Using neural networks and evolutionary information in decoy discrimination for protein tertiary structure prediction.
Ontology highlight
ABSTRACT:
SUBMITTER: Tan CW
PROVIDER: S-EPMC2267779 | biostudies-literature | 2008
REPOSITORIES: biostudies-literature
Publications
Using neural networks and evolutionary information in decoy discrimination for protein tertiary structure prediction.
Tan Ching-Wai CW Jones David T DT
BMC bioinformatics 20080211
<h4>Background</h4>We present a novel method of protein fold decoy discrimination using machine learning, more specifically using neural networks. Here, decoy discrimination is represented as a machine learning problem, where neural networks are used to learn the native-like features of protein structures using a set of positive and negative training examples. A set of native protein structures provides the positive training examples, while negative training examples are simulated decoy structur ...[more]
Similar Datasets
Project description:Knowing the structure of conserved structural RNAs is important to elucidate their function and mechanism of action. However, predicting a conserved RNA structure remains unreliable, even when using a combination of thermodynamic stability and evolutionary covariation information. Here we present a method to predict a conserved RNA structure that combines the following three features. First, it uses significant covariation due to RNA structure and removes spurious covariation due to phylogeny. Second, it uses negative evolutionary information: basepairs that have variation but no significant covariation are prevented from occurring. Lastly, it uses a battery of probabilistic folding algorithms that incorporate all positive covariation into one structure. The method, named CaCoFold (Cascade variation/covariation Constrained Folding algorithm), predicts a nested structure guided by a maximal subset of positive basepairs, and recursively incorporates all remaining positive basepairs into alternative helices. The alternative helices can be compatible with the nested structure such as pseudoknots, or overlapping such as competing structures, base triplets, or other 3D non-antiparallel interactions. We present evidence that CaCoFold predictions are consistent with structures modeled from crystallography.
| S-EPMC7657543 | biostudies-literature
Project description:BACKGROUND: Residue depth allows determining how deeply a given residue is buried, in contrast to the solvent accessibility that differentiates between buried and solvent-exposed residues. When compared with the solvent accessibility, the depth allows studying deep-level structures and functional sites, and formation of the protein folding nucleus. Accurate prediction of residue depth would provide valuable information for fold recognition, prediction of functional sites, and protein design. RESULTS: A new method, RDPred, for the real-value depth prediction from protein sequence is proposed. RDPred combines information extracted from the sequence, PSI-BLAST scoring matrices, and secondary structure predicted with PSIPRED. Three-fold/ten-fold cross validation based tests performed on three independent, low-identity datasets show that the distance based depth (computed using MSMS) predicted by RDPred is characterized by 0.67/0.67, 0.66/0.67, and 0.64/0.65 correlation with the actual depth, by the mean absolute errors equal 0.56/0.56, 0.61/0.60, and 0.58/0.57, and by the mean relative errors equal 17.0%/16.9%, 18.2%/18.1%, and 17.7%/17.6%, respectively. The mean absolute and the mean relative errors are shown to be statistically significantly better when compared with a method recently proposed by Yuan and Wang [Proteins 2008; 70:509-516]. The results show that three-fold cross validation underestimates the variability of the prediction quality when compared with the results based on the ten-fold cross validation. We also show that the hydrophilic and flexible residues are predicted more accurately than hydrophobic and rigid residues. Similarly, the charged residues that include Lys, Glu, Asp, and Arg are the most accurately predicted. Our analysis reveals that evolutionary information encoded using PSSM is characterized by stronger correlation with the depth for hydrophilic amino acids (AAs) and aliphatic AAs when compared with hydrophobic AAs and aromatic AAs. Finally, we show that the secondary structure of coils and strands is useful in depth prediction, in contrast to helices that have relatively uniform distribution over the protein depth. Application of the predicted residue depth to prediction of buried/exposed residues shows consistent improvements in detection rates of both buried and exposed residues when compared with the competing method. Finally, we contrasted the prediction performance among distance based (MSMS and DPX) and volume based (SADIC) depth definitions. We found that the distance based indices are harder to predict due to the more complex nature of the corresponding depth profiles. CONCLUSION: The proposed method, RDPred, provides statistically significantly better predictions of residue depth when compared with the competing method. The predicted depth can be used to provide improved prediction of both buried and exposed residues. The prediction of exposed residues has implications in characterization/prediction of interactions with ligands and other proteins, while the prediction of buried residues could be used in the context of folding predictions and simulations.
