interactions on the structure and thermodynamics of GU mismatches in RNA.

Combining protein secondary structure prediction models with ensemble methods of optimal complexity

Many sophisticated methods are currently available to perform protein secondary structure prediction. Since they are frequently based on different principles, and different knowledge sources, significant benefits can be expected from combining them. However, the choice of an appropriate combiner appears to be an issue in its own right. The first difficulty to overcome when combining prediction methods is overfitting. This is the reason why we investigate the implementation of Support Vector Machines to perform the task. A family of multi-class SVMs is introduced. Two of these machines are used to combine some of the current best protein secondary structure prediction methods. Their performance is consistently superior to the performance of the ensemble methods traditionally used in the field. They also outperform the decomposition approaches based on bi-class SVMs. Furthermore, initial experimental evidence suggests that their outputs could be processed by the biologist to perform higher-level treatments.

Statistical analysis of pair-wise compatibility of spatially nearest neighbor and adjacent residues in α-helix and β-strands: application to a minimal model for secondary structure prediction

Secondary structural elements like α-helix and β-strands posses distinctly different structural features and thus the relative positioning of the nearest neighbor residues, and also the sequence-wise adjacent residues is important in determining the structural preference. In the present work we have statistically examined the pair-wise compatibility pattern of physically nearest neighbors and separately the adjacent residue pairs along the sequence in between the nearest neighbor partners in α-helices and β-strands. It has been demonstrated that the patterns and hence, the physical basis of the compatibility of adjacent residue pairs and the spatially nearest neighbors are significantly different in most cases. The influence of tertiary contacts on the pair-wise compatibility is shown to be significant for β-strands while it is small for α-helices. Based on the compatibility of physically nearest neighbors and the sequence-wise adjacent residue pairs, a minimal model has been constructed to predict the α-helices, β-strands and coils of a protein from its sequence. Application of this method to 100 sequences shows that it has a predictive capability comparable to that of other more sophisticated statistical methods.