Improving Protein Expression Prediction Using Extra Features and Ensemble Averaging.
Ontology highlight
ABSTRACT:
SUBMITTER: Fernandes A
PROVIDER: S-EPMC4775025 | biostudies-literature | 2016
REPOSITORIES: biostudies-literature
Publications
Improving Protein Expression Prediction Using Extra Features and Ensemble Averaging.
Fernandes Armando A Vinga Susana S
PloS one 20160302 3
The article focus is the improvement of machine learning models capable of predicting protein expression levels based on their codon encoding. Support vector regression (SVR) and partial least squares (PLS) were used to create the models. SVR yields predictions that surpass those of PLS. It is shown that it is possible to improve the models predictive ability by using two more input features, codon identification number and codon count, besides the already used codon bias and minimum free energy ...[more]
Similar Datasets
Project description:N 6-methyladenosine (m6A) is one of the most widely studied epigenetic modifications, which plays an important role in many biological processes, such as splicing, RNA localization, and degradation. Studies have shown that m6A on lncRNA has important functions, including regulating the expression and functions of lncRNA, regulating the synthesis of pre-mRNA, promoting the proliferation of cancer cells, and affecting cell differentiation and many others. Although a number of methods have been proposed to predict m6A RNA methylation sites, most of these methods aimed at general m6A sites prediction without noticing the uniqueness of the lncRNA methylation prediction problem. Since many lncRNAs do not have a polyA tail and cannot be captured in the polyA selection step of the most widely adopted RNA-seq library preparation protocol, lncRNA methylation sites cannot be effectively captured and are thus likely to be significantly underrepresented in existing experimental data affecting the accuracy of existing predictors. In this paper, we propose a new computational framework, LITHOPHONE, which stands for long noncoding RNA methylation sites prediction from sequence characteristics and genomic information with an ensemble predictor. We show that the methylation sites of lncRNA and mRNA have different patterns exhibited in the extracted features and should be differently handled when making predictions. Due to the used experiment protocols, the number of known lncRNA m6A sites is limited, and insufficient to train a reliable predictor; thus, the performance can be improved by combining both lncRNA and mRNA data using an ensemble predictor. We show that the newly developed LITHOPHONE approach achieved a reasonably good performance when tested on independent datasets (AUC: 0.966 and 0.835 under full transcript and mature mRNA modes, respectively), marking a substantial improvement compared with existing methods. Additionally, LITHOPHONE was applied to scan the entire human lncRNAome for all possible lncRNA m6A sites, and the results are freely accessible at: http://180.208.58.19/lith/.
| S-EPMC7297269 | biostudies-literature
Project description:Brain age is an imaging-based biomarker with excellent feasibility for characterizing individual brain health and may serve as a single quantitative index for clinical and domain-specific usage. Brain age has been successfully estimated using extensive neuroimaging data from healthy participants with various feature extraction and conventional machine learning (ML) approaches. Recently, several end-to-end deep learning (DL) analytical frameworks have been proposed as alternative approaches to predict individual brain age with higher accuracy. However, the optimal approach to select and assemble appropriate input feature sets for DL analytical frameworks remains to be determined. In the Predictive Analytics Competition 2019, we proposed a hierarchical analytical framework which first used ML algorithms to investigate the potential contribution of different input features for predicting individual brain age. The obtained information then served as a priori knowledge for determining the input feature sets of the final ensemble DL prediction model. Systematic evaluation revealed that ML approaches with multiple concurrent input features, including tissue volume and density, achieved higher prediction accuracy when compared with approaches with a single input feature set [Ridge regression: mean absolute error (MAE) = 4.51 years, R 2 = 0.88; support vector regression, MAE = 4.42 years, R 2 = 0.88]. Based on this evaluation, a final ensemble DL brain age prediction model integrating multiple feature sets was constructed with reasonable computation capacity and achieved higher prediction accuracy when compared with ML approaches in the training dataset (MAE = 3.77 years; R 2 = 0.90). Furthermore, the proposed ensemble DL brain age prediction model also demonstrated sufficient generalizability in the testing dataset (MAE = 3.33 years). In summary, this study provides initial evidence of how-to efficiency for integrating ML and advanced DL approaches into a unified analytical framework for predicting individual brain age with higher accuracy. With the increase in large open multiple-modality neuroimaging datasets, ensemble DL strategies with appropriate input feature sets serve as a candidate approach for predicting individual brain age in the future.