| S-EPMC2567998 | biostudies-literature
Project description:We describe AlphaFold, the protein structure prediction system that was entered by the group A7D in CASP13. Submissions were made by three free-modeling (FM) methods which combine the predictions of three neural networks. All three systems were guided by predictions of distances between pairs of residues produced by a neural network. Two systems assembled fragments produced by a generative neural network, one using scores from a network trained to regress GDT_TS. The third system shows that simple gradient descent on a properly constructed potential is able to perform on par with more expensive traditional search techniques and without requiring domain segmentation. In the CASP13 FM assessors' ranking by summed z-scores, this system scored highest with 68.3 vs 48.2 for the next closest group (an average GDT_TS of 61.4). The system produced high-accuracy structures (with GDT_TS scores of 70 or higher) for 11 out of 43 FM domains. Despite not explicitly using template information, the results in the template category were comparable to the best performing template-based methods.
| S-EPMC7079254 | biostudies-literature
Project description:MotivationThe identification of catalytic residues is a key step in understanding the function of enzymes. While a variety of computational methods have been developed for this task, accuracies have remained fairly low. The best existing method exploits information from sequence and structure to achieve a precision (the fraction of predicted catalytic residues that are catalytic) of 18.5% at a corresponding recall (the fraction of catalytic residues identified) of 57% on a standard benchmark. Here we present a new method, Discern, which provides a significant improvement over the state-of-the-art through the use of statistical techniques to derive a model with a small set of features that are jointly predictive of enzyme active sites.ResultsIn cross-validation experiments on two benchmark datasets from the Catalytic Site Atlas and CATRES resources containing a total of 437 manually curated enzymes spanning 487 SCOP families, Discern increases catalytic site recall between 12% and 20% over methods that combine information from both sequence and structure, and by >or=50% over methods that make use of sequence conservation signal only. Controlled experiments show that Discern's improvement in catalytic residue prediction is derived from the combination of three ingredients: the use of the INTREPID phylogenomic method to extract conservation information; the use of 3D structure data, including features computed for residues that are proximal in the structure; and a statistical regularization procedure to prevent overfitting.
| S-EPMC2828116 | biostudies-literature
Project description:BACKGROUND: Predicting the function of a protein is one of the major challenges in the post-genomic era where a large number of protein sequences of unknown function are accumulating rapidly. Lectins are the proteins that specifically recognize and bind to carbohydrate moieties present on either proteins or lipids. Cancerlectins are those lectins that play various important roles in tumor cell differentiation and metastasis. Although the two types of proteins are linked, still there is no computational method available that can distinguish cancerlectins from the large pool of non-cancerlectins. Hence, it is imperative to develop a method that can distinguish between cancer and non-cancerlectins. RESULTS: All the models developed in this study are based on a non-redundant dataset containing 178 cancerlectins and 226 non-cancerlectins in which no two sequences have more than 50% sequence similarity. We have applied the similarity search based technique, i.e. BLAST, and achieved a maximum accuracy of 43.25%. The amino acids compositional analysis have shown that certain residues (e.g. Leucine, Proline) were preferred in cancerlectins whereas some other (e.g. Asparatic acid, Asparagine) were preferred in non-cancerlectins. It has been found that the PROSITE domain "Crystalline beta gamma" was abundant in cancerlectins whereas domains like "SUEL-type lectin domain" were found mainly in non-cancerlectins. An SVM-based model has been developed to differentiate between the cancer and non-cancerlectins which achieved a maximum Matthew's correlation coefficient (MCC) value of 0.32 with an accuracy of 64.84%, using amino acid compositions. We have developed a model based on dipeptide compositions which achieved an MCC value of 0.30 with an accuracy of 64.84%. Thereafter, we have developed models based on split compositions (2 and 4 parts) and achieved an MCC value of 0.31, 0.32 with accuracies of 65.10% and 66.09%, respectively. An SVM model