| S-EPMC8021919 | biostudies-literature
Project description:BACKGROUND: Prediction of protein-protein interaction sites is one of the most challenging and intriguing problems in the field of computational biology. Although much progress has been achieved by using various machine learning methods and a variety of available features, the problem is still far from being solved. RESULTS: In this paper, an ensemble method is proposed, which combines bootstrap resampling technique, SVM-based fusion classifiers and weighted voting strategy, to overcome the imbalanced problem and effectively utilize a wide variety of features. We evaluate the ensemble classifier using a dataset extracted from 99 polypeptide chains with 10-fold cross validation, and get a AUC score of 0.86, with a sensitivity of 0.76 and a specificity of 0.78, which are better than that of the existing methods. To improve the usefulness of the proposed method, two special ensemble classifiers are designed to handle the cases of missing homologues and structural information respectively, and the performance is still encouraging. The robustness of the ensemble method is also evaluated by effectively classifying interaction sites from surface residues as well as from all residues in proteins. Moreover, we demonstrate the applicability of the proposed method to identify interaction sites from the non-structural proteins (NS) of the influenza A virus, which may be utilized as potential drug target sites. CONCLUSION: Our experimental results show that the ensemble classifiers are quite effective in predicting protein interaction sites. The Sub-EnClassifiers with resampling technique can alleviate the imbalanced problem and the combination of Sub-EnClassifiers with a wide variety of feature groups can significantly improve prediction performance.
| S-EPMC2808167 | biostudies-literature
Project description:Recent algorithmic advances and continual increase in computational power have made it possible to simulate protein folding and dynamics on the level of ensembles. Furthermore, analyzing protein structure by using ensemble representation is intrinsic to certain experimental techniques, such as nuclear magnetic resonance. This creates a problem of how to compare an ensemble of molecules with a given reference structure. Recently, we used distance-based root-mean-square deviation (dRMS) to compare the native structure of a protein with its unfolded-state ensemble. We showed that for small, mostly alpha-helical proteins, the mean unfolded-state Calpha-Calpha distance matrix is significantly more nativelike than the Calpha-Calpha matrices corresponding to the individual members of the unfolded ensemble. Here, we give a mathematical derivation that shows that, for any ensemble of structures, the dRMS deviation between the ensemble-averaged distance matrix and any given reference distance matrix is always less than or equal to the average dRMS deviation of the individual members of the ensemble from the same reference matrix. This holds regardless of the nature of the reference structure or the structural ensemble in question. In other words, averaging of distance matrices can only increase their level of similarity to a given reference matrix, relative to the individual matrices comprising the ensemble. Furthermore, we show that the above inequality holds in the case of Cartesian coordinate-based root-mean-square deviation as well. We discuss this in the context of our proposal that the average structure of the unfolded ensemble of small helical proteins is close to the native structure, and demonstrate that this finding goes beyond the above mathematical fact.
| S-EPMC1304649 | biostudies-literature
Project description:Protein fold recognition is a critical step toward protein structure and function prediction, aiming at providing the most likely fold type of the query protein. In recent years, the development of deep learning (DL) technique has led to massive advances in this important field, and accordingly, the sensitivity of protein fold recognition has been dramatically improved. Most DL-based methods take an intermediate bottleneck layer as the feature representation of proteins with new fold types. However, this strategy is indirect, inefficient and conditional on the hypothesis that the bottleneck layer's representation is assumed as a good representation of proteins with new fold types. To address the above problem, in this work, we develop a new computational framework by combining triplet network and ensemble DL. We first train a DL-based model, termed FoldNet, which employs triplet loss to train the deep convolutional network. FoldNet directly optimizes the protein fold embedding itself, making the proteins with the same fold types be closer to each other than those with different fold types in the new protein embedding space. Subsequently, using the trained FoldNet, we implement a new residue-residue contact-assisted predictor, termed FoldTR, which improves protein fold recognition. Furthermore, we propose a new ensemble DL method, termed FSD_XGBoost, which combines protein fold embedding with the other two discriminative fold-specific features extracted by two DL-based methods SSAfold and DeepFR. The Top 1 sensitivity of FSD_XGBoost increases to 74.8% at the fold level, which is ~9% higher than that of the state-of-the-art method. Together, the results suggest that fold-specific features extracted by different DL methods complement with each other, and their combination can further improve fold recognition at the fold level. The implemented web server of FoldTR and benchmark datasets are publicly available at http://csbio.njust.edu.cn/bioinf/foldtr/.
| S-EPMC8768454 | biostudies-literature
Project description:Tuberculosis is one of the leading cause of death worldwide, particularly due to evolution of drug resistant strains. Antitubercular peptides may provide an alternate approach to combat antibiotic tolerance. Sequence analysis reveals that certain residues (e.g., Lysine, Arginine, Leucine, Tryptophan) are more prevalent in antitubercular peptides. This study describes the models developed for predicting antitubercular peptides by using sequence features of the peptides. We have developed support vector machine based models using different sequence features like amino acid composition, binary profile of terminus residues, dipeptide composition. Our ensemble classifiers that combines models based on amino acid composition and N5C5 binary pattern, achieves highest Acc of 73.20% with 0.80 AUROC on our main dataset. Similarly, the ensemble classifier achieved maximum Acc 75.62% with 0.83 AUROC on secondary dataset. Beside this, hybrid model achieves Acc of 75.87 and 78.54% with 0.83 and 0.86 AUROC on main and secondary dataset, respectively. In order to facilitate scientific community in designing of antitubercular peptides, we implement above models in a user friendly webserver (http://webs.iiitd.edu.in/raghava/antitbpred/).
| S-EPMC6121089 | biostudies-literature
Project description:BACKGROUND: MicroRNAs (simply miRNAs) are derived from larger hairpin RNA precursors and play essential regular roles in both animals and plants. A number of computational methods for miRNA genes finding have been proposed in the past decade, yet the problem is far from being tackled, especially when considering the imbalance issue of known miRNAs and unidentified miRNAs, and the pre-miRNAs with multi-loops or higher minimum free energy (MFE). This paper presents a new computational approach, miRenSVM, for finding miRNA genes. Aiming at better prediction performance, an ensemble support vector machine (SVM) classifier is established to deal with the imbalance issue, and multi-loop features are included for identifying those pre-miRNAs with multi-loops. RESULTS: We collected a representative dataset, which contains 697 real miRNA precursors identified by experimental procedure and other computational methods, and 5428 pseudo ones from several datasets. Experiments showed that our miRenSVM achieved a 96.5% specificity and a 93.05% sensitivity on the dataset. Compared with the state-of-the-art approaches, miRenSVM obtained better prediction results. We also applied our method to predict 14 Homo sapiens pre-miRNAs and 13 Anopheles gambiae pre-miRNAs that first appeared in miRBase13.0, MiRenSVM got a 100% prediction rate. Furthermore, performance evaluation was conducted over 27 additional species in miRBase13.0, and 92.84% (4863/5238) animal pre-miRNAs were correctly identified by miRenSVM. CONCLUSION: MiRenSVM is an ensemble support vector machine (SVM) classification system for better detecting miRNA genes, especially those with multi-loop secondary structure.
| S-EPMC3024864 | biostudies-other
Project description:Protein gamma-turn prediction is useful in protein function studies and experimental design. Several methods for gamma-turn prediction have been developed, but the results were unsatisfactory with Matthew correlation coefficients (MCC) around 0.2-0.4. Hence, it is worthwhile exploring new methods for the prediction. A cutting-edge deep neural network, named Capsule Network (CapsuleNet), provides a new opportunity for gamma-turn prediction. Even when the number of input samples is relatively small, the capsules from CapsuleNet are effective to extract high-level features for classification tasks. Here, we propose a deep inception capsule network for gamma-turn prediction. Its performance on the gamma-turn benchmark GT320 achieved an MCC of 0.45, which significantly outperformed the previous best method with an MCC of 0.38. This is the first gamma-turn prediction method utilizing deep neural networks. Also, to our knowledge, it is the first published bioinformatics application utilizing capsule network, which will provide a useful example for the community. Executable and source code can be download at http://dslsrv8.cs.missouri.edu/~cf797/MUFoldGammaTurn/download.html.