based on Position Specific Scoring Matrix (PSSM), generated by PSI-BLAST, was developed and achieved an MCC value of 0.36 with an accuracy of 68.34%. Finally, we have integrated the PROSITE domain information with PSSM and developed an SVM model that has achieved an MCC value of 0.38 with 69.09% accuracy. CONCLUSION: BLAST has been found inefficient to distinguish between cancer and non-cancerlectins. We analyzed the protein sequences of cancer and non-cancerlectins and identified interesting patterns. We have been able to identify PROSITE domains that are preferred in cancer and non-cancerlectins and thus provided interesting insights into the two types of proteins. The method developed in this study will be useful for researchers studying cancerlectins, lectins and cancer biology. The web-server based on the above study, is available at http://www.imtech.res.in/raghava/cancer_pred/
| S-EPMC3161874 | biostudies-other
Project description:MotivationThe computational prediction of regulatory function associated with a genomic sequence is of utter importance in -omics study, which facilitates our understanding of the underlying mechanisms underpinning the vast gene regulatory network. Prominent examples in this area include the binding prediction of transcription factors in DNA regulatory regions, and predicting RNA-protein interaction in the context of post-transcriptional gene expression. However, existing computational methods have suffered from high false-positive rates and have seldom used any evolutionary information, despite the vast amount of available orthologous data across multitudes of extant and ancestral genomes, which readily present an opportunity to improve the accuracy of existing computational methods.ResultsIn this study, we present a novel probabilistic approach called PhyloPGM that leverages previously trained TFBS or RNA-RBP binding predictors by aggregating their predictions from various orthologous regions, in order to boost the overall prediction accuracy on human sequences. Throughout our experiments, PhyloPGM has shown significant improvement over baselines such as the sequence-based RNA-RBP binding predictor RNATracker and the sequence-based TFBS predictor that is known as FactorNet. PhyloPGM is simple in principle, easy to implement and yet, yields impressive results.Availability and implementationThe PhyloPGM package is available at https://github.com/BlanchetteLab/PhyloPGM.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC9235490 | biostudies-literature
Project description:BACKGROUND: Development of computational tools that can accurately predict presence and location of B-cell epitopes on pathogenic proteins has a valuable application to the field of vaccinology. Because of the highly variable yet enigmatic nature of B-cell epitopes, their prediction presents a great challenge to computational immunologists. METHODS: We propose a method, BEEPro (B-cell epitope prediction by evolutionary information and propensity scales), which adapts a linear averaging scheme on 16 properties using a support vector machine model to predict both linear and conformational B-cell epitopes. These 16 properties include position specific scoring matrix (PSSM), an amino acid ratio scale, and a set of 14 physicochemical scales obtained via a feature selection process. Finally, a three-way data split procedure is used during the validation process to prevent over-estimation of prediction performance and avoid bias in our experiment results. RESULTS: In our experiment, first we use a non-redundant linear B-cell epitope dataset curated by Sollner et al. for feature selection and parameter optimization. Evaluated by a three-way data split procedure, BEEPro achieves significant improvement with the area under the receiver operating curve (AUC) = 0.9987, accuracy = 99.29%, mathew's correlation coefficient (MCC) = 0.9281, sensitivity = 0.9604, specificity = 0.9946, positive predictive value (PPV) = 0.9042 for the Sollner dataset. In addition, the same parameters are used to evaluate performance on other independent linear B-cell epitope test datasets, BEEPro attains an AUC which ranges from 0.9874 to 0.9950 and an accuracy which ranges from 93.73% to 97.31%. Moreover, five-fold cross-validation on one benchmark conformational B-cell epitope dataset yields an accuracy of 92.14% and AUC of 0.9066. CONCLUSIONS: Compared with other current models, our method achieves a significant improvement with respect to AUC, accuracy, MCC, sensitivity, specificity, and PPV. Thus, we have shown that an appropriate combination of evolutionary information and propensity scales with a support vector machine model can significantly enhance the prediction performance of both linear and conformational B-cell epitopes.