| S-EPMC6200818 | biostudies-other
Project description:CONSPECTUS: The active site of an enzyme is surrounded by a fluctuating environment of protein and solvent conformational states, and a realistic calculation of chemical reaction rates and kinetic isotope effects of enzyme-catalyzed reactions must take account of this environmental diversity. Ensemble-averaged variational transition state theory with multidimensional tunneling (EA-VTST/MT) was developed as a way to carry out such calculations. This theory incorporates ensemble averaging, quantized vibrational energies, energy, tunneling, and recrossing of transition state dividing surfaces in a systematic way. It has been applied successfully to a number of hydrogen-, proton-, and hydride-transfer reactions. The theory also exposes the set of effects that should be considered in reliable rate constants calculations. We first review the basic theory and the steps in the calculation. A key role is played by the generalized free energy of activation profile, which is obtained by quantizing the classical potential of mean force as a function of a reaction coordinate because the one-way flux through the transition state dividing surface can be written in terms of the generalized free energy of activation. A recrossing transmission coefficient accounts for the difference between the one-way flux through the chosen transition state dividing surface and the net flux, and a tunneling transmission coefficient converts classical motion along the reaction coordinate to quantum mechanical motion. The tunneling calculation is multidimensional, accounting for the change in vibrational frequencies along the tunneling path and shortening of the tunneling path with respect to the minimum energy path (MEP), as promoted by reaction-path curvature. The generalized free energy of activation and the transmission coefficients both involve averaging over an ensemble of reaction paths and conformations, and this includes the coupling of protein motions to the rearrangement of chemical bonds in a statistical mechanically correct way. The standard deviations of the transmissions coefficients provide information on the diversity of the distribution of reaction paths, barriers, and protein conformations along the members of an ensemble of reaction paths passing through the transition state. We first illustrate the theory by discussing the application to both wild-type and mutant Escherichia coli dihydrofolate reductase and hyperthermophilic Thermotoga maritima dihydrofolate reductase (DHFR); DHFR is of special interest because the protein conformational changes have been widely studied. Then we present shorter discussions of several other applications of EA-VTST/MT to transfer of protons, hydrogen atoms, and hydride ions and their deuterated analogs. Systems discussed include hydride transfer in alcohol dehydrogenase, xylose isomerase, and thymidylate synthase, proton transfer in methylamine dehydrogenase, hydrogen atom transfer in methylmalonyl-CoA mutase, and nucleophilic substitution in haloalkane dehalogenase and two-dimensional potentials of mean force for potentially coupled proton and hydride transfer in the ?-oxidation of butyryl-coenzyme A catalyzed by short-chain acyl-CoA dehydrogenase and in the pyruvate to lactate transformation catalyzed by lactate dehydrogenase.
| S-EPMC4334256 | biostudies-literature
Project description:MotivationProtein structure prediction has been greatly improved by deep learning, but the contribution of different information is yet to be fully understood. This article studies the impacts of two kinds of information for structure prediction: template and multiple sequence alignment (MSA) embedding. Templates have been used by some methods before, such as AlphaFold2, RoseTTAFold and RaptorX. AlphaFold2 and RosetTTAFold only used templates detected by HHsearch, which may not perform very well on some targets. In addition, sequence embedding generated by pre-trained protein language models has not been fully explored for structure prediction. In this article, we study the impact of templates (including the number of templates, the template quality and how the templates are generated) on protein structure prediction accuracy, especially when the templates are detected by methods other than HHsearch. We also study the impact of sequence embedding (generated by MSATransformer and ESM-1b) on structure prediction.ResultsWe have implemented a deep learning method for protein structure prediction that may take templates and MSA embedding as extra inputs. We study the contribution of templates and MSA embedding to structure prediction accuracy. Our experimental results show that templates can improve structure prediction on 71 of 110 CASP13 (13th Critical Assessment of Structure Prediction) targets and 47 of 91 CASP14 targets, and templates are particularly useful for targets with similar templates. MSA embedding can improve structure prediction on 63 of 91 CASP14 (14th Critical Assessment of Structure Prediction) targets and 87 of 183 CAMEO targets and is particularly useful for proteins with shallow MSAs. When both templates and MSA embedding are used, our method can predict correct folds (TMscore > 0.5) for 16 of 23 CASP14 FM targets and 14 of 18 Continuous Automated Model Evaluation (CAMEO) targets, outperforming RoseTTAFold by 5% and 7%, respectively.Availability and implementationAvailable at https://github.com/xluo233/RaptorXFold.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC9805584 | biostudies-literature