| S-EPMC3549808 | biostudies-other
Project description:The prediction of breeding values and phenotypes is of central importance for both livestock and crop breeding. In this study, we analyze the use of artificial neural networks (ANN) and, in particular, local convolutional neural networks (LCNN) for genomic prediction, as a region-specific filter corresponds much better with our prior genetic knowledge on the genetic architecture of traits than traditional convolutional neural networks. Model performances are evaluated on a simulated maize data panel (n = 10,000; p = 34,595) and real Arabidopsis data (n = 2,039; p = 180,000) for a variety of traits based on their predictive ability. The baseline LCNN, containing one local convolutional layer (kernel size: 10) and two fully connected layers with 64 nodes each, is outperforming commonly proposed ANNs (multi layer perceptrons and convolutional neural networks) for basically all considered traits. For traits with high heritability and large training population as present in the simulated data, LCNN are even outperforming state-of-the-art methods like genomic best linear unbiased prediction (GBLUP), Bayesian models and extended GBLUP, indicated by an increase in predictive ability of up to 24%. However, for small training populations, these state-of-the-art methods outperform all considered ANNs. Nevertheless, the LCNN still outperforms all other considered ANNs by around 10%. Minor improvements to the tested baseline network architecture of the LCNN were obtained by increasing the kernel size and of reducing the stride, whereas the number of subsequent fully connected layers and their node sizes had neglectable impact. Although gains in predictive ability were obtained for large scale data sets by using LCNNs, the practical use of ANNs comes with additional problems, such as the need of genotyping all considered individuals, the lack of estimation of heritability and reliability. Furthermore, breeding values are additive by design, whereas ANN-based estimates are not. However, ANNs also comes with new opportunities, as networks can easily be extended to account for additional inputs (omics, weather etc.) and outputs (multi-trait models), and computing time increases linearly with the number of individuals. With advances in high-throughput phenotyping and cheaper genotyping, ANNs can become a valid alternative for genomic prediction.
| S-EPMC7689358 | biostudies-literature
Project description:In recent years, event-based sensors have been combined with spiking neural networks (SNNs) to create a new generation of bio-inspired artificial vision systems. These systems can process spatio-temporal data in real time, and are highly energy efficient. In this study, we used a new hybrid event-based camera in conjunction with a multi-layer spiking neural network trained with a spike-timing-dependent plasticity learning rule. We showed that neurons learn from repeated and correlated spatio-temporal patterns in an unsupervised way and become selective to motion features, such as direction and speed. This motion selectivity can then be used to predict ball trajectory by adding a simple read-out layer composed of polynomial regressions, and trained in a supervised manner. Hence, we show that a SNN receiving inputs from an event-based sensor can extract relevant spatio-temporal patterns to process and predict ball trajectories.
| S-EPMC8180888 | biostudies-literature
Project description:MOTIVATION:Messenger RNA subcellular localization mechanisms play a crucial role in post-transcriptional gene regulation. This trafficking is mediated by trans-acting RNA-binding proteins interacting with cis-regulatory elements called zipcodes. While new sequencing-based technologies allow the high-throughput identification of RNAs localized to specific subcellular compartments, the precise mechanisms at play, and their dependency on specific sequence elements, remain poorly understood. RESULTS:We introduce RNATracker, a novel deep neural network built to predict, from their sequence alone, the distributions of mRNA transcripts over a predefined set of subcellular compartments. RNATracker integrates several state-of-the-art deep learning techniques (e.g. CNN, LSTM and attention layers) and can make use of both sequence and secondary structure information. We report on a variety of evaluations showing RNATracker's strong predictive power, which is significantly superior to a variety of baseline predictors. Despite its complexity, several aspects of the model can be isolated to yield valuable, testable mechanistic hypotheses, and to locate candidate zipcode sequences within transcripts. AVAILABILITY AND IMPLEMENTATION:Code and data can be accessed at https://www.github.com/HarveyYan/RNATracker. SUPPLEMENTARY INFORMATION:Supplementary data are available at Bioinformatics online.
| S-EPMC6612824 | biostudies-other